Build Your Own Arcade Controls Forum

Main => Main Forum => Topic started by: taz-nz on October 28, 2007, 05:27:25 am

Title: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 28, 2007, 05:27:25 am
I finally got my 4ghz Core 2 Duo built and it 100% stable  >:D, So since I promised a few people here benchmark scores on it here they are.

All benchmarks we preformed with official (I686 optimized) 0.120 MAME release & near complete set of MAME 0.120u1 ROMs.
The follow command line was run from command prompt window inside Windows XP Pro SP2 (32bit):

mamepp.exe -noautoframeskip -frameskip 0 -seconds_to_run 240 -nothrottle -nosleep -video ddraw -skip_gameinfo -effect none -nowaitvsync -noreadconfig -mt [ROM NAME]

Anyway here are the results.

gaelco3d.c
- radikalb           88.21%   52.93fps
- speedup        102.93%   61.76fps
- surfplnt           91.29%   54.77fps

Mediagx.c
- a51site4        185.95%   111.57fps

medvunit.c
- crusnusa        225.23%   128.38fps   
- crusnwld         229.70%   130.93fps
- offroadc            395.36%   225.36fps
- wargods         376.85%   214.80fps

namcos22.c
- airco22b         97.73%   58.64fps     (major graphics problems)
- alpinerd            42.36%   25.42fps   
- cybrcomm       67.79%   40.68fps
- cybrcycc           125.69%   75.41fps   
- propcycl            70.44%   42.50fps     (other than two pauses looks like it's playing at hyperspeed but still has low score  ???)
- raveracw        53.70%   32.22fps
- ridgerac            75.84%   45.50fps      
- timecris            70.84%   42.50fps

Seattle.c   
- biofreak            91.78%   55.07fps   
- blitz            122.34%   73.40fps
- blitz2k            121.94%   73.16fps
- blitz99            120.27%   68.55fps
- calspeed        146.21%   83.34fps
- carnevil            241.11%   137.43fps
- hyprdriv            140.84%   80.28fps
- mace            173.23%   98.74fps
- sfrush            144.95%   82.62fps
- wg3dh            253.19%   151.91fps

Vegas.c
- gauntdl            108.58%     61.89fps (seems slower than gauntleg due to fly overs)
- gauntleg         108.57%   61.88fps               :cheers:
- tenthdeg         62.03%   35.36fps

- xevi3dg           342.14%        205.28fps

model2.c
- Daytona         120.15%   72.06fps     (colours broken)

hornet.c
- gradius4         112.04%   67.91fps

Model3.c
- scud            40.98%   24.59fps     (graphics broken flickers like hell)

namcos21.c   
- starblad            140.06%   84.03fps

The namcos22.c driver looks to need a lot of work still, most of it roms show signs of emulation errors, so I would expect these scores to rise.

MAME performance basically scales 1 for 1 with clock speed, so say if you have a Core 2 Duo @ 3.2ghz your score will be approx 80% of these with the same setting.

If anyone has any other ROMs they would like me to benchmark on my system let me know, I'll do whole drivers if there is reason to. please no requests for pacman or donkey kong, for kicks I benched 1942 the result was 5570.54%,  3342.32fps (test lasted less than 10secs.) ;D

Also if anyone has a complied build of MAME 0.120u1 I686 optimized and MAME 0.120u1 64bit let me know, I would compile them myself but the last time I coded or compiled anything was back when I was writing Quake2 mods some 8 or 9 years ago so I'm a little rusty.  :dizzy:

I plan to benchmark these roms again under Vista 64bit in the near future, but I still have to install Vista and get it dual booting first.
For those that wish to know, the spec of my PC are below:

Intel Core 2 Duo e6850 @ 4ghz, 500fsb, 1.55v (3ghz, 333fsb, 1.35v stock )  8)
Thermalright Ultra 120 Extreme, with 96CFM 120x38mm fan, ducted, and other mods.
Gigabyte GA-X38-DQ6 (crazy cool heat plate in place)
Corsair Dominator Twin2x2048-8500C5D G (2x1GB DDR2-1066 dimms @ 2x500mhz)
XFX Geforce 8800gts 640MB (stock clock, has hit 12000+ in 3DMARK06 when overclocked)
Enermax Liberty 620watt power supply
3x Western digital 36gb Raptors in RAID-0
BLAH
Blah
blah
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: D4RKSL4Y3R on October 28, 2007, 07:56:29 am
hi i have almost the same computer as you:
Intel Core 2 Duo e6850 @  3ghz, 333fsb, 1.35v   
aDVANCED air cooling
Corsair Dominator 4GB
XFX Geforce 8800ultra 775mb
galaxy 800w power suppky
1x Western digital 36gb Raptor and a 76gb western digital Raptor.
motherboard( asus striker extream)

how the hell did you overclock so well? just good cooling? my air coolong is v good and my motherboards cooling is good as well (+i have a big case with lots of venaltion) so how far do you think i could overclock mine to without mods?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Red on October 28, 2007, 12:02:54 pm
Thanks taz.

"Seattle.c   
- biofreak            91.78%   55.07fps   
- blitz            122.34%   73.40fps
- blitz2k            121.94%   73.16fps
- blitz99            120.27%   68.55fps"

So, Blitz was fairly playable on your machine?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: metahacker on October 28, 2007, 03:16:27 pm
can you try the same tests without -mt ?

what voltages are you running on your cpu, hypertransport, northbridge, southbridge and ram ?

the fact that blitz & gauntlet legends have such nice fps is truly inspiring.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: D4RKSL4Y3R on October 28, 2007, 03:34:19 pm
every things on factory presets at the mo- will overclock it in bout six mounths. its just i herd that processor wasnt v good for overclocking (cutom pc magazine..)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 28, 2007, 03:46:41 pm

- blitz            122.34%   73.40fps
- blitz2k            121.94%   73.16fps
- blitz99            120.27%   68.55fps"

So, Blitz was fairly playable on your machine?


Totally, still a little sound stutter now and then but I think that's to do with having vsync on and playing on an LCD monitor.
(I suck at this game totally so I haven't tried to play it much as yet)

The settings I used to benchmark are design to give as close to an ingame score as possible, most MAME benchmarks are CPU preformance tests which are usefull to developemer, but not to those trying to play the game.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 28, 2007, 03:48:49 pm
For all those looking for more details of my overclocking setting, I'll post them up tonight, I'm late for work at the moment.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: genesim on October 28, 2007, 08:54:33 pm
Killer Instince 2 has sped up tremendously on my AMD 4400 64x2.     Wargods as well.

But the former is all I cared about.    Well...I am jealous about NFL Blitz, but at least I have the Dreamcast for that one.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on October 28, 2007, 08:55:58 pm
Great to see the benchmarks. Thanks! :applaud:

FWIW, according to most mameDev, an PM optimized build is better suited for core 2 CPUs than i686 optimization.  Do you mind testing that?  (Someone said it really helped propcycl, but the site has changed since then (http://mame32qa.classicgaming.gamespy.com/Bench.htm).)

Also, as the link above hints, 0.120u1 is supposed to help some of these games go even faster.  (But note some tested slower, too.)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: tommyinajar on October 28, 2007, 11:44:16 pm

how the hell did you overclock so well? just good cooling? my air coolong is v good and my motherboards cooling is good as well (+i have a big case with lots of venaltion) so how far do you think i could overclock mine to without mods?

*Most* Duo Cores Overclock well, (some better than others  ;) )
with a decent Mobo.

I've got an E4300 1.8GHZ overclocked to 3.0 GHZ on air with a big heatsink. It's on 24/7 .

E6850 OC'd to 4.0 GHZ isn't a problem with the right equipment.

Here is a little help...

http://www.techarp.com/showarticle.aspx?artno=465
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 29, 2007, 02:17:47 am
Jeez... Blitz is playable?  How about the Gauntlet Legends games?


Gauntlet Legends is totally playable too, slight sound stutter now and then most noticably in voice overs, but graphics look purfect and are super smooth, I am so going to waste this week playing it.

Great to see the benchmarks. Thanks! :applaud:

FWIW, according to most mameDev, an PM optimized build is better suited for core 2 CPUs than i686 optimization.  Do you mind testing that?  (Someone said it really helped propcycl, but the site has changed since then (http://mame32qa.classicgaming.gamespy.com/Bench.htm).)

Also, as the link above hints, 0.120u1 is supposed to help some of these games go even faster.  (But note some tested slower, too.)

I'm trying to compile 0.120u1 source right now, no go on first try, I'll probably try making it a PM optized version but I got to get it to compile first. I'll post scores if I get it to work.

Killer Instince 2 has sped up tremendously on my AMD 4400 64x2.     Wargods as well.

But the former is all I cared about.    Well...I am jealous about NFL Blitz, but at least I have the Dreamcast for that one.

I'm an arcade game whore, give me some loose change and an arcade machine, no matter how old, ugly and beaten up and I'll be broke in minutes, I love playing anything from old school vertical scrollers to the lastest light gun games. I just had to have a machine that could play Gauntlet Legends, many of the games I love run with easy, some still a lot of work and sum haven't even been dumped as far as I can tell, so having a PC that can run just about anything MAME can throw at is great.




Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 29, 2007, 05:57:30 am
For all of those that want to know my overclocking details:

CPU Multiplier    8x             
CPU FSB Clock   500Mhz
PCI-E Clock        Auto

Memory Multiplier 2x
Memory timing  5,5,5,15 all others auto (I've got room to go more extreme here, but I'm still tweaking)

DDR2 voltage       +0.35v
PCI-E voltage       +0.05v
FSB voltage          +0.15v
(G)MCH voltage    +0.075

CPU Voltage         1.550v  >:D   (1.520 idle in window , 1.502 underload with Vdrope)

C1E           disabled
TM2           disabled

I wrote a really long and probably boring post about overclocking, but my login timed out and I lost it, so here is the shorter version.

Hardware list for over clocking:

CPU: Core2duo E4x00 (M0 stepping) or E6x50 (G0 stepping)  33 -75% overclock possible

MB: Intel P35 or X38 chipset, nothing with Deluxe or SE in the name, just a good solid board with good cooling and plenty of voltage regulators. (I suggest the Gigabyte GA-P35-DS3 or better)

Memory: DDR2-800 or DD2-1066 match pair from good brand. (I suggest Corsair) Memory speed should be equal or greater in speed to target FSB if possible, like my system DDR2-1066 (533Mhz) target FSB of 500Mhz with 8x Multiplier to get 4Ghz, you could overclock DDR2-800 (400mhz) and run a 445Mhz FSB with a 9x multiplier to get 4ghz but this increases the risk of failure.

Power Supply: If it came in the case dump it, get a good brand name power supply one size too big you your system needs, (I suggest Enermax), cable management is good too.

Case: Plenty of front to back flow, forget anything with a dozen fans aimed in 6 different directions, you want to exchange the air out of the case not move it around, (I suggest Coolermaster Centurion 5 or CM Stacker 831)

Heatsink: Thermalright Ultra 120 Extreme, in the top 3 air coolers around and easy to come by. listed below is what I did to mine.
- Fitted 96 CFM 120x120x36mm fan, slowed to about 50-65 CFM (it was a little noisy), this is mounted a little low of the heatsink to give airflow below the heatsink fins to cool the back of the heatsink block and the north bridge heatsink.
- removed mounting studs from rear X-Brace and fitted them with washers to spread the load, allowed for fitting of heatsink while retailing gigabyte crazy cool heatsink.
- Placed 10c coin between top of heatsink block and mounting X-bracket, increased mounting force and gave a 10deg c improvement in tempature @ 100% load.
- put tape down the sides of the heatsink fins from the fan around to the half way point on the side of the heatsink to act as air duct, forcing air to pass though the whole heatsink. also taped top edge of fan on the top fin to improve air duct effect.
-arctic silver 5 paste, very very thin layer.

Time: Overclock takes time, here is a blow by blow of what I basically did.
Assembly Motherboard, CPU, RAM, Heatsink, Graphics card and PSU on desk, installed TINY XP. Set CPU Multiplier to 6x and memory to 2x, set FSB to 500mhz (CPU is still at 3ghz), tested and set memory timing, increase voltages on memory, north & south bridge, and PCI-E bus. tested for 1 hour at 100% load, increased CPU multiplier to 7x  no extra CPU voltage need yet (CPU now at 3.5ghz) tested for 1 hour 100% load. dropped FSB to 450Mhz and increased CPU multiplier to 8x and CPU voltage to 1.4v (CPU now at  3.8ghz) tested, increased CPU voltage to 1.45v to allow for Vdrope to 1.4v @ 100% load, test for 1 hour @ 100% load, increased FSB to 475Mhz, (CPU now at 3.9ghz) tested, increased CPU voltage to 1.5v to allow for Vdrope to 1.45v at 100% load, tested for 1 hour @ 100% load, increased FSB to 500Mhz with 8x CPU multiplier (CPU now at target 4ghz) post issues, tweaked FSB, & memory voltages cleared up post issues, tested increase CPU voltage to 1.55v to allow for Vdrope in windows @ 100% load to 1.5v, tested for two hours @ 100% load and tweaked little things. Set running Orthos blend test for 100% CPU load and went to bed, 10 hours later, still running 100% load no errors, shut down and spent 2 hours building system. installed fresh copy of WinXP Pro with latest drivers & updates.

Benchmarked MAME to see real world results of all that hard work.

That was still kind of long, and I sure it's full of gramma and spelling mistakes, but hopefully someone will find it interesting.

I've manage to compile a standard version of MAME 0.120 in the mean time, so now on to try a PM optimised version, and then a PM optimised version of MAME 0120u1. (benchmarks to follow in the next couple of days)

so how far do you think i could overclock mine to without mods?

I'd say 3.5-3.6ghz easy, 3.8ghz with some work, and tommyinajar said it best with:

E6850 OC'd to 4.0 GHZ isn't a problem with the right equipment.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 29, 2007, 06:46:57 am
Great to see the benchmarks. Thanks! :applaud:

FWIW, according to most mameDev, an PM optimized build is better suited for core 2 CPUs than i686 optimization.  Do you mind testing that?  (Someone said it really helped propcycl, but the site has changed since then (http://mame32qa.classicgaming.gamespy.com/Bench.htm).)

Also, as the link above hints, 0.120u1 is supposed to help some of these games go even faster.  (But note some tested slower, too.)

I've got the hang of the whole compiling bit, the basics atleast, It's late so full benchmarks will have to wait till tommorrow night, but here's a preview.

PROPCYCL (60hz)
C2D (4.00Ghz)       70.44%,      42.26fps         0120       i686 optimized.
C2D (4.00Ghz)       74.25%,      44.55fps         0120         PM optimized
C2D (4.00GHz)      100.39%,     60.23fps        0120u1     PM optimized.   :cheers: (looks like propcycle just made the playable list with minor sound stutter issues.)

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on October 29, 2007, 10:06:12 am
Just out of curiosity, how does Star Wars Trilogy do.

Great machine, btw!!!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: FrizzleFried on October 29, 2007, 10:12:32 am
The problem here is that I am trying to save up enough money for a CORE2DUO setup...and when I do,  that computer is going RIGHT HERE ON MY DESK...

...NOT in my MAME cabinet...it it's going to take at least another 2 generations before a CORE2DUO makes it in to my MAME cabinet.   I refuse to spend that kind of dough to play games from the 90's (only)...

When i do upgrade,  this Opteron 165 I have on my desk will go in the Horizontal MAME cabinet,  the 3200+ that is in the horizontal will go to the vertical...

>sigh<

So it will be MANY MOONS before I can play Blitz!

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on October 29, 2007, 10:18:50 am
The problem here is that I am trying to save up enough money for a CORE2DUO setup...and when I do,  that computer is going RIGHT HERE ON MY DESK...
Wonder how hard it would be and what kind of performance you would get if you networked the cabinet and desktop PC and ran the arcade as a client and ran Blitz off MAME on the desktop as a server?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: FrizzleFried on October 29, 2007, 11:06:59 am
The problem here is that I am trying to save up enough money for a CORE2DUO setup...and when I do,  that computer is going RIGHT HERE ON MY DESK...
Wonder how hard it would be and what kind of performance you would get if you networked the cabinet and desktop PC and ran the arcade as a client and ran Blitz off MAME on the desktop as a server?


Uh?!?  There is a difference between file STORAGE (what you propose) and CPU PROCESSING POWER which is what your computer does on your end when playing games, etc.  I'd have to essentially run a REALLY LONG VGA cord and USB cord from the computer in the office to the gameroom in the garage!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on October 29, 2007, 11:53:58 am
Uh?!?  There is a difference between file STORAGE (what you propose) and CPU PROCESSING POWER which is what your computer does on your end when playing games, etc.  I'd have to essentially run a REALLY LONG VGA cord and USB cord from the computer in the office to the gameroom in the garage!
Well, I'm not a network guru, but wouldn't you be able to use the CPU Processing power of the desktop Core2Duo for running MAME, and just use the networked slower box in the arcade for displaying graphics and feeding inputs to the main CPU.

You could use a wireless router and wireless card if they are really far apart and you don't want to string CAT 5 through the house.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: rdowdy95 on October 29, 2007, 01:18:06 pm
This is really great news.  I will have to upgrade my computer system in 2-3 years and get some of those nice games going like Gauntlet Dark Legacy.  It is just a pain to upgrade roms and config files.  Good thing I backed everything up to a portable hard drive and I also wrote down all my instructions as well.

Mainly setting up that MameWah was a pure ---smurfette--- to do, but it does run good now with all my settings configed.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: FrizzleFried on October 29, 2007, 01:27:20 pm
Uh?!?  There is a difference between file STORAGE (what you propose) and CPU PROCESSING POWER which is what your computer does on your end when playing games, etc.  I'd have to essentially run a REALLY LONG VGA cord and USB cord from the computer in the office to the gameroom in the garage!
Well, I'm not a network guru, but wouldn't you be able to use the CPU Processing power of the desktop Core2Duo for running MAME, and just use the networked slower box in the arcade for displaying graphics and feeding inputs to the main CPU.

You could use a wireless router and wireless card if they are really far apart and you don't want to string CAT 5 through the house.

It doesn't work that way....

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on October 29, 2007, 01:37:44 pm
Okay, sorry!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on October 29, 2007, 02:29:18 pm
I was going to wait until next week, to post my results for the new mame machine, my main desktop is a q6600 quad core, its 200% faster than my 6600 dual core I was running, so I ordered the same machine for my mame
q6600 quad core
4 gig of ram
gigabyte motherboard
I will have the parts in on wednesday, as soon as I'm built I will list the fps on the higher end chd games
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 29, 2007, 03:39:53 pm
I was going to wait until next week, to post my results for the new mame machine, my main desktop is a q6600 quad core, its 200% faster than my 6600 dual core I was running, so I ordered the same machine for my mame
q6600 quad core
4 gig of ram
gigabyte motherboard
I will have the parts in on wednesday, as soon as I'm built I will list the fps on the higher end chd games
dm

I'll be really interested to see how the roms that ran on 3DFX hardware do on your system, it will be interesting to see how the new MAME multithreading scales on a quad core.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: metahacker on October 29, 2007, 04:58:34 pm
isnt mame with -mt just 2 threads ?  with the second thread just doing framebuffer stuff.

im not sure what else would be left for the other cpus to do other than 'run' disk i/o on CHDs or eat up cycles in AC97 ?  i would think the mame helper thread would not busy up the 2nd core enough to need a 3rd or 4th. 

but i really hope you do see some improvement.  it's nice to see new hardware tech making emus catch up and making stuff that was previously unusable now useful.
 

btw 500 fsb is ---smurfing--- hot.  nice work on your set up dood im impressed.

im runnin a e6600 @ 3.4 here on my desktop.  abit in9 32x max (i dont recommend it, unless u just want the cool BIOS-driven LEDs mounted under the mobo stock :))  had to crank ~1.7v into it tho, for whatever reason.  scythe infinity 120.  1 total fan in the system besides psu.  no nb/sb mods besides as5, no fans.

c2ds are mean.  reminds me of the old celeron 300A, but even better.

i hope i can get something comparable to your results with my new 2.66 6750. i dont think i'll be hittin any 4GHz tho. 

it sure is inspiring to see your results, though....

and apparently 120u1 pentium-M optimized is where the party's at....


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on October 29, 2007, 05:10:33 pm
Good or bad, I have used pctuneup for my benchmarks up until a few months ago
I have a 6600 intel dual core...
score on pctuneup for 6600 intel 3400 w/vista
I also built a 6750 for my racer score 3650 w/vista
2 months I rebuilt my 6600 to a q6600 quad core score 7300 w/vista
I am going to run a strip down xp w/over clock i'm hoping to close to 8000 w/my quad core xp, since xp is faster than vista, its worth a try
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: metahacker on October 29, 2007, 05:50:07 pm
hmmm, now i wonder how the 64 bit mame would compare to 32 bit

taz you are our benchmarking hero :).
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on October 29, 2007, 07:43:49 pm
isnt mame with -mt just 2 threads ?  with the second thread just doing framebuffer stuff.

Old news.  Aaron found a way to split some parts of the emulation into variable number (http://aarongiles.com/?p=217) of threads back in 0.119u3: :notworthy:

Code: [Select]
Added support for controlling multithreading behavior through an
environment variable OSDPROCESSORS. To override the default behavior,
set OSDPROCESSORS equal to the number of logical processors you wish
the OSD layer to pretend you have. [Aaron Giles]

And 0.120u1 improves it even more.  If you have a quad code set OSDPROCESSORS=4.  It won't be four times as fast, but I hear it will be faster for most slow games.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 30, 2007, 05:55:35 am
Well here they are M.A.M.E. 0.120u1 PM optimised benchmark scores:

Scores with 0.120 in front were benchmark with official I686 optimised MAME 0.120
Scores with 0.120u1 in front were benchmark with my build of PM optimised MAME 0.120u1

I use the same command line as I did for the 0.120 benchmarks but using "set OSDPROCESSORS=2"  command before tests (not even sure if I using it right but it seems to work  :dunno)

Anyway here are the results:

- 1492      
0.120      5570.54%   3342.32fps


gaelco3d.c
- radikalb   
0.120      88.21%      52.93fps          
0.120u1      117.74%      70.64fps

- speedup   
0.120      102.93%      61.76fps   
0.120u1      127.66%      76.60fps

- surfplnt   
0.120      91.29%      54.77fps   
0.120u1      112.79%      67.67fps


Mediagx.c
- a51site4   
0.120      185.95%      111.57fps   
0.120u1      186.04%      111.62fps


medvunit.c
- crusnusa   
0.120      225.23%      128.38fps   
0.120u1      220.16%      125.49fps

- crusnwld   
0.120      229.70%      130.93fps   
0.120u1      221.42%      126.21fps

- offroadc   
0.120      395.36%      225.36fps   
0.120u1      365.57%      208.38fps   

- wargods   
0.120      376.85%      214.80fps   
0.120u1      330.00%      188.10fps


namcos22.c
- airco22b
0.120      97.73%      58.64fps    
0.120u1      110.64%     66.38fps

- alpinerd   
0.120      42.36%      25.42fps   
0.120u1      65.95%      39.57fps

- cybrcomm   
0.120      67.79%      40.68fps   
0.120u1      95.78%      57.49fps

- cybrcycc   
0.120      125.69%      75.41fps   
0.120u1      157.40%      94.44fps

- propcycl   
0.120      70.44%      42.50fps   
0.120u1      100.39%      60.23fps

- raveracw   
0.120      53.70%      32.22fps   
0.120u1      81.37%      48.82fps

- ridgerac   
0.120      75.84%      45.50fps   
0.120u1      108.13%      64.88fps

- timecris   
0.120      70.84%      42.50fps   
0.120u1      101.81%      61.09fps


Seattle.c   
- biofreak
0.120      91.78%      55.07fps
0.120u1      101.70%      57.97fps

- blitz      
0.120      122.34%      73.40fps   
0.120u1      127.38%      72.61fps

- blitz2k   
0.120      121.94%      69.51fps   
0.120u1      123.73%      70.52fps

- blitz99   
0.120      120.27%      68.55fps   
0.120u1      120.26%      68.55fps

- calspeed   
0.120      146.21%      83.34fps   
0.120u1      165.08%      94.10fps

- carnevil
0.120      241.11%      137.43fps   
0.120u1      221.69%      126.36fps

- hyprdriv   
0.120      140.84%      80.28fps   
0.120u1      144.27%      82.23fps

- mace      
0.120      173.23%      98.74fps   
0.120u1      186.67%      106.40fps

- sfrush   
0.120      144.95%      82.62fps   
0.120u1      152.01%      86.64fps

- wg3dh      
0.120      253.19%      144.32fps   
0.120u1      265.32%      151.23fps


Vegas.c
- gauntdl
0.120      108.58%     61.89fps    
0.120u1      110.06%      62.73fps

-gauntleg
0.120      108.57%      61.88fps
0.120u1      111.60%      63.61fps

- tenthdeg   
0.120u1      62.03%      35.36fps   
0.120u1      67.42%      38.43fps


model2.c
- Daytona         
0.120      120.15%      72.06fps   
0.120u1      120.08%      72.05fps


hornet.c
- gradius4   
0.120      112.04%      67.91fps
0.120u1      fails instantly with memory error


Model3.c
- scud      
0.120      40.98%      24.59fps   
0.120u1      44.21%      26.53fps


namcos21.c   
- starblad
0.120      140.06%      84.03fps
0.120u1      139.95%      83.97fps

Just out of curiosity, how does Star Wars Trilogy do.

-swtrilgy (Emulation need a lot of work still major graphics issues)
0.120u1      61.66%      39.97fps


hmmm, now i wonder how the 64 bit mame would compare to 32 bit

taz you are our benchmarking hero :).

Thanks, 64bit MAME benchmarks to follow in a couple of days. Hoping to find time tomorrow night to install Vista Ultimate 64bit in dual boot with XP Pro, if that all goes well then I just have to work out how to compile 64bit versions of MAME. Once I've got those two things sorted I'll run all the benchmarks again in 64bit and any new ROMs people request.

If anyone has any other hints or trick to improving MAME preformance let me know.


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 30, 2007, 05:59:34 am
isnt mame with -mt just 2 threads ?  with the second thread just doing framebuffer stuff.

You are correct but it's still good for about 5% improvement in score so I use it.

im not sure what else would be left for the other cpus to do other than 'run' disk i/o on CHDs or eat up cycles in AC97 ?  i would think the mame helper thread would not busy up the 2nd core enough to need a 3rd or 4th. 


the 2nd, 3rd and 4th core of a quad core are going to be doing nothing but play hot patato with windows services in the background with 90% of mame roms, but with the few that are Multithreaded now, the 2nd Core get a real work out and in theory the 3rd and 4th will get in on the some of the action too.

btw 500 fsb is ---smurfing--- hot.  nice work on your set up dood im impressed.

im runnin a e6600 @ 3.4 here on my desktop.  abit in9 32x max (i dont recommend it, unless u just want the cool BIOS-driven LEDs mounted under the mobo stock :))  had to crank ~1.7v into it tho, for whatever reason.  scythe infinity 120.  1 total fan in the system besides psu.  no nb/sb mods besides as5, no fans.

c2ds are mean.  reminds me of the old celeron 300A, but even better.

i hope i can get something comparable to your results with my new 2.66 6750. i dont think i'll be hittin any 4GHz tho. 

it sure is inspiring to see your results, though....

and apparently 120u1 pentium-M optimized is where the party's at....

Sounds like your not do to bad yourself on the overclocking front, but 1.7v ouch, bet that makes the core temp ramp up like hell under load.

My mate still has a Celeron 300A overclocked @ 450mhz running as a gateway server on his home network, been overclocked for so many years it doesn't run stock clock anymore.

E6750 are good to about 3.6-3.8ghz with air, you really need a good water cooling kit to take them any higher, but there are some that get lucky and make it all the way to 4.0ghz on air alone.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on October 30, 2007, 07:37:27 am
-swtrilgy (Emulation need a lot of work still major graphics issues)
0.120u1      61.66%      39.97fps
Thanks - that's actually better than I expected!!!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: headkaze on October 30, 2007, 10:12:51 am
Compiling Mame is quite easy. Check out Mame Compiler (http://forum.arcadecontrols.com/index.php?topic=71845.0) for a front end and installer for all the tools necessary to compile. It has options for compiling 64-bit versions etc.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on October 30, 2007, 01:03:34 pm
... and in theory the 3rd and 4th will get in on the some of the action too.

set OSDPROCESSORS=4
for the 3rd & 4th get the same as the 2nd.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on October 30, 2007, 01:05:38 pm
right now im running 32 bit home xp, would it be worth the jump to 64 bit xp before I rebuild to the quad core
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on October 30, 2007, 11:27:28 pm
Hi there, if you have a chance please run the pure CPU test bench on the standard build using the benchmarking params here:
http://mame32qa.classicgaming.gamespy.com/Bench.htm

Aaron and I are curious about that and a similar run on a 64bit OS + 64bit Mame.  Regards -

Game Driver Arguments 0.119 .120 .120.1
crusnusa midvunit.c -str 90 -video none -nosound -nothrottle -norc -nosleep 212.24% 212.12% 178.27%
starblad namcos21.c -str 90 -video none -nosound -nothrottle -norc -nosleep 234.33% 120.83% 116.97%
gauntleg vegas.c -str 90 -video none -nosound -nothrottle -norc -nosleep 47.92% 114.97% 132.38%
blitz seattle.c -str 90 -video none -nosound -nothrottle -norc -nosleep 122.25% 87.86% 111.59%
daytona model2.c -str 90 -video none -nosound -nothrottle -norc -nosleep n/a 86.18% 87.22%
gradius4 hornet.c -str 90 -video none -nosound -nothrottle -norc -nosleep 60.36% 79.34% n/a
radikalb gaelco3d.c -str 90 -video none -nosound -nothrottle -norc -nosleep 77.46% 76.11% 95.72%
ridgerac namcos22.c -str 90 -video none -nosound -nothrottle -norc -nosleep 65.56% 64.73% 90.77%
scud model3.c -str 90 -video none -nosound -nothrottle -norc -nosleep 34.41% 32.91% 33.00%

Vista Ultimate 32 • Intel C2D E6400 3.4Ghz • 2GB Corsair DDR2 800 • ATI X1950 Pro     
Standard baseline build w/ GCC tools
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 31, 2007, 06:10:57 am
Hi there, if you have a chance please run the pure CPU test bench on the standard build using the benchmarking params here:
http://mame32qa.classicgaming.gamespy.com/Bench.htm

Aaron and I are curious about that and a similar run on a 64bit OS + 64bit Mame.  Regards -

Game Driver Arguments 0.119 .120 .120.1
crusnusa midvunit.c -str 90 -video none -nosound -nothrottle -norc -nosleep 212.24% 212.12% 178.27%
starblad namcos21.c -str 90 -video none -nosound -nothrottle -norc -nosleep 234.33% 120.83% 116.97%
gauntleg vegas.c -str 90 -video none -nosound -nothrottle -norc -nosleep 47.92% 114.97% 132.38%
blitz seattle.c -str 90 -video none -nosound -nothrottle -norc -nosleep 122.25% 87.86% 111.59%
daytona model2.c -str 90 -video none -nosound -nothrottle -norc -nosleep n/a 86.18% 87.22%
gradius4 hornet.c -str 90 -video none -nosound -nothrottle -norc -nosleep 60.36% 79.34% n/a
radikalb gaelco3d.c -str 90 -video none -nosound -nothrottle -norc -nosleep 77.46% 76.11% 95.72%
ridgerac namcos22.c -str 90 -video none -nosound -nothrottle -norc -nosleep 65.56% 64.73% 90.77%
scud model3.c -str 90 -video none -nosound -nothrottle -norc -nosleep 34.41% 32.91% 33.00%

Vista Ultimate 32 • Intel C2D E6400 3.4Ghz • 2GB Corsair DDR2 800 • ATI X1950 Pro     
Standard baseline build w/ GCC tools

Ha no problem, glad to be of some use.

All Benchmark run with Offical MAME 0.120 standard 64bit build on clean install of Vista Ultamite 64bit.

v64mame.exe -str 90 -video none -nosound -nothrottle -norc -nosleep crusnusa      271.81%
v64mame.exe -str 90 -video none -nosound -nothrottle -norc -nosleep starblad      153.87%
v64mame.exe -str 90 -video none -nosound -nothrottle -norc -nosleep gauntleg      183.42%
v64mame.exe -str 90 -video none -nosound -nothrottle -norc -nosleep blitz      164.15%
v64mame.exe -str 90 -video none -nosound -nothrottle -norc -nosleep daytona      142.72%
v64mame.exe -str 90 -video none -nosound -nothrottle -norc -nosleep gradius4      122.16%   
v64mame.exe -str 90 -video none -nosound -nothrottle -norc -nosleep radikalb      150.07%   
v64mame.exe -str 90 -video none -nosound -nothrottle -norc -nosleep ridgerac      106.77%
v64mame.exe -str 90 -video none -nosound -nothrottle -norc -nosleep scud      33.81%     :banghead:

I would have benchmarked 0.119 & 120u1 64bit builds, but I've had no joy trying to compile a 64bit build, If you can to send me a link of where I can get a 64bit build of 0.119 & 0.120u1 I'll benchmark them for you.


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 31, 2007, 06:17:21 am
Compiling Mame is quite easy. Check out Mame Compiler (http://forum.arcadecontrols.com/index.php?topic=71845.0) for a front end and installer for all the tools necessary to compile. It has options for compiling 64-bit versions etc.

Thanks for the link, great app by the way. Works great but as soon as I tick the 64bit option I get the error message below.


Deleting Object Folder...
Compiling Mame...
Using Parameters  PTR64=1
Compiling src/osd/windows/winwork.c...
cc1.exe: warnings being treated as errors
src/osd/windows/winwork.c: In function 'compare_exchange_pointer':
src/osd/windows/winwork.c:77: warning: implicit declaration of function 'InterlockedCompareExchange64'
src/osd/windows/winwork.c:77: warning: cast from pointer to integer of different size
src/osd/windows/winwork.c:77: warning: cast from pointer to integer of different size
src/osd/windows/winwork.c:77: warning: cast from pointer to integer of different size
src/osd/windows/winwork.c:78: warning: cast to pointer from integer of different size
mingw32-make: *** [obj/windows/mame/osd/windows/winwork.o] Error 1
Finished!
0 Hours 0 Minutes and 0 Seconds Elapsed.

If you've got any idea what I might be doing wrong let me know.


If anyone wants to compile a PM optimized 64bit version of MAME 0.120u1 for me & post it somewhere I can download it,  that would be great.

I did a quick test of the preformance of the standard 64bit build on MAME 0.120 under Vista 64bit and it makes a big difference, the scores not as good as the PM optimised 0.120u1 build but a lot better that the PM optimised 0.120 build, so I think there will be some killer scores from a full optimised 64 build of 0.120u1

have a look at what I mean:

C2D (4.00Ghz)   70.44%,      42.26fps   0.120 i686 optimized.
C2D (4.00Ghz)   74.25%,      44.55fps   0.120 PM optimized
CDC (4.00GHz)  100.39%,          60.23fps   0.120u1 Pm Optimized.
CDC (4.00GHz)   96.24%,      57.74fps   0.120 official 64bit build.(standard build)

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on October 31, 2007, 05:13:19 pm
Thanks for that 64bit run, are you fully 64bit Vista now or can you dual boot to 32bit and run an apples to apples w/ my numbers above.  You can also use my official Mame32 .120u1 as the .exe and just redirect output. Thx -
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: headkaze on October 31, 2007, 10:36:13 pm
Deleting Object Folder...
Compiling Mame...
Using Parameters  PTR64=1
Compiling src/osd/windows/winwork.c...
cc1.exe: warnings being treated as errors
src/osd/windows/winwork.c: In function 'compare_exchange_pointer':
src/osd/windows/winwork.c:77: warning: implicit declaration of function 'InterlockedCompareExchange64'
src/osd/windows/winwork.c:77: warning: cast from pointer to integer of different size
src/osd/windows/winwork.c:77: warning: cast from pointer to integer of different size
src/osd/windows/winwork.c:77: warning: cast from pointer to integer of different size
src/osd/windows/winwork.c:78: warning: cast to pointer from integer of different size
mingw32-make: *** [obj/windows/mame/osd/windows/winwork.o] Error 1
Finished!
0 Hours 0 Minutes and 0 Seconds Elapsed.

If you've got any idea what I might be doing wrong let me know.

Oh crap I never actually tested that option. After a bit of investigation I think you actually need the Windows Platform SDK and a recent DirectX SDK to compile 64-bit versions of Mame. Aparently the Windows SDK includes a VS 64-bit compiler. I will have to do another update of Mame Compiler to support this, so when I get some time I'll look into it. If MinGW can support compiling 64-bit versions of Mame, please let me know what is required to get it compiling. Thanks.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 01, 2007, 03:05:02 am
Thanks for that 64bit run, are you fully 64bit Vista now or can you dual boot to 32bit and run an apples to apples w/ my numbers above.  You can also use my official Mame32 .120u1 as the .exe and just redirect output. Thx -

No problem glab to be of help, I'm running dual boot and will do for some time to come.

Ok apples for apples CPU bench test. (All 32bit benchmarks run in Windows XP Pro , 64bit benchcmarks run in Vista ultimate 64bit)

I downloaded the standard build of Mame 0.119 and re-named the mame.exe to mame119.exe
I downloaded the standard build of Mame 0.120 and re-named the mame.exe to mame120.exe
I downloaded the souce code fore Mame 0.120 and the 0.120u1 difffile applied the diff and compiled a standard build with mingw.
I then re-name the resulting mame.exe to mame120u1.exe (Sorry couldn't for the life of me get Mame32 0.120u1 to output to a txt file)

Then I created a batch file called "bench.bat" to make like easy:

>>>> start bench.bat <<<<
mame119.exe -str 90 -video none -nosound -nothrottle -norc -nosleep %1

mame120.exe -str 90 -video none -nosound -nothrottle -norc -nosleep %1

mame120u1.exe -str 90 -video none -nosound -nothrottle -norc -nosleep %1
>>>> end bench.bat <<<<

And call that by typing "bench [ROM NAME]" for the command prompt window.

>>>>>> UPDATED: Now including 0.120u2 results <<<<<<<

mame120u2.exe -str 90 -video none -nosound -nothrottle -norc -nosleep [ROM NAME]

Anyway here are the results:

CPU
ROM
Driver
      0.119   
     0.120   
     0120u1 
     0120u2 
   0.120(64bit)
E6400 @ 3.4ghz     crusnusa   midvunit.c
212.24%
212.12%
178.27%
   n/a
  n/a
E6850 @ 4.0ghzcrusnusa   midvuint.c
257.69%
257.32%
218.20%
214.79%
271.81%   
E6400 @ 3.4ghz    starblad   namcos21.c
234.33%
120.83%
116.97%
   n/a
  n/a
E6850 @ 4.0ghzstarblad   namcos21.c
299.30%
144.10%
144.00%
142.10%
153.57%   
E6400 @ 3.4ghz    gauntleg   vegas.c
47.92%
114.97%
132.38%
   n/a
  n/a
E6850 @ 4.0ghzgauntleg   vegas.c
68.91%
166.17%
173.07%
166.03%
183.42%   
E6400 @ 3.4ghz    blitz   seattle.c
122.25%
87.86%
111.59%
   n/a
  n/a
E6850 @ 4.0ghzblitz   seattle.c
153.43%
138.59%
143.28%
136.99%
164.15%   
E6400 @ 3.4ghz    daytona   model2.c
   n/a
86.18%
87.22%
   n/a
  n/a
E6850 @ 4.0ghzdaytona   model2.c
   n/a
106.17%
106.43%
104.94%
142.72%   
E6400 @ 3.4ghz    gradius4   hornet.c
60.36%
79.34%
   n/a
   n/a
  n/a
E6850 @ 4.0ghzgradius4   hornet.c
116.72%
164.94%
   n/a
180.32%
122.16%   
E6400 @ 3.4ghz    radikalb   gaelco3d.c
77.46%
76.11%
95.72%
   n/a
  n/a
E6850 @ 4.0ghzradikalb   gaelco3d.c
94.25%
93.97%
116.77%
129.44%
150.07%   
E6400 @ 3.4ghz    ridgerac   namcos22.c
65.56%
64.73%
90.77%
   n/a
  n/a
E6850 @ 4.0ghzridgerac   namcos22.c
80.00%
79.54%
114.89%
112.44%
106.77%   
E6400 @ 3.4ghz    scud   model3.c
34.41%
32.91%
33.00%
   n/a
  n/a
E6850 @ 4.0ghzscud   model3.c
41.21%
39.60%
39.56%
38.93%
33.81%   


If you have any other benchmarks you would like me to run let me know.

Later I'll post In-Game benchmark result for the standard build of 64bit mame in Vista 64bit.

I'm also playing around with the Microsoft SDK & Visual studio express to see if I can build a PM optimised 64bit build or Mame 0120u1.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 01, 2007, 07:09:17 am
Well after running all the benchmarks again in Vista 64 with the standard build or 64bit MAME I have to say, 64bit is where it's at. If your serious about running MAME you should be running a 64bit OS. Check out the score for yourself you'll see what I mean.

Scores with 0.120 in front were benchmarked with official I686 optimised MAME 0.120
Scores with 0.120u1 in front were benchmarked with my build of PM optimised MAME 0.120u1
Socres with 0.20 64bit in front were benchmarked with official 64bit MAME 0.120 build.

- 1492      
0.120      5570.54%   3342.32fps
0.120 64bit   6503.71%   3902.23fps

gaelco3d.c
- radikalb   
0.120      88.21%      52.93fps          
0.120 64bit   134.23%      
0.120u1      117.74%      70.64fps

- speedup   
0.120      102.93%      61.76fps   
0.120 64bit   157.14%      
0.120u1      127.66%      76.60fps

- surfplnt   
0.120      91.29%      54.77fps   
0.120u1 64bit   139.72%
0.120u1      112.79%      67.67fps


Mediagx.c
- a51site4   
0.120      185.95%      111.57fps   
0.120 64bit   234.34%      
0.120u1      186.04%      111.62fps


medvunit.c
- crusnusa   
0.120      225.23%      128.38fps   
0.120 64bit   271.99%
0.120u1      220.16%      125.49fps

- crusnwld   
0.120      229.70%      130.93fps   
0.120 64bit   249.66%
0.120u1      221.42%      126.21fps

- offroadc   
0.120      395.36%      225.36fps   
0.120 64bit   425.80%
0.120u1      365.57%      208.38fps   

- wargods   
0.120      376.85%      214.80fps   
0.120 64bit   411.71%
0.120u1      330.00%      188.10fps


namcos22.c
- airco22b
0.120      97.73%      58.64fps    
0.120 64bit   124.71%
0.120u1      110.64%     66.38fps

- alpinerd     (I wish I knew why this rom is so slow, I getting sick of looking at the skiers pink arse.
0.120      42.36%      25.42fps   
0.120 64bit   53.37%
0.120u1      65.95%      39.57fps

- cybrcomm   
0.120      67.79%      40.68fps   
0.120 64bit   96.65%
0.120u1      95.78%      57.49fps

- cybrcycc   
0.120      125.69%      75.41fps   
0.120 64bit   161.28%
0.120u1      157.40%      94.44fps

- propcycl   
0.120      70.44%      42.50fps   
0.120 64bit   96.31%
0.120u1      100.39%      60.23fps

- raveracw   
0.120      53.70%      32.22fps   
0.120 64bit   68.33%
0.120u1      81.37%      48.82fps

- ridgerac   
0.120      75.84%      45.50fps   
0.120 64bit   103.33%      
0.120u1      108.13%      64.88fps

- timecris   
0.120      70.84%      42.50fps   
0.120 64bit   93.17%
0.120u1      101.81%      61.09fps


Seattle.c   
- biofreak
0.120      91.78%      55.07fps
0.120 64bit   140.22%      
0.120u1      101.70%      57.97fps

- blitz      
0.120      122.34%      73.40fps   
0.120 64bit   153.09%
0.120u1      127.38%      72.61fps

- blitz2k   
0.120      121.94%      69.51fps   
0.120 64bit   146.08%
0.120u1      123.73%      70.52fps

- blitz99   
0.120      120.27%      68.55fps   
0.120 64bit   142.65%
0.120u1      120.26%      68.55fps

- calspeed   
0.120      146.21%      83.34fps   
0.120 64bit   181.91%
0.120u1      165.08%      94.10fps

- carnevil
0.120      241.11%      137.43fps   
0.120 64bit   287.40%
0.120u1      221.69%      126.36fps

- hyprdriv   
0.120      140.84%      80.28fps   
0.120 64bit   185.50%
0.120u1      144.27%      82.23fps

- mace      
0.120      173.23%      98.74fps   
0.120 64bit   217.20%
0.120u1      186.67%      106.40fps

- sfrush   
0.120      144.95%      82.62fps   
0.120 64bit   199.68%
0.120u1      152.01%      86.64fps

- wg3dh      
0.120      253.19%      144.32fps   
0.120 64bit   342.70%
0.120u1      265.32%      151.23fps


Vegas.c
- gauntdl
0.120      108.58%     61.89fps    
0.120 64bit   123.46%
0.120u1      110.06%      62.73fps

-gauntleg
0.120      108.57%      61.88fps
0.120 64bit   153.76%            (tends to lockup)
0.120u1      111.60%      63.61fps

- tenthdeg   
0.120u1      62.03%      35.36fps   
0.120 64bit   76.21%
0.120u1      67.42%      38.43fps


model2.c
- Daytona         
0.120      120.15%      72.06fps   
0.120 64bit   157.64%
0.120u1      120.08%      72.05fps


hornet.c
- gradius4   
0.120      112.04%      67.91fps
0.120      92.69%
0.120u1      fails instantly with memory error


Model3.c
- scud      
0.120      40.98%      24.59fps   
0.120 64bit   33.57%
0.120u1      44.21%      26.53fps


namcos21.c   
- starblad
0.120      140.06%      84.03fps
0.120 64bit   146.24%
0.120u1      139.95%      83.97fps

(I'll edit this post and fill in the FPS tomorrow sometime, it's late and between the Pure CPU & In-Game benchmarks I've been at this almost 6 hours tonight.)

Well there you go, I hope to be able to post PM opitised 64bit MAME 0.120u1 benchmarks by the end of the weekend, but that all depend how things go with compiling a 64bit build.




Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: headkaze on November 01, 2007, 07:55:03 am
This post might help

http://www.mameworld.info/ubbthreads/showthreaded.php?Cat=&Number=129879&page=0&view=expanded&sb=5&o=&fpart=1&vc=1
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on November 01, 2007, 01:23:38 pm
Thanks for the run.  Yes you're missing the fastest configuration of .120u1 at 64bit.  The jumps Aaron made in the software sli and applying that to the other 3d drivers really gave some nice boosts.  He does his 64bit builds [PTR64=1 ]w/out PM=1 so it will be interesting to see if there are any changes w/ PM=1.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 01, 2007, 11:50:48 pm
Since this thread is starting reads like a long list numbers, and the point of these benchmarks is to help out those of you looking to find out what you need to run the most demanding M.A.M.E. ROMs, I decided to post something other than benchmarks today, mainly because I'm still trying to wrap my head around two different Microsoft SDKs, 64 Mame compiling and my Hard Drives looks like MAMEDEV exploded all over them.

So for all those of you wanting to build a preformance M.A.M.E. PC on a budget, I did a quick shopping list and then found some prices over at www.clubit.com (http://www.clubit.com) (There may be better and cheaper places out there, but they had the right gear at what looked like the right price)

(http://www.clubit.com/images/clubit_web/header_01.gif)

(http://www.clubit.com/products/50x50/A4830711_1.jpg)    GIGABYTE GA-P35-DS3R Rev. 2.0 LGA 775 Intel P35 ATX Intel Motherboard Retail     
$128.50
(http://www.clubit.com/products/50x50/A1906716_1.jpg)    Cooler Master RR-CCH-LB12-GP Hyper 212 CPU Cooler   
$33.99
(http://www.clubit.com/products/50x50/A1938256_1.jpg)    Intel Core 2 Duo E4500 M0 Stepping Conroe 2.2GHz 2MB L2 LGA 775 Processor Retail BX80557E4500 SLA95   
$123.50
(http://www.clubit.com/products/50x50/A4330509_1.jpg)   CORSAIR XMS2 2GB (2 x 1GB) DDR2-800 CL 5-5-5-12 Dual Channel Kit Retail TWIN2X2048-6400
$74.50
Sub Total:   
$360.49

Add a dirt cheap PCI-E VGA card, case with atleast a 400-450watt PSU & a 120gb HDD for your OS & MAME,and with a little overclocking you should hit 3.2ghz (8x 400fsb) and with a some more extreme overclocking and some luck you could get as high as 3.6ghz  >:D (9x 400fsb), without the need for a lot expensive hardware.

(I suggest dropping the Multiplier below 11x and increasing the FSB to 400mhz, as the P35 chipset will easily handle 400fsb and the extra bandwidth doing this will give you will help hide the any drop in preformance you may get from the E4500 having only 2mb cache.)

That should get you 80-90% of my benchmark scores which as long as your running MAME64 0.120u1 in Vista 64, that will put most of the working ROMs on my benchmark list in the playable basket for you.

Thanks for the run.  Yes you're missing the fastest configuration of .120u1 at 64bit.  The jumps Aaron made in the software sli and applying that to the other 3d drivers really gave some nice boosts.  He does his 64bit builds [PTR64=1 ]w/out PM=1 so it will be interesting to see if there are any changes w/ PM=1.

As soon as I can get myself sorted with the whole compiling a 64bit build of mame, I'll post both In-game & CPU benchmarks for MAME64 0.120u1 with and without PM optimisation. (It really shouldN'T be this hard  :P, but like I said I'm rusty, and the documantion on compiling MAME64 sucks.)

This post might help

http://www.mameworld.info/ubbthreads/showthreaded.php?Cat=&Number=129879&page=0&view=expanded&sb=5&o=&fpart=1&vc=1


Thanks for the link, I think I have all the required files now, I've just got to install everything get everything in the right place on my HDD, and then I can try it all out.


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on November 03, 2007, 04:18:16 am
Just FYI, I released the 64bit version of Mame32 .120.2 after going to Vista-64 the other night.  Got some nice increases as you're seeing too.

Game   Driver   Arguments   .120.2-32   .120.2-64   Δ
crusnusa   midvunit.c   -str 90 -video none -nosound -nothrottle -norc -nosleep   182.84%   220.81%   20.77%
starblad   namcos21.c   -str 90 -video none -nosound -nothrottle -norc -nosleep   119.37%   127.74%   7.01%
gauntleg   vegas.c   -str 90 -video none -nosound -nothrottle -norc -nosleep   139.10%   163.50%   17.54%
blitz   seattle.c   -str 90 -video none -nosound -nothrottle -norc -nosleep   113.12%   145.63%   28.74%
daytona   model2.c   -str 90 -video none -nosound -nothrottle -norc -nosleep   89.09%   120.89%   35.69%
gradius4   hornet.c   -str 90 -video none -nosound -nothrottle -norc -nosleep   97.97%   79.57%   -18.78%
radikalb   gaelco3d.c   -str 90 -video none -nosound -nothrottle -norc -nosleep   109.88%   163.93%   49.19%
ridgerac   namcos22.c   -str 90 -video none -nosound -nothrottle -norc -nosleep   92.37%   147.79%   60.00%
scud   model3.c   -str 90 -video none -nosound -nothrottle -norc -nosleep   33.88%   28.48%   -15.94%
Vista Ultimate 64 • Intel C2D E6400 3.5Ghz • 2GB Corsair DDR2 800 • ATI X1950 Pro               20.47%
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 03, 2007, 08:43:10 am
Just FYI, I released the 64bit version of Mame32 .120.2 after going to Vista-64 the other night.  Got some nice increases as you're seeing too.

Sweet, that saves me from another day of going around in circles trying to compile a 64bit build,  Does this mean there will be an official 64bit of MAME32 from now on ?   :notworthy: (I'd love a step by step how-to of what I need and where to put it, to make my own 64bit MAME builds if you have time to write one)

Running MAME in 64bit really does make for some great improvements, but it's interesting that gradius4 CPU score takes such a hit in preformance when you jump to 64bit, where as the 32bit versions show an increase in preformance with each new build, yet the 64bit builds take a pounding. (Maybe it's a little too optimised for the 32bit Enviroment to work well in 64bit currently.)

I ran a set of the pure CPU benchmarks on your MAME32 64bit build, and update the score chart. (I finally figured out why I wasn't getting an output to file from Mame32)

CPU
ROM
Driver
      0.119   
     0.120   
     0120u1 
     0120u2 
   0.120(64)
   0.120u2(64)
E6400 @ 3.4ghz     crusnusa   midvunit.c
212.24%
212.12%
178.27%
182.84%
  n/a
220.81%   
E6850 @ 4.0ghzcrusnusa   midvuint.c
257.69%
257.32%
218.20%
214.79%
271.81%
269.31%   
E6400 @ 3.4ghz    starblad   namcos21.c
234.33%
120.83%
116.97%
119.37%
  n/a
127.74%   
E6850 @ 4.0ghzstarblad   namcos21.c
299.30%
144.10%
144.00%
142.10%
153.57%
150.71%   
E6400 @ 3.4ghz    gauntleg   vegas.c
47.92%
114.97%
132.38%
139.10%
  n/a
163.50%   
E6850 @ 4.0ghzgauntleg   vegas.c
68.91%
166.17%
173.07%
166.03%
183.42%
191.32%   
E6400 @ 3.4ghz    blitz   seattle.c
122.25%
87.86%
111.59%
113.12%
  n/a
145.63%   
E6850 @ 4.0ghzblitz   seattle.c
153.43%
138.59%
143.28%
136.99%
164.15%
185.35%   
E6400 @ 3.4ghz    daytona   model2.c
   n/a
86.18%
87.22%
89.09%
  n/a
120.89%   
E6850 @ 4.0ghzdaytona   model2.c
   n/a
106.17%
106.43%
104.94%
142.72%
140.42%   
E6400 @ 3.4ghz    gradius4   hornet.c
60.36%
79.34%
   n/a
97.97%
  n/a
79.57%   
E6850 @ 4.0ghzgradius4   hornet.c
116.72%
164.94%
   n/a
180.32%
122.16%
125.69%   
E6400 @ 3.4ghz    radikalb   gaelco3d.c
77.46%
76.11%
95.72%
109.88%
  n/a
163.93%   
E6850 @ 4.0ghzradikalb   gaelco3d.c
94.25%
93.97%
116.77%
129.44%
150.07%
200.22%   
E6400 @ 3.4ghz    ridgerac   namcos22.c
65.56%
64.73%
90.77%
92.37%
  n/a
147.79%   
E6850 @ 4.0ghzridgerac   namcos22.c
80.00%
79.54%
114.89%
112.44%
106.77%
194.55%   
E6400 @ 3.4ghz    scud   model3.c
34.41%
32.91%
33.00%
33.88%
  n/a
28.48%   
E6850 @ 4.0ghzscud   model3.c
41.21%
39.60%
39.56%
38.93%
33.81%
33.89%   

Looks like scud is the only ROM still holding out, but since it's a non-working rom and the emulation needs a lot of work, it only makes sense that it's scores are low. I had Task Manager open on the Preformance tab while running this lastest set of benchmarks, it showed that the model2.c & model3.c drivers are noticably lacking any form of multi-threading with one core being loaded to near 100% while the other is lucky to hit 10%, It will be interesting see if any of Aaron's software SLI magic can be applied to these drivers in the future.

For those still interested I'll run a full set of In-Game benchmarks tommorow with the 64bit build of MAME 0.120u2, but in the mean time here's a preview:

Propcycl:
0.120u2 (64bit)       151.88%         91.28fps

Blitz:
0.120u2 (64bit)       171.18%       102.71fps

Gauntleg:
0.120u2 (64bit)       142.84%         81.42fps
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: AaronGiles on November 03, 2007, 04:39:40 pm
Thanks for the benchmark results. scud and gradius4 both use the PowerPC, which has a DRC on 32-bit but not on 64-bit, so it's not surprising that 64-bit is slower.

In terms of future work, model2 and model3 can definitely be accelerated the same way, just haven't gotten around to it yet. System21 probably can be as well.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Red on November 03, 2007, 06:13:21 pm
Thanks for the benchmark results. scud and gradius4 both use the PowerPC, which has a DRC on 32-bit but not on 64-bit, so it's not surprising that 64-bit is slower.

In terms of future work, model2 and model3 can definitely be accelerated the same way, just haven't gotten around to it yet. System21 probably can be as well.

Thanks for all your work Aaron.  It is much appreciated.

Red
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 04, 2007, 01:06:58 am

Thanks for the benchmark results. scud and gradius4 both use the PowerPC, which has a DRC on 32-bit but not on 64-bit, so it's not surprising that 64-bit is slower.

Just glad I be help, even if It only in a little way. I figured there had to be something about the 32bit code that didn't translate to 64bit I just didn't know what it would be.


In terms of future work, model2 and model3 can definitely be accelerated the same way, just haven't gotten around to it yet. System21 probably can be as well.

I figured as much, if it works as well as it did vegas.c and the other we should see some really nice preformance gains for it. I was suprised by how effectively it maxed out both cores on my CPU, If I get a chance in the next couple of days I'll run a set of the Pure CPU benchmark on one of the Q6600 quad cores on display at work, atleast one of them is running Vista 64 so I'll probably benchmark 64bit MAME 0.120u2 and see how it goes.

Anyway thanks for answering my queries', and if there is anything else i can do to help just let me know.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 04, 2007, 01:17:36 am
Here are the In-game benchmark results for MAME32 64bit 0.120u2 (i'll tidy them up into a easy to read table in the next couple of day, but for now it's a cut and paste job.


- 1492      
0.120      5570.54%   3342.32fps
0.120 64bit   6503.71%   3902.23fps

gaelco3d.c
- radikalb   
0.120      88.21%      52.93fps          
0.120 64bit   134.23%      
0.120u1      117.74%      70.64fps
0.120u2   64bit   177.31%      

- speedup   
0.120      102.93%      61.76fps   
0.120 64bit   157.14%      
0.120u1      127.66%      76.60fps
0.120u2   64bit   177.36%

- surfplnt   
0.120      91.29%      54.77fps   
0.120u1 64bit   139.72%
0.120u1      112.79%      67.67fps
0.120u2   64bit   162.83%

Mediagx.c
- a51site4   
0.120      185.95%      111.57fps   
0.120 64bit   234.34%      
0.120u1      186.04%      111.62fps
0.120u2 64bit   239.42%      

medvunit.c
- crusnusa   
0.120      225.23%      128.38fps   
0.120 64bit   271.99%
0.120u1      220.16%      125.49fps
0.120u2 64bit   269.87%

- crusnwld   
0.120      229.70%      130.93fps   
0.120 64bit   249.66%
0.120u1      221.42%      126.21fps
0.120u2 64bit   238.78%

- offroadc   
0.120      395.36%      225.36fps   
0.120 64bit   425.80%
0.120u1      365.57%      208.38fps   
0.120u2 64bit   427.64%

- wargods   
0.120      376.85%      214.80fps   
0.120 64bit   411.71%
0.120u1      330.00%      188.10fps
0.120u2 64bit   404.79%

namcos22.c
- airco22b
0.120      97.73%      58.64fps    
0.120 64bit   124.71
0.120u1      110.64%     66.38fps
0.120u2 64bit   150.83%

- alpinerd   
0.120      42.36%      25.42fps   
0.120 64bit   53.37%
0.120u1      65.95%      39.57fps
0.120u2   64bit   97.53%

- cybrcomm   
0.120      67.79%      40.68fps   
0.120 64bit   96.65%
0.120u1      95.78%      57.49fps
0.120u2   64bit   145.39%

- cybrcycc   
0.120      125.69%      75.41fps   
0.120 64bit   161.28%
0.120u1      157.40%      94.44fps
0.120u2 64bit   209.53%

- propcycl   
0.120      70.44%      42.50fps   
0.120 64bit   96.31%
0.120u1      100.39%      60.23fps
0.120u2 64bit   152.83%

- raveracw   
0.120      53.70%      32.22fps   
0.120 64bit   68.33%
0.120u1      81.37%      48.82fps
0.120u2 64bit   130.37%

- ridgerac   
0.120      75.84%      45.50fps   
0.120 64bit   103.33%      
0.120u1      108.13%      64.88fps
0.120u2 64bit   164.51%

- timecris   
0.120      70.84%      42.50fps   
0.120 64bit   93.17%
0.120u1      101.81%      61.09fps
0.120u2 64bit   158.05%

Seattle.c   
- biofreak
0.120      91.78%      55.07fps
0.120 64bit   140.22%      
0.120u1      101.70%      57.97fps
0.120u2   64bit   137.62%


- blitz      
0.120      122.34%      73.40fps   
0.120 64bit   153.09%
0.120u1      127.38%      72.61fps
0.120u2 64bit   173.04%

- blitz2k   
0.120      121.94%      69.51fps   
0.120 64bit   146.08%
0.120u1      123.73%      70.52fps
0.120u2   64bit   160.07%

- blitz99   
0.120      120.27%      68.55fps   
0.120 64bit   142.65%
0.120u1      120.26%      68.55fps
0.120u2 64bit   152.24%

- calspeed   
0.120      146.21%      83.34fps   
0.120 64bit   181.91%
0.120u1      165.08%      94.10fps
0.120u2      211.28%


- carnevil
0.120      241.11%      137.43fps   
0.120 64bit   287.40%
0.120u1      221.69%      126.36fps
0.120u2 64bit   268.86%

- hyprdriv   
0.120      140.84%      80.28fps   
0.120 64bit   185.50%
0.120u1      144.27%      82.23fps
0.120u2 64bit   175.13%

- mace      
0.120      173.23%      98.74fps   
0.120 64bit   217.20%
0.120u1      186.67%      106.40fps
0.120u2 64bit   255.76%

- sfrush   
0.120      144.95%      82.62fps   
0.120 64bit   199.68%
0.120u1      152.01%      86.64fps
0.120u2 64bit   204.46%

- wg3dh      
0.120      253.19%      144.32fps   
0.120 64bit   342.70%
0.120u1      265.32%      151.23fps
0.120u2 64bit   383.10%


Vegas.c
- gauntdl
0.120      108.58%     61.89fps    
0.120 64bit   123.46%
0.120u1      110.06%      62.73fps
0.120u2 64bit   132.08%

-gauntleg
0.120      108.57%      61.88fps
0.120 64bit   153.76%            (tends to lockup)
0.120u1      111.60%      63.61fps
0.120u2 64bit   152.79%

- tenthdeg   
0.120u1      62.03%      35.36fps   
0.120 64bit   76.21%
0.120u1      67.42%      38.43fps
0.120u2 64bit   83.69%

model2.c
- Daytona         
0.120      120.15%      72.06fps   
0.120 64bit   157.64%
0.120u1      120.08%      72.05fps
0.120u2 64bit   155.59%

hornet.c
- gradius4   
0.120      112.04%      67.91fps
0.120 64bit   92.69%
0.120u1      fails instantly with memory error
0.120u2      117.38%
0.120u2 64bit   96.02%

Model3.c
- scud      
0.120      40.98%      24.59fps   
0.120 64bit   33.57%
0.120u1      44.21%      26.53fps
0.120u2 64bit   n/a


namcos21.c   
- starblad
0.120      140.06%      84.03fps
0.120 64bit   146.24%
0.120u1      139.95%      83.97fps
0.120u2 64bit   144.54%

-swtrilgy (Emulation need a lot of work still graphics issues)
0.120u1      61.66%      39.97fps

Basically the results show if it's a working ROM it's playable and by a good margin in most cases, there are a couple like tenthdeg and aplinerd that still coming in a little low, but gauntleg looked up playable a couple of builds back and now it runs great so only time will tell with these two.




Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Haze on November 04, 2007, 09:33:55 am
could you benchmark this? http://www.mameworld.net/maws/set/puzzlekg  (Puzzle King Dance & Puzzle.. by Eolith)


I'd be interested to know how well it performs on the 4ghz machine, yes, it's a simple 2d game, but it pushes the e132xs (hyperstone) core pretty hard, so the speedups have little effect.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on November 04, 2007, 09:37:16 am
I purchased vista 64 yesterday as soon as I get my new quad 4 built w/vista I will also post framerates, im going to use his guide for overclocking also, much better than I have been able to do
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Red on November 04, 2007, 12:24:13 pm
Thanks for all your hard work on the benchmarks taz. 

It's looking like my next computer purchase will finally be able to play Blitz!

Do you have to compile a 64bit build of MAME to get these results?  Or can you just run regular MAME 64?

Did I miss it in the thread that said why you were compiling MAME 64?  I'm new to MAME and just don't understand the whole compiling stuff and why one would want to do it if the MAME devs have already done it for us with MAME 64.

Also, what's better for 64 bit MAME- Windows XP or Vista?  Thanks guys.

Red
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on November 04, 2007, 03:37:52 pm
could you benchmark this? http://www.mameworld.net/maws/set/puzzlekg  (Puzzle King Dance & Puzzle.. by Eolith)


I'd be interested to know how well it performs on the 4ghz machine, yes, it's a simple 2d game, but it pushes the e132xs (hyperstone) core pretty hard, so the speedups have little effect.

This is at 3.5Ghz
mame32 -str 90 -video none -nosound -nothrottle -norc -nosleep puzzlekg
Average speed: 95.19% (89 seconds)

About 85% during gameplay part of demo.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 05, 2007, 03:57:51 am
could you benchmark this? http://www.mameworld.net/maws/set/puzzlekg  (Puzzle King Dance & Puzzle.. by Eolith)


I'd be interested to know how well it performs on the 4ghz machine, yes, it's a simple 2d game, but it pushes the e132xs (hyperstone) core pretty hard, so the speedups have little effect.

Core 2 Duo E6850 @4.0ghz running

Puzzlekg:
MAME32 01.20u2 (32bit)            119.68%           71.81fps
MAME32 01.20u2 (64bit)            109.00%           65.40fps

Go figure, who would have thought such a simple game could eat up so much processor time to emulate. But since most of the in game screen is static, it should be playable even at those scores as your unlikely to see wild swings in frame rate while playing.

I purchased vista 64 yesterday as soon as I get my new quad 4 built w/vista I will also post framerates, im going to use his guide for overclocking also, much better than I have been able to do
dm

I'm very interested to see what you overclocked scores are, I ran a set of benchmarks on a stock Q6600 today (results below) at I got more questions than answers out of do it.

Pure CPU benchmarks for Q6600 @2.4ghz, 4gb, 8800gts, Vista 64

CPU
ROM
Driver
   0.120u2(64)
E6400 @ 3.5ghz     crusnusa   midvunit.c
220.81%   
E6850 @ 4.0ghzcrusnusa   midvuint.c
269.31%   
Q6600 @ 2.4ghz     crusnusa   midvunit.c
139.86%   
E6400 @ 3.5ghz    starblad   namcos21.c
127.74%   
E6850 @ 4.0ghzstarblad   namcos21.c
150.71%   
Q6600 @ 2.4ghz     starblad   namcos21.c
90.47%   
E6400 @ 3.5ghz    gauntleg   vegas.c
163.50%   
E6850 @ 4.0ghzgauntleg   vegas.c
191.32%   
Q6600 @ 2.4ghz     gauntleg   vegas.c
133.76%   
E6400 @ 3.5ghz    blitz   seattle.c
145.63%   
E6850 @ 4.0ghzblitz   seattle.c
185.35%   
Q6600 @ 2.4ghz     blitz   seattle.c
128.91%   
E6400 @ 3.5ghz    daytona   model2.c
120.89%   
E6850 @ 4.0ghzdaytona   model2.c
140.42%   
Q6600 @ 2.4ghz     daytona   model2.c
83.73%   
E6400 @ 3.5ghz    gradius4   hornet.c
79.57%   
E6850 @ 4.0ghzgradius4   hornet.c
125.69%   
Q6600 @ 2.4ghz     gradius4   hornet.c
65.95%   
E6400 @ 3.5ghz    radikalb   gaelco3d.c
163.93%   
E6850 @ 4.0ghzradikalb   gaelco3d.c
200.22%   
Q6600 @ 2.4ghz     radikalb   gaelco3d.c
109.55%   
E6400 @ 3.5ghz    ridgerac   namcos22.c
147.79%   
E6850 @ 4.0ghzridgerac   namcos22.c
194.55%   
Q6600 @ 2.4ghz     ridgerac   namcos22.c
33.74%   
E6400 @ 3.5ghz    scud   model3.c
28.48%   
E6850 @ 4.0ghzscud   model3.c
33.89%   
Q6600 @ 2.4ghz     scud   model3.c
20.16%   

I'm not sure what to make of these results, for most of the result the Q6600 results are in keeping with MAME scaling with CPU clock, but the score are almost those I like those I would expect from a 2.4ghz Core 2 Duo, there is not sign of any preformance gain on the Multi-thread drivers even though all 4 core were being used to about 75%+ load on average. 

But the really weird result is from ridgerac, which tanks total on the quad core.

I guess we will have to wait for more Quad core benchmarks at a couple of different CPU clocks before we get any real idea of a preformance pattern for Quad Core CPUs. (I've got a feeling the low FSB bus speed and thus limited FSB bandwidth is getting in the way of the Quad core really preforming)

Thanks for all your hard work on the benchmarks taz. 

It's looking like my next computer purchase will finally be able to play Blitz!

Thanks, I'm just glad people are get some use out of all it, and hope this put the myth that you need a 10ghz CPU to run CHD rom to rest once and for all.

If your not buying until next year the Intel Yorkdale (quad) and Wolfdale (dual) cored processors look like to hold a lot of potential for overclocking and may make 4.5ghz & 5.0ghz overclocks possible. (without the ultra extreme cooling) I don't think anyone here is going to be running out to buy a Core 2 Extreme QX9650 any time soon, so we will have to wait and see what happens next year.

Do you have to compile a 64bit build of MAME to get these results?  Or can you just run regular MAME 64?

Did I miss it in the thread that said why you were compiling MAME 64?  I'm new to MAME and just don't understand the whole compiling stuff and why one would want to do it if the MAME devs have already done it for us with MAME 64.

I currently using standard MAME32 0.120 builds by John IV for both 64 & 32 bit benchmarks.

All the official builds are non-optimised so they will run on any CPU, but by compiling your our build you can optimised the builds to the processor your using and thus gain an extra few percent in the benchmark scores, using a PM optimised build on a Core 2 Duo appears to add 5-8% to your scores.

I'd also like to start playing with the source to see if I can get to know it a bit and may help out in the future.

Also, what's better for 64 bit MAME- Windows XP or Vista?  Thanks guys.

Red

To tell the truth I'm not a huge fan of Vista, but it has been growing on me, I much prefer Windows XP as my main OS. But in saying that I'd have to say get Vista 64 for a couple of pratical reasons, 64bit XP never really took off and driver support for it is fairly limited, where as Vista 64 is fairly well supported and I expect that will only improve with time, 64bit XP also still retains some rather nasty memory addressing limitations for 32bit windows that Vista 64bit does away with.

You can always run dual boot like myself if you can't live with Vista on a full time basis.


 

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on November 05, 2007, 10:00:29 am
Thanks, I'm just glad people are get some use out of all it, and hope this put the myth that you need a 10ghz CPU to run CHD rom to rest once and for all.
In fairness, I believe Aaron originally posted the 10ghz spec when people were struggling with Pentium 4's and Athlon's at less than 2 or 2.5 Ghz.  This was before Quad-core or even C2D or A64 had come to market.

I suspect your quad-core at 4 Ghz, is roughly equivalent to one of the processors of the time running at 10 Ghz.

I appreciate all the testing and all the gains made by MameDev, though!!!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on November 05, 2007, 10:06:28 am
The reason I jumped to the quad core, on the benchmarks I ran, the quad is twice as fast as my dual core e6600 was.  I think if the quad had your magic like the other 2 computers, it would be much faster in mame.  But after I finish the build if I find the quad is slower than the dual core due to the FSB no problem, I will switch the quad for the E6750 dual core in my racing setup & use that one.
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: metahacker on November 05, 2007, 02:11:25 pm
taz, thanks again for this wonderful thread & research :)

i've found it rather inspiring.  so much so that i am getting rid of my tinyxp and going to vista64...and i've got my 2.66 cranked up to 3.6 (so far).. no sweat running orthos 24-7.....maybe i can get lucky and hit 4.0 =) but not so sure about that.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: ARTIFACT on November 05, 2007, 11:14:29 pm
why use DDRAW on all these games which are ... 3D?

D3D would seem to fit much better with these 3D games.
Just curious if you see better performance... I'd imagine... Technically DDRAW isn't meant to be used to render 3D like that.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 06, 2007, 02:49:47 am

In fairness, I believe Aaron originally posted the 10ghz spec when people were struggling with Pentium 4's and Athlon's at less than 2 or 2.5 Ghz.  This was before Quad-core or even C2D or A64 had come to market.

I suspect your quad-core at 4 Ghz, is roughly equivalent to one of the processors of the time running at 10 Ghz.

I appreciate all the testing and all the gains made by MameDev, though!!!
Your right my 4ghz Core 2 Duo (dual core) is equal to about a P4 8ghz, with :notworthy: the MAME Dev team's great work taking up the slack to the 10ghz mark.

I'm not saying that the statement "you need a 10ghz CPU to run CHD roms" wasn't accurate at the time it was first used, 3 years or so ago, (well it was more like 5ghz at first then people upped it 10ghz with time) and I not attacking the people who said it back then, but the Core 2 Duo has been out for well over a year now and I was still seeing people using it as little as a couple of weeks ago, and it's simply no longer true. 

 :soapbox:

I saw it as MAME tall poppy syndrome, where anyone that dared to ask what they needed to run all the MAME roms at full speed was shot down and told to go buy a used P4 and don't waste their money. I don't expect everyone to run out a build 4ghz MAME monster machines, but atleast now people know it can be done and can choose for themselves that preformance level they want to take their MAME box to.

I just hope it puts it to rest for a while, atleast until we have some new fully emulated ROMs that can't be run on current PC hardware.

The reason I jumped to the quad core, on the benchmarks I ran, the quad is twice as fast as my dual core e6600 was.  I think if the quad had your magic like the other 2 computers, it would be much faster in mame.  But after I finish the build if I find the quad is slower than the dual core due to the FSB no problem, I will switch the quad for the E6750 dual core in my racing setup & use that one.
dm

Quad Core processors can pull of some extreme preformance gains running the kind of apps, I don't think the Q6600 did that bad in my benchmarks other than in ridgerac which I'm at a lost to explain, but I was expect a boost in scores on with the multi-threaded drivers and I just didn't see it. Maybe with a clock speed the quad core will shine more, but I guess we will have to wait until you post your result to see.  So I'm really looking forward to seeing you benchmark results.

taz, thanks again for this wonderful thread & research :)

i've found it rather inspiring.  so much so that i am getting rid of my tinyxp and going to vista64...and i've got my 2.66 cranked up to 3.6 (so far).. no sweat running orthos 24-7.....maybe i can get lucky and hit 4.0 =) but not so sure about that.

2.66ghz to 3.6 that a nice overclock, everything after 3.6ghz gets harder no matter what CPU clock you start with, but if it's a 100% stable like you say, and you've not already pumping insanely high core voltages into it, then I can say keep going and see where it take you, just watch those core temps.

I love TinyXP it's great for testing, 10mins to install and your in windows, now if only someone would make a TinyVista64, 15GB just for a base install is insane, my C: partition for XP Pro is only 6.4GB and it half empty, someone need to cut the fat out of Vista big time.

why use DDRAW on all these games which are ... 3D?

D3D would seem to fit much better with these 3D games.
Just curious if you see better performance... I'd imagine... Technically DDRAW isn't meant to be used to render 3D like that.

MAME doesn't use your 3D hardware to render anything, even if you running a ROM that uses all 3D graphics everything is done on your CPU, and then passed as 2D frames to your graphics card to display, MAME could easily take advantage of your 3D graphics hardware like many other emulators do, but the results you would get on screen would not be true to the orginal arcade machine.

Just to see what the difference would be I ran a quick benchmark on propcycl.
MAME32 0120u2 64bit      DDRAW        152.83%
MAME32 0120u2 64bit      Direct3D       116.72%

As you can see it was noticably slower and I also noticed a drop in the quality of what was being displayed. You would have to ask one of the Dev's to explain this.

If anyone know how I can extract from mame a complete list of parent ROMs based on the driver they used let me know.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: genesim on November 06, 2007, 03:01:57 am
Quote
In fairness, I believe Aaron originally posted the 10ghz spec when people were struggling with Pentium 4's and Athlon's at less than 2 or 2.5 Ghz.

The problem is that people keep repeating these things as if the facts never change.   Even back when I first pointed out the obvious multithread advantages there were many that argued in denial....without even testing the fact.

The funny thing is that while many have kept repeating the obsolete information, the devs starting working behind their backs.   ;D

taz-nz,

Thanks for your work, and I also have been seeing speed jumps with my AMD 4400.   This is after it was configured correctly.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on November 06, 2007, 06:11:57 am
If anyone know how I can extract from mame a complete list of parent ROMs based on the driver they used let me know.
Emuloader might be able to do this, depending on what you are looking for - also I think BuddaBing wrote a -listgen utility that would likely do a better job of that.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: ozzi22 on November 06, 2007, 10:42:37 am
I wonder what the bench marks would be on linux 64
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: ahofle on November 06, 2007, 11:00:32 am
This is slightly off topic, but also slightly on topic.  ;D

Last night I overclocked my E6750 from 2.66 Ghz to 3.2 Ghz.  I simply adjusted the FSB to 400 Mhz and set the memory to 800Mhz for 1:1.  I was expecting to have to go back in and adjust the voltage, but I can't seem to make the voltage any lower than it already is (1.30 - 1.31V).  It seems to be running fine, but most of the guides I've read have people trying to find the minimum stable voltage to minimize heat and I have no way of decreasing the value (only increasing).   ???  This is on an Abit IP35 Pro mobo.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: xmenxmen on November 06, 2007, 11:15:46 am
Refurb HP a6152n, Core 2 Quad Q6600, 3GB, 400GB, Vista Premium, $550 + $12 shipped (Frys Online)

http://www.fatwallet.com/t/18/778709/ (http://www.fatwallet.com/t/18/778709/)

Enjoy!!!!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on November 06, 2007, 02:27:03 pm
I was expecting to have to go back in and adjust the voltage, but I can't seem to make the voltage any lower than it already is (1.30 - 1.31V).  It seems to be running fine, but most of the guides I've read have people trying to find the minimum stable voltage to minimize heat and I have no way of decreasing the value (only increasing).
Generally, you raise the voltage to increase stability and lower it to reduce heat.

Typically, you bump it up a bit, find the max overclock it will boot at - drop down a bit from this for what you want to run at, and then drop the voltage from what you ramped up to to reduce heat if possible.

I am not current enough to know on your specific processor, but Taz is running 1.5 something volts and DM is running 1.7, so if you are stable at 1.3, I wouldn't worry, but that might be way off if say they have a different core config than you do, so take it with a grain of salt.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 06, 2007, 02:55:28 pm
If anyone know how I can extract from mame a complete list of parent ROMs based on the driver they used let me know.
Emuloader might be able to do this, depending on what you are looking for - also I think BuddaBing wrote a -listgen utility that would likely do a better job of that.

thanks I'll check it out, I look for a way I can create a benchmark call file for a large number of roms without a lot of typing, if I can please a plain txt list, i can soon right a bit of code to format it into a batch file.

I wonder what the bench marks would be on linux 64

I would to like to see 64 bit linux benchmarks results too, but I unlikely to be running them any time soon, Linux + latest chipset motherboard + raid array = come back in 6 months when we there are drivers. (atleast that been the story the last 3 times I tried to install Linux on a new machine)

This is slightly off topic, but also slightly on topic.  ;D

Last night I overclocked my E6750 from 2.66 Ghz to 3.2 Ghz.  I simply adjusted the FSB to 400 Mhz and set the memory to 800Mhz for 1:1.  I was expecting to have to go back in and adjust the voltage, but I can't seem to make the voltage any lower than it already is (1.30 - 1.31V).  It seems to be running fine, but most of the guides I've read have people trying to find the minimum stable voltage to minimize heat and I have no way of decreasing the value (only increasing).   ???  This is on an Abit IP35 Pro mobo.


Your talking about undervolting and it's normally do to reduce heat and power useage, I have an undervolted and underclocked Athlon64 3000+ in my media box with passive cooling. People also undervolt with extreme cooling systems like phase change systems, but it your only useing air cooling you should be run stock voltage up to able 3.4-3.6ghz then you will need to increase it to overcome Vdrope, the catch is the more voltage you put in the more heat your cpu produces, the higher the CPU core temp the higher the voltage generally has to be to make the system stable, there is a point of zero return where all your doing is cooking your CPU.

Refurb HP a6152n, Core 2 Quad Q6600, 3GB, 400GB, Vista Premium, $550 + $12 shipped (Frys Online)

http://www.fatwallet.com/t/18/778709/ (http://www.fatwallet.com/t/18/778709/)

Enjoy!!!!

Good price on the surface, but it an HP box, so gutless 350watt PSU, no talk of the chipset used so probably something nasty, the bios will have zero overclocking settings. 3gb of points to another weild setup, probably only DDR2-667. If your looking for a cheap box with vista it's ok, but useless for overclocking or preformance computing. Stay away from brand name PC where ever possible they are built to look good and be cheap, and make the manufacture great margin at the same time, they hide a list of sins then you crack the case.



Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on November 06, 2007, 03:06:08 pm
If anyone know how I can extract from mame a complete list of parent ROMs based on the driver they used let me know.

Hmm, mame -ls gives a full list, parents and clones. For not a complete list, there are maws (driver list), and the source files (of course ;), look at list at end of the file).

However, you'll have do some sorting to get the parents.  One way, in the source, the GAME MACRO goes:
GAME( YEAR, NAME, PARENT, MACHINE, INPUT, INIT, ROT, COMPANY, FULLNAME, FLAGS )
If the parents part is 0 then it's a parent, otherwise it's the name of the parent.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on November 06, 2007, 03:57:58 pm
thanks I'll check it out, I look for a way I can create a benchmark call file for a large number of roms without a lot of typing, if I can please a plain txt list, i can soon right a bit of code to format it into a batch file.
I know EL can select only parent ROMS (and roms based on game CPU or driver, for that matter) and can export the selected games to a text file.  I don't recall, but I think the text file might have:
mame=aburner
mame=asteroid
mame=bzone
etc.
but a little bit of search and replace "mame=" with "" in Word or a text editor might get you what you want, I hope!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on November 06, 2007, 05:10:10 pm
If anyone know how I can extract from mame a complete list of parent ROMs based on the driver they used let me know.

Oh, and -listxml, too, but as is it's, umm, bulky.  RomLister (http://www.waste.org/~winkles/ROMLister/) can convert the xml to a list, as well as sort out clones, and output a batch file to run games.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 07, 2007, 06:01:50 am
If anyone know how I can extract from mame a complete list of parent ROMs based on the driver they used let me know.

Oh, and -listxml, too, but as is it's, umm, bulky.  RomLister (http://www.waste.org/~winkles/ROMLister/) can convert the xml to a list, as well as sort out clones, and output a batch file to run games.

Thanks for the tip worked great, created the XML file imported it into Romlister, filtered it for all working parent ROMs, and saved the list to a txt file. (3125 roms in total) Whipped up a bit of code in QBasic to turn the list of roms in to a call file for the benchmarking batch I use. (Yes I used Quick Basic, 8 lines of code and no need to compile.)I set the call file going and let it run for about 2.5 hours it got though about 350 roms, the worst score was for finalapr @ 5.99% you figure that one out.

I need to whip another bit of code to turn all the resulting txt files in to one file with all the ROM names and results. I may set the call file going and just let it run one day while I'm at work and see what I get in the way of result, some ROMs will get insane scores because they need user input to get pass the test screens, I seen a couple already that have scores around the 12000% mark. Probably not much use as a preformance test, but good for picking out the those roms that still have preformance issues.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Red on November 07, 2007, 12:57:50 pm
What's Tiny XP and where do I get it?  Thanks.

Red
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: tommyinajar on November 07, 2007, 01:39:41 pm
It 's a stripped down version of XP with alot of junk you don't need taken out, originally made for slower PC's.

It's NOT a Mic@$oft  release, it is a pirated ware. Make sure you own an original copy :) 1st.

Do a torrent Search for it.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: metahacker on November 07, 2007, 03:37:42 pm
What's Tiny XP and where do I get it?  Thanks.

Red

google "TinyXP rev06"... "Tiny2003" is worth investigating as well.... it's quite an interesting build of windows. You can build your own copy of XP like TinyXP using nLite..... also, like he said, you need to have your own XP or W2K3 SVR license to use these legally.
:)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Red on November 07, 2007, 06:06:09 pm
Thanks guys, much appreciated.

Red
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 07, 2007, 06:49:03 pm
What is PM and where could I find a PM build?
I would like to compare my benchmarks with yours (scaled down to 2.4GHz).

Thanks.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Shoegazer on November 07, 2007, 07:39:23 pm
Just read through this thread with great interest... very nice.

It's odd seeing all these great framerates.  I have a 2ghz dual-core laptop (core duo, NOT core2duo mind you), running xp32 and MAME32.  I realize I won't be able to even approach some of the stratospheric results I've been seeing from the likes of taz-nz, but still I did notice something weird: I checked "Multi-threaded rendering" and tried out every one of the games that have been tested in this thread (blitz2k, propcycl, etc).  Result?  0% increase in all cases.

My 2nd core is turned on in the BIOS, so what gives?  Weird.  I'm probably going to upgrade to a Penryn laptop next year when Intel releases it, though in the meantime it would be nice to see at least SOME performance increase out of this old dog...

Shoegazer
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 07, 2007, 08:11:56 pm
I did not see much from enabling MT either.
When you compare your results to those of the author of the post, make sure to run his same command line parameters.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 08, 2007, 03:46:34 am
What is PM and where could I find a PM build?
I would like to compare my benchmarks with yours (scaled down to 2.4GHz).

Thanks.

PM stands for Pentium M (mobile) the Pentium M, Core Solo, Core Duo, Core 2 Duo, & Core 2 Quad are all in same family of processors, and thus if you use the PM switch to compiling an optimised MAME build, these processors will gain a few % in preformance, but that build of MAME will no longer run on other processors, thus the offical MAME builds don't use this or any of the other CPU optimisation. Where do you find a PM optimised build, the easiest is to make one yourself by compiling the MAME source code.  Everything you need to compile your own 32bit build can be found here http://mamedev.org/tools/ (http://mamedev.org/tools/)  and here http://mamedev.org/release.html (http://mamedev.org/release.html). If you work out how to do it for a 64bit build send me a set of step by step instruction. (I still haven't gotten around to doing this myself)

MAME scales almost one to one with CPU clock speed, so if you get a score on a2ghz processor, that processor at 3ghz will get approx 1.5x it's score at 2ghz. So you can scale my scores the same way, 2.4ghz is 60% of 4ghz so your CPU should score around 0.6x my scores, allow +/- 10% for differences in FSB and cache memory etc. , this should get you in the ball park. (but your really need to hit 3ghz or better to make a lot of these games playable)


Just read through this thread with great interest... very nice.

It's odd seeing all these great framerates.  I have a 2ghz dual-core laptop (core duo, NOT core2duo mind you), running xp32 and MAME32.  I realize I won't be able to even approach some of the stratospheric results I've been seeing from the likes of taz-nz, but still I did notice something weird: I checked "Multi-threaded rendering" and tried out every one of the games that have been tested in this thread (blitz2k, propcycl, etc).  Result?  0% increase in all cases.

My 2nd core is turned on in the BIOS, so what gives?  Weird.  I'm probably going to upgrade to a Penryn laptop next year when Intel releases it, though in the meantime it would be nice to see at least SOME performance increase out of this old dog...

Shoegazer

the -MT does make a difference but it varies from ROM to ROM, some MAME drivers see a big boost others don't. The gain also scales with your CPU, so what might be a 1% or 2% gain for you might be a 5% or 6% gain for me, so at slower clock speeds it may be hard to pick any gains form the margin of error in the benchmarks.

I did a quick benchmark of some of the ROM to show the difference I get.

I use the command line:

mame32-64u2.exe -noautoframeskip -frameskip 0 -seconds_to_run 240 -nothrottle -nosleep -video ddraw -skip_gameinfo -effect none -nowaitvsync -noreadconfig -mt  [ROM NAME] >.\bench\[ROM NAME].txt  (with and without the -mt switch)

ROM                with -MT       without -MT

radikalb          177.31%          159.18%
speedup         177.36%           158.01%
a51site4         239.42%          224.46%   
crusnusa          269.87%          253.39%
wargods         404.79%          385.23%
propcycl          152.83%          147.59%
timecris           158.05%          149.28%
blitz                 173.04%          167.22%
carnevil           268.86%          258.99%
wg3dh            383.10%          364.30%
gauntdl           132.08%          129.23%
gradius4           96.02%            93.07%
starblad          144.54%          139.86%

As you can see there is a 5-20% gain to be had on my system from using the -MT switch. (you should see some improvement too, but it may not be as great)

Your best bet to gain some preformance is to compile a PM optimised build and run that I saw about 8-10% gain with the use of a PM optimised build it could be more, I would love to be able to post a set of PM optimised MAME 64bit 0.120u2 benchmarks, but I jsut haven't had time this week to have another go at compiling a 64bit MAME build.







Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 08, 2007, 12:44:31 pm
Thank you very much for taking the time to write that helpful post.
I will be a little more discering with the next benchmark as I did not run it using your process without the mt parameter disabled.  I did use your parameters exactly as you described them, mt enabled.   
I took your numbers for mace and scaled them down to 2.4GHz (my processor).  I am running MAME Plus 120u1 and my % frame output matched almost exactly (just a little over) your scaled number for version 120 but fell short of 120u1 by about 8 percentage points.  However, this is confounded by the fact that your 120u1 version was PM optimized so I will have to give that a try and see where I fall.
I will definitely get into compiling my own version.  Unfortunately, I don't konw if I will be able to help you with a 64bit optimized version as I don't have Vista so I will not be able to tell whether it's working or not.

A recommendation for the futue is to run a fixed number of frames rather than a fixed number of seconds.  The reason is that if someone wants to compare his benchmark to yours (if you care, anyway), and his/her computer is slower, that computer will run a shorter sequence of the game in 240sec so it will not be a 100% apples to apples comparison since some parts of the attract mode of a game are more taxing than others.  This could explain also why I see a slight improvement over your scheduled numbers.  Just an observation.

PS: this also goes to show how overwhelmingly dependent MAME is on processor speed and how little FSB, video card, memory speed and the rest matter.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 08, 2007, 07:47:58 pm
Can anyone tell me what available switches are there while compiling with mingw and how do I specify them?  I also have a PIII that I would like to use on my future cabinet and would like to test different builds on it.
I could not figure this out from the compiling instructions.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Shoegazer on November 08, 2007, 10:23:26 pm
@taz-nz: Thanks for the helpful and informative post.  What you wrote sounds sensible, and I'll definitely be testing more in the near future with this new information in mind.

Regards,
Shoegazer
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 08, 2007, 11:58:51 pm
Can anyone tell me what available switches are there while compiling with mingw and how do I specify them?  I also have a PIII that I would like to use on my future cabinet and would like to test different builds on it.
I could not figure this out from the compiling instructions.

You just need to edit the "makefile" in the MAME source folder before you compile it. Just open the "makefile" with notepad snd scroll down until you find this section of the test.

#-------------------------------------------------
# specify build options; see each option below
# for details
#-------------------------------------------------

# uncomment one of the next lines to build a target-optimized build
# NATIVE = 1
# ATHLON = 1
# I686 = 1
# P4 = 1
# PM = 1
# AMD64 = 1
# G4 = 1
# G5 = 1
# CELL = 1

Just remove the "# " from infront on the "PM = 1" and save and close file then compile MAME as normal, you will note that the MAME exe produced is now called mamepm.exe

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 09, 2007, 09:13:51 am
Thanks.
I am actually compiling a MAME Plus version which looks a little different than that and did change i686=1 lines to pm=1 lines.  In the end I got a mame file called mamepmp.exe which I imagine is the PM optimized build but it did not make a difference on game performance.  Oh well.  I'll keep looking.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: xmenxmen on November 09, 2007, 02:32:55 pm
For those interested, most of the optimized versions are available online:

http://redump.emubase.de/mame.php (http://redump.emubase.de/mame.php)

Wonder if there's much differene between the P4 and PM version?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 09, 2007, 02:58:37 pm
Thank you.
I had seen that website but there is no PM version.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 09, 2007, 03:13:19 pm
For those interested, most of the optimized versions are available online:

http://redump.emubase.de/mame.php (http://redump.emubase.de/mame.php)

Wonder if there's much differene between the P4 and PM version?

More than you might expect, the Pentium M/Core Duo family of processors have more in common with the Pentium 3 than they do with Pentium 4 in many ways, the Netburst architecture used in the P4 was ment to scale all the way to 5Ghz, but due to pressure from the verious versions of the AMD Athlons Intel had to accelerate the scaling of the P4s clock speed, thus they hit a clock speed wall at 3.8-4ghz where they couldn't go any higher because the manufacture processes where now 3 years behind the clock speed curve of the P4. So instead they gave us two years of bandaid fixes with the prescott cores while they when back and developed the Core 2 Duo. (There is a lot more to the history of this but I don't want to bore everyone, and AMD still has the better system architecture, but Intel has the better Core Architecture at the moment)

I knew of the website, but I figured it was better if everyone learned make theier own builds. The pre optimised builds tend to get out of date, like mame is now at 0.120u3 and the site still at 0.120u2 but it will catch up in a few days.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on November 09, 2007, 06:34:14 pm
A recommendation for the futue is to run a fixed number of frames rather than a fixed number of seconds.  The reason is that if someone wants to compare his benchmark to yours (if you care, anyway), and his/her computer is slower, that computer will run a shorter sequence of the game in 240sec so it will not be a 100% apples to apples comparison since some parts of the attract mode of a game are more taxing than others.

Alread done.  Mame's "seconds" in the benchmark is emulated seconds and Mame switched the benchmark/test option to "-seconds_to_run" from "-frames_to_run" a little while ago.

IOW, a game with 60 Hz refresh runs 600 frames if -str 10, no matter if the game runs at 500% or 50%.

The only "differences" between -ftr and -str changes between games with different refresh rates.  On 53 Hz games, -ftr 600 equals about -str 11, and -str 10 equals about -ftr 530; on 61 Hz games, -ftr 600 falls between -str 9 & -str 10, and str 10 equals about -ftr 610.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 09, 2007, 09:07:30 pm
Thank you for correcting my ignorance.  Things have changed in last three an a half years I have been away from the hobby.

By the way, it is good to see you (your web persona I guess) around.  You were very helpful when I was building my control panel years ago.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 09, 2007, 09:12:11 pm
Hit "post" button too early...

I am a little frustrated.
I have tested i686, PM and P3 builds of MAME and they all yield virtually the same result, at least on the game I am benchmarking against which is Mace (it sucks, by the way).
Could I be missing something?  Even the -mt parameter makes no difference and I did set osdprocessors=2.

I am using the same command line parameters as tar-nz on my Core 2 Duo e4300 overclocked to 2.4GHz.  I would like to see the same kind of improvements (proportional to my processor speed) tar-nz saw with the PM build but it is not working for me.

Any pointers will be appreciated.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on November 10, 2007, 12:23:03 pm
Hey guys could I get a couple of opinions I have stopped setting up my new quad until i get some good feedback used to video did not matter but now which video card would you guys use
1. pci-e arcadevga or I have a extra 8800 gts laying around.
My monitor is a betson I did some performance test & the 8800 just runs all over the arcadevga.
thanks for your help
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 11, 2007, 02:56:20 am
CPU
ROM
Driver
      0.119   
     0.120   
     0120u1 
     0120u2 
   0.120(64)
   0.120u2(64)
   0.120u3(64)
E6400 @ 3.4ghz     crusnusa   midvunit.c
212.24%
212.12%
178.27%
182.84%
  n/a
220.81%   
  n/a
E6850 @ 4.0ghzcrusnusa   midvuint.c
257.69%
257.32%
218.20%
214.79%
271.81%
269.31%   
277.86%   
E6400 @ 3.4ghz    starblad   namcos21.c
234.33%
120.83%
116.97%
119.37%
  n/a
127.74%   
  n/a
E6850 @ 4.0ghzstarblad   namcos21.c
299.30%
144.10%
144.00%
142.10%
153.57%
150.71%   
150.75%   
E6400 @ 3.4ghz    gauntleg   vegas.c
47.92%
114.97%
132.38%
139.10%
  n/a
163.50%   
  n/a
E6850 @ 4.0ghzgauntleg   vegas.c
68.91%
166.17%
173.07%
166.03%
183.42%
191.32%   
200.33%   
E6400 @ 3.4ghz    blitz   seattle.c
122.25%
87.86%
111.59%
113.12%
  n/a
145.63%   
  n/a
E6850 @ 4.0ghzblitz   seattle.c
153.43%
138.59%
143.28%
136.99%
164.15%
185.35%   
172.56%   
E6400 @ 3.4ghz    daytona   model2.c
   n/a
86.18%
87.22%
89.09%
  n/a
120.89%   
  n/a
E6850 @ 4.0ghzdaytona   model2.c
   n/a
106.17%
106.43%
104.94%
142.72%
140.42%   
141.41%   
E6400 @ 3.4ghz    gradius4   hornet.c
60.36%
79.34%
   n/a
97.97%
  n/a
79.57%   
  n/a
E6850 @ 4.0ghzgradius4   hornet.c
116.72%
164.94%
   n/a
180.32%
122.16%
125.69%   
128.15%   
E6400 @ 3.4ghz    radikalb   gaelco3d.c
77.46%
76.11%
95.72%
109.88%
  n/a
163.93%   
  n/a
E6850 @ 4.0ghzradikalb   gaelco3d.c
94.25%
93.97%
116.77%
129.44%
150.07%
200.22%   
196.07%   
E6400 @ 3.4ghz    ridgerac   namcos22.c
65.56%
64.73%
90.77%
92.37%
  n/a
147.79%   
  n/a
E6850 @ 4.0ghzridgerac   namcos22.c
80.00%
79.54%
114.89%
112.44%
106.77%
194.55%   
177.79%   
E6400 @ 3.4ghz    scud   model3.c
34.41%
32.91%
33.00%
33.88%
  n/a
28.48%   
  n/a
E6850 @ 4.0ghzscud   model3.c
41.21%
39.60%
39.56%
38.93%
33.81%
33.89%   
30.36%   

No big preformance changes with 0.120u3, the biggest change in my mind is that SCUD no longer looks like a strobe light, but still has a lot of graphics issues.


I am a little frustrated.
I have tested i686, PM and P3 builds of MAME and they all yield virtually the same result, at least on the game I am benchmarking against which is Mace (it sucks, by the way).
Could I be missing something?  Even the -mt parameter makes no difference and I did set osdprocessors=2.

I am using the same command line parameters as tar-nz on my Core 2 Duo e4300 overclocked to 2.4GHz.  I would like to see the same kind of improvements (proportional to my processor speed) tar-nz saw with the PM build but it is not working for me.

Any pointers will be appreciated.

I'm not sure why your seeing no difference with the -mt, there may be something else in your system that is limiting your prefomance, CPU FSB/Cache, memory speed or amount, graphics card. I did a little testing on the PM optimisation and it seams it lost some of it's edge with the new builds, probably due to the fact the drivers are now so much better optimised than the were before.

I compile two 32bit builds of mame 0.120u3 with and with out the PM swtich inable in the make file it then bench marked a selection of ROMs with both version with and without the -MT swtch.

ROM            STANDARD          STD -MT                  PM                   PM -MT

carneveil    220.38%            229.76%            222.15%            229.87%
a51site4     178.56%            186.05%            181.06%            187.67%
starblad      130.53%            136.82%            135.86%            142.34%
mace           193.00%            195.97%            189.39%            189.75% (32bit graphics bug)
gradius4     115.47%            120.49%            111.49%            115.96% (32bit graphics bug)
propcycl        68.68%              79.93%             71.29%             73.39%
crusnusa     223.62%            242.82%            226.68%            235.00%
gauntdl       110.27%            113.19%            108.82%            111.18% (32bit graphics bug)

As you can see some roms gain a few % with the PM optimisation, all the drivers with the u3 Build 32bit graphics bug drop a little.
It looks like the PM optimised build may have become obsolete with the last few release of MAME, the early build gain alot more for the optimised builds.

Hey guys could I get a couple of opinions I have stopped setting up my new quad until i get some good feedback used to video did not matter but now which video card would you guys use
1. pci-e arcadevga or I have a extra 8800 gts laying around.
My monitor is a betson I did some performance test & the 8800 just runs all over the arcadevga.
thanks for your help
dm

If your Betson will run ok off the 8800 gts and you don't have another use for it already I probably use that, It total over-kill for MAME I only run a 8800 gts as I also PC game alot on my system. The 8800gt may have a preformance advantage with Vista, I wouldn't think you would see much difference in MAME benchmarks between the two cans in Windows XP, but as Vista likes to render the Aero desktop in the backgrond even when it's not visible,  the 8800gts may have an advantage there.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: manny2003 on November 11, 2007, 05:28:08 pm
i remember reading that the guy who wrote the software SLI driver for rendering (he called in SLI because it splits the rendering between 2 or more cpus) said on his site that .120 builds through to u2 if you have a quad using OSDPROCESSOR=2 would be faster on a quad than using OSDPROCESSORS=4 because of the way the render code worked.

The work in progress for the 120u3 build of mame states as a feature that the renderer supports quad processors. (maybe that means there isn't a penalty for using OSDPROCESSORS=4,  or it could mean that it works properly.) He has also only added support for this SLI rendering for some of the drivers at this point (hence the resaon why some of them do no really get an improvement from the switch.)

-Manny
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 12, 2007, 11:22:07 am
Thank you for all the information and advice, taz-nz.  It sounds like recent versions of mame are already pretty well optimized so perhaps I should not concern myself to much with that.

One final question to all, though:
Is there a way to set the environment variable osdprocessor permanently in the registry or do we always have to set it before running mame to get the benefit?

Thanks.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: tommy on November 12, 2007, 11:30:15 am
I didn't read this whole thread. Did anyone find Gauntlet Legends to be anymore playable with a good dual processor PC?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on November 12, 2007, 11:45:23 am
Is there a way to set the environment variable osdprocessor permanently in the registry or do we always have to set it before running mame to get the benefit?
I would expect there to be a mame.ini file line for it, but haven't checked.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 12, 2007, 01:43:57 pm
Well, this is not a MAME setting per se but a parameter that is set from a command prompt windows so I don't know if it could be taken care of from the MAME ini file.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 12, 2007, 02:35:59 pm
I didn't read this whole thread. Did anyone find Gauntlet Legends to be anymore playable with a good dual processor PC?

-gauntleg          0.120u2 64bit   152.79%         87.09fps        (Core 2 Duo E6850 @ 4ghz)

Totally playable, but still tended to lock up at random in 0.120u2, not sure if this bug is fixed in 0.120u3.




Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Carnevil on November 13, 2007, 02:57:23 pm
I am curious. Has anyone tried 120u3 with a quad core processor to see how well the new quad rendering in polynew.c works?
I plan on buying a Core2Duo real soon and I would like to know if I should go with a dual core or quad core.
Thanks
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on November 14, 2007, 04:13:52 pm
Is there a way to set the environment variable osdprocessor permanently in the registry or do we always have to set it before running mame to get the benefit?

Yes.
Not sure about Vista, but XP: open Control Panel, Open System, click the Advanced tab, click the Environment Variables button, click New in the System Variables (lower half).
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: AaronGiles on November 14, 2007, 08:01:40 pm
Let's clear up some misinformation:

1. You don't need to set OSDPROCESSORS, unless you are debugging a problem. By default, MAME detects the number of processors in your system and uses that. The default implementation should be good. Leave it alone.

2. The -mt switch does not affect the multicore 3D acceleration. The multicore 3D code is enabled always. The -mt switch merely controls whether or not MAME uses a second thread to manage windows and blitting. Generally if you have multiple cores, this is a good thing; however, it is not enabled by default, so you will need to enable it in your mame.ini.

3. "Quad rendering" has nothing to do with quad core. The quad rendering functions mentioned in the latest whatsnew refer to rendering a polygon with 4 vertices (called a "quad").

4. The 3D acceleration code scales well to 2 processors. Above 2 you get diminishing returns, and at some point it will start to get slower rather than faster.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on November 14, 2007, 08:14:53 pm
Well that makes my decision I will throw my dual core 6750 in my mame & use the quad core in my racer plus I cannot overclock my quad no matter what I do, 2 exact quad cores, 1 overclocks perfect the 2nd one is terrible, same motherboards, cpu coolers etc
thanks
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 14, 2007, 09:19:02 pm
Is there a way to set the environment variable osdprocessor permanently in the registry or do we always have to set it before running mame to get the benefit?

Yes.
Not sure about Vista, but XP: open Control Panel, Open System, click the Advanced tab, click the Environment Variables button, click New in the System Variables (lower half).

Thanks, man.
You have just made my life easier...

... and thanks Aaron for clearing all of that up.
Now it makes more sense why I don't see much difference with some of the settings I tried.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 15, 2007, 12:39:30 am
Let's clear up some misinformation:

1. You don't need to set OSDPROCESSORS, unless you are debugging a problem. By default, MAME detects the number of processors in your system and uses that. The default implementation should be good. Leave it alone.

2. The -mt switch does not affect the multicore 3D acceleration. The multicore 3D code is enabled always. The -mt switch merely controls whether or not MAME uses a second thread to manage windows and blitting. Generally if you have multiple cores, this is a good thing; however, it is not enabled by default, so you will need to enable it in your mame.ini.

3. "Quad rendering" has nothing to do with quad core. The quad rendering functions mentioned in the latest whatsnew refer to rendering a polygon with 4 vertices (called a "quad").

4. The 3D acceleration code scales well to 2 processors. Above 2 you get diminishing returns, and at some point it will start to get slower rather than faster.

Thanks for that Aaron, I had figured as much from what I seen testing different builds etc, but wasn't sure enough to start making statements about any of it, I would have asked but I didn't want to waste your time.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Red on November 15, 2007, 01:22:46 am
2. The -mt switch does not affect the multicore 3D acceleration. The multicore 3D code is enabled always. The -mt switch merely controls whether or not MAME uses a second thread to manage windows and blitting. Generally if you have multiple cores, this is a good thing; however, it is not enabled by default, so you will need to enable it in your mame.ini.

"Generally if you have multiple cores, this is a good thing; however, it is not enabled by default, so you will need to enable it in your mame.ini."

Any plans to make this enabled by default, so one doesn't have to enable it in your mame.ini file?  Thanks.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on November 15, 2007, 08:31:46 am
Any plans to make this enabled by default, so one doesn't have to enable it in your mame.ini file?  Thanks.
At risk of stating the obvious, if he planned to, I think they would have, it's an easy enough change to make.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Red on November 15, 2007, 10:38:44 am
Hopefully then it will be set to Default on later versions.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: ozzi22 on November 17, 2007, 07:24:04 pm
how does using one of these builds in a frontend affect the bech results?  examples mala or game ex
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 18, 2007, 04:14:08 am
Hopefully then it will be set to Default on later versions.

I think you'll find in hurts performance on single core processors and thus is defaultly off, that doesn't mean someone couldn't have mame turn it on automatically if a multi-core processors was detected, it probably wouldn't be that hard to do since Mame already does this for Arron's software SLI code.

how does using one of these builds in a frontend affect the bech results?  examples mala or game ex

Frontends are just ROM launchers, they take up very little system resources, and are basically inactive while a ROM is being emulated, so I wouldn't expect to see any noticeably difference. There are dozens of others tasks running the background on average windows PC, and most of them have little to no effect on MAMEs performance, my Antivirus on the other hand has a bad habit of kicking in while I'm trying to benchmark ROMs, that is very noticeable.

I would like to see how a 64bit version of SDLMAME benchmarked, running on a 64bit version of Linux, it would be interest to see if Windows resource usage has any negative effect MAMEs performance.  I'm  looking into this currently, but as soon as you say linux everything get 10x more complex than it needs to be, so there probably will not be results on this one until atleast the next stable build of MAME is released.

Looks like I might have to get a E8500 after all in the new year, below are overclocking results with on pre-production sample, air cooler with a less than fantastic Thermal Take V1 heatsink (lot of room to improve there)

497X9.5=>4722Mhz on air cooler   
(http://img217.imageshack.us/img217/972/e85004722pirh3.png)

For full details jump over to http://forums.tweaktown.com/showthread.php?t=25544 (http://forums.tweaktown.com/showthread.php?t=25544)

Wish I had that CPU to play with.


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: ozzi22 on November 22, 2007, 10:38:34 am
Any new bench results with mame 121?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 23, 2007, 02:55:11 am
Any new bench results with mame 121?

Yeah will be up tomorrow, I'll post a full set once I re-run them with 0.120u1, vegas.c was broken in 0.120  :cry:.
But you can see my 0.120 less gauntleg, gauntdl, tenthdeg over at http://benchmark.mameworld.net/ (http://benchmark.mameworld.net/) where I currently hold the title of "speed king" >:D just click on "Benchmark Database", and then select "0.121" under "MAME Build", then hit "Show me the list" this will give you my lastest results.

Update:

Had some PC issues this weekend lots of random lockups, BSODs and restarts, figured it was a heat or stablility issue with the overclocking, wasted a day trying to fix a problem that wasn't there  :banghead:, turned out it was my DVD-Writer on it's way out  :hissy:  unplugged it and all was OK again but then I had to undo everything from the previous day, so no benchmarks until tommorow at the earliest, sorry.
 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on November 27, 2007, 10:58:44 am
So for all those of you wanting to build a preformance M.A.M.E. PC on a budget, I did a quick shopping list and then found some prices over at www.clubit.com (http://www.clubit.com) (There may be better and cheaper places out there, but they had the right gear at what looked like the right price)

Taz-nz - thanks for all the helpful info in this thread.  I'm really not looking to replace my MAME machine, but was curious why you picked some of the components you did (I understand the theory, but not all the requirements)., and my budget is much less than $360.

(http://www.clubit.com/products/50x50/A4830711_1.jpg)    GIGABYTE GA-P35-DS3R Rev. 2.0 LGA 775 Intel P35 ATX Intel Motherboard Retail     
$128.50
Is it important to use this particular board, or just a P35 board.  For instance, Newegg has a Open box MSI P35-Neo2 FR (http://www.newegg.com/Product/Product.aspx?Item=N82E16813130098R) for $65, or the Gigabyte GA-P35-DS3L (http://www.newegg.com/Product/Product.aspx?Item=N82E16813128059) for $90.  Club-It also has similar (slightly better) prices on P35 boards.
(http://www.clubit.com/products/50x50/A1906716_1.jpg)    Cooler Master RR-CCH-LB12-GP Hyper 212 CPU Cooler   
$33.99
I guess the cooler is pretty critical to stable overclocking, but $35 seems a bit high.  I don't know of good alternates, though.  I've like Arctic Cooling in the past (but that was on Athlon XP systems), and the new fanless towers (like Tuniq) look cool, but again not sure how they'd be for overclocking.  Any idea how the stock Intel cooler would do?
(http://www.clubit.com/products/50x50/A1938256_1.jpg)    Intel Core 2 Duo E4500 M0 Stepping Conroe 2.2GHz 2MB L2 LGA 775 Processor Retail BX80557E4500 SLA95   
$123.50
How would the E2140, E2160, or E2180 compare with this processor - they are all 800 FSB parts and priced at $70-$90.  (Also, some of these mention a particular "Stepping", but I don't know how this factors in.)
(http://www.clubit.com/products/50x50/A4330509_1.jpg)   CORSAIR XMS2 2GB (2 x 1GB) DDR2-800 CL 5-5-5-12 Dual Channel Kit Retail TWIN2X2048-6400
$74.50
I'm not sure 2GB is required for a MAME machine - Newegg and Club-It have 1GB DDR2-800 Cas 5 for $25-$35 and 2GB (matched pair) for $54.  Would this be acceptable?  Would DDR2-1066 offer any advantages?

If the pieces above would work, you could knock $200 off the price above and put together a system for around $160 (65+70+25)

Thanks again for all your help!!!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 27, 2007, 11:43:21 am
I have played with different memory timings and speed on my main computer and none of it does squat.  I went from 533 to 800 FSB and 4-4-4-12 to 5-5-5-15 and it only looks pretty in the Sandra graphs but MAME does not care.  I only cares for one thing: processors speed. 

The tests above where on a Core 2 Duo E4300 running at 2.4GHz.  I ran it at 3.0GHz for a while and the FPS did not quite scale linearly to 25% faster but to about 22% faster.  The games I was looking at were mace and umk3.

On my intended MAME cab machine (which I have yet to fully configure) I tried 384 vs 512 and PC100 vs PC133 and so no difference there either but I only benchmarked umk3, mvsc and garou.  I don't have enough evidence but I tend to think that you probably don't get added performance above 512MB of memory even for the larger neogeo games.  I don't know if this is the case with hard drive games because that machine will not run it at any decent speed so I did not even bother to benchmark it.

I suppose I will have to use an older version of MAME for umk3 and other of the more demanding games.  Luckily, I don't care for any of the hard drive games but, like I said a few posts ago, I'm out of luck for SFIII.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: metahacker on November 27, 2007, 08:53:18 pm
can you try a comparison to your regular benchmarks with the following in your Makefile ARCH= line ?

-march=nocona -mtune=nocona -minline-all-stringops -maccumulate-outgoing-args -mmmx -msse -msse2 -msse3 -mfpmath=sse -funroll-loops -fomit-frame-pointer

and perhaps even compare that to

-march=pentium-m -mtune=pentium-m -minline-all-stringops -maccumulate-outgoing-args -mmmx -msse -msse2 -msse3 -mfpmath=sse -funroll-loops -fomit-frame-pointer
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on November 27, 2007, 11:14:31 pm
Ok, i finally have my mame e6750 w/vista 64, 4 gig ram running on mame, 121.1, carnevil & mace run perfect, Gauntlet legends & blitz run good but they still have a slight sound jumping.  Taz how does blitz run on your 6850, & 121 have you noticed a slowdown if so i may go back to v120.  thanks for the help also i overclocked to 3.4
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 28, 2007, 01:13:08 am
Taz-nz - thanks for all the helpful info in this thread.  I'm really not looking to replace my MAME machine, but was curious why you picked some of the components you did (I understand the theory, but not all the requirements)., and my budget is much less than $360.

When I compiled this list of parts, I wanted give people a good starting point I knew would overclock well, so I went with parts I deal with on a daily basis.

(http://www.clubit.com/products/50x50/A4830711_1.jpg)    GIGABYTE GA-P35-DS3R Rev. 2.0 LGA 775 Intel P35 ATX Intel Motherboard Retail     
$128.50
Is it important to use this particular board, or just a P35 board.  For instance, Newegg has a Open box MSI P35-Neo2 FR (http://www.newegg.com/Product/Product.aspx?Item=N82E16813130098R) for $65, or the Gigabyte GA-P35-DS3L (http://www.newegg.com/Product/Product.aspx?Item=N82E16813128059) for $90.  Club-It also has similar (slightly better) prices on P35 boards.

Any P35 chipset board is a good start, but they are not all created equal, the Gigabyte P35-D** series of board are proven overclockers, and they use better quality parts, see Ultra Durabilty 2. The GA-P35-DS3L should be fine stay away from the GA-P31-DS3L the chipset is rubbish. I'd stay away from the MSI unless you can find plenty of proof it's a good overclocker, I not a fan of the brand they fail to often for my liking. (The main reason for going with a P35 chipset board is that they are very stable at high FSBs which is very important when overclocking, extra cooling of the northbridge doesn't hurt any)

(http://www.clubit.com/products/50x50/A1906716_1.jpg)    Cooler Master RR-CCH-LB12-GP Hyper 212 CPU Cooler   
$33.99
I guess the cooler is pretty critical to stable overclocking, but $35 seems a bit high.  I don't know of good alternates, though.  I've like Arctic Cooling in the past (but that was on Athlon XP systems), and the new fanless towers (like Tuniq) look cool, but again not sure how they'd be for overclocking.  Any idea how the stock Intel cooler would do?

You really need the heatsink if you want to get any really good overclocking results, the factory heatsink is overkill for these CPUs out of the box, but soon fails to keep up as you start to overclock them. There are plenty of good coolers out there, but currently the Hyper 212 is the best value for money as far as I'm concerned, it's performance is only slightly below that of theThermalright 120 Ultra I used in my system, at about half the price. There are loads of coolers out there that don't live up to the hype or their cost, the Hyper 212 just gets the job done and is affordable.

(http://www.clubit.com/products/50x50/A1938256_1.jpg)    Intel Core 2 Duo E4500 M0 Stepping Conroe 2.2GHz 2MB L2 LGA 775 Processor Retail BX80557E4500 SLA95   
$123.50
How would the E2140, E2160, or E2180 compare with this processor - they are all 800 FSB parts and priced at $70-$90.  (Also, some of these mention a particular "Stepping", but I don't know how this factors in.)

The E21** series overclock well like all the Core 2 Duo, but the 1mb cache has a noticable effect of their preformance when compared to a E4*00 or E6**0 series Core 2 Duo of the same clock speed, they are also limited in most cases to around the 3ghz overclocked from what i've seen, with a few managing 3.2-3.4ghz. The E4*00 series processors, are more likely to hit the 3.2-3.6ghz mark and have the large cache which helps their preformance.

I choose the E4500 M0 stepping as the 9x multiplier means you only need overclock to 400mhz FSB to get to 3.6ghz, and thus you only need DDR2-800 memory. The M0 stepping is the same as the G0 in the E6*50 series processors, these stepping overclock better than the older steppings of Core 2 Duo, and thus are worth having if your looking to hit big numbers. (steppings are small changes made in the CPU design to fix bugs or increase production yeilds, they tend to optimise the design toward stability and some make for great improvements in overclocking.)
(http://www.clubit.com/products/50x50/A4330509_1.jpg)   CORSAIR XMS2 2GB (2 x 1GB) DDR2-800 CL 5-5-5-12 Dual Channel Kit Retail TWIN2X2048-6400
$74.50
I'm not sure 2GB is required for a MAME machine - Newegg and Club-It have 1GB DDR2-800 Cas 5 for $25-$35 and 2GB (matched pair) for $54.  Would this be acceptable?  Would DDR2-1066 offer any advantages?

2gb is not a must for MAME, but the catch is that the best OS option for mame Preformance is Vista 64bit which is a memory hog, and really needs 2gb to run well, to give you an idea, while doing some of the CPU only benchmark up to 1.7gb of physical ram were in use, and that with nothing running but Vista and MAME. Windows XP 64bit might be easier on the memory usage but is not as well supported as Vista 64bit, and you can get Vista Home Prem 64bit a lot cheaper & easier than you can XP Pro 64bit.

In regard to ram speed I really haven't seen much difference in MAMEs preformance when using different preformance memory, but make sure you run dual channel no matter how much memory you run. Any half respectable DDR-800 ram will do just make sure it's compatible with the P35 chipset, there are a few Dimms out there that work great on the older Intel chipsets and with AM2 CPUs but are totally unstable withe P35 chipset.
If the pieces above would work, you could knock $200 off the price above and put together a system for around $160 (65+70+25)

Thanks again for all your help!!!

Preformace is just a question of money you have to ask yourself how fast do you want to go, and then speed the money need to get their. To give you an Idea my system for CPU, RAM, Motherboard, & Heatsink cost around $1300 NZD and number of months planning and saving.

Hope this helps fills in some of the blanks for you.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 28, 2007, 02:30:48 am
Ok, i finally have my mame e6750 w/vista 64, 4 gig ram running on mame, 121.1, carnevil & mace run perfect, Gauntlet legends & blitz run good but they still have a slight sound jumping.  Taz how does blitz run on your 6850, & 121 have you noticed a slowdown if so i may go back to v120.  thanks for the help also i overclocked to 3.4
dm

Haven't noticed much change with 0.121, most of the big changes were in 0.121u# releases
gauntleg is about the same, runs fine speed wise but still likes to lock up at random.
blitz is down a little maybe 5%, I suck at this game totally so haven't tried in game lately.

Good to see you've got your PC up and running well, and welcome to the fast lane. what heatsink are you using by the way?

Any new bench results with mame 121?

Full set of in game benchmarks, run in Vista 64bit, use MAMEUI 64bit, with the command line:
-noautoframeskip -frameskip 0 -seconds_to_run 240 -nothrottle -nosleep -video ddraw -skip_gameinfo -effect none -nowaitvsync -noreadconfig -mt [ROM NAME]

- 1942                      0.121u1      6572.08%

- a51site4                0.121u1      235.35%

- airco22b                0.121u1      143.19%

- alpinerd                 0.121u1      88.50%

- biofreak                 0.121u1      145.12%

- blitz2k                   0.121u1      160.68%

- blitz99                   0.121u1      153.09%

- blitz                       0.121u1      167.30%

- calspeed                0.121u1      204.23%

- carnevil                  0.121u1      285.30%

- crusnusa                0.121u1      276.53%

- crusnwld                0.121u1      249.91%

- cybrcomm              0.121u1      135.27%

- Daytona                 0.121u1      212.79%

- gauntdl                  0.121u1      134.20%

-gauntleg                 0.121u1      159.81%

- gradius4                 0.121u1      96.85%       (64bit MAME /64bit Windows)
                                 0.121u1      110.77%      (32bit MAME /32bit Windows)      
                                 0.121u1      113.95%      (32bit MAME /64bit Windows)

- hyprdriv                  0.121u1      175.17%

- mace                      0.121u1      251.07%

- offroadc                  0.121u1      438.94%

- propcycl                  0.121u1      137.27%

- radikalb                  0.121u1      177.72%

- raveracw                0.121u1      121.21%

- ridgerac                  0.121u1      151.72%

- scud                        0.121u1      28.61%    (score keeps getting worse, but demo speed keeps getting better, can't wait for this one to be a working ROM)

- sfrush                     0.121u1      211.70%

- sidebs2                  0.121u1      215.90%

- speedup                 0.121u1      179.16%

- starblad                  0.121u1      145.58%

- surfplnt                   0.121u1      163.14%

- tenthdeg                 0.121u1      85.30%

- timecris                   0.121u1      145.30%

- wargods                 0.121u1      411.74%

- wg3dh                    0.121u1      375.54%

- xevi3dg                  0.121u1      371.37%

can you try a comparison to your regular benchmarks with the following in your Makefile ARCH= line ?

-march=nocona -mtune=nocona -minline-all-stringops -maccumulate-outgoing-args -mmmx -msse -msse2 -msse3 -mfpmath=sse -funroll-loops -fomit-frame-pointer

and perhaps even compare that to

-march=pentium-m -mtune=pentium-m -minline-all-stringops -maccumulate-outgoing-args -mmmx -msse -msse2 -msse3 -mfpmath=sse -funroll-loops -fomit-frame-pointer


I've been really busy of late, but if I get a chance in the next few days I give it a go, mind you it will have to be a 32bit build, 64bit builds are still beyond me.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on November 28, 2007, 08:02:11 am
Taz do you think it would be worth the jump to a 6850
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on November 28, 2007, 08:38:31 am
Taz - that helped a lot.  What I am mainly looking for is the ability to play some of the more demanding games like Cruisin' and SFrush.  Based on your specs (150-200% in these games), I am hoping a E2100 at 3 Ghz or so might give 75% performance, which would still be around 100% (and I could live with less than 100%, but 60% is not playable).  I don't plan to go to 64-bit, and understand that it's not a totally linear scale.

I just have a couple of additional questions, but your replies already helped a lot!

As far as coolers, any idea how the Arctic Cooling Freezer 7 Pro (http://www.newegg.com/Product/Product.aspx?Item=N82E16835186134) would compare with the others?

Quote
but make sure you run dual channel no matter how much memory you run.
Still true with XP?  (I've read reviews that said dual-channel wasn't that important and was thinking of getting a single 1GB stick to keep some ram slots free - not sure the reviews were of dual-core systems, though).

Quote
Any half respectable DDR-800 ram will do just make sure it's compatible with the P35 chipset, there are a few Dimms out there that work great on the older Intel chipsets and with AM2 CPUs but are totally unstable withe P35 chipset.
How can you tell? (Or do you just read tons of reviews?)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 28, 2007, 09:31:04 am
Quote
Quote
but make sure you run dual channel no matter how much memory you run.
Still true with XP?  (I've read reviews that said dual-channel wasn't that important and was thinking of getting a single 1GB stick to keep some ram slots free - not sure the reviews were of dual-core systems, though).


TigerHeli:

I have run my computer with and without dual channel configuration and it makes no difference whatsoever even if the bandwidth is improved in synthetic benchmarks.  I tested it with mace and with the "Splinter Cell: Pandora Tomorrow" computer game which I have installed merely for benchmarks as I don't play PC games (or mace for that matter but it makes for nice benchmarks).

My PC is an e4300 which I am running at 300FSB for 2.7GHz although I ran it at 3.0GHz for a week or so before it became unstable.  All of this was with stock voltage and cooler.  The motherboard is Abit IB9 which is the Intel P965 chipset.  Memory is 2GB DDR2-667 running stock although I can run it at DDR2-800 but I don't like to push the memory long term as I don't get any benefit.  Video card: old Geforce PX-6200TD unlocked to 4 pixel pipelines.

If you are interested, I can run a couple of configurations that you might want to consider as long as they don't exceed 3.0GHz for the CPU or 800MHz for the memory since I don't like to mess around with voltages,  to help you make up your mind about what you need to purchase.

If you don't plan to increase voltages, I don't think you need any fancy coolers.  My CPU runs normally with a 67C reserve to the maximum Tjunction temperature according to CoreTemp.  Under Orthos load, the reserve can get as low as 32C which is a bit scary but still safe when you consider that most normal applications will not stress the CPU that much even at 100% CPU load as reported by the Task Manager.  In the summer, the reserve is about 5C shorter due to the temperature difference inside my house.  What you need to make sure it that you seat cooler properly which is not easy to do the Core 2 Duo's socket layout.  I use Arctic Silver because it is cheap but I don't know if it makes a difference vs the stock paste.

Finally, to extend the life of the processor, I set my power scheme to laptop/portable so that EIST kicks in and the CPU multiplier is knocked down to 6X form 9X while the computer is idle or doing light duty like browsing the web or playing pacman :-) but immediately goes to full throttle when more processing power is required.  As a result, my 2.7GHz is running at 1.8GHz most of the time which happens to be the stock speed.

Good luck and let me know if you need help.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on November 28, 2007, 10:14:20 am
I am running the Rosewill Z-3 coolers I have 3 of these & they work great, the artic cooler you are looking at is fine.  But with the tags on it, it makes it a pain to install these coolers are not good for being used over & over.  That is why I like the rosewill or similar they use a back plate w/screws & nuts.  I am kicking around dumping my 6750 & going to the 6850 just for the extra performance.  I also prefer Gigabyte motherboards I have 3 of the GA-P35-DS3L, these boards are tough & great overclockers.
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on November 28, 2007, 10:26:59 am
DiveMaster - Thanks!

Thanks TheManuel!

DDR2-800 is really cheap right now - I can understand you not upgrading, but it wouldn't make sense for me to buy less than that.

Before we start, I have some dumb newb questions coming from the AMD world and being somewhat out of touch:

Can you change both the multiplier and FSB on the C2D's or just the FSB or both but only up to the max.  On AMD, usually you can only mess with the FSB b/c they are multiplier locked.  For example, the E4500 is stock at 11x200 FSB, but Taz mentioned a 9x multiplier.  Your E4300 is stock at 9x200FSB, but you said you had it at 3 Ghz, was that 10x300, or 9x333FSB?  (Errmm - you said you're at 300FSB at 2.7 so that tells me you are running at 9x, but Taz said the E4500 was picked for the 9x multiplier, so I'm guessing maybe you can reduce the multiplier but not increase it?)

Also, can you run the memory bus independently of the CPU FSB or not (or does that vary from mobo to mobo)?

The games I would mainly be interested in would be
SFrush
Cruisin'USA
SWTrilogy (not much chance)
RidgeRacer

and the like.

If you don't mind, I would like to see framerates at Stock clock (1.8 Mhz), 2.4 Ghz, 2.7 Ghz, and 3.0 Ghz, for the above games.

(I thought I would save you some work and just look at the MAME benchmarks site, but CrusnUSA is running at 69% with a 2133 Mhz Core2Solo/Duo and 101% with a 2033 Mhz Core2Solo/Duo both with 0.118, so ....)

I'm just kicking around the upgrade idea now, so no rush on the results, but I'm curious to see what you come up with!!!

Thanks again! 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 28, 2007, 10:41:19 am
Quote
DDR2-800 is really cheap right now - I can understand you not upgrading, but it wouldn't make sense for me to buy less than that.
You are absolutely right on this.  I built my PC in April right around the middle of the price drop curve and they are dirt cheap right now so just go for the fastest you can afford although I would not pay too much extra for boutique memory with low timings.

Quote
Can you change both the multiplier and FSB on the C2D's or just the FSB or both but only up to the max.  On AMD, usually you can only mess with the FSB b/c they are multiplier locked.  For example, the E4500 is stock at 11x200 FSB, but Taz mentioned a 9x multiplier.  Your E4300 is stock at 9x200FSB, but you said you had it at 3 Ghz, was that 10x300, or 9x333FSB?  (Errmm - you said you're at 300FSB at 2.7 so that tells me you are running at 9x, but Taz said the E4500 was picked for the 9x multiplier, so I'm guessing maybe you can reduce the multiplier but not increase it?)
Multiplier for Core 2 Duo's is locked if you are increasing so you will be limited by the stock multiplier.  However, you can run a lower multiplier which is what some people do because they want to increase their FSB fo improve communication with the memory (for what it's worth) but they don't want their CPU speed beyond the point where they cannot control stability with their setup.

Quote
Also, can you run the memory bus independently of the CPU FSB or not (or does that vary from mobo to mobo)?
In my motherboard, I can run the memory bus faster than the CPU bus but I don't know if I can running it slower.  There is a limited selection of multipliers I can use to set this up in my motherboard.  Maybe someone can pitch in with more info?  I am not much of an overclocker.

Quote
The games I would mainly be interested in would be
SFrush
Cruisin'USA
SWTrilogy (not much chance)
RidgeRacer

and the like.

If you don't mind, I would like to see framerates at Stock clock (1.8 Mhz), 2.4 Ghz, 2.7 Ghz, and 3.0 Ghz, for the above games.

(I thought I would save you some work and just look at the MAME benchmarks site, but CrusnUSA is running at 69% with a 2133 Mhz Core2Solo/Duo and 101% with a 2033 Mhz Core2Solo/Duo both with 0.118, so ....)
I will try to run this tonight when I get home or tomorrow if I can't get to it since I will have to find the games first. 
While I'm at it, if you want me to mess around with the memory speed, let me know.  I can run it at 800MHz since this is what you want to buy although I don't expect a difference.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on November 28, 2007, 10:42:38 am
You can pick up the adata 2 gig ddr ram 800 on newegg for less than $56.00, its a no name but tons of people on newegg on given 5 stars.  I purchased 12 gig of it & this stuff works great & overclocks very good.  I have a 2 page form that I printed off the internet that is a step by step guide for the gigabyte overclocking of the boards, if you pm me a fax number I can send it over, I cannot remember where I found this guide but its great
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on November 28, 2007, 11:26:25 am
TheManuel - I'm not too worried about the memory speed - I've never seen it to make much difference.  Thanks again.

DM - I'll remember A-Data.  Thanks!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 29, 2007, 12:53:47 am
Just to clarify a couple of things (this got way long winded, repeats some of what I've already said but still please read it)

First I got the Core Multiplier on the E4500 wrong it's 11x not 9x my mistake, long day. :-[

The stock Core Multiplier matters as you can't increase this on a Core 2 Duo only decrease it in steps of 1x down to 6x, so the higher the Core Multiplier the higher you can get the CPUs clock speed with and given FSB speed.

So if you want to hit say 3.6ghz and don't want to go any higher than a 400mhz FSB, because your using cheep DDR2-800 and don't want to overclock it , then you need at least a Core Multiplier of 9x to achieve this that CPU speed.

So why would you buy a E4500 with a multiplier of 11x when you could buy a E4300 with a multiplier of 9x would in thoery do the job? Well the answer is that the faster stock clock speed a CPU has the better binning it has, this mean the fastest model or a given series of CPUs will tend to have the highest overclocking potential. Any example of this is the E6750 with a multiplier of 8x @ 500mhz FSB it should be able to hit 4.0ghz but in reality they tend to hit a wall around the 3.8ghz mark with air cooling, as where the E6850 is know to be good up to 4.0-4.2ghz before it hits the wall on air cooling.

So running a E4500 @ 9x 400Mhz FSB is a safer bet to get to 3.6ghz (a 63% overclock) than an E4300 @ 9x 400 FSB to get to 3.6hgz (a 100% overclock).

When deciding on what FSB to run to achieve your final clock speed you need to think about what else your going to overclock then you increase the FSB, the FSB speed effect the speed of your CPU, Memory and Chipset, and these all need to be taken into account. The lowest FSB you can run is the Final CPU speed you want to hit divided by the stock Mutliplier of you CPU, for a E4500 @3.6ghz that is  3600/11 = 327mhz (1307 FSB), now 327mhz * 2.4 memory multiplier gets you DDR2-784 so now your memory is underclocked at there for you have less memory bandwidth, if you increase the memory multiplier to 2.6 you end up with your memory at DDR2-850 now it's overclocked, so the easy thing to do is find the common ground between your memory speed and the final CPU speed you want of 3600mhz with is 400mhz 2x for the memory multiplier to give DDR2-800, and 9x for the core multiplier to give 3.6ghz.

The one other thing you have to watch out for when selecting you FSB is whether your motherboard and chipset can handle the new FSB speed, now the P35 Chipset is good for well over 500Mhz FSB speed, but this is only on the right motherboard with good chipset cooling, some motherboard become unstable when you increase the FSB speed due to their design, others because the North bridge heatsink can not keep the chipset cool at the higher FSB speed. Also the higher you increas the FSB the more likely it is that you will need to overvolt the FSB and Chipset some to make it stable and the higher speed, that extra voltage equal more chipset heat.

Higher FSB speed give the CPU more bandwidth to talk to the memory and the rest of your system with, but there is limit to what is practical, an extreme setup would be run say a CPU at 6x 600mhz FSB to get to 3.6ghz, this would require a very stable motherboard with very good chipset cooling, and a lot of extra voltage to the chipset & FSB to work, it would give you massive FSB bandwidth but would be very hard to get stable.

Memory Speed & bandwidth why should you care?
Memory bandwidth is the speed at which the system can get information from your RAM, basically more is better as long as you CPU can put it to use, little point in having a 800 FSB CPU with dual cannel DDR3-1600 the CPUs FSB bandwidth is just now wide enough to make use of the huge memory bandwidth with would give you.

Memory bandwidth & FSB are important because of the way CPUs work, without getting into a whole heap of tech-talk, The great the Memory & FSB bandwidth a system has the more able the system is to supply the CPU with information to process, that catch is if you don't have enough memory or FSB bandwidth then the system has trouble keeping up with the speed of the CPU (this is made worse if the CPU is noticeably overclocked). This is why CPU have Cache Memory it acts as a buffer between the CPU and the system memory, hiding any gaps in the flow information from the CPU.

Now what happens if the memory bandwidth can't keep up with the CPUs needs, and the memory access is to random for the cache memory to buffer fully, then the CPU becomes starved or information and can't process anything for a split second, now it's worse than that because of the way a CPU works, what might be a one cycle break in the flow of the data can result in a 20-40 cycle break in the processing of data, so the penalty for not having enough memory or FSB bandwidth can be much great than you would think.

A modern Celeron is nothing but a Pentium 4 Core with 1/2-1/4 of the cache memory and a lower FSB, these two things make the same CPU Core perform much slower than it would in a Pentium 4 at the same CPU Clock speed because it spends so much more time wait for data to process.

This where memory & FSB speed & dual channel kick in.

Theoretical DDR2 Memory bandwidth:

DDR2-800 Single channel   ~6.4GB/s   (400mhz)
DDR2-1000 Single channel   ~8.0GB/s   (500mhz)
DDR2-800 Dual channel   ~12.8GB/s (400mhz)
DDR2-1000 Dual channel   ~16.0GB/s (500mhz)

800 FSB         ~6.4GB/s (200mhz)
1600 FSB         ~12.8GB/s (400mhz)
2000 FSB         ~16.0GB/s (500mhz)

As you can see the drop from DDR2-1000 to DDR2-800 is only 23% but the Drop from Dual channel to single channel is 100%, this is why it's important to run dual channel, you loose way to much memory bandwidth if you don't run dual channel.

How does this effect MAME if you drop from dual channel to single channel, well very little at 500mhz (2000 FSB) DDR2-1000 with a E6850 with 4mb of cache like I'm running, about 2-3% across the board in fact as you can see in the benchmarks below.

The catch is that while MAME is basically CPU limited and doesn't appear to require huge memory bandwidth, these result are on my system and thus not the norm, the effect of dropping to only 6.4Gb/s memory bandwidth with a single DDR2-800 Dimm on say a E4*00 series with only 2mb CPU Cache will probably be much more noticeable that the effect of dropping to 8.0GB/s with 4mb of CPU cache on my system.

Benchmark performed same as normal just with my memory in single not dual channel. (still 2gb of RAM in system)

ROM NAME   MAME Ver   dual Channel   Single Channel

- 1942      0.121u1      6572.08%   6555.78%

- a51site4   0.121u1      235.35%      234.89%

- airco22b   0.121u1      143.19%      141.29%

- alpinerd   0.121u1      88.50%      87.20%

- biofreak   0.121u1      145.12%      143.02%

- blitz2k   0.121u1      160.68%      160.12%

- blitz99   0.121u1      153.09%      151.04%

- blitz      0.121u1      167.30%      166.52%

- calspeed   0.121u1      204.23%      203.53%

- carnevil   0.121u1      285.30%      283.93%

- crusnusa   0.121u1      276.53%      275.63%

- crusnwld   0.121u1      249.91%      249.36%

- cybrcomm   0.121u1      135.27%      134.07%

- Daytona   0.121u1      212.79%      209.73%

- gauntdl   0.121u1      134.20%      133.14%

- gauntleg   0.121u1      159.81%      151.36%

- gradius4   0.121u1      96.85%      96.45%

- hyprdriv   0.121u1      175.17%      167.02%

- mace      0.121u1      251.07%      248.84%

- offroadc   0.121u1      438.94%      436.40%

- propcycl   0.121u1      137.27%      135.14%

- radikalb   0.121u1      177.72%      176.58%
   
- raveracw   0.121u1      121.21%      119.77%

- ridgerac   0.121u1      151.72%      148.99%

- scud      0.121u1      28.61%      27.87%

- sfrush   0.121u1      211.70%      199.13%

- sidebs2   0.121u1      215.90%      213.46%

- speedup   0.121u1      179.16%      179.30%

- starblad   0.121u1      145.58%      144.87%

- surfplnt   0.121u1      163.14%      161.74%

- tenthdeg   0.121u1      85.30%      83.64%

- timecris   0.121u1      145.30%      148.09%

- wargods   0.121u1      411.74%      411.54%

- wg3dh      0.121u1      375.54%      374.59%

- xevi3dg   0.121u1      371.37%      372.76%

I am running the Rosewill Z-3 coolers I have 3 of these & they work great, the artic cooler you are looking at is fine.  But with the tags on it, it makes it a pain to install these coolers are not good for being used over & over.  That is why I like the rosewill or similar they use a back plate w/screws & nuts.  I am kicking around dumping my 6750 & going to the 6850 just for the extra performance.  I also prefer Gigabyte motherboards I have 3 of the GA-P35-DS3L, these boards are tough & great overclockers.
dm

I had a look at the cooler your using and while it's the right design type for overclocking it's only a mini tower-cooler, with only a 92mm fan and what looks like three heat pipes, I'd look at tyring something bigger like the Coolermaster Hyper 212 or the thermalright 120 utlra before you change to a E6850, I would be suprised if you couldn't get to at least 3.6-3.8ghz out of your e6750 with a larger heatsink and a bit of tweaking, presuming your ram is not what is holding you back.

 


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 29, 2007, 09:19:14 am
Quote
How does this effect MAME if you drop from dual channel to single channel, well very little at 500mhz (2000 FSB) DDR2-1000 with a E6850 with 4mb of cache like I'm running, about 2-3% across the board in fact as you can see in the benchmarks below.

The catch is that while MAME is basically CPU limited and doesn't appear to require huge memory bandwidth, these result are on my system and thus not the norm, the effect of dropping to only 6.4Gb/s memory bandwidth with a single DDR2-800 Dimm on say a E4*00 series with only 2mb CPU Cache will probably be much more noticeable that the effect of dropping to 8.0GB/s with 4mb of CPU cache on my system.

tar-nz:
I think you are well intentioned and you've got the theory down in great shape for the mid-terms :-)
However, I think in practice, it can all be mis-leading.  When I tried dual vs single channel on my setup, just out of curiosity, I did not see any significant difference.  I did not run the benmchmarks in a very disciplined manner but there was nothing that jumped out at me.  I will try to run some tomorrow night (I have to do Tiger-Heli's benchmarks tonight :-) ).  Beside, the theoretical bandwith you quote above is just that, theoretical.  Please run some synthetic benchmarks on your system using Sandra or some other software and report back on your bandwidth.  I'm sure you will notice that it falls way short of theoretical.  In fact, for a more eye-opening experiment, run this bechmark on single channel mode as well and see if dual channel gets anywhere close to twice the bandwidh of dual channel.  Oh, and sysnthetic benchmarks are always the most optimistic test you can run and real world performance is usually lower anyway.
Overclocking webistes tend to get too hung-up on memory bandwith but every time I test different setups I don't see any differences worth writing home about so I'd hate for people planning out their systems to spend too much time and money for extra bandwidth when it does not do much in practice.  Looking at your benchmarks, most games improved by less than 2% (dividing dual channel percentage by single channel percentage), some even reduced performance while a few improved by as much as 6% and this is in the extreme case of single vs dual channel.  So in the end you have to ask yourself if 6% in a few isolated games is worth going after. 

Nevertheless, going dual channel probably makes financial sense since most modern motherboards support it and a pair of matched memory sticks is only a few bucks more than a single stick with the same total memory.  Even if you are not sure it's going to make much difference, you just protect yourself for the unknown for a few bucks more.  However, spending a lot of money on super fast memory doesn't make much sense to me.

I still owe you some benchmarks to put some evidence behind my claims.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on November 29, 2007, 12:55:56 pm
Taz did post both specs and the info was useful - and he said his system was likely less affected by it than most.

I still want to see TheManuel's benchmarks, but I did get a chance to test three of the game's out here on the work, ermmm, test system and wanted to post them here:

This is an Hewlett Packard E6400 running at stock clock of 2.13Ghz, WinXP, 2G of Ram (dual channel).  I used standard (non multi-core optimised MAME 0.121) with total default settings and didn't run anything specific, just looked at F11 (I also had Access, Outlook, and Seamonkey, and maybe Word running in the background):

Crusnusa ran at pretty near 100%, dropped to 90% at times.
Swtrilgy ran at around 34% from what I could tell
Sfrush ran at about 53-57% but I just got past the startup screens and closed it out (won't really work without a joystick).

Not bad at all and looks like if I get to about 3.0 Ghz, those games are likely playable.

I've about decided how I want to tackle this is a stock E2xxx processor and cooler, either a P35 or 965 mobo (probably Gigabyte or Abit, maybe Asus, Asrock, or BioStar (are these okay?) (also on the 965, I assume I want P965 rather than G or Q since I won't have integrated graphics, but are there other disadvantages to a G965 or Q965?) also I saw FoxConn uses solid capacitors also - any opinions on them, one stick of 1G ram, and a cheap vid card (might need a new power supply also - recommmended brands? - I've used Fortron in the past).

I'll probably see how this does stock, might try to overclock and hit close to 3Ghz.  May add a second stick of 1G ram and a better CPU cooler at that time.

Like TheManuel said, I'm really not too concerned if CrusnUSA runs at 91% instead of a possible 93%, but getting it to 91% from about 39% (Last I remember - XP Barton 2800+) is important.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 29, 2007, 06:54:56 pm
The info was useful indeed.
Taz is the man.  I certainly was not meaning to diminish his comments in any way.
He obviously knows this stuff better than I do.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 29, 2007, 08:22:25 pm
The info was useful indeed.
Taz is the man.  I certainly was not meaning to diminish his comments in any way.
He obviously knows this stuff better than I do.


Ha I get where your coming from, there is way  to much hype around bandwidth and getting that last 100 point in this benchmark or that. I probably shouldn't have posted the Theorical numbers knowing good well it's impossible to reach those figures in the real world, in fact the best Intel memory controllers are only about 50% efficient, the intergated memory controller in the 939 Ahtlon64 on the other hand is 90%+ efficient and get much closer to the theorical number than any other system setup.

Memory and system bandwidth play a greater of lesser roll in preformance depend on your the software your running, But there is point where if you decrease the available bandwidth to the CPU enough no amount of Cache memory will stop a noticably drop in prefromance, now it appears we're lucky with MAME and it's memory bandwidth requirements are fairly low, but a drop in memory bandwidth will still effect it's preformance to a greater or lesser degree depend on your over all system setup.

I lot of my knowledge of effects of bandwidth on system preformance come from my P4 days, when I ran a 2.8ghz P4 northwood (512k cache) @ 3.5ghz 250mhz FSB with DDR-500 , that system was faster than a 3.6ghz P4 Prescott (2mb cache) with DDR-400, it was almost as fast as a 3.8ghz P4 Prescott. The extra cache memory in Prescott Core could not make up for the lack of system & memory bandwidth, the P4 Core simply needed more bandwidth to keep it work hard at high clock speeds.  I also spend a lot time disigning Dual CPU Quad Core Xeon server setup for customers at work, these use a Quad Channel memory setup to supply enough memory bandwidth to keep 8 cores working hard. 

Now not all of this knowledge directly applies to Core 2 Duo, but the basic rules still apply bandwidth matters it just depend of your setup how much. I'm just trying to get people to look at their system setups as a whole rather than just focusing on the CPU clock speed, the best preformance always comes from balanced systems.

I hope you get where I'm trying to come from.


I've about decided how I want to tackle this is a stock E2xxx processor and cooler, either a P35 or 965 mobo (probably Gigabyte or Abit, maybe Asus, Asrock, or BioStar (are these okay?) (also on the 965, I assume I want P965 rather than G or Q since I won't have integrated graphics, but are there other disadvantages to a G965 or Q965?) also I saw FoxConn uses solid capacitors also - any opinions on them, one stick of 1G ram, and a cheap vid card (might need a new power supply also - recommmended brands? - I've used Fortron in the past).

Watch yourself with the 965 chipset boards, there was much larger spread in overclockablity on these boards, the P35 chipset handle high FSBs better and the P35 boards tend to designed to handle those high FSBs better, there are some good 965 overclocking boards out there but you'll probably find you can pick up a P35 chipset board for about the same price. As for brand stick with Gigabyte of ASUS, I was a big fan of Abit up until about 2 years ago, and then they just seamed to loss it, Asrock & Biostar both make cheap rubbish stay away from them. Power supply Cooler master makes some ok 460watt PSU at a good price, but you may not need anything that big depending on what other hardware you plan to run.




 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 29, 2007, 08:58:32 pm
A quick post here because I have to run off to a friend's house but did not want to leave Tiger-Heli hanging.
I only managed to run half of the benchmarks:

      1.8GHz      2.7GHz
sfrush      60.20%      84.33%
crusnusa                   99.21%      150.16%
swtrilgy                   25.64%      40.82%
ridgerac                   44.81%      66.17%

Some games scale linearly, some don't.
I ran taz's command line:
mamep.exe -noautoframeskip -frameskip 0 -seconds_to_run 240 -nothrottle -nosleep -video ddraw -skip_gameinfo -effect none -nowaitvsync -noreadconfig -mt -rompath f:\games\mame\roms sfrush

For sfrush, I press P1 button at the calibration screen to get rid of it in both cases.
I did not run swtrilgy to completion for the 1.8GHz (only 187sec) because I am in hurry so it may be somewhat biased.

Tomorrow I will run the other half of the benchmarks and also check the in-game FPS while actually playing the games with the CPU at 3.0GHz since this is ultimately what matters.

Regards.

Taz:
I got a glimpse of your message but will read it thoroughly tomorrow.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on November 30, 2007, 03:39:48 am
Also just an FWIW note for those that have had their C2D machines for a while, I just opened my case after a year or so and used compressed air to blow out the dust that had accumulated on the heatsink/fan assemblage and it immediately dropped 10+ degrees under load.  So be sure to keep your equipment clean so it can do its job. :)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 30, 2007, 05:14:22 am
Also just an FWIW note for those that have had their C2D machines for a while, I just opened my case after a year or so and used compressed air to blow out the dust that had accumulated on the heatsink/fan assemblage and it immediately dropped 10+ degrees under load.  So be sure to keep your equipment clean so it can do its job. :)

Yeah, those dust bunnies will get you everytime.  ;D

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 30, 2007, 09:36:32 am
I agree.
My case sucks in dust like you woun't believe.
When re-sat my heat sink a couple of weeks ago I cleaned everything well so I am not sure what made the most difference, the re-seating or the cleaning but I dropped a few degrees at idle. 

Also just an FWIW note for those that have had their C2D machines for a while, I just opened my case after a year or so and used compressed air to blow out the dust that had accumulated on the heatsink/fan assemblage and it immediately dropped 10+ degrees under load.  So be sure to keep your equipment clean so it can do its job. :)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on November 30, 2007, 08:54:05 pm
Tiger-Heli:

Here are all the benchmarks the CPU allowed me to do:
      1.8GHz   2.4GHz   2.7GHz
sfrush                      60.2%   75.9%   84.3%
crusnusa                   99.2%   133.6%   150.2%
swtrilgy                   25.6%      40.8%
ridgerac                   44.8%   59.6%   66.2%
All of the above was run on Windows XP with the official MAME binary.  This is the generic one with no optimization.

I could not get to 3.0GHz as much as I tried.  Windows simply would not start.  I don't think I am doing anything different from a few weeks ago when I managed to have it running at 3.0GZ for a whole week until one day it just would not load Windows.  I can't imagine what kind of threshold I might have crossed that now 3.0 is off limits with stock voltage.  I want to run at stock voltage since I want the processor to live long so it does not look like I will be able to get to that benchmark but you can extrapolate from the results above.

All of the notes below are for 2.7GHz:

For sfrush, the results might not be too accurate because, as I mentioned before, I had to hit P1 to get rid of the controller calibration screen or it stays there for the duration of the benchmark.  The problem is that, while at the calibration test screen, MAME runs very fast since there is not 3D modelling going on.  So according to exactly when the game registered the cancellation of the screen, I could have more or less average performance on each benchmark.
During the actual game, the FPS fluctuated between 40% and 80%.  Not very playable.

Crusnusa ran 100%, no problem.

I did not bother to re-run the missing swtrilgy benchmark since it is so woefully slow.  During gameplay, the game ranin the low 30%.

Ridgerac ran in the 30%, very slow.

I suppose you can enable framskip for some of these games and get by.

Regards.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on December 01, 2007, 08:20:53 am
Quote
I lot of my knowledge of effects of bandwidth on system preformance come from my P4 days, when I ran a 2.8ghz P4 northwood (512k cache) @ 3.5ghz 250mhz FSB with DDR-500 , that system was faster than a 3.6ghz P4 Prescott (2mb cache) with DDR-400, it was almost as fast as a 3.8ghz P4 Prescott. The extra cache memory in Prescott Core could not make up for the lack of system & memory bandwidth, the P4 Core simply needed more bandwidth to keep it work hard at high clock speeds.  I also spend a lot time disigning Dual CPU Quad Core Xeon server setup for customers at work, these use a Quad Channel memory setup to supply enough memory bandwidth to keep 8 cores working hard. 

Now not all of this knowledge directly applies to Core 2 Duo, but the basic rules still apply bandwidth matters it just depend of your setup how much. I'm just trying to get people to look at their system setups as a whole rather than just focusing on the CPU clock speed, the best preformance always comes from balanced systems.

I hope you get where I'm trying to come from.

taz:
I had more time to read you post carefully.
I do understand your perspective on it.  As I was researching my system, I read how bandwidth was a big deal on P4's so much more than with C3D's due to their architecture (I don't know the details, though).  But of course, there should be a minimum you have to supply before you cut into peformance as your benchmarks showed.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on December 01, 2007, 12:24:11 pm
i got my 6850 yesterday i will drop it in today & overclock to see how it does
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on December 01, 2007, 10:46:41 pm
i got my 6850 yesterday i will drop it in today & overclock to see how it does
dm

Cool, good luck with the overclock.

I'll be interest to see what you get out of it, be nice to have someone else at 4ghz to compare system preformance againest.

The more I read about the E8400-E8500 Core 2 Duo's the more I think I'll be changing CPU's at the end of January, 4.5-5.0ghz sounds good to me  >:D, of cause that last figure will probably required a switch to water cooling.

I'm about to shut down my system, install a spare HDD I have laying around and have a go at instlling 64bit linux & then SDLMAME 64bit, so that should keep me busy for a couple of days getting everything right. I'll post benchmarks when I'm done.



Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on December 02, 2007, 07:06:47 am
Watch yourself with the 965 chipset boards, there was much larger spread in overclockablity on these boards, the P35 chipset handle high FSBs better and the P35 boards tend to designed to handle those high FSBs better, there are some good 965 overclocking boards out there but you'll probably find you can pick up a P35 chipset board for about the same price. As for brand stick with Gigabyte of ASUS, I was a big fan of Abit up until about 2 years ago, and then they just seamed to loss it, Asrock & Biostar both make cheap rubbish stay away from them.
Thanks Taz - I can find TheManuel's Abit 965 board open box for about $45, and other P35's for about $60 while the Gigabyte P35's are about $90 (and the Gigabyte 965's are more than that oddly).  I suppose you get what you pay for to some extent, and I obviously don't replace my systems every six months so nickel-and-dimeing on the mobo doesn't seem like a good idea.

Quote
Power supply Cooler master makes some ok 460watt PSU at a good price, but you may not need anything that big depending on what other hardware you plan to run.
I believe the current PS is a Fortron 300W (FSP300-60PN) but most of the reviews said it was actually closer to 350W given the specs on the rail ratings - (Thought it was a 350 until I checked the order history - guess it probably needs to go).
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on December 02, 2007, 07:21:39 am
Thanks TheManuel -

CruisnUSA was likely a poor choice, at one time it was a real dog in MAME, but I tried with my Athlon XP 2800 (Barton) and got 58-60% in game with probably MAME 0.113 (not sure), almost but not quite playable.  SF Rush ran about 19-21% in game, but it took about 5 minutes to get past the two 15-second countdowns, totally unplayable.  I didn't have the other two games available on that system.
During the actual game, the FPS fluctuated between 40% and 80%.  Not very playable.
But a lot better than I'm getting. 8)

Quote
Ridgerac ran in the 30%, very slow.
Hmmmmn, interesting that it's that much slower in-game than the benchmark indicates - not an encouraging sign.

Quote
I suppose you can enable framskip for some of these games and get by.
Actually, I don't think you can - I don't remember the actual page, but I think it was on Aaron Giles website when people were complaining about slow speeds in Cruisin.  Aaron said that frameskipping helped in 2D games (like say Tiger-Heli or Striker1945 when the game had to calculate and draw the whole frame.  I crusin, where you are drawing in 3D, Aaron said the game still runs all the calculations and then just doesn't draw them - so you don't get a speed increase and just get choppier video.  (That's probably not 100% technically accurate, but that's the basic concept).

What you can probably do is go into the cheat menu and UNDERclock (I used to know why it was under and not over) the game CPU's and increase performance, but that sometimes messes up the audio.  (Or do like Taz and buy a 5Ghz CPU - just kidding :laugh2:)

Again - I really appreciate you taking the time to run those tests for me!!!!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Popcorrin on December 02, 2007, 12:03:33 pm

What you can probably do is go into the cheat menu and UNDERclock (I used to know why it was under and not over) the game CPU's and increase performance, but that sometimes messes up the audio.  (Or do like Taz and buy a 5Ghz CPU - just kidding :laugh2:)


You underclock it so that mame is in a sense emulating a slower cpu, but like you said, if you underclock it too much you get problems with the audio.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: ozzi22 on December 17, 2007, 04:58:14 pm
Is there diffrent results with windows xp 64 and vista 64?  Which is faster?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on December 17, 2007, 05:03:02 pm
I'm running vista 64, im sure xp 64 is faster but the drivers were never developed much for it.  Also the arcadevga does not support xp 64
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: jdjuggler on December 22, 2007, 05:17:37 pm
Are there any mame benchmarks to suggests that a quad core processor is faster/slow/same as a core 2 duo processor?  And, when I say quad, I don't mean the $500+ processors out there.  I referring to something that could be purchased for not much more than a core 2 duo... in the $200-300 range.
Thanks,
JD
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on December 22, 2007, 05:52:17 pm
Are there any mame benchmarks to suggests that a quad core processor is faster/slow/same as a core 2 duo processor?  And, when I say quad, I don't mean the $500+ processors out there.  I referring to something that could be purchased for not much more than a core 2 duo... in the $200-300 range.
Thanks,
JD

No hs done a full on test of a quad core to date that I know of, I did some testing on a Q6600 at stock speeds, and was less than impressed with the results when compared to a E6850 at stock speeds.  Basically those MAME drivers that are multithread gain hugely switching from single to dual core, but only a little more preformance is gained with the switch to quad core, this small preformance gain from the third and four cores is counter by the dual core higher stock clock speed (2.4ghz for the quad, 3.0 ghz for the dual) add to this the fact the dual core can be overclocked a lot more than the quad core, and the dual core becomes the clear winner currently.

Now this could change with the release next year of the Q9000 series 45nm quad cores and the possibitly on everyday 4ghz+ overclocker quad cores, but in saying that there is the new E8000 series dual core lauching at the same time offer up the possiblity of 4.5-5.0ghz overclocks.

In the end MAME cares more about clock speed than just about anything else and further multithread optimisations are problably going to be slow to come, add to that the fact that only about 2% of all non-MAME software actual make full use of the extra two cores in a quad, I'm sticking with dual core for now and plan to swap my e6850 for a core 2 duo E8500 in the new year.


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: joeH on December 26, 2007, 08:31:58 pm
Will the difference in L2 cache affect performance?  For example, e2180 (1M L2 cache, 10x multiplier) vs. e4500 (2M L2 cache, 11x multiplier)?   Both can easily hit the 3.0ghz range on stock cooling, however, currently there is about a $40 price difference between the two.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Jdurg on December 26, 2007, 08:39:20 pm
I'm no expert, but I think that a larger cache means that the CPU has more data waiting for it, and therefore is able to inherently run faster.  (Since it doesn't have to wait for the data to come to it since it's already sitting there in the cache).  Whenever I've bought CPUs for my day-to-day use or for overclocking, if given a choice I've taken the one with the larger cache.

Please feel free to correct me, everybody, if I'm wrong.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: joeH on December 26, 2007, 08:44:36 pm
Sorry...should have been more specific. I realize the more cache the better. The question was directly towards MAME specifically.   (This would be a machine for a cab...not a day-2-day machine). :)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on December 26, 2007, 09:55:25 pm
Take a look at this article (http://www.tomshardware.com/2007/10/24/does_cache_size_matter/page5.html) at Tom's Hardware addressing this very issues.
The most they managed to get by doubling the cache size was 8% on WinRAR.  Some applications did not gain anything.

I don't know how exactly this would play out in MAME but assume the best you can possibly get is 8% and think whether it is worth the extra $40.  Probably not.  This might get you a few extra frames on those CHD games but nothing worth writing home about.  Then again, you could get nothing for your $40.

Maybe the MAMEWorld forums would be a better place to ask the question but there aren't many people over there willing to help anymore from what I've seen coming back to the hobby.  I think there is too many jaded people there.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: joeH on December 26, 2007, 11:53:43 pm
Thanks for the post.  I doubt the Mame forums will be much help.  This was just going to be a stop-gap processor until the 45nm cores came out, so the 2180 may be the better buy in the short run.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Jdurg on January 27, 2008, 03:14:35 pm
Since filing my taxes, I'm getting a nice present from Uncle Sam.  That means I'll be getting myself a laptop since it's inherently more useful to me than replacing my desktop.  (I can sit in my living room and watch TV while surfing the web with my laptop, and I can also move around the house and do other things while still having my computer on.  Gives me some mobility).

Anyway, with the refund I got i'm looking at getting a new 45nm Core 2 Duo system and just trying to decide if I want the T9500 or the T9300 system.  I'm just not sure if the 100 MHz is worth the extra $225.  From what I've seen in this thread, I wouldn't think so.

So i hope to get this system once my refund arrives and get a chance to see how it holds up.  (It will be a 64-bit system so hopefully the "how-to" for 64-bit compiling will be available at that point).
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: headkaze on February 11, 2008, 05:54:43 am
Just a heads up Mame Compiler 64 has been released in the Software forum. This should make it easier to compile custom 64bit versions of Mame with optimizations for your CPU. So it might be worthwhile taking a look and doing some more tests for Mame64 if you don't know how to compile 64bt Mame already.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Jdurg on February 11, 2008, 08:08:19 am
Just a heads up Mame Compiler 64 has been released in the Software forum. This should make it easier to compile custom 64bit versions of Mame with optimizations for your CPU. So it might be worthwhile taking a look and doing some more tests for Mame64 if you don't know how to compile 64bt Mame already.

Fantastic!!!  I'm just waiting for UPS to arrive with my laptop and then I'll be looking to compile a 64 bit version of MAME.  This is great news!   ;D
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on February 17, 2008, 01:00:41 am
Well after way to many months waiting, I scored myself an Core 2 Duo E8500 engineering sample (It helps to know the right people sometimes) So out with the old 65nm E6850 and in with the new 45nm E8500 (3.16ghz 1333fsb stock). Now I've had this CPU a little over 24 hours as I type this and it's been in the my system less than 20, so I still need to tweak a few things, but 4.4ghz (4410mhz) seams to be my limit right now, while it will boot windows and run everyday apps at 4.5ghz, it locks after only a few minutes at 100% load, Air-cooling just isn't enough to keep it cool.  4.4ghz @ 490mhz FSB looks to be stable for the mean time more testing is need, but I may just splash out on a new case and water cooling kit and get it over and done with.

So now I bring you Core 2 Duo E8500 @ 4.4ghz vs MAME 0.123u1.  >:D (benchmark run on MAMEUI 64bit v123.1 in Vista Ulimate 64bit)

ROM NAME   
- 1942      7114.33% (4.5ghz CPU drag race)
- a51site4   225.85%
- airco22b      148.66%
- alpinerd      87.86% (still can't get this sucker to run at 100%)
- biofreak                   154.86%
- blitz2k      172.00%
- blitz99      164.36%
- blitz      176.95%
- calspeed   216.95%
- carnevil   301.32%
- crusnusa   289.38%
- crusnwld   258.61%
- cybrcomm   138.90%
- Daytona   (colours look better, but crashes within seconds unable to benchmark)
- gauntdl   143.39% (was noticably slower this time round, not sure why just yet)
- gauntleg   166.17%
- gradius4   122.94%   (actual used MAMEUI 32bit for this one, still in Vista 64bit)
- hyprdriv   189.75%
- mace      268.49%
- mk4                       186.26% (this is actual too high, but in game is over 100% all the times.)
- offroadc   468.22%
- propcycl   142.66%
- radikalb   178.03%   
- raveracw   118.34%
- ridgerac   159.87%
- scud      30.77% (Ha, back over 30% again, but this still needs alot of work)
- sfrush   219.12%
- sidebs2   178.88%
- speedup   182.32%
- starblad   156.96%
- surfplnt   170.44%
- tenthdeg   97.93% (so close to that magic 100%, but dips to the 70's in some areas game)
- timecris   149.15%
- wargods   406.11%
- wg3dh      387.59%
- xevi3dg   398.29%

Some scores are down on where I would have expected them, but that could just be the Dev's at work or my install of Vista 64 maybe a little broken after the dozen or so lockups testing overclocking settings, I'll probably reinstall and benchmark one of the older builds to confirm which it is.

To anyone looking at building a MAME Monster Machine, I suggest picking up an Core 2 Duo E8400, should be a easy 4ghz overclock with little added voltage needed, just make sure you upgrade the heatsink as they still get hot went you push them hard and the new stock HSF is tiny compared with the older Core 2 Duo's. (I can confirm crazy tempature readies are the order of the day with the E8#00 series CPUs, one core never reads below 44 deg C well the other drops to 29 deg C, over 44 deg C the move together like you would expect.)

Just a heads up Mame Compiler 64 has been released in the Software forum. This should make it easier to compile custom 64bit versions of Mame with optimizations for your CPU. So it might be worthwhile taking a look and doing some more tests for Mame64 if you don't know how to compile 64bt Mame already.

I've download this and I give it a go in the near future, more benchmarks will follow once I get everything tweaked a little better.

If anyone knows of any ROMs or Drivers I should test please let me know, I'm down to only half dozen Roms that are putting up any resistance now.




Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: releasedtruth on February 21, 2008, 11:05:32 am
Very impressize performance Taz, you are really doing us an awesome service here. I've been looking at the Quad core for experimental purposes, see what's possible there, even if it's not in the same league it'd be interesting to see how the architecture works at least.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: headkaze on February 21, 2008, 11:35:58 am
Those results are pretty amazing taz! I got myself an E8400 recently but havn't had a chance to overclock it yet.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on February 21, 2008, 11:41:56 am
I have a overclocked e6850 & the chd's overall run very good but gauntlet legends still needs a computer with about 15% more legs than mine has...maybe one of the newer cpus would work
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on February 21, 2008, 07:55:36 pm
Got my e8400 on the way, I'll be loading gauntlet first. I'll let you know in a week when its all up and running.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on February 22, 2008, 02:17:54 am
Very impressize performance Taz, you are really doing us an awesome service here. I've been looking at the Quad core for experimental purposes, see what's possible there, even if it's not in the same league it'd be interesting to see how the architecture works at least.

I had quick go with a stock quad core a few months back, but the result didn't impress me and I haven't had another go since, I may try again with the new Q9000 series once they're readly available, there is a Q9300 engineer sample kicking around work but I've done my impulse buying for the month.
I'd really love to see some MAME benchmark results for Q9000 series quad core at 4ghz (yes people have them running that high).

Those results are pretty amazing taz! I got myself an E8400 recently but havn't had a chance to overclock it yet.

Get to it man, It took me like 10 mins to get 4.0ghz on my E8500, as long as your system is up to it and you've got a good cooler go for, just turn off anything that may get in the way of overclocking, bump the chipset voltages to allow for higher FSB and hit the CPU with 1.4v and crank up the FSB to 445mhz, make any memory setting changes needed to keep your memory speed in check, and you should have yourself a 4ghz Core 2 Duo, that's about all I did. There's a little more to it than that, just ask if you want more details.

I have a overclocked e6850 & the chd's overall run very good but gauntlet legends still needs a computer with about 15% more legs than mine has...maybe one of the newer cpus would work
dm

I'm not going to tell you to dump your E6850 and get a E8400, I think that Z-cooler is still holding your E6850 back some. But the E8400 does look to be an easy 4.0ghz and you can probably keep your current setup including your heatsink, I my new CPU up to 43-46 deg C at 100% load at 4ghz. Every thing after 4.2ghz was hard work, but I think that more down to cooling and luck.

Got my e8400 on the way, I'll be loading gauntlet first. I'll let you know in a week when its all up and running.

Good luck with it, they are a great CPUs, just watch out for those crazy core tempature values, stick to the lastest version of CoreTemp and don't be suprised if one of the Core temps is stuck in the 40s.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on February 22, 2008, 02:30:32 am

Got my e8400 on the way, I'll be loading gauntlet first. I'll let you know in a week when its all up and running.

Good luck with it, they are a great CPUs, just watch out for those crazy core tempature values, stick to the lastest version of CoreTemp and don't be suprised if one of the Core temps is stuck in the 40s.

Thanks for the awesome thread and all the hard work. I expect to push it to around 3.6 from what I read, and because of the fact I ordered ddr2 800 it may be a bit difficult to overclock to around 4ghz on fsb and voltage/timing ocing alone, I will probably be back for more advice (in another thread) on the ocing of the board and any advice you may have. Thanks again and I'll be lurking this for a while ;D
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on February 22, 2008, 04:10:38 am
Thanks for the awesome thread and all the hard work. I expect to push it to around 3.6 from what I read, and because of the fact I ordered ddr2 800 it may be a bit difficult to overclock to around 4ghz on fsb and voltage/timing ocing alone, I will probably be back for more advice (in another thread) on the ocing of the board and any advice you may have. Thanks again and I'll be lurking this for a while ;D

Thanks,

The fact that your getting DDR2-800 doesn't mean you can't overclock to 4ghz, It just mean it's more complex and thus more differcult to do. To get a E8400 with it's 9x multiply to 4ghz you need to be running a 445mhz FSB (445*9=4005mhz), since the mininum memory ratio you can run on a P35 chipset board is 1:1 (2.0 in bios) your memory will end up running a DDR2-890 mininum, so you'll need to overclock your ram too, bumping your Memory voltage up a bit say to 2.0v will probably be all you need, but if voltage alone doesn't work for your ram then you can loosen the memory timing some, say it stock 4-4-4-12 then you might try 5-5-5-15 instead, A little bit of testing and tweaking should get you there.

Don't try and overclock everything at once, it's too hard to workout what's causing a problem.

Start with the ram just increase the Memory Multiplier from the stock 2.4 to say 2.66 with everything else stock and test the PC, with the stock 333mhz FSB this will give you a RAM speed of DDR2-886 (333*2.6=886), this is close enough to your required RAM speed of DDR2-890 to test the system for stability with the only the RAM overclocked.

Once you happy you got the Memory timing and voltage right you can move onto the FSB, drop the CPU multiplier to 6x, and the Memory Multiply to 2.0, then pump up the FSB to 445mhz and increase the chipset & FSB voltages as need to stablize the system, The CPU will be underclocked at this point at only 2.67ghz (445*6=2670mhz) and you've already set the memory timings to work at this speed, so your only dealing with the chipset stability.

Once you happy with the system with the FSB and RAM overclocked, increase the CPU Multiplier one step at a time from 6x until you get to 9x, test the system for stability at each Multiplier step, and increase the CPU voltage as need to get the system stable before moving on to the next Mutliplier, Until you get the CPU Multiplier to 9x, you should now be running a 445mhz FSB with the CPU multiplier at 9x and you Memory Multiplier at 2.0, giving you a 4.0ghz CPU with a 1780fsb and DDR2-890 ram.

If done right and with a little luck it will be nice and stable at these settings, now you need to torture test your CPU with something like Orthos, to take it to 100% load and hold it there for hours, I suggest at least 10 hours for you final test with the PC house as it will be in operation. Keep an eye on the CPU tempature and make sure it stays within safe limits anything up to 65 degs C is ok, over that is getting hot, and if it gets to 80 Deg C it will more than likely lockup before it can do any real harm, you really want it in the 20-30s at idle and in the 40s to low 50s at full noise. If it pass that it should be ready to use, it you want to further test it warm up the room tempature to that of a hot summers day and test it again for 24 hours, if it pass that you good to go.

Then all your've got to do is have fun.

Make sure your BIOS and Drivers are up to date before you start, I suggest using CPUz to get Live actual CPU speed & voltage information, the lastest CoreTemp is you best bet for watching CPU core temps, Orthos does a great job of stress you CPU & RAM to in limits (use blend test) and Windows task manager will confirm your CPU is at 100% load on all cores.

Just take your time, and test each new setup with orthos as you go.





Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on February 22, 2008, 05:11:49 am
Awesome, and functional approach, thanks a lot for the reply. Ive built tons of machines and done some overclocking, but I like your method better than mine, which is dabble with the fsb and voltage until it wont boot. Then if it starts to die in windows back it off.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: headkaze on February 22, 2008, 02:30:16 pm
I must admit I'm a little hessitant to do this now judging by the explaination there taz lol.

I have an Asus P5KR motherboard, E8400 @ 3Ghz, 2xPC5300 1 GB (which I believe is 667 Mhz).

I have the ASUS overclocking software AISuite installed and I'm staring at the screen. I really can't afford to screw this PC up, just how risky is overclocking? I have reasonable air cooling but I run this PC 24/7. If I overclock can I run it like that all the time or should I only do it for when I need the extra speed?

Here is a screenshot I took of AISuite. What temperatures should I be expecting and what temps should I be worried about?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on February 22, 2008, 02:42:59 pm
Taz is a better overclocker than I am, but unless he disagrees I prefer to overclock from the bios, a rule of thumb for me is 25% overclock then I usually just call it good.
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: lanman31337 on February 22, 2008, 02:46:52 pm
DM, I know you have some AMD x2 rigs - have you tried ocing your rigs, and do they do well with mame?  I have a 4800+ for my mame rig.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on February 22, 2008, 03:01:33 pm
Before I started all of the upgrade I went from:
first mame was a
1st: 4000 amd+
2nd : 4600 x2
3rd: 5200 x2
4th: 6600 quad
5th 6850 dual core

To be honest with a lot of wasted money I did not see a difference until I hit the intel dual or quad cores... the chd roms ran about the same on 1,2, & 3
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on February 22, 2008, 03:06:04 pm
I am by no means the expert taz is, but I can at least help break it down a little bit
DM, I know you have some AMD x2 rigs - have you tried ocing your rigs, and do they do well with mame?  I have a 4800+ for my mame rig.

The best athlon Ive run on is a 64 3200 and got it up to 2.6ghz. And yes they do well for mame rigs, you just wont be able to play gauntlet legends / NFL blitz. The first time Ive seen these playable is with Taz's quad core benchmarks.
I must admit I'm a little hessitant to do this now judging by the explaination there taz lol.
I have an Asus P5KR motherboard, E8400 @ 3Ghz, 2xPC5300 1 GB (which I believe is 667 Mhz).

I have the ASUS overclocking software AISuite installed and I'm staring at the screen. I really can't afford to screw this PC up, just how risky is overclocking? I have reasonable air cooling but I run this PC 24/7. If I overclock can I run it like that all the time or should I only do it for when I need the extra speed?

Here is a screenshot I took of AISuite. What temperatures should I be expecting and what temps should I be worried about?

The temps he is talking about is what looks like a bug in the chip itself. Toms hardware wrote an article on this and they also posted a big one about overclocking your chip.
http://www.tomshardware.com/2008/02/19/wolfdale_on_steroids/ (http://www.tomshardware.com/2008/02/19/wolfdale_on_steroids/)
The temps skyrocket on one core and not the other and give bad readings on some of the earlier versions. You may have one, you may not, don't worry about it.

The rest he can break down, but before he does i recommend doing some basic reading about what overclocking is exactly. Learn about

Multipliers
Front side bus speed
Vcore - processor voltage
Memory overclocking - ie ram and ram timings like 4-4-4-12


The


If done right and with a little luck it will be nice and stable at these settings, now you need to torture test your CPU with something like Orthos, to take it to 100% load and hold it there for hours, I suggest at least 10 hours for you final test with the PC house as it will be in operation. Keep an eye on the CPU tempature and make sure it stays within safe limits anything up to 65 degs C is ok, over that is getting hot, and if it gets to 80 Deg C it will more than likely lockup before it can do any real harm, you really want it in the 20-30s at idle and in the 40s to low 50s at full noise. If it pass that it should be ready to use, it you want to further test it warm up the room tempature to that of a hot summers day and test it again for 24 hours, if it pass that you good to go.

Then all your've got to do is have fun.

Make sure your BIOS and Drivers are up to date before you start, I suggest using CPUz to get Live actual CPU speed & voltage information, the lastest CoreTemp is you best bet for watching CPU core temps, Orthos does a great job of stress you CPU & RAM to in limits (use blend test) and Windows task manager will confirm your CPU is at 100% load on all cores.

Just take your time, and test each new setup with orthos as you go.







This is important. Programs like orthos and prime95 help you to max out your cpu to burn it in. Cpu-z will help you pull the temp off your cpu. I don't know what I'm missing and I hope I helped in some small way.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on February 22, 2008, 08:30:08 pm
I must admit I'm a little hessitant to do this now judging by the explaination there taz lol.

I have an Asus P5KR motherboard, E8400 @ 3Ghz, 2xPC5300 1 GB (which I believe is 667 Mhz).

I have the ASUS overclocking software AISuite installed and I'm staring at the screen. I really can't afford to screw this PC up, just how risky is overclocking? I have reasonable air cooling but I run this PC 24/7. If I overclock can I run it like that all the time or should I only do it for when I need the extra speed?

Here is a screenshot I took of AISuite. What temperatures should I be expecting and what temps should I be worried about?


Overclocking is easy once you get to grips with the basics and get an understanding of what all the bios setting do, everything effect everything else, that's why you need to it in stages otherwise it becomes almost impossible to work out where you when wrong. If you have questions as to what all those option in bios do, hit me with it, I'll do my best to explain, just don't ask me to explain it all at once.

Your memory will be your biggest issue, DDR2-667 like you have runs at 333mhz double pumped, so the 333mhz FSB of you CPU puts your memory at it's maximum stock speed straight away, say your aim for 4ghz with your CPU, for memory would end up almost 50% overclocked to get there, now that a big push for most memory and outside what I would rate as practical or save, you best option would be to be dump your current memory on a friend or family member with a PC in need of a bit more get up and go, and grab yourself a couple of GB of good DDR2-800 or better yet DDR2-1066 RAM. Memory is dirt cheap these days so it doesn't have to cost you the earth. Then as long as you have a good aftermarket heatsink, you should be good to go.

Software overclocking has it's place, but it doesn't give you access to nearly as many setting to adjust, so it soon limits the level of overclocking you can achive, There are a number of bios features that needed to be disable before any form or overclocking is attempted, as they will cause stability issues with an overclocked CPU, so you end up having to change BIOS settings anyway so you may as well just do it all in BIOS where you'll get the best results.

Overclocking very safe as long as you don't push things too far, too much Voltage or heat and things can get nasty, A good heatsink & Powersupply are a must. The thing to remember is the Core 2 Duo is not an Athlon XP, the Core 2 Duo has great built in safeties for heat and will shut it self down if needed before any damage is done, just be smart about it, if  you crank the FSB up to 600mhz and pumping 1.8v into your CPU and having it run a 75degs you would just be asking for trouble.

Those tempatures look normal for a stock setup, I would expect lower temps if you were using an aftermarket cooler, but it depends of the room temp and the design of your case.

Taz is a better overclocker than I am, but unless he disagrees I prefer to overclock from the bios, a rule of thumb for me is 25% overclock then I usually just call it good.
dm

25% is a good overclock for most CPUs, but the Core 2 Duo is a whole other league with the average overclock falling in the 33%-75% range, they have so much head room it's basically a crime not to overclock them, you can get 25% overclocks with the stock heatsink I many cheaper models.

DM, I know you have some AMD x2 rigs - have you tried ocing your rigs, and do they do well with mame?  I have a 4800+ for my mame rig.

The Athon64 x2 overclock well, the last one I had in my primary system was overclocked by about 40%, and they do well in MAME to a point, but they can't jump the preformance gulf between what is needed to run most ROM and what is required to run all ROM (well almost all). They just don't have the preformance to clock ratio that the Core 2 Duo does, and the extreme overclockablity (is that even a word) of Core 2 Duo only widens the preformace gap between the two CPUs.


If I had the spare cash laying around I'd probably grab a GA-G33M-DS2R boarch and transfer over my CPU, Heatsink and ram to it, and benchmark it to see if using the onboard graphics had any negative on MAME preformance, because if it didn't then it would be a good choice for people trying to slim down the cost of preformance MAME system. The board is well documented as a great overclocker, with people run anywhere up to 500fsb and some beyond. When the next shipment of stock comes in a work, I may have to see if I get the boss to lead me one for a week to test, it's not likely to happen but it's possible.







Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Jdurg on February 23, 2008, 02:22:27 am
With my tax refund I went out an got myself a new laptop with a 2.50 GHz T9300 Core2Duo CPU in there.  I just ran MK4 on a non-optimized, 64-bit version of MAMEUI64 and had a VERY playable session.  I was averaging about 90% in game and was at 100% for many of the cut scenes.  I was very shocked to see such good performance from a relatively low-speed CPU.  I'm also running 64-bit Windows Vista which I have yet to optimize yet.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on February 23, 2008, 10:28:42 am
I have the ASUS overclocking software AISuite installed and I'm staring at the screen. I really can't afford to screw this PC up, just how risky is overclocking? I have reasonable air cooling but I run this PC 24/7. If I overclock can I run it like that all the time or should I only do it for when I need the extra speed?
HK - I ended up not spending the money on a new rig - but in your case, I really like the advice The Manuel posted on Page 3 (at the bottom) of this thread:

Finally, to extend the life of the processor, I set my power scheme to laptop/portable so that EIST kicks in and the CPU multiplier is knocked down to 6X form 9X while the computer is idle or doing light duty like browsing the web or playing pacman :-) but immediately goes to full throttle when more processing power is required.  As a result, my 2.7GHz is running at 1.8GHz most of the time which happens to be the stock speed.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on February 26, 2008, 05:35:56 am
So sweet!!!!!!! Got the processor in the mail today, and built the machine. The processor came in at 3ghz on first boot, I updated the bios and did a burn in. After some tweaking I got this up to 4ghz. The e8400 is amazing. If you don't have a newer processor yet, you have to buy this. To Taz - You helped a lot with the timings and the ocing. K back to the burn in. Ill let ya know in the morning how it all turned out.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on February 26, 2008, 06:08:29 am
So sweet!!!!!!! Got the processor in the mail today, and built the machine. The processor came in at 3ghz on first boot, I updated the bios and did a burn in. After some tweaking I got this up to 4ghz. The e8400 is amazing. If you don't have a newer processor yet, you have to buy this. To Taz - You helped a lot with the timings and the ocing. K back to the burn in. Ill let ya know in the morning how it all turned out.

 :applaud: Sweet dude, Welcome to the 4ghz club, :cheers:

I'd being interested to know what voltages etc your running once you've got it all tweaked and tested.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on February 26, 2008, 03:35:19 pm
K here is my full dump from cpu-z to see how I have it set. To keep things organized I am going to make 2 posts :-)

Processor(s)   

Number of processors            1
Number of cores               2 per processor
Number of threads         2 per processor
Name               Intel Core 2 Duo E8400
Code Name            Wolfdale
Specification             Intel(R) Core(TM)2 Duo CPU E8400 @ 3.00GHz
Package                    Socket 775 LGA
Family/Model/Stepping         6.7.6
Extended Family/Model         6.17
Core Stepping            C0
Technology            45 nm
Core Speed            4005.1 MHz
Multiplier x Bus speed         9.0 x 445.0 MHz
Rated Bus speed                 1780.1 MHz
Stock frequency            3000 MHz
Instruction sets         MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, EM64T
L1 Data cache (per processor)      2 x 32 KBytes, 8-way set associative, 64-byte line size
L1 Instruction cache (per processor)   2 x 32 KBytes, 8-way set associative, 64-byte line size
L2 cache (per processor)      6144 KBytes, 24-way set associative, 64-byte line size

Chipset & Memory   

Northbridge            Intel P35/G33/G31 rev. A2
Southbridge            Intel 82801IB (ICH9) rev. 02
Graphic Interface         PCI-Express
PCI-E Link Width         x16
PCI-E Max Link Width         x16
Memory Type            DDR2
Memory Size            2048 MBytes
Memory Frequency         445.0 MHz (1:1)
CAS# Latency (tCL)         5.0 clocks
RAS# to CAS# (tRCD)         6 clocks
RAS# Precharge (tRP)         6 clocks
Cycle Time (tRAS)         17 clocks
Command Rate (CR)         2T

System   

System Manufacturer         Gigabyte Technology Co., Ltd.
System Name            P35-DS3L
System S/N   
Mainboard Vendor         Gigabyte Technology Co., Ltd.
Mainboard Model                 P35-DS3L
BIOS Vendor            Award Software International, Inc.
BIOS Version            F8a
BIOS Date            12/06/2007
Memory SPD   
Module 1            DDR2, PC2-6400 (400 MHz), 1024 MBytes, G.Skill
Module 2            DDR2, PC2-6400 (400 MHz), 1024 MBytes, G.Skill
Software   
Windows Version                 Microsoft Windows XP Professional Service Pack 2 (Build 2600)

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on February 26, 2008, 03:40:26 pm
Vcore - 1.512
memory - 1.170
Pci - 1.55 (stock)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on February 26, 2008, 03:52:04 pm
Quick question why is the 8400 cheaper than the E6850 on newegg.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on February 26, 2008, 06:00:55 pm
Quick question why is the 8400 cheaper than the E6850 on newegg.

'Cause it's "Out Of Stock", so you can't buy it anyway? ;D

edit: speeling ;)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on February 26, 2008, 06:33:34 pm
Quick question why is the 8400 cheaper than the E6850 on newegg.

Warning Geek stuff!!

Because the (Wolfdale) E8#00 series Core 2 Duos are manufactured using 45nm process they, the transistors they are made of are smaller than those found in the E6#50 series which is manufactured using a 65nm process, so while the E8400 has more Cache memory and thus more transistors in it than an e6850, it's actually has a small die 107 mm² compared with the e6850s 143 mm², Now this effects cost for three main reasons, because the Core 2 Duo are manufactured on the same 300mm silicon wafers that cost the same no matter what CPU you make with them, the smaller the die the more you CPUs you can make from one silicon wafer and thus the cheaper they are, also a smaller die means they can shuffle them arround a on the silicon wafer more to cut down on wasted space that can't be used around the edges of the silicon wafer this reducing costs, all Silicon wafers will have a few defects in them at the end of the manufacturing process, die that a layed down over these areas will be defective and thus end up as waste, now the small dia is less likely to have a defect in it that a larger die, and there is less wasted silicon when a small dia is defective. These plus a host of other things mean Intel can produce the E8400 a lot cheaper than they can an E6850 thus the price is lower, also there are market forces at work to.

I could have just said they are small so they are cheap, but where's the fun in that.  ;D Oh and before anyone asks why they make square chips on a round wafer, it's because each layer of the chip is added to the center of the wafer as a liquid as the wafer is spun at speed, this makes for a near perfect application of the liquid accross the whole surface of the Silicon wafer.

'Cause it's "Out Of Stock", so you can't buy it anyway? ;D

He's right too, lots of online stored do it with new or very popular products that are unavilable, they dump the price to get people to their site, hoping once there they will buy something else.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on February 27, 2008, 02:30:55 am
Allrighty, Im back with the final update. This whole pc cost $600 in brand new parts and it screams. I ran the benchmark for around 24hrs and it is stable as a mule. Even with the full torture test running on both cores (which means processor usage is pegged at 100%) it stayed a solid 65c-66c. I am now running idle, because im bored of prime numbers, and my temp is sitting steady at 42c-44c. Once I re-download my chds and roms ill do some benchmarks to see what this mammer jammer can do.

*on a side note, has anyone in the community thought to build a program similar to 3d mark that benches your system and automates frame rate tracking based on the most troublesome mame games? I'd love to help, but I don't know if I have the patience to sit and test every beefy game.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: ids on February 27, 2008, 09:02:39 am
Quick question why is the 8400 cheaper than the E6850 on newegg.

Warning Geek stuff!!



Correct me if I am wrong, but as I understand it, in this case, they were able to reuse a lot of the fabrication stuff.  Often when going to a smaller die, there is a huge investment in equipment that needs to be recovered.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Jdurg on February 27, 2008, 01:31:43 pm
Another nice thing that we've all seemed to find out about recent Intel chips is that their ability to produce CPUs that can run at a high speed is phenomenal.  They are doing such a good job at making chips that can run at high speeds that they are forced to take some of these high-speed CPUs and lock them down to a lower default speed in order to fill demand for that CPU speed.  Therefore, we are able to overclock the living hell out of them and get great CPU speeds on our CPUs.  For all intents and purposes, Intel would have loved to have sold those CPUs as a high speed variety, but not everybody out there can afford those chips and they had to "lower them down" to meet demand.   :applaud:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on February 27, 2008, 04:48:50 pm
If they unlocked the multiplier on this chip, god only knows how fast we could get it going. Toms hardware did a pretty good writeup about what this chip can do. http://www.tomshardware.com/2008/02/19/wolfdale_on_steroids/  (http://www.tomshardware.com/2008/02/19/wolfdale_on_steroids/)
Back in the day you could go crazy with the overclocking, but any test required the usage of pretty extreme cooling. Their test sample never got that hot, and they even ripped the cover off the chip to see if they could cool it better, but that did not work. It seems as if they built in a cap in the fsb speed.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on February 27, 2008, 07:08:30 pm
Oh darn, I was typing so long my session timed out, so I lost my huge post aarrgh, so here I go trying to remember everything I just wrote.  :timebomb: :timebomb: :timebomb:

Hello again, I am still in the process of downloading the full chd set for this rom version (122u3 i think it is up to so far) and I was wanting to do some set up before everything finishes tomorrow. I have only ever really configured mame via mamui or other front end, and I was wondering what the best settings would be for my setup. My full specs are above, and I am only running xp 32 bit. I am running mame 123u1 w/ highscore.diff files for this version (compiled using mame compiler 64). I just ran mame and it was getting a bit of screen tearing (is it teering or tearing...whatever) and I just wanted to work that out as well.

On a side note, is there any advantage from running mame via xp64 over xp32, othen then ram addressing? I have looked all over and have found to actual in depth explanation. Am I just holding my awesome proc back because of my os?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on February 27, 2008, 07:39:03 pm
Ok, Im sorry, asked a question you allready answered like 4 times in this thread

 
On a side note, is there any advantage from running mame via xp64 over xp32, othen then ram addressing? I have looked all over and have found to actual in depth explanation. Am I just holding my awesome proc back because of my os?

Oh boy, I just set this whole machine up using xp32, and now I need to dump all the data I have onto another machine to load vista. I am so against vista and all I have ever seen/read about it has been, its slow slow slow slow. Do you know if they make tinyVista64?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Jdurg on February 27, 2008, 07:47:09 pm
Ok, Im sorry, asked a question you allready answered like 4 times in this thread

 
On a side note, is there any advantage from running mame via xp64 over xp32, othen then ram addressing? I have looked all over and have found to actual in depth explanation. Am I just holding my awesome proc back because of my os?

Oh boy, I just set this whole machine up using xp32, and now I need to dump all the data I have onto another machine to load vista. I am so against vista and all I have ever seen/read about it has been, its slow slow slow slow. Do you know if they make tinyVista64?

A lot of what you've read is exaggeration, exaggeration, exaggeration.  It's just an instinct to lash out and bash a new Microsoft product.  Is Vista somewhat slower than XP?  Yes, but it's easy to tweak and XP isn't exactly the speed demon it's cracked out to be.  It took quite a while to get it to where it is right now.

In Vista, I've found that my software loads MUCH quicker, my internet speed seems to be twice what it is on my XP system, and I have yet to have any problems that I didn't cause myself.  So don't go into Vist with poor expectations and a bad attitude.  Open your mind up a bit and you'll be pleasently surprised.  I'm now liking Vista quite a bit and know that it will be getting even better as time goes on.   :cheers:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on February 27, 2008, 07:53:18 pm
Ok, I am getting tinyvista rev01 right now, and I'll load it as soon as I am done with this dling I'm doing.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: illtww on March 03, 2008, 05:17:51 pm
Alright Guys...

I have a 3.0ghz E2140 running Winxp Pro.  1gb ddr2 ram

I am using MameUI (32 bit version)

Is that not enough oomph to rung gauntlet Legends / NFL Blitz?   :angry:

Do I need to change to another OS??  Where can I get a build that is optimized for
our Dual Core Intel Procs?

Thanks,
Travis
 ???
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 03, 2008, 09:41:39 pm
Alright Guys...

I have a 3.0ghz E2140 running Winxp Pro.  1gb ddr2 ram

I am using MameUI (32 bit version)

Is that not enough oomph to rung gauntlet Legends / NFL Blitz?   :angry:

Do I need to change to another OS??  Where can I get a build that is optimized for
our Dual Core Intel Procs?

Thanks,
Travis
 ???

Nice overclock, that's almost a 90% overclock.  :applaud:

Running 64bit OS is a must if you want to get the most out of MAME when running on a Core 2 Duo. You will probably want another gigabyte of ram too, as Vista 64 is your best option when it comes to 64bit OS and it needs 2gb to run well.

MAME preformance scales almost 1 for 1 with CPU clockspeed, so a 3ghz you should land in the 105-120% range on these ROMs running MAME 64bit, which is pushing it a little, you really want a hard 120%+ to be sure that the games will run well perfectly. Also I'm not sure what, if any effect the smaller Cache on the E2140 will have on your preformance.

Optimized build had a noticable effect in the pass, but that gains seem to be been reduced with the 64bit builds. I tried compiling a 64bit optimized build the other day to test ,but 64bit compiling still seems to beyond me, it alway stops with errors but I'm still working on it, it can't be that hard.

 

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: headkaze on March 03, 2008, 09:51:19 pm
*on a side note, has anyone in the community thought to build a program similar to 3d mark that benches your system and automates frame rate tracking based on the most troublesome mame games? I'd love to help, but I don't know if I have the patience to sit and test every beefy game.

Get a program called "Fraps" it can overlay the FPS on a Direct3D program in realtime.

taz-nz: Have you checked out Mame Compiler 64 in the software forum? It can compile 64 bit versions of Mame now. The only thing I'm unsure of though is if the optimization flags are only for the GCC compiler and not for the cl.exe 64 bit compiler found in the Platform SDK (which is used to compile 64 bit versions). So in other words I'm not sure if compiling your own version of Mame64 will result in a binary any different the official one you can download at mamedev.org. Anyway install Mame Compiler 64 just to get the environment setup and check out the MinGW\source\Mame0123 folder for a batch file that demonstrates compiling Mame64 manually.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: illtww on March 03, 2008, 11:31:54 pm
I may get it to 3.2....   :cheers:

Is there a build on the net of  Vista 64 that is "nlighted" so to speak? 

I have 2 1gb sticks of Balistick Ram I can snap in there..

Will 1.5 gigs work?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on March 04, 2008, 01:40:33 am
What you want is the Microsoft.Windows.Vista.Ultimate.x64.Integrated.January.2008.OEM and take that and run vlite on it. Remove all the fat and install.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Popcorrin on March 06, 2008, 10:38:21 am
I see that there are big increases with running 64bit mame under 64bit vista.  What about 64bit mame under 64bit xp has anybody tried that?

I'm guessing that these benchmarks don't take into account the speed decrease for ingame as compared to attract mode.  In most 3d games I have noticed anywhere up to 50% decrease in speed during ingame gameplay.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 06, 2008, 02:42:37 pm
I see that there are big increases with running 64bit mame under 64bit vista.  What about 64bit mame under 64bit xp has anybody tried that?

I'm guessing that these benchmarks don't take into account the speed decrease for ingame as compared to attract mode.  In most 3d games I have noticed anywhere up to 50% decrease in speed during ingame gameplay.

I run the benchmarks for 240 and not 100 game secs for this reason, While many games display title and high score screens when running attract mode that can bump the average benchmark, they only make up a small part of the attract mode. Most games run in game within 20% on the final average benchmark score, that's why you want atleast 120% average if possible to be sure it will be playable, there are some games where the framerate is higher ingame than it is in parts of the attract mode, also many of the 3D games are limted by the CPU emulation, not the graphics chip emulation, so run the same ingame as they do in attract mode.

Benchmarks are just a guide to preformance requirements in the end, they only way to confirm the result is to load the ROM and play the game.

MAME 64 works well under XP Pro 64 by all accounts.




Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Silver on March 06, 2008, 08:38:06 pm
I see that there are big increases with running 64bit mame under 64bit vista.  What about 64bit mame under 64bit xp has anybody tried that?

Mame is fine but practically everything else on my system can not work due to lack of hardware support.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: trustno1 on March 12, 2008, 03:19:06 pm
Hello,I was wondering how a a system with two xeon 64bit 3.4GHZ with 2mb l2 cache and 800 mhz front side bus with ddr2 2gb sdram 400mhz would compare to some of the systems that you guys have tested. My buddy is selling this and I would like to use it for my mame cab but this is a first for me and this seems like the only place where people have any knowledge on this subject. Thanks. Would hate to throw away money for system when taz has posted how to build one comparable to his =)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on March 12, 2008, 05:33:34 pm
I'm curious how vista sp1 will affect performance, in reading I have seen statements of upwards 25% performance boost, should be interesting how this works out.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 13, 2008, 05:34:48 am
This thread just hit 10,000 views :dizzy: , nevers saw that coming when I first posted, I always figured I'd get a dozen or so replies and that's about it, I was happy when it hit 200 views  :) , Well chairs everyone still following this thread  :cheers:

I'm curious how vista sp1 will affect performance, in reading I have seen statements of upwards 25% performance boost, should be interesting how this works out.

I don't think the preformance jump will be that great, most of the preformance tweaks were to do with file copying etc. I've got a Vista SP1 update disk, If I get a chance on the weekend I'll do a before and after benchmark test on Vista. I've been really busy of late and so haven't had time to run as many test as I have in the past, but I see what I can do.

Hello,I was wondering how a a system with two xeon 64bit 3.4GHZ with 2mb l2 cache and 800 mhz front side bus with ddr2 2gb sdram 400mhz would compare to some of the systems that you guys have tested. My buddy is selling this and I would like to use it for my mame cab but this is a first for me and this seems like the only place where people have any knowledge on this subject. Thanks. Would hate to throw away money for system when taz has posted how to build one comparable to his =)

A 3.4ghz Xeon has the same basic CPU architecture as a Pentium 4, so the sytem would likely have comparable MAME preformance to a Pentium D of around the same speed, possibly a little fast due to the large cache memory the Xeons have. I would expect a Core 2 Duo at anything over 2.5ghz to beat it in MAME I'm sorry to say.

If decide to go with a new system, hit me any questions you have about what to get.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: lanman31337 on March 14, 2008, 12:28:04 am
I'm probably going to get beat with a wet noodle, but i'm upgrading my desktop to an amd sli board and a 5000+ black edition, and 4 gigs of ram.  ima see how it does, and i might upgrade the 4800+ in my mame cabinet to the 5000+ black.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: trustno1 on March 14, 2008, 04:57:11 am
I was hoping that wasn't going to be your answer ;), but at that using that chip would your 2nd page posting be the ideal setup to achieve your overclocking (which is a whole other topic in itself =)) or would you recommend anything else. I was looking at:
Intel® Core 2 Duo Processor E8400
Crucial 2GB (2 x 1GB) DDR2 1066 (PC2 8500) Dual Channel Kit Memory - Retail (5-5-5-15)
GIGABYTE GA-EP35-DS3R LGA 775 Intel P35 ATX
Antec NeoPower 650 650W Power Supply
ARCTIC COOLING Freezer 7 Pro 92mm CPU Cooler

Looking foward to matching your benchmarks ;)
thanks..
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 14, 2008, 08:53:41 am
I was hoping that wasn't going to be your answer ;), but at that using that chip would your 2nd page posting be the ideal setup to achieve your overclocking (which is a whole other topic in itself =)) or would you recommend anything else. I was looking at:
Intel® Core 2 Duo Processor E8400
Crucial 2GB (2 x 1GB) DDR2 1066 (PC2 8500) Dual Channel Kit Memory - Retail (5-5-5-15)
GIGABYTE GA-EP35-DS3R LGA 775 Intel P35 ATX
Antec NeoPower 650 650W Power Supply
ARCTIC COOLING Freezer 7 Pro 92mm CPU Cooler

Looking foward to matching your benchmarks ;)
thanks..

My current recommendation for minium specs are below, all items are available for Newegg and prices quoted are from there. ( I whipped this up the other day for another fourm member)

Intel Core 2 Duo E8400 3.0ghz (333*9 stock)$249.99
XIGMATEK HDT-S1283 CPU Cooler$36.99
Arctic Silver 5 Thermal Compound $5.99
GIGABYTE GA-P35-DS3L Motherboard$89.99Open box avaliable for $20 less
Transcend AxeRAM 2GB $79.99
GIGABYTE GV-RX24T256H Radeon HD 2400XT$46.99
SILVERSTONE ST350 350W Power supply   $39.99
Total:
$547.93

You could go cheaper by going to G.Skill F2-8500CL5D-2GBPK Ram and a MSI RX1550-TD128EH Radeon X1550 graphics card, doing this and getting an open box motherboard will get you below $500.

The 350watt PSU is smaller than I would normally suggest, but as long as your only planning on one hdd a DVD-Rom it should be ok, It's a good brand and it's specs look better that a lot of cheap 500w PSUs out there.

The larger PSU will not hurt, and I highly recommend it if you going to be running any more powerful than an entry level graphics card, I chose the ati 2400xt because of it very low power usage.

If your going to go for the P35-DS3R get the P35-DS3P instead, it's the same board with better cooling and you can get one in an open boxed one for $109.

The only thing on you list I really don't like is the heatsink, they aren't bad heatsinks but it's not good enough for extreme overclocking. I suggest the one list above or the COOLER MASTER RR-CCH-LB12-GP (hyper 212)


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Popcorrin on March 14, 2008, 09:40:44 am


My current recommendation for minium specs are below, all items are available for Newegg and prices quoted are from there. ( I whipped this up the other day for another fourm member)

Intel Core 2 Duo E8400 3.0ghz (333*9 stock)$249.99
XIGMATEK HDT-S1283 CPU Cooler$36.99
Arctic Silver 5 Thermal Compound $5.99
GIGABYTE GA-P35-DS3L Motherboard$89.99Open box avaliable for $20 less
Transcend AxeRAM 2GB $79.99
GIGABYTE GV-RX24T256H Radeon HD 2400XT$46.99
SILVERSTONE ST350 350W Power supply   $39.99
Total:
$547.93

You could go cheaper by going to G.Skill F2-8500CL5D-2GBPK Ram and a MSI RX1550-TD128EH Radeon X1550 graphics card, doing this and getting an open box motherboard will get you below $500.

The 350watt PSU is smaller than I would normally suggest, but as long as your only planning on one hdd a DVD-Rom it should be ok, It's a good brand and it's specs look better that a lot of cheap 500w PSUs out there.

The larger PSU will not hurt, and I highly recommend it if you going to be running any more powerful than an entry level graphics card, I chose the ati 2400xt because of it very low power usage.

If your going to go for the P35-DS3R get the P35-DS3P instead, it's the same board with better cooling and you can get one in an open boxed one for $109.

The only thing on you list I really don't like is the heatsink, they aren't bad heatsinks but it's not good enough for extreme overclocking. I suggest the one list above or the COOLER MASTER RR-CCH-LB12-GP (hyper 212)




If Newegg ever gets the E8400 back in stock.   They do have the E6750 in stock, it's a tad slower but it's also $60 cheaper.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: trustno1 on March 14, 2008, 01:22:13 pm
hah, thanks taz. I was placing the order and not only can you not find the 8400 because newegg actually deactived the item, it is sold out everywhere on the net. Good luck trying to find that chip anytime soon =). well guessi will ust have to wait for a bit. thanks again.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 14, 2008, 07:46:22 pm
hah, thanks taz. I was placing the order and not only can you not find the 8400 because newegg actually deactived the item, it is sold out everywhere on the net. Good luck trying to find that chip anytime soon =). well guessi will ust have to wait for a bit. thanks again.

I not sure what's deal is with Intel's 45nm CPUs, the only ones that seem to have any availablity are the E54x0 Xeons and the QX9650. We got one and only one shipment of E8400 into work almost a month ago now, and since we've only had a small shipment of E8200s, the ETA on the next shipment E8400s and the availablity of the E8500 and Q9000 series CPU is way off, and the dates keep slipping which is very strange, It normal to see storages at release of a new CPU but the gaps between shipments is normally only a week or two.

There is either a stortage due to extreme demand, which I doubt would go on for so long, or Intel is limiting stock to clear out old stock of the Q6000 & E6000 series CPUs, they can since there is nothing in AMDs range to force them to release the lastest and greatest.  Or the sticking tempature sensor issue on the E8400 is a bigger deal than Intel is willing to let on about and they are working like mad to fix it, while hopeing no one notices.

But it looks like a sit and wait game for everyone wanting a new 45nm Core 2 Duo at the moment.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: billpa on March 14, 2008, 09:46:10 pm
Is the E6750 a viable alternative? I've heard some people being able to OC close to 4ghz.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 14, 2008, 10:11:11 pm
Is the E6750 a viable alternative? I've heard some people being able to OC close to 4ghz.

The E6750 is great CPU, but it tops out for overclocking about 3.6-3.8ghz on good air cooling, You need to get more extreme with your cooling to get to 4.0ghz. As where the E8400 by all accounts will hit 4ghz at the drop of a hat, and there is room to go well below that with the right setup.

The went you factor in easy of overclocking, heat, power use, operating tempatures, the E8400 is the safer bet if you overclocking.


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: lanman31337 on March 17, 2008, 09:14:51 am
Dead on with the performance with 64 bit os + 64 bit mame.  I was able to finally get vista/xp to dual boot, and there's definitely a lot of speed increase, especially on CHD's. 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: rdenis on March 17, 2008, 02:53:08 pm
Okay I have my Quad 6600 at 3.45Ghz stable (Prime95, OCCT V2.0 RC2, Memtest 86+).  I know some people here have been less than impressed with its performance but now that I've tweaked the overclocking I think its worth a revisit for information purposes.

But I have no idea how to benchmark so if someone could kindly point the way I am more than willing to spend the time and post some results.

Here is my setup:

Quad 6600 (G0 stepping) 9x384 = 3.45 Ghz
OCZ 4 GB DDR2-800 o/c to 920Mhz (6:5 divider)
Asus Maximus Formula Bios Settings:
  Vcore - 1.424 under load with Vdroop pencil mod
  Dram - 2.0 (board overvolts 0.08 to 0.10 so actual is 2.08-2.10)
  Spectrums disabled
  All other settings Auto
Arctic Pro 7 Cooling (Cores at 67,67,62,62 at 100% load stress test - 33,33,32,32 idle)
eVga GTS8800 512mb (o/c to 770/1923/1080)
Vista 64 Home Premium edition

3dMark 06 - 15,347

I think the system should put out some decent results now.

In addition to how do I benchmark, what 64 bit version of Mame should I compile to run the tests?

Rich

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on March 17, 2008, 02:56:12 pm
I have 2 q6600 & 3.45 was also the best I could overclock with the coolers I am using
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: rdenis on March 17, 2008, 03:05:48 pm
I haven't tried going higher yet but I know some guys are claiming to have got the quads stable at 3.8 on air - I don't think I believe it.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: rdenis on March 17, 2008, 03:09:43 pm
DM - did you run the benchmarks at 3.45 - how did they compare?

Rich
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on March 17, 2008, 03:15:35 pm
I'm not using either of these computers for mame, I have a dual core e6850 in my mame system
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on March 17, 2008, 05:22:05 pm
But I have no idea how to benchmark so if someone could kindly point the way I am more than willing to spend the time and post some results.
...
In addition to how do I benchmark, what 64 bit version of Mame should I compile to run the tests?

Look at Taz's first post in this thread to see what settings he's using.  I'm not sure how others are setting up (search for "seconds_to_run" or "-str" in this thread for examples), but other standard ways can be found at mamebenchmark (http://benchmark.mameworld.net/howto.html) (about what Taz is using AFAICT) and mameui  (http://mameui.classicgaming.gamespy.com/Bench.htm)sites.  The problem with MameBenchmark is -video ddraw; the default is now d3d and most (non-aarcade monitor cabs) people use it now.  MameUI's settings have -video none, which is rarely used too.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: MBaran on March 27, 2008, 01:41:03 pm
If the 2nd core is only accountable for ~5% increase, could a P4 or Pentium D at 3.2 - 4ghz, not provide the same results,within the 5%?

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on March 27, 2008, 03:07:42 pm
If the 2nd core is only accountable for ~5% increase, could a P4 or Pentium D at 3.2 - 4ghz, not provide the same results,within the 5%?

No, one core of the CoreTM2 is about twice as powerful as one core on a P4, as far as mame.  IOW, you'd need a 8Ghz P4 to match a 4Ghz C2, solo or duo.

Ghz is like RPMs is to a car:  a higher max RPM engine only means a faster 0-60 if the engines are the same otherwise.  And the CoreTM2 engine has twice the horsepower and torque per RPM as a P4.


BTW, I hate intel's generic brand "CoreTM".  Especially in topics like this where one vs two core & pentium or athlon vs CoreTM are discussed.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 27, 2008, 03:24:42 pm
If the 2nd core is only accountable for ~5% increase, could a P4 or Pentium D at 3.2 - 4ghz, not provide the same results,within the 5%?

No, the Pentium 4 and Pentium D and based on the "Netburst" architecture, the Core 2 Duo is based the "Core" architecture, the core architecture does almost double the work per clock than the Netburst architecture.  Because of this a Pentuim 4 would need to be clocked at around 4.5ghz to match the preformance of a Core 2 duo at 2ghz.

The Netburst architecture behind the P4 was a bit of a failure, It was slower than the P3 architecture at same clock speed at launch, didn't become competitive until the P4c 800fsb HT version lauched with the 865 chipset, the large cache of prescott P4s was nothing more than a band aid fix to a failing CPU design. The Pentium D was a rubbish CPU up and down, from day one it was total out classed by the Athlon64 X2, The Pentium D has hot, power huggry, noisy, and expensive, all things the Athlon X2 was not, and the Athlon X2 was faster in 95% of tasks, how Intel managed to sell so many Pentium D cpus is beyond me.

The Core 2 Duo is the only CPU currently able to jump the MAME preformance gap.



Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Dmod on March 27, 2008, 04:43:08 pm
The E8400 OEM's are back in stock and I plan on ordering and overclocking a machine based on Taz's recommendations.  I don't currently have a case.  Can someone make a recommendation here on what features I should look for?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 28, 2008, 07:48:36 am
The E8400 OEM's are back in stock and I plan on ordering and overclocking a machine based on Taz's recommendations.  I don't currently have a case.  Can someone make a recommendation here on what features I should look for?


The Coolermaster Centurion 5 is a good option and can be had fairly cheap, there is a version that comes with a 460w power suplly that is passable for the kind of hardware your likely to have in a MAME box.

There are plenty of other good cases out there, anything with good front to back airflow will do, avoid cases with doors, solid face plates, or that have dozens of fans pointed in random directions.



Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: xmenxmen on March 28, 2008, 01:10:14 pm
The E8400 OEM's are back in stock and I plan on ordering and overclocking a machine based on Taz's recommendations.  I don't currently have a case.  Can someone make a recommendation here on what features I should look for?


The Coolermaster Centurion 5 is a good option and can be had fairly cheap, there is a version that comes with a 460w power suplly that is passable for the kind of hardware your likely to have in a MAME box.

There are plenty of other good cases out there, anything with good front to back airflow will do, avoid cases with doors, solid face plates, or that have dozens of fans pointed in random directions.





another choice if any available locally:  Feature:  Cheap and 500W
http://www.bestbuy.com/site/olspage.jsp?skuId=8329864&st=Dynex+-+ATX+Mid-Tower&lp=1&type=product&cp=1&id=1175388730209 (http://www.bestbuy.com/site/olspage.jsp?skuId=8329864&st=Dynex+-+ATX+Mid-Tower&lp=1&type=product&cp=1&id=1175388730209)

Decent cooling too with the 92 front and 120mm fan in the rear.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: MBaran on March 31, 2008, 02:50:09 pm
new question then  :)

Fry's has a combo deal on an E6550 and motherboard.

I have a 6600/gigabyte in my desktop computer. I was gonna throw the 6550 on my desktop and use the 6600 (they clock better)

Is a 6600 at 3.4ish going to be powerful enough for jumping the gap anyways.. or am I wasting my time overclocking it since its not at the 4ghz mark anyways and probably wont do the blitz type stuff anyways.. should I just leave the 6550 at stock speeds.

The combo is 149.99 so its a pretty solid deal and helps keep it on a slight budget.

Thx!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on April 01, 2008, 07:04:40 am
new question then  :)

Fry's has a combo deal on an E6550 and motherboard.

I have a 6600/gigabyte in my desktop computer. I was gonna throw the 6550 on my desktop and use the 6600 (they clock better)

Is a 6600 at 3.4ish going to be powerful enough for jumping the gap anyways.. or am I wasting my time overclocking it since its not at the 4ghz mark anyways and probably wont do the blitz type stuff anyways.. should I just leave the 6550 at stock speeds.

The combo is 149.99 so its a pretty solid deal and helps keep it on a slight budget.

Thx!

3.4ghz will get you in the ball park, but you will still have issues with some of the most demanding ROMs. I'd give it a try, with the right cooling and a little luck you may be able to get it to 3.6ghz, every little bit helps.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Dmod on April 01, 2008, 05:49:10 pm
3.4ghz will get you in the ball park, but you will still have issues with some of the most demanding ROMs. I'd give it a try, with the right cooling and a little luck you may be able to get it to 3.6ghz, every little bit helps.

Here's a related question...

Any idea what Intel's plans are for later this year?  Are dual core processors in 40nm expected to exceed 3GHz or is this the limit of the technology? 

I'm still trying to decide if I should jump on the E8400 or wait until later in the year.  Seems like the E8400 at 4GHz is just about working at the threshold where the late 90s driving games become playable.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on April 02, 2008, 01:48:49 am
Any idea what Intel's plans are for later this year?  Are dual core processors in 40nm expected to exceed 3GHz or is this the limit of the technology? 

I'm still trying to decide if I should jump on the E8400 or wait until later in the year.  Seems like the E8400 at 4GHz is just about working at the threshold where the late 90s driving games become playable.

There are atleast four more 45nm dual core CPUs in the pipe line from Intel, all are due out sometime in May, but since Intel isn't doing such a great job of supplying the World with the current batch of 45nm CPUs, I'd expect them to miss that date. The new models are the E7200, E7300, E8300, E8600. The E7000 series is basically a 45nm Wolfdale core version of the E4000 series, having half the cache of the E8000 series, and a lower 1066FSB.

Probably of the most interest to MAME users are the E7300 @ 2.67ghz with a 1066FSB and the E8600 @ 3.33 with a 1333FSB, what makes them interesting is they both have 10x multipliers, which means in theory you can hit 4ghz with these CPUs with only a 400mhz FSB & DDR2-800, which means you will be able to use cheap ram as it will be running at stock speeds, and no need for extreme FSB speeds and thus reduction in the amount of stress put of the motherboard chipset, so you don't have to worry about cooking it along side your CPU.

Only time will tell how well these new models will overclock, but E7300 might end up being the CPU of choice for MAME users, as it should be a lot cheaper than the E8400 and less cache equals less power use and less heat production, which means it should be a great overclocker, but we will have to wait and see.

Early previews look good though.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Dmod on April 02, 2008, 02:26:11 am
Great info. Think I might wait a bit. 

Thanks Taz.   :cheers:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: styxx on April 14, 2008, 11:34:13 pm
I there Taz, looking for some help in upgrading my MAME cabinet.
I'll upgrade to a C2D or CQuad, but I've an AGP ArcadeVGA, which is a downall as i have to stick to AGP motherboards. The one that best suites my needs is this one http://www.asrock.com/mb/cpu.asp?Model=4CoreDual-SATA2%20R2.0
From the list, which Processor would you recommend, apart form the xtrm ones ($$$ ;D$$$). The other downfall is a maximum 667 MHz DDR2 :banghead: :banghead:. How far can i go OC wise?

 :cheers:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Vash on April 15, 2008, 01:52:27 am
I'm a ways off from purchasing the computer for my cab (a month or so), but I was wondering how Soulcalibur was running with your setup.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on April 15, 2008, 07:20:38 am
I there Taz, looking for some help in upgrading my MAME cabinet.
I'll upgrade to a C2D or CQuad, but I've an AGP ArcadeVGA, which is a downall as i have to stick to AGP motherboards. The one that best suites my needs is this one http://www.asrock.com/mb/cpu.asp?Model=4CoreDual-SATA2%20R2.0
From the list, which Processor would you recommend, apart form the xtrm ones ($$$ ;D$$$). The other downfall is a maximum 667 MHz DDR2 :banghead: :banghead:. How far can i go OC wise?

 :cheers:

I'm busy moving house so the short answer is forget it, just sell the AGP ArcadeVGA I'm sure someone here will pay you a far price for it. The Asrock board is going to limit your options no end, Asrock is the last brand I'd recommend anyone use, and  the via chipset just isn't going to overclock well. Cut your losses and do it right the first time, it will save you money in the long run.

I'm a ways off from purchasing the computer for my cab (a month or so), but I was wondering how Soulcalibur was running with your setup.

Soulcalibur is not a working rom at this time, major graphics issues. but it runs at 180% in 32bit mame currently dipping to 165% when the characters are visable, should be plenty playable once emulation is complete with an overclocked core 2 duo.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Jdurg on April 15, 2008, 09:01:11 am
In addition, you get no benefit from having a QuadCore CPU in MAME.  By the time any benefit would even conceivably be possible, the speed of your CPU would be quite obsolete anyway.  I would suggest saving the money and getting a good overclockable DualCore CPU.  Besides, overclocking a DualCore CPU should be easier than a Quad.  (Fewer cores to have to rely on overclocking well).
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: lanman31337 on April 15, 2008, 10:01:47 am
Some of the ASRock boards overclock like a champ.  My old 939 board would overclock like no other, and was rock solid stable too. 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: massive88 on April 17, 2008, 09:24:44 pm
Just thought Id post my results as I just built a new Core 2 Duo computer.

I only ran a few games, in a very small sample.  And while I snagged my arguments from http://benchmark.mameworld.net/ once I had started I realized I should have used a longer sample time.  Blitz 2k for instance, never gets to the actual gameplay.  Oh well.  So take these numbers for what they are worth, at the very least, a comparative example between OS's and clock speeds.

All binaries were the official binaries.  Settings were:
mame -noautoframeskip -frameskip 0 -seconds_to_run 100 -nothrottle -nosleep -video ddraw -skip_gameinfo -effect none -nowaitvsync -noreadconfig -mt ROMNAME

I also saw about 5% increase due to multithreading across the board as mentioned earlier in this thread.

Old PC - Athlon XP 1700 - mame.exe
Killer Instinct 2 - 84.6%
Cruisin USA - 83.9%
Gauntlet Dark Legacy - 24.0%
Blitzk 2k - 25.3%
Gradius 4 - 17.9%

New PC in 32bit XP - 2.66ghz - mame.exe:
Killer Instinct 2 - 352.9%
Cruisin USA - 149.3%
Gauntlet Dark Legacy - 86.4%
Blitz 2k - 100.9%
Gradius 4 - 74.3%

New PC in 32bit XP - 2.66ghz - mamepp.exe:
Basically the same as mame.exe

New PC in 32bit Vista - 2.66ghz - mame.exe:
Basically the same as XP.

New PC in 64bit Vista - 2.66ghz - mame.exe:
Basically the same as 32bit.

New PC in 64bit Vista - 2.66ghz - vmame64.exe:
Killer Instinct 2 - 430.5%
Cruisin USA - 175.3%
Gauntlet Dark Legacy - 97.8%
Blitz 2k - 126.4%
Gradius 4 - 49.2%

Overclocked PC in 64bit Vista - 3.33ghz - vmame64.exe:
Killer Instinct 2 - 538.1%
Cruisin USA - 217.8%
Gauntlet Dark Legacy - 119.1%
Blitz 2k - 157.3%
Gradius 4 - 61.9%

Gradius is much slower in the 64 bit binary, but the other 4 games I tested saw anywhere from 5-20% speed increase, just by going 64 bit.  So my assertion if you get a core 2 duo, get a 64 bit OS, and get rockin.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Jdurg on April 18, 2008, 09:51:25 am
Nice results.  With Blitz, I wouldn't be too concerned.  The demo, if run long enough, gets into some gameplay and that does tax your system.  I would think at that speed that you'd be good to go.  I have a 2.50 Penryn Core2Duo in my laptop, and Blitz is fully playable but with sound hiccups in the middle of gameplay. 

MK4 is another good one to test on, but from what I get out of my system I'm pretty certain yours would run just fine.  (Hopefully Aaron gets the 'bug' to continue working on that driver.  It's about 75% "playable".   :cheers: )
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: massive88 on April 18, 2008, 10:05:19 am
Yeah, I just really wished to illustrate my results of going from good old XP to 64 bit vista and the 64 bit binary on a Core 2, to add my results into the "64 bit is king" arena.  That was a major jump for just changing binaries.

Now if only I can get Mamewah working under Vista...
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: styxx on April 19, 2008, 05:54:53 pm
I'm busy moving house so the short answer is forget it, just sell the AGP ArcadeVGA I'm sure someone here will pay you a far price for it. The Asrock board is going to limit your options no end, Asrock is the last brand I'd recommend anyone use, and  the via chipset just isn't going to overclock well. Cut your losses and do it right the first time, it will save you money in the long run.

I think you're right, and after some research I decided to go for this option:

Motherboard Gigabyte GA-P35C-DS3R P35 S775

Intel CORE 2 DUO E8400 3.00GHZ FSB1333 6MB

Corsair Dual Channel 2GB PC8500 DDR2 Dominator 1066

Asus Ati Radeon x600 - Modded with Soft15Khz(I love this Tool)

I' ll get the components in a week or two, afterwards I'll post some results... >:D

As I'm not an expert overclocker I don't know how far can I go, but hopefully I won't blow up the hole thing, my real concern is the fact that it will all go inside my MAME cabinet.
Looks like the back door has to go ;D

 :cheers:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: illtww on April 22, 2008, 10:44:50 pm
Anywhere to download an already compiled mame64 for the core2duo cpus?  I am running vista 64bit and would like to try out the mame64.exe but cannont locate one anywhere. 

I am running a core 2 duo (e2160) @ 3.2
1.5 gig ram
Radeon hd2600pro
Vista Services Disabled that are NOT needed

I believe I should have enough horespower to run almost any game..
I am looking at game-ex as my front end.















/
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Farb on April 27, 2008, 02:33:44 pm
I just put together a Core 2 Duo E8400 (3 Ghz) machine with a Gigabyte GA-P35-DS3L, Arcade VGA 2 and 2Gb of DDR2-667 memory.

I ran a few benchmarks with the following command-line used above:

mame -noautoframeskip -frameskip 0 -seconds_to_run 100 -nothrottle -nosleep -video ddraw -skip_gameinfo -effect none -nowaitvsync -noreadconfig -mt ROMNAME

Here are some numbers:

Cruisin' USA - 167%
Gauntlet: Dark Legacy - 101.77%
Blitz 2k - 109.66%
Blitz - 92.00%
Killer Instinct 2 - 413.02%
Gradius 4 - 82.36%

->Dan
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Jox43w on May 05, 2008, 01:17:07 pm
Wow this is the best thread relating to mame hardware ever! The benchmarking  is such a awsome idea.ok well im not worried about playing the 3d games but i want to be able to run all the neogeo titles,mortal kombat up to 3 , killerinstint 1 and 2 and also sf third strike will a e2220 2.4ghz duelcore 1mb cache run them in a 32bit build?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: massive88 on May 05, 2008, 02:40:35 pm
Wow this is the best thread relating to mame hardware ever! The benchmarking  is such a awsome idea.ok well im not worried about playing the 3d games but i want to be able to run all the neogeo titles,mortal kombat up to 3 , killerinstint 1 and 2 and also sf third strike will a e2220 2.4ghz duelcore 1mb cache run them in a 32bit build?

Without a doubt.  The most taxing game in that list is probably KI2, which I was running at around 430% with a 2.666ghz Core 2 Duo, so I would expect you should run it at 387%

To be "playable" you want to be able to hit 120% roughly, so you should be able to hit those games without question.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Jox43w on May 05, 2008, 04:08:31 pm
Sweet! After reading this thread properly start to finish im considering going for the e8400 now if i do go for it the best mobo i can afford will be the gigabyte ga-p31-ds3l my friend has this mobo and it overclocked his e6750 to 3.6ghz will it be up to the job of doing a e8400 to 4ghz. Also isit posible to save more than 1 set of settings in the bios as i dont plan on overclocking 24/7 and dont want to manuly configure it every time i want an oc.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on May 05, 2008, 05:04:44 pm
Also isit posible to save more than 1 set of settings in the bios as i dont plan on overclocking 24/7 and dont want to manuly configure it every time i want an oc.
From TheManuel on the bottom of Page 3 of the thread:

Quote
Finally, to extend the life of the processor, I set my power scheme to laptop/portable so that EIST kicks in and the CPU multiplier is knocked down to 6X form 9X while the computer is idle or doing light duty like browsing the web or playing pacman :-) but immediately goes to full throttle when more processing power is required.  As a result, my 2.7GHz is running at 1.8GHz most of the time which happens to be the stock speed.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: styxx on May 05, 2008, 06:35:28 pm
Sweet! After reading this thread properly start to finish im considering going for the e8400 now if i do go for it the best mobo i can afford will be the gigabyte ga-p31-ds3l my friend has this mobo and it overclocked his e6750 to 3.6ghz will it be up to the job of doing a e8400 to 4ghz.
As Taz mentioned earlier on this thread, the P35 chipset is one of the best out there, I think for a little more money you should get a P35 Mobo. I'll get the Gigabyte GA-EP35C-DS3R it has improved OC capabilities, and supports DDR II and DDR III  :applaud: The P35 is widely considered one of the best Chipsets to OC, at least until P45 comes out.
As for the OC capabilities of the E8400, just take a look at this snapshot i got from an OC forum, it speaks for it self...
(http://img28.picoodle.com/img/img28/4/5/5/t_e8400cpuz56m_56cb7b1.jpg) (http://www.picoodle.com/view.php?img=/4/5/5/f_e8400cpuz56m_56cb7b1.jpg&srv=img28)
5,62 Ghz... :notworthy: :notworthy:
This guy runs this E8400 at 4ghz stable with Vcore 1,29 V which is very good.
From what I've been seeing in other forums, with the right config you can run this baby's at 4,5 Ghz and UP stable on air cooling.

Speaking of right config... a major issue in getting a good OC is the stepping of the processor. The one mentioned above is  a Q750A196, Q808A476 are also great. Avoid the Q809A... ones

 :cheers:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on June 15, 2008, 07:54:14 pm
New batch of benchmarks for .125.4 on various C2D's Conroe and Wolfdale + some sad AMDs. :)
I'll be dropping in an E8400 shortly to my workforce 3.5Ghz E6400 to last me till Nehalem and will post some new benches then.

http://mameui.classicgaming.gamespy.com/Bench.htm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on June 16, 2008, 07:30:46 am
New batch of benchmarks for .125.4 on various C2D's Conroe and Wolfdale + some sad AMDs. :)
I'll be dropping in an E8400 shortly to my workforce 3.5Ghz E6400 to last me till Nehalem and will post some new benches then.

http://mameui.classicgaming.gamespy.com/Bench.htm

Yeah I  ran a few benchmarks the other day to see what the new changes to compiler made, running in Gradius4 in 64bit 125.4 looks all good  ,but 125.5 is a case of what the dev's can give they can take away.

with my normal setting and my CPU at 4ghz in vista 64bit SP1:

125.4 Gradius4            129.31%
125.5 Gradius4             74.21%  :cry:

I thought for a minute I'd got my 64bit and 32bit benchmark numbers mixed up, but no in 125.4 gradius4 take a boost in 64bit and drop in 32bit, in 125.5 64bit is back to it's old ways and 32bit is back on top. 

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on June 16, 2008, 12:07:32 pm
Aaron had left some debugging code in there in .125.5 so you'll see bad performance.. and also giant *.asm files generated in the .exe root. FYI.  Should be fixed in u6.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on July 04, 2008, 03:55:38 pm
New bench pass on .125.9 on C2D E8400 at 4.05Ghz. [445x9]

http://mameui.classicgaming.gamespy.com/Bench.htm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on July 04, 2008, 11:40:41 pm
Sweet, nice to see a wide range of drivers benchmarked.

Welcome to the 4ghz+ club, what core voltage are you running ? (my E8500 is an early Engineering Sample and runs on above average voltages, I'm waiting for the release of the E7300 and E8600 to replace it something a little less voltage hungry.)

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on July 05, 2008, 06:52:53 pm
Asus P5K-E Wifi 445*9
4G Corsair DDR2-800 XMS2 memory 5x5x5x12 @1.9V [same memory from my e6400 that went to 3.5Ghz]
Vcore 1.4V
PCI = 100
Everything else on auto.
45 at idle 67 under load.

Even bumping the NB/SB voltages I couldn't get stable at 4.2.. got into Windows but Orthos, Prime, and Mame's benches didn't pass.. could be my memory.  Might try some ddr2-1066.

Sadly the latest version of Mame w/ the debugger rolled in has impacted high end games vs .125u6, but I've been keeping Aaron and RB in the loop. :)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on July 15, 2008, 01:02:50 am
One more bench run:

Cleaned up and collected from multiple machines on .126.

http://mameui.classicgaming.gamespy.com/Bench.htm

Note: Pre-RB submitted SH-2 UDRC. 



--------------------------------------------------------------------------------
john iv
http://mameui.classicgaming.gamespy.com/ 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Paul Olson on July 15, 2008, 03:23:10 pm
I need to upgrade from my xp1800+, but I currently have a really tight budget. This ad from fry's fits in my budget. http://www.netaffilia.com/ads/electronics/frys/Intel-Core-2-Duo-Processor-E7200-ECS-GF7050VT-M-Motherboard/2008/07/11/33900

You guys are the experts on these; what do you think of this setup? I would want to use the onboard graphics with soft-15khz. Reviews on newegg say the mb has few features, but is a good overclocker.

A friend is coming to visit from San Jose this weekend, so Fry's is finally an option.

Thanks,
Paul
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on July 15, 2008, 05:29:57 pm
Yeah that's a great deal on the 7200, it's $129 at newegg right now for just the cpu.. and you can check the reviews on that page fwiw some claim to get to 4Ghz w/ it.  You'll probably need to budget for better cooling if you try that route.  That will vault you quite a ways from your 1800+!

http://www.newegg.com/Product/Product.aspx?Item=N82E16819115052&Tpk=E7200%2bWolfdale
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Ummon on July 15, 2008, 07:25:34 pm
Search the soft15 thread for Nvidia 7000 series posts. I seem to recall mixed success.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Popcorrin on July 16, 2008, 01:46:02 pm
Quote from: John IV [MameUI64
link=topic=72776.msg854893#msg854893

Sadly the latest version of Mame w/ the debugger rolled in has impacted high end games vs .125u6, but I've been keeping Aaron and RB in the loop. :)

How much has the debugger impacted performance?  Can it be disabled?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Popcorrin on July 16, 2008, 04:04:06 pm
I'm running xp64.   Does anyone know if there is a difference in performance between running xp 64 as compared to vista 64?

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on July 17, 2008, 01:37:49 am
It's about 5-9 percent hit on most games.

However on some of the intensive benched games it was as high as 15% unfortunately.  No there is no way to turn it off short of removing the code and recompiling.

You'll find better support for drivers etc in Vista64 and better performance overall w/ its intelligent caching and prefetch/superfetch these days.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: massive88 on July 17, 2008, 10:59:05 am
I'm running xp64.   Does anyone know if there is a difference in performance between running xp 64 as compared to vista 64?

In my own personal tests, I found them to be dead on the exact same.  Now thats on a small sample size to be sure, but it was enough to convince me that it did not make a difference big enough to worry about.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on July 22, 2008, 01:35:23 pm
The best CPUs for Mame just got a price cut.. FYI. Should have held out a little longer for the e8500 (31% cut!) now the same price I paid for my e8400.

http://blogs.zdnet.com/hardware/?p=2267


Here’s a rundown of the price cuts on the desktop:

Q6600 (Quad-core, 2.40GHz)
Now: $193 | Was: $224 - 14% cut
E8500 (Dual-core, 3.16GHz)
Now: $183 | Was: $266 - 31% cut
E8400 (Dual-core, 3.00GHz)
Now: $163 | Was: $183 - 11% cut
E7200 (Dual-core, 2.53GHz)
Now: $113 | Was: $133 - 15% cut 



--------------------------------------------------------------------------------
john iv
http://mameui.classicgaming.gamespy.com/ 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Blanka on July 22, 2008, 01:46:47 pm
The E8500 is the same as a E8400, only tested longer at the given speed. They both clock over equally well to around 4ghz.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on July 22, 2008, 02:02:09 pm
I have a e8500 arriving from newegg today, it will replace my e6850
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: lettuce on July 22, 2008, 07:23:06 pm
Got a E7200 back the other week for my new cab, OC to 3.8ghz  ;D, thats about a 52% increase in performace!  :cheers:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: retrometro on August 02, 2008, 12:03:38 am
My head is about to explode....  I've just read every message from beginning to end.... 

With that said/written, I would REALLY like the opinion of all of you guys (and taz the mame oc champ himself) on a used computer I may be buying.  The cost of the sum of the parts is greater than what he's asking for.  So even though this isn't the optimum setup with an E8500, 64bit vista, nice memory, cooling, etc. 

What sort of overclocking do you guys expect that I'd be able to get off of this?  ...and how well do you think this will run v.126 out of the gate?  Finally, how much of an improvement (rough %) do you think this will be over my current Pentium4 2.53ghz?  tons appreciated!

- Gigabyte GA-G31M-S2L LGA 775 mATX Motherboard
- Intel Core 2 Duo e6300 1.86GHz Processor
- Crucial Ballstix 2x1GB PC-6400 800MHz DDR2 RAM in Dual Channel
- Sapphire Radeon X700 Pro 256MB PCI-E Video Card
- Antec NSK4480 Mid Tower Case w/380W Antec Earthwatts PSU
- Cooler Master Rifle Bearing CPU Fan
- Antec 120MM TriCool Rear Case Exhast Fan

thanks again!

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Paul Olson on August 02, 2008, 05:40:11 am
lettuce - what board and heatsink are you using with your e7200? I have a cheap ecs board and stock fan, and I can't do much with it.

Is there a modestly priced board that would be good for overclocking? I think I remember a 35 board mentioned here, but has anyone tried a 45? The e7200 would be nice to oc, but my e8400 is the one that I really want to push. It will be the one going in the cab. I have the zalman 9700 on that one, but the board I have is about useless for ocing. If anyone here has the zalman -  mine is not very tight on the cpu. It shifts a little once in a while. I don't see a way to tighten it any more.

So far, Vista 64 is a pita. I ended up having to use my good wireless n card for the cab computer because it is the only one I have with 64bit drivers. Does anyone have a suggestion for a temp monitor that runs in Vista 64?

I will be working on this as much as I can, but I am kinda sidetracked at the moment. I just brought home a dedicated donkey kong, and I am working on the cap kit. The monitor wouldn't display full width which makes it hard to play. If I don't screw it up, I should have it done this afternoon.

So many projects, so little time.  :dunno
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: lettuce on August 02, 2008, 06:21:19 am
lettuce - what board and heatsink are you using with your e7200? I have a cheap ecs board and stock fan, and I can't do much with it.

Gigabyte S775 Intel P35 ATX Audio Lan DDRII FSB133
Intel Core 2 Duo E7200 2.53GHz
Xigmatek HDT-S1283 Heatsink
Corsair Memory TWIN2X2048-6400C4 2x1GB 240-Pin DIMM XMS2-6400 CL4
Samsung Spinpoint 500GB 7200RPM 16MB SATA300
Nvidia Geforce 7600GT  512MB  PCI-E
OCZ Technology 500W STEALTHXSTREAM POWER SUPPLY
LiteOn DVD-ROM 16x48x Internal SATA Black
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on August 03, 2008, 05:21:54 am
My head is about to explode....  I've just read every message from beginning to end.... 

With that said/written, I would REALLY like the opinion of all of you guys (and taz the mame oc champ himself) on a used computer I may be buying.  The cost of the sum of the parts is greater than what he's asking for.  So even though this isn't the optimum setup with an E8500, 64bit vista, nice memory, cooling, etc. 

What sort of overclocking do you guys expect that I'd be able to get off of this?  ...and how well do you think this will run v.126 out of the gate?  Finally, how much of an improvement (rough %) do you think this will be over my current Pentium4 2.53ghz?  tons appreciated!

- Gigabyte GA-G31M-S2L LGA 775 mATX Motherboard
- Intel Core 2 Duo e6300 1.86GHz Processor
- Crucial Ballstix 2x1GB PC-6400 800MHz DDR2 RAM in Dual Channel
- Sapphire Radeon X700 Pro 256MB PCI-E Video Card
- Antec NSK4480 Mid Tower Case w/380W Antec Earthwatts PSU
- Cooler Master Rifle Bearing CPU Fan
- Antec 120MM TriCool Rear Case Exhast Fan

thanks again!



That system will give you about double the preformance of your current P4 in MAME, but it will not overclock well. the G31 & P31 chipsets from intel are cut down rubbish, and the E6300 being the slowest of the E6#00 series core 2 duos doesn't overclock that well either, your better off with a E4700 than a E6300 if your overclocking.

Depending how much you would have to pay for the system, you maybe better off getting E7200 and a P45 board with a cheap graphics card.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: retrometro on August 03, 2008, 10:03:50 am
Thanks tons taz.  I just had him run your mame arguments on the 32bit build of v0.126 on starblade and stock he was getting 67%.  When overclocked to 2.45ghz, he had it at 90%.  My pentium 4 build gets 37%.  I expect that after vista 64bit is installed to get starblade into 100% or higher.  i love that game!

Oh yeah, he's selling this setup for $300.  I priced the pieces separately and the cpu is around $160, board is $60, memory is 100 (or less).  The bonus of getting a used x700 which was a great card just a few years ago is nice.


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: retrometro on August 03, 2008, 08:23:39 pm
Can someone post new percentages for v0.126 32bit and 64bit for the games you guys have been doing (mainly taz)?  thanks!

I understand that v0.126 may have taken a performance hit recently b/c of debugging.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on August 08, 2008, 08:32:13 am
Can someone post new percentages for v0.126 32bit and 64bit for the games you guys have been doing (mainly taz)?  thanks!

I understand that v0.126 may have taken a performance hit recently b/c of debugging.



ask and you will receive: (I included Direct3D preformance number aswell since MAME defaultly output via D3D)

Core 2 Duo E8500 (engineering sample) @ 4.4ghz Vista Ultimate 64bit SP1, MAMEUI 64bit v1.26u3

DDRaw command line:
mameui64.exe -noautoframeskip -frameskip 0 -seconds_to_run 240 -nothrottle -nosleep -video ddraw -skip_gameinfo -effect none -nowaitvsync -noreadconfig -mt [Rom Name]

D3D command line:
mameui64.exe -noautoframeskip -frameskip 0 -seconds_to_run 240 -nothrottle -nosleep -skip_gameinfo -effect none -nowaitvsync -noreadconfig -mt [Rom Name]

ROM      DDraw      D3D

1942      4751.87%   4272.79%
a51site4   Broken      Broken
airco22b   138.03%      138.43%
alpinerd   84.27%       81.68%
biofreak   142.76%      -----
blitz      166.30%      162.36%
blitz2k      157.05%      151.99%
blitz99      149.92%      145.89%
calspeed   215.25%      214.07%
carnevil   270.10%      266.88%
crusnusa   281.54%      270.45%
crusnwld   242.90%      239.12%
cybrcomm   130.48%      129.15%
cybrcycc   209.31%      195.07%
cyvern      810.06%    796.23%
daytona      217.55%      215.76%
gauntdl      132.71%      132.07%
gauntleg   157.77%      148.20%
gnbarich   3233.50%   3049.22%
gradius4   130.79%      127.51%
harddriv   415.63%      414.71%
hyprdriv   168.19%      164.18%
kinst2      678.36%      691.01%
mace      253.75%      250.10%
mk4      175.31%      172.28%
offroadc   333.61%      239.70%
propcycl   140.12%    133.39%
radikalb   168.95%      163.95%
raveracw   114.09%      111.08%
ridgerac   152.75%      145.75%
roadblst   1300.38%   1285.10%
rvschool   232.96%      225.76%
scud      Broken      Broken
sfrush      192.45%      173.70%
sidebs2      165.08%      162.68%
soulclbr   241.15%    239.70%
speedup      168.21%      163.44%
starblad   154.76%      152.11%
stunrun      621.32%      618.85%
surfplnt   156.40%    150.67%
tekken2      339.65%      336.21%
tekken3      199.57%      191.97%
tenthdeg   85.22%      84.36%
timecris   Broken      Broken
vfkids      207.16%      198.32%
wargods      389.88%      372.71%
wg3dh      374.09%      350.48%
wrally      1818.01%   1817.51%
xevi3dg      364.08%      358.75%


I see Aaron and the Dev team has been working hard lately to get Laser disc support intergated in MAME, Like I wasn't running out of Hard Disk space as it was  ;D
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: retrometro on August 08, 2008, 06:55:17 pm
Taz, thanks for still following up with this thread.  I've just blown a week and am pissed and tired...  it's very nice to see some baseline run %'s from mame v0.126!

I'm going to post some numbers and my dilemma shortly but I somehow thought that just going 64bit would give me massively improved numbers... but argh.  I'm taking a HUGE hit running XP x64 compared to Vista x64...

Have you or anyone else found that XP x64 performs significantly slower than Vista x64?  Details coming soon plus why i'm not just running Vista x64.


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: retrometro on August 08, 2008, 07:42:32 pm
Hey everyone.  First, here are some percentages for 6 games of varying run speeds.  My preference is if you guys can help me figure out what's wrong with my configuration or confirm what I'm experiencing is normal (hopefully not).

mame-v126.exe -noautoframeskip -frameskip 0 -seconds_to_run 100 -nothrottle -nosleep -video ddraw -skip_gameinfo -effect none -nowaitvsync -noreadconfig -mt

  --------------------------------------------------------------------
  CPU ------------------ Pentium4    E6300    E6300    E6300    E6300
  Clockspeed -----------     2.53     2.45     2.45     2.45     2.45
  OS Used --------------     XP32     XP32  Vista64     XP64     XP64
  MAME executable ------    32bit    32bit    64bit    32bit    64bit
  --------------------------------------------------------------------
  Killer Instinct 2    -   143.2%   312.7%   365.7%   240.6%   276.7%
  Cruisin USA          -    55.4%   131.9%   139.8%    96.6%   108.2%
  Gauntlet Legends     -    30.1%    92.7%   107.6%    72.1%    82.8%
  Blitz 2k             -    27.9%    89.0%   101.9%    64.1%    72.8%
  Gradius 4            -    19.2%    66.1%    75.4%    49.4%    58.7%
  Starblade            -    37.3%    89.3%    83.6%    68.8%    64.2%
  --------------------------------------------------------------------

After reading this entire thread (awesome but long), I figured it may not cost me so much to upgrade.  I recently bought a used system on craigslist for $300 to stretch out performance on some mame games as well as other emulators. 

My disappointment right now isn't so much that the system isn't performing as well as 4ghz and up systems mentioned in this thread but so much that there are apparently some trade off's that I hope I won't have to make (this is where you come in!)

My P4 at 2.53ghz was paired with an old AGP GeForce4 Ti.  You can see the performance above.  It ran nearly all of the "regular" mame games fine as you can guess but anything that required a little muscle, it was barely ok to poor.

The E6300 normally at 1.8ghz has been successfully overclocked to 2.45ghz.  Although I didn't record the results above, it basically runs proportionally faster by the clock speed percentage.  It is paired with an old PCI-E ATI x700 Pro and the system runs PC-6400 corsairs with blinky lights.

Staying on Windows XP 32bit there is a about a 2.5x o 3x speed improvement between the old and new pc.  Then once I go to to Vista x64 and run a 64bit version of mame, I get another 10% from that.  If everything worked great from here, my post may be about tweaking or planning a next CPU / motherboard purchase.

But the problem right now with Vista x64 is that SailorSat's fantastic Soft15Khz isn't working with Vista x64.... argh!!!  :banghead:  I've tried the latest powerstrip and haven't had any success with going below 640x480.  I've read the faq but am welcomed to suggestions.  The last alternative is to buy an ArcadeVGA v2 PCI-E and hope it also works with Vista x64.  Even if it does, other emulators will suffer since I think the x700 pro is a superior card to the ATI 9250 the ArcadeVGA v2 is based on.

With XP x64 everything works but I get the horrible numbers you see above for both 32bit and 64bit compiles of MAME.  Arghhh!!!!    :cry:

My hope is that either SailorSat fixes Vista x64 issues (or tell me how I've got it misconfigured) or one of you brainy forum readers can help me out with my potentially screwed up XP x64 box.  Yes, the latest ATI drivers and patches, etc have been installed.  Anti-Virus off, etc.  But please suggest more things to look at!

I ran these tests with 100 seconds but can do 240 as some of the more recent posts have been but it's the relative percentages to each other that I'm concerned about mostly.  Thanks everyone in advance....  you're my only hope.


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: divemaster127 on August 08, 2008, 08:14:43 pm
the arcadevga works perfect with vista 64 i am running it
dm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: retrometro on August 09, 2008, 01:29:00 pm
Hey everyone.  First, here are some percentages for 6 games of varying run speeds.  My preference is if you guys can help me figure out what's wrong with my configuration or confirm what I'm experiencing is normal (hopefully not).

mame-v126.exe -noautoframeskip -frameskip 0 -seconds_to_run 100 -nothrottle -nosleep -video ddraw -skip_gameinfo -effect none -nowaitvsync -noreadconfig -mt

  --------------------------------------------------------------------
  CPU ------------------ Pentium4    E6300    E6300    E6300    E6300
  Clockspeed -----------     2.53     2.45     2.45     2.45     2.45
  OS Used --------------     XP32     XP32  Vista64     XP64     XP64
  MAME executable ------    32bit    32bit    64bit    32bit    64bit
  --------------------------------------------------------------------
  Killer Instinct 2    -   143.2%   312.7%   365.7%   240.6%   276.7%
  Cruisin USA          -    55.4%   131.9%   139.8%    96.6%   108.2%
  Gauntlet Legends     -    30.1%    92.7%   107.6%    72.1%    82.8%
  Blitz 2k             -    27.9%    89.0%   101.9%    64.1%    72.8%
  Gradius 4            -    19.2%    66.1%    75.4%    49.4%    58.7%
  Starblade            -    37.3%    89.3%    83.6%    68.8%    64.2%
  --------------------------------------------------------------------


...bunch of problems deleted...

I ran these tests with 100 seconds but can do 240 as some of the more recent posts have been but it's the relative percentages to each other that I'm concerned about mostly.  Thanks everyone in advance....  you're my only hope.


 :laugh2:

Okay it turns out after patching or tweaking some BIOS settings, the CPU defaulted back to its 1.86ghz.  Put memory speed and FSB back to the way it was and bam.  I guess at this rate, I won't need Vista x64 since new tests show XP x64 running 64bit mame is the same speed since i turn off just about every feature and service I can on Vista anyway.

Even MALA and xvid seem to play together better now.  Can't wait to customize hyperspin tool. 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: pinballwizard79 on September 05, 2008, 01:13:41 am
Wow, 64bit 4.0ghz overclocked with Cruisin World @ 249.66% a full year ago!

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: kelemvor on September 05, 2008, 08:56:03 am
So wait, I could get better performance if I upgraded my Pentium 4 2.4Ghz machine?  :)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: retrometro on September 06, 2008, 12:34:53 am

I understand that v0.126 may have taken a performance hit recently b/c of debugging.
ask and you will receive: (I included Direct3D preformance number aswell since MAME defaultly output via D3D)

Core 2 Duo E8500 (engineering sample) @ 4.4ghz Vista Ultimate 64bit SP1, MAMEUI 64bit v1.26u3

DDRaw command line:
mameui64.exe -noautoframeskip -frameskip 0 -seconds_to_run 240 -nothrottle -nosleep -video ddraw -skip_gameinfo -effect none -nowaitvsync -noreadconfig -mt [Rom Name]


Taz, your numbers helped me out a lot to decided whether or not to upgrade the cab's PC.  Here are my numbers using your command line parameters from the $300 used computer I bought last month.  The pc's got a cheap mobo with an old ATI X700 pci-e card.

If others could add their % to these specific games that'll be useful to someone trying to find an upgrade path within their budget and not overspend on the quad core cpu's for mame.  I'd be interested in seeing some high numbers for AMD processors too.

Just like you've been writing in this thread, mame certainly seems to follow the proportional speed increases by the clockspeed.  Although looking at the numbers below, some of your games seem to go substantially faster than the roughly 75% speed difference between our CPUs.  Take a look at gnbarich for example.  Why do you think that is?


             C2D E8500  C2D E6300  C2D E6300
               4.4 ghz    2.5 ghz    2.5 ghz
           64bit 126u3  64bit 126  32bit 126
---------------------------------------------
1942          4751.87%   2611.04%   2697.46%
a51site4        Broken    118.01%     94.97%
airco22b       138.03%     80.26%     59.87%
alpinerd        84.27%     45.63%     30.05%
biofreak       142.76%     Broken     Broken
blitz          166.30%     92.63%     72.30%
blitz2k        157.05%     86.22%     69.56%
blitz99        149.92%     83.82%     66.28%
calspeed       215.25%     Broken     Broken
carnevil       270.10%    142.49%    111.00%
crusnusa       281.54%    149.22%    134.72%
crusnwld       242.90%    246.68%    245.60%
cybrcomm       130.48%     74.40%     54.00%
cybrcycc       209.31%    114.02%     90.30%
cyvern         810.06%    316.23%    294.12%
daytona        217.55%    328.96%    322.74%
gauntdl        132.71%     74.15%     60.59%
gauntleg       157.77%    100.11%    101.14%
gnbarich      3233.50%    766.85%    768.81%
gradius4       130.79%     74.44%     61.87%
harddriv       415.63%    237.19%    191.60%
hyprdriv       168.19%     94.87%     76.06%
kinst2         678.36%    384.33%    331.82%
mace           253.75%    138.52%    110.65%
mk4            175.31%     96.38%     89.31%
offroadc       333.61%    185.25%    168.36%
propcycl       140.12%     74.61%     43.37%
radikalb       168.95%     91.01%     78.45%
raveracw       114.09%     65.81%     49.05%
ridgerac       152.75%     81.37%     61.77%
roadblst      1300.38%    674.58%    534.92%
rvschool       232.96%    122.24%    121.11%
sfrush         192.45%     Broken     Broken
sidebs2        165.08%     91.45%    101.54%
soulclbr       241.15%    131.36%    139.21%
speedup        168.21%     91.21%     81.30%
starblad       154.76%     81.37%     87.93%
stunrun        621.32%    335.90%    280.72%
surfplnt       156.40%     84.91%     73.14%
tekken2        339.65%    182.04%    179.76%
tekken3        199.57%    112.28%    106.16%
tenthdeg        85.22%     48.73%     36.48%
vfkids         207.16%     76.01%     75.16%
wargods        389.88%    220.23%    199.09%
wg3dh          374.09%    210.67%    176.18%
wrally        1818.01%    899.52%    775.34%
xevi3dg        364.08%    192.35%    165.58%
---------------------------------------------


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on September 06, 2008, 09:02:27 pm
Perhaps you're not using a version of Mame that has the SH-2 DRC in it.

http://mameui.classicgaming.gamespy.com/Bench.htm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: retrometro on September 06, 2008, 09:57:29 pm
Perhaps you're not using a version of Mame that has the SH-2 DRC in it.

http://mameui.classicgaming.gamespy.com/Bench.htm

Holy smokes there's a big difference between 126 and 126u1.  Downloaded 127 64bit and some of these 3D games had a major improvement.  Now to recompile again with all the necessary patches.  thanks for pointing this out John.


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: retrometro on September 07, 2008, 02:11:37 am
It seems that as usual as the version of mame goes up so down goes the general performance of some games.  Discounting performance difference within +/- 5% as some accepted deviation, a lot of these games took a hit going from 126 to 127. 

As John pointed out from the cpu changes since 126u1, games that use that CPU like Virtual Fighter Kids got a substantial speed boost.



-----------------------------------------------------------------------------------
Rom          C2D E6300  C2D E8500  C2D E6300  C2D E6300      % diff  Faster
               2.5 ghz    4.4 ghz    2.5 ghz    2.5 ghz   of v0.126  version for
             32bit-126  64bit-126  64bit-126  64bit-127  over v0.12  this rom
-----------------------------------------------------------------------------------
1942          2697.46%   4751.87%   2611.04%   2707.59%         -4%   ---
a51site4        94.97%     Broken    118.01%    932.14%       -690%   0.127  <-----
airco22b        59.87%    138.03%     80.26%     77.82%          3%   ---
alpinerd        30.05%     84.27%     45.63%     45.17%          1%   ---
biofreak        Broken    142.76%     Broken     Broken         ---   ---
blitz           72.30%    166.30%     92.63%     83.68%         10%   0.126
blitz2k         69.56%    157.05%     86.22%     79.57%          8%   0.126
blitz99         66.28%    149.92%     83.82%     76.53%          9%   0.126
calspeed        Broken    215.25%     Broken    225.08%         ---   ---
carnevil       111.00%    270.10%    142.49%    141.59%          1%   ---
crusnusa       134.72%    281.54%    149.22%    142.24%          5%   ---
crusnwld       245.60%    242.90%    246.68%    244.91%          1%   ---
cybrcomm        54.00%    130.48%     74.40%     71.41%          4%   ---
cybrcycc        90.30%    209.31%    114.02%    103.44%          9%   0.126
cyvern         294.12%    810.06%    316.23%    347.24%        -10%   0.127  <-----
daytona        322.74%    217.55%    328.96%    327.29%          1%   ---
gauntdl         60.59%    132.71%     74.15%     73.42%          1%   ---
gauntleg       101.14%    157.77%    100.11%     98.54%          2%   ---
gnbarich       768.81%   3233.50%    766.85%   1648.59%       -115%   0.127  <-----
gradius4        61.87%    130.79%     74.44%     71.97%          3%   ---
harddriv       191.60%    415.63%    237.19%    231.60%          2%   ---
hyprdriv        76.06%    168.19%     94.87%     89.12%          6%   0.126
kinst2         331.82%    678.36%    384.33%    378.22%          2%   ---
mace           110.65%    253.75%    138.52%    127.21%          8%   0.126
mk4             89.31%    175.31%     96.38%     93.71%          3%   ---
offroadc       168.36%    333.61%    185.25%    181.99%          2%   ---
propcycl        43.37%    140.12%     74.61%     71.16%          5%   ---
radikalb        78.45%    168.95%     91.01%     73.73%         19%   0.126
raveracw        49.05%    114.09%     65.81%     60.67%          8%   0.126
ridgerac        61.77%    152.75%     81.37%     74.40%          9%   0.126
roadblst       534.92%   1300.38%    674.58%    680.38%         -1%   ---
rvschool       121.11%    232.96%    122.24%    124.67%         -2%   ---
sfrush          Broken    192.45%     Broken     Broken         ---   ---
sidebs2        101.54%    165.08%     91.45%     84.84%          7%   0.126
soulclbr       139.21%    241.15%    131.36%    134.15%         -2%   ---
speedup         81.30%    168.21%     91.21%     79.86%         12%   0.126
starblad        87.93%    154.76%     81.37%     82.49%         -1%   ---
stunrun        280.72%    621.32%    335.90%    333.14%          1%   ---
surfplnt        73.14%    156.40%     84.91%     73.12%         14%   0.126
tekken2        179.76%    339.65%    182.04%    181.83%          0%   ---
tekken3        106.16%    199.57%    112.28%    110.65%          1%   ---
tenthdeg        36.48%     85.22%     48.73%     46.50%          5%   ---
vfkids          75.16%    207.16%     76.01%    114.51%        -51%   0.127  <-----
wargods        199.09%    389.88%    220.23%    193.78%         12%   0.126
wg3dh          176.18%    374.09%    210.67%    185.35%         12%   0.126
wrally         775.34%   1818.01%    899.52%    911.01%         -1%   ---
xevi3dg        165.58%    364.08%    192.35%    194.21%         -1%   ---
-----------------------------------------------------------------------------------

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on October 01, 2008, 07:04:27 pm
Wow, my MAME dreams have pretty much come true. I just upgraded from a 3.4GHz P4 to an E8500 (E0 stepping) overclocked to 4Ghz (at the moment, im gonna try to push it farther soon). My favorite arcade racing game of all time San Francisco Rush, is running pretty much 100% speed with Mame .127 64-bit (I never thought I'd live to see this day). The only problem I have is that the sound is 1 or 2 seconds behind the video, when I smash into a wall I dont hear the sound for about 1 to 2 seconds after, even though the sound and the video are running at 100%. How can I fix this?

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on October 01, 2008, 09:04:47 pm
You probably need to drive more carefully  :laugh2:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on October 11, 2008, 04:01:14 pm
I now have my E8500 running at 4.5Ghz stable, and the sound in SFRUSH is still lagging about 2 seconds behind the video even though the game runs 100% pretty much all of the time. I downloaded NFL blitz because I know it uses the seattle hardware too, and the sound is not lagging behind like it is with RUSH. Fraps says NFL Blitz is running at 57fps, and SFRUSH is only running at 30fps, I even manually set it to 60hz and it still dead locked at 30fps.

Is it possible that maybe this game isnt emulated correctly? Or maybe my ROM is outdated, its been sitting on my hard drive for 5 years probably.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on October 11, 2008, 05:37:29 pm
Seriously, try messing around with the sound buffer parameter to see if it helps at all.
Is this the only game where you are experiencing this?
If you have other games that use the same MAME driver, try one of those as well to see if you can narrow it down from MAME setup to driver to game.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: maniac e on October 15, 2008, 06:04:45 pm
So I finally got around to try and setup MAME.
But have yet to put together a PC for it.
I have some older attributes laying around what I am planning to use:
AMD X2 4800+
Nvidia 7900GT
2gig ram
250gig harddisk

I just wanted to know what can I expect from this setup, I really want to make it work with this processor. Maybe you guys can give me some help or better suggestions.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: FrizzleFried on October 15, 2008, 06:25:18 pm
So I finally got around to try and setup MAME.
But have yet to put together a PC for it.
I have some older attributes laying around what I am planning to use:
AMD X2 4800+
Nvidia 7900GT
2gig ram
250gig harddisk

I just wanted to know what can I expect from this setup, I really want to make it work with this processor. Maybe you guys can give me some help or better suggestions.


It depends on what you want to run.  There is a huge space between the power necessary to run old-school 2D games and the power necessary to run old-school 3D games.

Classics like Ms. Pac Man, Galaga, etc can be run on slower computers without issue.  I have am XP1800+ in one of my cabs and it runs 99% of the classics without issue.

Fighters/Shooters require a little more power than classics.  That same XP1800+ scoots along fine on the vast majority of fighters and shooters though some games DO push it.  CPS3 fighters,  for example,  and some of the newer (as in 2000 or so) shooters that use pseudo-3d techniques, etc will slow the system down.  I'd say you'd be safe with just about any AMD64 CPU or P4 3ghz or better.

Just about anything 3D requires a CORE2DUO processor.  You're not going to be happy with ANYTHING AMD produces,  period.   If you want to play Blitz, the racers, 3d fighters, etc... you're looking at a CORE2DUO.

So what you have there is a system that will play all non-3d games really really nicely,  but will handle 3d games like crap.  It sucks,  I know...I am right there with you.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: maniac e on October 15, 2008, 06:34:36 pm
Well it's going to be my first setup for it so should be good with the classic 2D things. Mostly doing it for the King of Fighters serie.
Havent really gotten the change to work out on the 3D games :(

And did hear about windows 32 bit en 64bit differences but does it really matter?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: FrizzleFried on October 15, 2008, 06:45:44 pm
Well it's going to be my first setup for it so should be good with the classic 2D things. Mostly doing it for the King of Fighters serie.
Havent really gotten the change to work out on the 3D games :(

And did hear about windows 32 bit en 64bit differences but does it really matter?

For 2D fighters and such your rig will excel.  It will eat the King of Fighter series alive.

With the old school games and your processor I doubt you'll experience enough of an increase in speed to warrant going from 32bit to 64bit.  Core2Duo...again,  another story,  well worth considering.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on October 15, 2008, 07:07:56 pm
So I finally got around to try and setup MAME.
But have yet to put together a PC for it.
I have some older attributes laying around what I am planning to use:
AMD X2 4800+
Nvidia 7900GT
2gig ram
250gig harddisk

For a semi-comparable rig benchmarked, check out mameUI's benchmark page (http://mameui.classicgaming.gamespy.com/Bench.htm).  He includes a AMD X2 5000+, but the benchs are 64bit os & mame, and no video & sound, you're system will be a little slower on the same games.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on October 15, 2008, 07:41:54 pm
Quote
Just about anything 3D requires a CORE2DUO processor.  You're not going to be happy with ANYTHING AMD produces,  period.   If you want to play Blitz, the racers, 3d fighters, etc... you're looking at a CORE2DUO.

... and not just any Core2Duo.  For the most demanding games (Seattle driver, etc.) you need your C2D running over 3GHz so it's either one of the very expensive ones a cheaper one overclocked to those speeds.
I would say it's not worth it if you don't care for 3D games (I don't personally).
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 16, 2008, 02:15:47 am
It all depends on what ROMS you want to run, MAME has a huge preformance chasm between the older 2D games and 3D/CHD games, Pentium 4s run up to the chasm full in head first, the Pentium Ds burst into flames before they even get to the edge, Celerons die on the start line of the run up, Athlon 64s leap over the edge but don't even make it to half way, Athlon X2s make to about half way before dropping like a stone. Almost any Core2duo at stock clock speed will get you to the other side of the performance chasm, but it may just be holding on to the other side with it's finger tips, an overclocked Core2duo at 4ghz on the other hand will easily clear the gap leaving only a half dozen stones to trip over in the form of ROMS still running at less that 100% playable. (Ok that enough of the metaphor)

If you want to be able to run all but a handful of the ROMs MAME you need a Core 2 Duo overclocked around 4ghz, there is no other solution currently available or likely to be available in the near future that will do this. In regards to Windows 64bit vs 32bit, an Athlon64/AthlonX2/Core2duo will benefit from running 64bit, but you only really see an ingame difference in those ROMs that only the Core 2 Duo can run.

While you can't build a Core 2 Duo system as cheap as a Athlon system, you do get a hell of a lot more preformance out of a Core 2 Duo setup, and you don't have to spend the earth to get it. Here is a quick run down on what I would use if I wanted to build a complete MAME system from scatch on a budget:

- Intel Core 2 Duo E7300 (http://www.newegg.com/Product/Product.aspx?Item=N82E16819115132) - 10x stock multiplier makes for an easy overclock to 4ghz without the need for expensive RAM.
$139.99

- Sunbeam(tuniq) Core Contact Freezer (http://www.newegg.com/Product/Product.aspx?Item=N82E16835207004) - great cooling which is a must for overclocking and without a huge price.
$34.99 (($24.99 after $10.00 Mail-In rebate)

- Gigabyte GA-EP45-DS3L (http://www.newegg.com/Product/Product.aspx?Item=N82E16813128345) - Stable & proven overclocking plateform at a good price.
$101.99 ($86.99 after $15.00 Mail-In rebate) or $71.26 (for open box item)
 (http://www.newegg.com/Product/Product.aspx?Item=N82E16813128345R)
- Corsair 2x1GB DD2-800 (http://www.newegg.com/Product/Product.aspx?Item=N82E16820145034) - Stable reliable brand at a good price, at 400mhz (1600 FSB) you will still be able to run 1:1 timing and the ram will be a stock speed.
$49.99 ($19.99 after $30.00 Mail-In rebate)

Core components SUB TOTAL : $256.23 (presuming you claim all rebates and get the un-boxed motherboard)

- Western Digital WD3200AAJS HDD (http://www.newegg.com/Product/Product.aspx?Item=N82E16822136098) - 320GB, 7200rpm, 3.5", should be large enough and fast enough even to handle all the future Laser Disc games.
$57.99

- GIGABYTE Radeon HD2400-XT (http://www.newegg.com/Product/Product.aspx?Item=N82E16814125076) - 256MB happily run in Vista and should be more than enough for MAME.
$36.99 ($16.99 after $20.00 Mail-In rebate)

- COOLER MASTER Centurion 5 (http://www.newegg.com/Product/Product.aspx?Item=N82E16811119153) - stock 430watt included is good enough for most MAME user needs.
$69.99

Basic System SUB TOTAL : $401.20 (presuming again you claim all mail in rebates and get the open box motherboard)

- Lite-ON 16X DVD-ROM (http://www.newegg.com/Product/Product.aspx?Item=N82E16827106261) - lets you install OS and load system with ROM set.
$17.99

- Vista Home Basic 64bit OEM (http://www.newegg.com/Product/Product.aspx?Item=N82E16832116483) - don't need the extra as long as it's 64bit.
$89.99

Complete System TOTAL : $509.18  (Just make sure you claim all the rebates, otherwise it's a hair under $600)





Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: maniac e on October 16, 2008, 06:10:51 am
Well guys thanks for the info :)
I'll probably go with 2 systems if i read it this way, one out of my old stuff and later on getting new stuff for the second one.
Play around with the old stuff so I know what to do for the new one.

Again thanks.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Flake on October 16, 2008, 10:06:50 am
Just for the record I am able to play Cruisin World on my system (Pentium D 2.8 GHZ, 3.25 GB Ram, 250 GB HD, NVidia 8400GS).  It doesnt run 100% but is definitely playable.  I was under the impression that my processor wouldnt come close to handling that game but suprisingly it does.  The only game that I cant play but wish I could is Tekken 3 (well besides Blitz games).  It also plays NBA Jam 100% as well.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TheManuel on October 16, 2008, 03:05:08 pm
Taz and retrometro:
How much RAM are you using in your setups (at least when you ran the benchmarks you provided in this post)?
I'm trying to get a feel for what expect with:
1GB
2GB
4GB
Particularly with Vista 64-bit.

Thanks.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: FrizzleFried on October 16, 2008, 04:12:58 pm
Are E7300's hitting 4GHZ easily these days?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: FrizzleFried on October 16, 2008, 05:36:10 pm
Welp,  we'll find out...cuz I just bought everything you recommended up there...

The plan is to upgrade the horizontal MAME with this computer,  then take the AMD64 3200+ currently in the MAME and use it for the dedicated driver I will be working on shortly...

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 16, 2008, 08:09:49 pm
Are E7300's hitting 4GHZ easily these days?

Welp,  we'll find out...cuz I just bought everything you recommended up there...

The plan is to upgrade the horizontal MAME with this computer,  then take the AMD64 3200+ currently in the MAME and use it for the dedicated driver I will be working on shortly...

Ok so 'easily' should be taken as a realive term, but yes you should with a little luck and some tweaking be able to get it stable at 4ghz (there is always a little luck involved with overclocking).

I haven't overclocked an E7300 myself as yet, but I've seen enough examples of it being done to say you shouldn't have to many issues achieving it, some of the more extreme examples are 4.1ghz with only the stock cooler, 4.4ghz with air cooling and more than a litte voltage, but there are plenty of people hitting the magic 4ghz mark without any extreme measures.

Remember a year ago about the time I started this thread, people were getting the E6750 (stock 2.66ghz) to 4ghz (most got them to 3.7-3.9ghz) but it shows that a core2duo with a stock 2.66ghz core speed like the E7300 can reach those speeds, add to that the manufacture and stepping improvement between then and now, and you'll probably have less problems hitting 4ghz than I did with my original E6850.

Anyway good luck and let us know how you get on.




Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on October 18, 2008, 06:51:52 am
This was in the "Whats New" text document for MAME .0128

Source Changes
--------------
Added new tool ldresample to assist in resynchronizing audio tracks in
a CHD with frames. Currently still WIP but useful if you know what
you're doing. [Aaron Giles]


Does anyone know how to use the new ldresample tool, or where I could find directions to?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 18, 2008, 08:03:33 am
This was in the "Whats New" text document for MAME .0128

Source Changes
--------------
Added new tool ldresample to assist in resynchronizing audio tracks in
a CHD with frames. Currently still WIP but useful if you know what
you're doing. [Aaron Giles]


Does anyone know how to use the new ldresample tool, or where I could find directions to?

Sorry no, I make a point of reading the 'whats new' file every week, but I'm almost a full developement cycle out of date currently on my roms and version of MAME I'm running, don't have any of the laser disc CHD's as yet, figured I'd wait until the dev team stopped playing with them, then get them.

If this is related to your problem in sfrush, I don't think this tool will help you any, I think you'll find it only relates to Laser Disc CHDs and getting the audio tracks in sync with the video frames.   

You might have more luck over at MAME Chat Forum (http://www.mameworld.info/ubbthreads/postlist.php?Cat=&Board=mamechat) most of dev team hang out there and somebody can probably here you out.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on October 18, 2008, 11:16:43 pm
Well I actually found a way to get the sound synced in sfrush, its kind of a flukey way. Thanks for responding though, I know this isn't the place to talk about this. 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on October 20, 2008, 03:01:27 am
For anyone who cares...I recorded a video and posted it on Youtube of me playing San Francisco Rush in MAME.

http://www.youtube.com/watch?v=9CYREgWQFFM&watch_response

Keep in mind I was running FRAPS in the background, so it might not of been running as smooth as normal, some audio stuttering here and there. I'll stop spamming this forum now.  :cheers:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: FrizzleFried on October 20, 2008, 09:56:26 am
How do you control Rush?  Spinner?

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on October 20, 2008, 04:38:23 pm
I use a playstation 2 controller, the analog part of it for driving games, it's too sensitive for playing Rush, I need to figure out how to make it less.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Popcorrin on October 21, 2008, 09:36:06 am
Well I actually found a way to get the sound synced in sfrush, its kind of a flukey way. Thanks for responding though, I know this isn't the place to talk about this. 

What did you have to do to get it to sync up?  Adjust the latency in the mame.ini?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on October 22, 2008, 06:27:16 pm
I'm not exactly sure, during the steering wheel test at start up I keep pressing abort, and maybe about 1 out of 10 times the sound is synced. Either that or I enabled the Boot Rom Test Dip Switch, and after trying to exit it about 3 times I then disable the Boot Rom Test Dip Switch and restart the game, and magically 1 out of 10 times or less, the sound is synced.

I wish I had a better answer.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: FrizzleFried on October 22, 2008, 06:52:37 pm
Alright....I have everything up and running...and my CPU overclocks to 3700mhz with a simply bump of the vcore to 1.3 and FSB to 370.  Anything after that and I lose stability.  What other settings should I be looking at to get it to 4,000mhz?    This board has a bunch of voltage settings I am not used to.  Do I need to mess with any of them?  Should I mess with any of the memory settings?   

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on October 22, 2008, 08:38:51 pm
What motherboard is it, what CPU is it and what memory is it?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: FrizzleFried on October 22, 2008, 09:20:05 pm
Intel Core 2 Duo E7300
Sunbeam(tuniq) Core Contact Freezer
Gigabyte GA-EP45-DS3L
Corsair 2x1GB DD2-800
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on October 22, 2008, 10:10:36 pm
I think that CPU has a 10x multiplier, if so set it to 10x. Make sure the memory isnt running above its stock speeds so you know its not the bottle neck, especially if its cheaper memory. Slowly raise the voltage on the cpu? Id personally google some safe voltages to try first. "E7300 overclocking" for example. Maybe download RealTemp to keep an eye on your CPU temperature.
 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on October 22, 2008, 10:22:44 pm
Do you have a bios setting "DRAM Frequency" try setting it to AUTO.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: FrizzleFried on October 22, 2008, 11:58:55 pm
Bah...this thing looks to top out at 3.7ghz...  the tweaking ensues.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on October 23, 2008, 12:42:54 am
Overclocking a new system is a lot of trial and error, it took me about a week to get things optimal.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 23, 2008, 12:56:15 am
Alright....I have everything up and running...and my CPU overclocks to 3700mhz with a simply bump of the vcore to 1.3 and FSB to 370.  Anything after that and I lose stability.  What other settings should I be looking at to get it to 4,000mhz?    This board has a bunch of voltage settings I am not used to.  Do I need to mess with any of them?  Should I mess with any of the memory settings?   

Your probably going to have to play with more than the basics to get 4.0ghz, but 3.7ghz @ 1.3v your still got plenty of head room CPU voltage wise, from what I've seen you'll need between 1.36-1.4v to get 4.ghz stable (1.45v is generally concidered the max save day to day voltage for a 45nm Core2Duo), you will problably want to tweek a few of the chipset voltage too.

Going straight for the kill, with CPU voltage and FSB alone almost never works, it best to take it in stages.

Start by checking you have the lastest bios (http://www.giga-byte.com/Support/Motherboard/BIOS_Model.aspx?ProductID=2778) for the mother board, if not download the last version and update using Q-Flash in bios.

In Bios under 'Advanced Bios Features' disable: C1E, TM2, IEST (these features can fight you when your overclocking)

Next you want to try and get to the FSB and RAM working stablely at 400mhz (1600 FSB) while keeping the CPU clock speed and core voltage basically stock. To do this you want to get the 'CPU Clock Ratio' to between 6-7x(6x +0.5 while be the closest to stock), Set the 'CPU Host Frequency' to 400mhz, I like to manual set the 'PCI-E Clock Freqency' to 100mhz, disable CIA2, set the 'System Memory Multiplier' to 2.0B, leave the 'DRAM Timing Selectable' to auto unless the memory timings don't match those on the written on the RAM, leave the CPU core voltage stock, you may want set 'DRAM OverVoltage Control' to +0.2v (Corsair RAM seem to like the extra voltage). This will get you the CPU running at about 2.6ghz with 400mhz (1600 FSB), with the ram running at stock DDR2-800, do a few stress tests it at these setting and tweak the PCI-E/FSB/MCH Overvoltage Controls as need to get it stable probably on need about +0.1v on each but you'll need to play with each and see what result you get.

Once you have the system 100% for like 2 hours at 100% load in Orthos, you can move onto the next step which is to increasing the 'CPU Clock Ratio', one step at a time so from 6x to 7x, then to 7x to 8x ...., and test the system for stablity with each step, increase the CPU voltage as needed, in theory you should get to 9x at ~1.3volts which with a 400mhz (1600FSB) will give you a 3.6Ghz clock speed,at this point you will probably want to start using the 'Fine CPU Clock Ratio' to add +0.5 to get a cpu mutliplier of 9.5, also suggest without change any other setting dropping the 'CPU HOST Frequency' to 390mhz this will under clock your RAM a little but give you a CPU clock speed of 3.7ghz (which you've aready had stable) but with a higher FSB, once you happy the system is stable at those setting you can increase 'CPU HOST Frequency' back to 400mhz which will give you 3.8ghz with 400FSB thise will probably require more CPU core voltage but with a with little luck you shouldn't have to play with anything else, once stable there the next step is change the  'CPU Clock Ratio' to 10x the 'Fine CPU Clock Ratio' to 0.0 and lower the 'CPU HOST Frequency' down to 390mhz once again, this will give 3.9ghz again your will likely need to add more CPU core voltage (don't get carried away) you may need to tweak the chipset voltage again at this point to get it stable (very likely if it fails to POST) once your happy if's stable there go for the kill, bump the 'CPU HOST Frequency' back to 400mhz add tweak CPU voltage as needed to get it stable at 4.0ghz.

Don't get silly with the CPU Core voltage you don't want to use anymore than you have to, also check what the actual CPU Core voltage is in CPUz you'll notice that the actual voltage is often lower than the voltage set in bios (this becomes more notice as you raise the clock speed of the CPU), it will also drop lower under full load, you want the Acutal CPU Core voltage to stay below 1.45v for day to day running, but I wouldn't think you'll need much more than 1.4v to get it stable. You will want to stress test the system for 1 to 2 hours each step of the way, may sound like a waste of time but it's no good increasing the overclock if it's not 100% stable at the current settings.

The newer versions of the bios have some addition tweaking options, but I'm working from the PDF version of the manual for your board, I've got a GA-X38-DQ6 which has basically the same bios, but I'd need you to confirm that feature and options are available in the 'MB Intelligent Tweaker' section of you boards bios, before can offer advice of what else might help.


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Neverending Project on October 23, 2008, 05:50:27 pm
This is quite the informative thread. Does anyone have any thoughts on whether the Nehalem architecture that Intel will be manufacturing next year will provide a substantial leap over the Core 2 in MAME? My initial thoughts are that it won't be substantial, but I am not really in the know... just speculating.

Here are some of the features I have read about:
* Turbo Boost - CPU will shut down idle cores to save power - not much help for MAME here.
* Integrated graphics core in the CPU - not much help for MAME here.
* Integrated memory controller - possibly helpful?
* Quick Path Interconnect (QPI) - faster pipes for chips and system components to communicate - possibly helpful, but it seems like this would most benefit multi-core operations.
* DDR3 memory and shared L3 cache - this should help.
* Each core can execute two simultaneous software threads - this would help, but be most helpful for highly-threaded applications - hence not really MAME.

Any other opinions on all this?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on October 23, 2008, 07:08:31 pm
On Nehalem - keep in mind MAME now supports a lot of multi-threading which is one of the reasons C2D outperforms AMD on it.

Keep in mind also that eventually most of the Dev Team will likely upgrade to C2D or Nehalem, so it is in their interest to capitalize on its enhancements.

So while 0.120 might not run much better on it, 0.150 certainly could.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on October 23, 2008, 07:49:50 pm
On Nehalem - keep in mind MAME now supports a lot of multi-threading which is one of the reasons C2D outperforms AMD on it.

No, not a reason: 2, 3 and 4 core AMDs don't get the same boost as C2D or C2Q.  Because the Core2 is more powerful per core.  (Just like the dual P4s don't get as must boost as dual core AMDs, because the AMD is powerful than the P4, but the difference isn't as much as between the core2 and anything below it.)

If the Nehalem is less power per core than core2, it won't help mame.  We'll need to wait and see.

Quote
Keep in mind also that eventually most of the Dev Team will likely upgrade to C2D or Nehalem, so it is in their interest to capitalize on its enhancements.

So while 0.120 might not run much better on it, 0.150 certainly could.

Agree.  It's much easier to code for what you have, than for what you don't.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on October 23, 2008, 08:29:40 pm
This is quite the informative thread. Does anyone have any thoughts on whether the Nehalem architecture that Intel will be manufacturing next year will provide a substantial leap over the Core 2 in MAME? My initial thoughts are that it won't be substantial, but I am not really in the know... just speculating.

Any other opinions on all this?

- I would expect clock for clock a Core i7 (Nehalem) will be a little faster than a Core2duo due to improvements in basic architure of the Nehalem core.

- I don't think the intergrated three channel memory contoller will have much if any real effect on MAMEs perfomance, while this is probably the largest single improvement in the Core i7 design over the Core2duo memory bandwidth and latency doesn't seem to be that big an issue for MAME on atleast not on a Core2duo system.

- The elimitation of the FSB bottle neck with the introduction of QPI, and the large amounts of internal shared Cache memory in the Core I7 may throw up some surprises when it comes to MAME performance, the high FSB Core2duo don't really show any major signs of being bottle necked, the Core2quads on the other hand do.

- Hyper threading on the Core i7 will likely get in the way of MAME preformance with it's mostly Single Threaded design, I'm guessing disabling this feature if it is possible will aid the perfomance of MAME on the Core i7, unless Intel have made some major improvement to how it works from the P4 days.

- Clock speed will be the down fall of the Core i7, MAME is the ultimate Ghz whore, nothing gains you more preformance in MAME than upping the clock speed of your CPU, good CPU architure does matter but it's unlike that the architural improvements in the Core i7 will be able to add enough preformance to match the brute force of a heavily overclocked Core2duo. The Core i7 being a new CPU design and being a quad core will be unlikely to overclock anywhere near as well as the lastest Core2Duo E8600 E0 stepped CPUs do, the Core i7 will be limited by it's need for power and heat it will produce just like the Core2quad is when it comes to overclocking. I expect to see the Core i7 hit 4ghz, but with the Core2duo is already able to hit 5ghz+ with highend cooling, I expect the Core2duo to hold onto it's single threaded preformance crown for some time to come.

Future developement in MAME may well see it gain more performance on the Core i7 with time, but this will be limited unless MAME suddenly becomes fully multi threaded to take advantage of all four of Core i7 cores, until then the power saving features will get a workout powering down the cores left unused by MAME.
(Note: this is not a jab at the Dev Team, I understand there are very good reasons behind why MAME is largely lacking in mutli thread support)





Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: holtzboy on November 05, 2008, 06:05:30 pm
Wow, it's great to see San Francisco RUSH running so smoothly! What kind of components does your computer have BigTymer?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on November 05, 2008, 10:48:57 pm
It's an Asus P5Q3 Deluxe motherboard, 2GB Corsair XMS3 DDR3 1600mhz memory, and the E8500 (E0 stepping) cpu. Altogether barely costing over $500. I'm reusing everything else from my old machine.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: holtzboy on November 05, 2008, 11:21:26 pm
Cool thanks for the info. I don't know if you remember, but we were talking about how much Midway Arcade Treasures 3 sucked on the IGN boards a couple years ago but now that doesn't matter since Rush is MAME-able! Is Rush the Rock playable too? Did it have any new songs besides the techno-ish 'The Rock' song?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on November 05, 2008, 11:37:07 pm
I sent you a personal message.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: headkaze on November 06, 2008, 07:59:38 pm
Has anyone noticed these new settings in mame.ini? I never seen them before? They are off by default. I probably wouldn't mess with process priority by the multithreading option is interesting. I wonder if this will take advantage of a Quad Core?

Code: [Select]
#
# WINDOWS PERFORMANCE OPTIONS
#
priority                  0
multithreading            0

Just gave it a try and I got about a 5% increase on Blitz.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on November 06, 2008, 08:30:55 pm
What Mame version are you using? Ive used MameUI and Ive seen those options before.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on November 08, 2008, 08:16:20 pm
Has anyone noticed these new settings in mame.ini? I never seen them before? They are off by default. I probably wouldn't mess with process priority by the multithreading option is interesting. I wonder if this will take advantage of a Quad Core?

Code: [Select]
#
# WINDOWS PERFORMANCE OPTIONS
#
priority                  0
multithreading            0

Just gave it a try and I got about a 5% increase on Blitz.

My understanding is that the -mt command creates an additional thread that handles the final outputs. Any mutlicore CPU will gain something from this switch, but it depends on the CPU speed and the ROM being emulated as to how much you gain. It doesn't effect the software SLI feature of MAME used to emulate 3DFX hardware and alike, this feature work regardless of the -mt switch.

I had someone on another forum run a MAME benchmark on his Core 2 Quad Q9450 which is overclocked to 4ghz, on Vista 64bit, running MAMEUI64 it benchmarked Gradius4 at 126.75% where as my Core 2 Duo E8500 @ 4ghz gets 119.7% running the same setup, so while the gain on a quadcore it's not really worth the extra cost of the CPU.



 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: holtzboy on December 16, 2008, 09:10:34 am
So I got my new computer put together which consists of:

Gigabyte GA-P45-UD3P motherboard with F7A bios
8GB of G.Skill PC-8000 BPQ memory
Core 2 Quad Q6600 @ 3.78Ghz (420 * 9X) @ 55° load
Thermalright Ultra Extreme 120 CPU cooler
Corsair HX620 Power Supply
Samsung Burner
Western Digital 640AAKS main drive, Samsung Spinpoint 1TB storage drive
Windows Vista Ultimate x64 SP1

To my surprise, San Francisco RUSH on my system runs fairly playable with some sound stutters here and there. After some tweaking with my wireless xbox 360 controller I can actually control it pretty good. It's too bad Rush the Rock gets stuck after you select your vehicle, that would be quite fun to play. I tried pressing the view buttons during the track/car selection to enable 'Solo' mode and disable 'Drones' but I guess they are correct when it says "You will not get this game working don't even try." I also messed with the service menu settings for too long which didn't help. I doubt there will be a fix anytime soon but until that day I guess I can keep on playing the 3 tracks on plane ol Rush!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on December 16, 2008, 05:51:24 pm
What Mame version are you using to play Rush? Are you able to get the sound synced up? If you haven't already try using Mame.121 (64-bit), it's about 10% faster in Rush than other versions that I've tried. I use MameUI .121 (64-bit). Another thing is, the actual arcade had 4 channel surround sound, I wonder if their is a way to get that hooked up in Mame instead of 4 channel sound only coming through 2 speakers.

If you go to YouTube and search "Mame San Francisco Rush" you can see my Rush videos, I have tracks 1, 2 and 3 on there now.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: holtzboy on December 16, 2008, 07:43:05 pm
I am using the 64-bit version of MameUI .121. Maybe that's why its so playable even though my cpu is under 4.0Ghz. The sound has never been synced up before and according to the menu in Mame, I have launched/played it 35+ times. Do you know what exactly is holding up Rush the Rock after you select your vehicle and it is flashing "Preparing Car?" I wonder how hard it would be for Aaron Giles or whoever is working on MAME to fool the game so it thinks the settings are correct or whatever so we can play it!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on December 16, 2008, 08:07:56 pm
I've messed with Rush the Rock too, after you select a car the race never starts because it relies on networking even in single player mode. That's kind of weird.

But, if you want the sound to sync up in normal SF Rush try this...

What you do is start the game, go into the general MAME options by hitting tab, go to dip switches and enable the "Boot Rom Test" dip switch and exit the game. Start the game again,when the Boot Rom Tests menu appears exit it, the game will restart and the menu will appear again, exit it again, when the menu appears for the third time go back into the general MAME options and disable the "Boot Rom Test" dip switch, then exit the Boot Rom Tests menu, the game will restart and now just hit abort to skip the steering wheel tests and when the game starts the sound will be synced.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: holtzboy on December 16, 2008, 08:36:20 pm
Sweet thanks for the tip it worked great. It's a whole new game playing it with the sounds right on cue. The cpu really struggles on track 3 because there's a lot more detail than track 1. If Mame came with netplay I wonder if Rush the Rock could see those settings and somehow work, I doubt it but I am just throwing out ideas.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Havok on December 17, 2008, 09:53:43 pm
Anyone with a high end system tried Firefox yet? It works on my AMD Sempron, but stutters a bit.

(Might be time to finally come back into the Intel fold, after a four year hiatus...)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Tiger-Heli on December 18, 2008, 09:02:30 am
Sweet thanks for the tip it worked great. It's a whole new game playing it with the sounds right on cue. The cpu really struggles on track 3 because there's a lot more detail than track 1. If Mame came with netplay I wonder if Rush the Rock could see those settings and somehow work, I doubt it but I am just throwing out ideas.
There is a misunderstanding here - Netplay enables you to play MAME head-to-head on separate computers over a connected network.

Rush The Rock doesn't work b/c the computer that MAME is emulating doesn't have a network card or network connector emulated - not the same thing and enabling net play (i.e. Killerera) would have NO EFFECT.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TAG on December 18, 2008, 07:01:33 pm
Anyone with a high end system tried Firefox yet? It works on my AMD Sempron, but stutters a bit.

(Might be time to finally come back into the Intel fold, after a four year hiatus...)

I've tried it on my P4 3.0 GHz and it runs fine, although I had read somewhere else that it would take a dual core for MAME to run the laserdisc games well.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on December 19, 2008, 11:35:26 am
Anyone with a high end system tried Firefox yet? It works on my AMD Sempron, but stutters a bit.

(Might be time to finally come back into the Intel fold, after a four year hiatus...)

I've tried it on my P4 3.0 GHz and it runs fine, although I had read somewhere else that it would take a dual core for MAME to run the laserdisc games well.

Did you hear dual core, or Core 2TM?  Huge difference between the two.

Not that it really matters; that must have been incorrectly deduced from Cube Quest benchmarks.  Cube Quest, the first laserdisk added to mame, is thought to be the most CPU intense laserdisk game, emulation-wise, and according to johnIV's benchmarks (http://mameui.classicgaming.gamespy.com/Bench.htm), a 3.0 GHz Core2TM emulates it easy, and that the harddrive speed is a major factor.  Anyway, all other laserdisk games are thought to need less CPU power than Cube Quest, so trying to guess how much CPU they'll need from CQ numbers isn't well founded.  I'm not surprised that a 3 Ghz P4 can run firefox.

FWIW, what harddrive are you using?  7200 rpm?  (I'm checking if firefox is as HD limited as CQ.)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TAG on December 21, 2008, 04:03:34 pm
Anyone with a high end system tried Firefox yet? It works on my AMD Sempron, but stutters a bit.

(Might be time to finally come back into the Intel fold, after a four year hiatus...)

I've tried it on my P4 3.0 GHz and it runs fine, although I had read somewhere else that it would take a dual core for MAME to run the laserdisc games well.

Did you hear dual core, or Core 2TM?  Huge difference between the two.

Not that it really matters; that must have been incorrectly deduced from Cube Quest benchmarks.  Cube Quest, the first laserdisk added to mame, is thought to be the most CPU intense laserdisk game, emulation-wise, and according to johnIV's benchmarks (http://mameui.classicgaming.gamespy.com/Bench.htm), a 3.0 GHz Core2TM emulates it easy, and that the harddrive speed is a major factor.  Anyway, all other laserdisk games are thought to need less CPU power than Cube Quest, so trying to guess how much CPU they'll need from CQ numbers isn't well founded.  I'm not surprised that a 3 Ghz P4 can run firefox.

FWIW, what harddrive are you using?  7200 rpm?  (I'm checking if firefox is as HD limited as CQ.)

My harddrive is 7200 rpm, yes.  I'm just glad I took a shot at grabbing the CHD, even though I wasn't sure how it'd run on my system.  That would've been a lot of GBs to download only to find out it didn't run well.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: retrometro on December 21, 2008, 06:58:12 pm
Anyone with a high end system tried Firefox yet? It works on my AMD Sempron, but stutters a bit.


I forget, does firefox runon .127 or does it require .128 or higher.  May attempt this week.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: TAG on December 21, 2008, 09:12:35 pm
I forget, does firefox runon .127 or does it require .128 or higher.  May attempt this week.

It was added in one of the .127 updates (.127u4, I believe).
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Paul Olson on January 14, 2009, 04:11:26 am
Well, I finally got a new motherboard for my cab computer, an ep45 ds3l, and I have an e8400. I am stable at 4ghz for about 9 minutes in orthos, then orthos crashes. My temp is at 67c, which seems high since I am using a zalman 9700. If I lower the overclock, orthos doesn't crash, but it just stops at around the same time, I think around 9:30 or so. In the log for one test, it read bye bye. How do you get it to stay running? I still have a lot of tweaking to try, and I am waiting on some ram. I had one stick die (from another comp, not related to the oc) and 1gig is a bit light. Should my temps be lower than this with this cooler at 4ghz?

I am trying to decide which OS to use. I would like to use xp64 for the extra speed (using soft-15khz, so I can't use Vista64), but it is a big tradeoff. I use the U-HID on my cab, and I can't program the encoder in 64bit. I need to take it out and program it from another computer, so that is not very good. If I can get this stable at 4ghz, what games would I actually lose by sticking with 32bit? I know there is a difference, but what games would be unplayable at full speed in 32bit, but are full speed in 64? If no games that I really care about are going to be affected, I will just stick with 32.

I am still learning this stuff, so I really don't know the answer to this. The ram I ordered today is 1066. Is it better to keep the multiplier lower and run the ram full rated speed, or is it better to run the multiplier higher?

Thanks,
Paul
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on January 14, 2009, 08:23:45 am
It's 2AM here right now, so I keep the answers short.

Install gigabyte easy tune 6, a try bumping the CPU PLL voltage just a bit to say 1.54v (1.5v is stock), it helps stablity often rasing the PLL voltage often let you get the same overclock with less Core Voltage. (if your only running DDR2-800 ram it will be overclocked to DDR2-900 and may not be stable unless you apply more voltage to it)

67c is high in my book, my CPU is running in the 45-55c at full load (and running way more voltage than you should be), sorry to say but the Zalman 9700 is way overrated, your better off with a 2x 120mm fans &  tower type heatsink with 4 or more hear pipes.

 Vista 64bit is the safer bet in the long run (though Windows 7 64bit is look good so far, I'm testing the beta currently ) XP64 isn't well supported, try looking a EnTech PowerStrip for running 15Khz , the lastest version runs under Vista 64bit, and while it may not be as simple to use as soft-15Khz I think you'll find it will let you run windows on your arcade monitor.

Higher FSB and lower Multiplier will give you greater FSB bandwidth and better preformance, catch is the high FSB will often needs more chipset voltage to get stable and thus your chipset will run hotter. with ddr2-1066 I'd run 500mhz FSB and, 8x CPU multiplier, 2x memory multiplier, if you can get it stable with out jacking the north bridge voltage to much.

 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Paul Olson on January 14, 2009, 02:00:44 pm
Thanks for the reply. I need to cool it down some; what is the best cooler at the moment? It is stable but hot right now. I ran orthos for an hour but stopped it because I didn't want to run it that hot for too long. It was actually at 72c. I don't mind buying a new cooler, but I don't want to buy another mediocre one.

I had xp64 on my cab before the upgrade because my wireless card doesn't have vista64 drivers. The biggest issue for me is the encoder; I need to be able to switch the inputs for different control types on the fly.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on January 14, 2009, 07:47:29 pm
Thanks for the reply. I need to cool it down some; what is the best cooler at the moment? It is stable but hot right now. I ran orthos for an hour but stopped it because I didn't want to run it that hot for too long. It was actually at 72c. I don't mind buying a new cooler, but I don't want to buy another mediocre one.

For AIR cooling it's still hard to beat a Thermalright Ultra-120 eXtreme, but I suggest you get the newer version the Thermalright True Black 120 (http://www.crazypc.com/products/true-black-50984.html) which comes with two sets of wire fan clips so you can pair of fans in a push pull setup.

For the fans I suggest you get a two Scythe S-FLEX SFF21F 120x120x25mm 1600rpm Fans (http://www.crazypc.com/products/58472.html), they have good air flow, low noise and the Fluid Dynamic Bearing means they just keep going and going and going.

This is not a cheap solution but it is one of the best, also Crazy PC that I linked to about offers a Lapping service on many of the heatsinks they sell, which may not be a bad idea to get done too.

If you go this route make sure you do the penny mod, basically you place a thin coin on top of the heat sink block under the mounting bracket, which increases the mounting force and noticable improves the heatsinks preformance.

There are a number of cheaper heatsinks of the market with similar designs some come very closes in preformance overs are badly made rip off of the design. The Sunbeam (Tuniq) Core Contact Freezer (http://www.crazypc.com/products/core-contact-5048.html) is one of the best of cheap versions of this style of heatsinks, but it only supports one fan, so there is a bit of a trade off between fan noise and preformance, but it does offer great value for money.




Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Paul Olson on January 15, 2009, 11:27:52 am
The True sounds great, but my budget doesn't like it much. I ordered the Core Contact Freezer from Newegg. They sell it for $39.99, but there is a $10 rebate and free shipping.

Hopefully it will be here by Saturday, and I can get this system back up and running. I decided to go back to XP64; my wireless card won't work with vista64.

Thanks
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Paul Olson on January 17, 2009, 04:32:15 pm
I'm still waiting for the new cooler, but I couldn't wait to test. The difference between 3GHz and 4GHz in Gauntlet Legends is amazing. It crawled at 3, but is mostly full speed at 4. It still slows down when there are a lot of enemies on screen, but it may have done that some on the dedicated machines as well - I can't remember. I am hoping to push the speed up a bit with better cooling. It is stable without any tweaking at 1.37 core voltage, so I am hoping there is quite a bit of room left.

Has anyone tested the e7300 yet? Is there any chance it could outclock an e8400 since it has the 10x multiplier? I just put a PC together using one for my girlfriend which is not going to be overclocked, and I don't want the chip to go to waste if it is better. At the same time, I don't want her to complain about me tearing here computer apart if it won't do me any good.  ;)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on January 18, 2009, 11:51:04 pm
Has anyone tested the e7300 yet? Is there any chance it could outclock an e8400 since it has the 10x multiplier? I just put a PC together using one for my girlfriend which is not going to be overclocked, and I don't want the chip to go to waste if it is better. At the same time, I don't want her to complain about me tearing here computer apart if it won't do me any good.  ;)

I wouldn't like to call that one Paul, clock for clock the E8400 is going to be faster than the E7300, but as to which one will overclock better is down to luck, one CPU might be from a great production batch and other a very average one, just comes down to how Intel was binning the dies the day the CPU were made.

Only real way to know for sure is try them both.


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: nipsmg on January 19, 2009, 04:56:13 pm
Has anyone done any testing with the Windows-7 64-bit beta?  By every account I've been able to find, Windows-7 is less resource intensive and faster than vista, and it seems the fastest emulation so far is using 64-bit vista.  So I'm wondering if the smaller OS footprint might translate to larger framerates in emulation?  I'm running it now and it's definitely faster on my machine than vista, but my processor isn't fast enough to do anything high-end with emulation, so it's not really worth me testing.

--Just wondering.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on January 19, 2009, 07:01:10 pm
Has anyone done any testing with the Windows-7 64-bit beta?  By every account I've been able to find, Windows-7 is less resource intensive and faster than vista, and it seems the fastest emulation so far is using 64-bit vista.  So I'm wondering if the smaller OS footprint might translate to larger framerates in emulation?  I'm running it now and it's definitely faster on my machine than vista, but my processor isn't fast enough to do anything high-end with emulation, so it's not really worth me testing.

--Just wondering.

Windows 7 is a noticable improvement, It still uses a ton of hard disk (64bit more so than the 32bit version) but Memory usage is down, The UI is much snapper and very clean, everything has been tweaked to the new standards even MS Paint and the Calculater, UI doesn't feel like a rushed patch job like Vista did. 

I Benchmarked MAMEUI 64 0.129 in both Vista and Windows 7 the other day, Windows 7 scores were a bit mixed, faster for some slower for others, I'd put it down to the fact it's still a beta and the very broken beta Nvidia graphics drivers. I'll post the result later when I get a chance.



Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: bent98 on January 19, 2009, 08:24:36 pm
Are there any plans for an Intel i-7 mame compile? Curious to see benchmarks with new chip.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on January 20, 2009, 07:07:54 am
MAMEUI 64bit v0.129 on Windows 7 Beta 64bit benchmark results:        Core 2 Duo E8500 @ 4ghz

Rom      WIndows 7 (Beta)   Vista SP1

1942      4381.98%      4378.50%
airco22b   127.80%         133.86%
alpinerd   76.90%         77.74%
blitz      161.04%         164.82%
blitz2k      154.92%         157.25%
blitz99      152.37%         149.57%
calspeed   197.59%         210.20%
crusnusa   278.50%       275.58%
crusnwld   243.85%         242.59%
cybrcomm   121.74%         121.08%
cybrcycc   194.67%         193.05%
cyvern      806.02%       808.70%
daytona      200.34%         196.29%
gauntdl      165.54%         129.01%
gauntleg   201.65%         185.41%
gnbarich   1244.56%      999.89%
gradius4   129.10%       126.49%
harddriv   656.36%       1054.54%
hyprdriv   174.18%         174.83%
kinst2      677.53%         699.78%
mace      240.66%         237.60%
mk4      180.93%         182.16%
offroadc   356.25%       351.71%
propcycl   129.36%         128.29%
radikalb   156.69%       155.88%
raveracw   112.32%         107.36%
ridgerac   144.60%       138.69%
roadblst   1169.47%      1154.81%
rvschool   193.79%         190.96%
sfrush      189.34%         171.54%
sidebs2      148.04%         145.41%
soulclbr   189.26%         189.67%
speedup      159.92%         159.01%
starblad   134.86%       133.33%
stunrun      637.91%         634.48%
surfplnt   147.50%         148.21%
tekken2      301.35%         298.68%
tekken3      171.41%         170.69%
tenthdeg   88.44%         86.21%
timecris   210.43%         123.23%
vfkids      187.91%         186.71%
wargods      373.90%       367.71%
wg3dh      354.14%         341.51%
wrally      1415.24%      1477.20%
xevi3dg      318.59%         317.94%

Some of the results are a little random but that's to be expected with Windows 7 and the Nvidia graphics drivers still be a Beta.

Are there any plans for an Intel i-7 mame compile? Curious to see benchmarks with new chip.

Sure someone will do it in time, but currently the Price Premium on Core i7 CPUs & boards is to high for the additional preformance you see over a Core 2 Quad in MAME.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on January 20, 2009, 12:08:42 pm
Are there any plans for an Intel i-7 mame compile? Curious to see benchmarks with new chip.

Someone did over at mameworld, and didn't get much improvement over core 2 (some faster, some slower):  link (http://www.mameworld.info/ubbthreads/showthreaded.php?Cat=&Number=172849&page=0&view=expanded&sb=5&o=&fpart=1&vc=1).  :-\

Assuming the system tested wasn't bottlenecked somewhere else, looks like i7 not worth it ATM for mame.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Paul Olson on January 23, 2009, 01:51:05 am
I'm still working on the e8400 overclock. It looks stable at 3.9GHz right now. I am testing it with Intelburntest. Have any of you tried it? It jacks the temp up 10c higher than Orthos does. I am still having a cooling problem. It was maxing out at 60c with Orthos, but it hit 70c once using IBT. It is mostly at 66-67, I just saw the 70 for a few seconds. I put the Core Contact Freezer on and it helped a bit, about 8c I think. I had to use the mount from my Zalman, so that probably didn't help much. The clip was hanging up on the NB heatsink on the EP45-DS3L. This mount isn't as tight as I would like, even after I shoved a washer in there. Has anyone else tried to use this cooler on this board?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on January 23, 2009, 02:32:16 am
I'm still working on the e8400 overclock. It looks stable at 3.9GHz right now. I am testing it with Intelburntest. Have any of you tried it? It jacks the temp up 10c higher than Orthos does. I am still having a cooling problem. It was maxing out at 60c with Orthos, but it hit 70c once using IBT. It is mostly at 66-67, I just saw the 70 for a few seconds. I put the Core Contact Freezer on and it helped a bit, about 8c I think. I had to use the mount from my Zalman, so that probably didn't help much. The clip was hanging up on the NB heatsink on the EP45-DS3L. This mount isn't as tight as I would like, even after I shoved a washer in there. Has anyone else tried to use this cooler on this board?

IntelBurntest is a evil peice of software, it's generally considered unsave to run it for extended periods on any overclocked CPU, my understand of how it works is make a huge number of direct command calls to the CPU it such a way to light up almost every transistor in the CPU simulateously, this is only possible because of Intels internal knowledge of their processor, in effect it runs the CPU at 120%, no normal set of operations or calculations will ever push the CPU close to what IntelBurntest does.

Mounting pressure is very important to the cooling on modern CPUs, so you really want to use the mounting clip that came with the core contact freezer.
I had a quick look at picture of the EP45-DS3L and the bracket on the CCF, I think you can gain the extra clearance required to fit the stock CCF bracket by simple turning the northbridge heatsink around on the motherboard, this will mean you can't use the first PCI-E 1x slot but there are three more on the board so I can't see it being an issue.

(http://common.ziffdavisinternet.com/util_get_image/18/0,1425,sz=1&i=187817,00.jpg)

As you can see the heatsink fins on edge closest to the PCI-E slot is lower than the rest, so buy rotating the NB heatsink 180deg it should give you the clearance you need.

(see PM for detailed steps)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Paul Olson on January 23, 2009, 03:09:59 am
Great idea, and thanks for the advice! I am at 4GHz at the moment, and it seems stable. I would like to get the temps down, so I will definitely try your solution. I ran IBT for about 15 minutes and the temp topped out at 73c. I have been running Orthos for around 20 minutes after that, and it has only reached 62c. I will try to mount the CCF with the correct bracket, then I will run Orthos for the night. Hopefully it will still be running in the morning. My vcore is at 3.38 (I think), but it drooped all the way down to 1.296 while running IBT. CPU-z is showing 1.312 while running Orthos.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Neverending Project on February 13, 2009, 02:07:50 pm
MAMEUI 64bit v0.129 on Windows 7 Beta 64bit benchmark results:        Core 2 Duo E8500 @ 4ghz

Rom      WIndows 7 (Beta)   Vista SP1

...


Can anyone run these tests with one of the new Atom 330 processors? I am more curious how they compare to a standard Core 2 Duo than a massively overclocked one, but any comparison would be great to see.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on February 14, 2009, 01:59:03 am
Can anyone run these tests with one of the new Atom 330 processors? I am more curious how they compare to a standard Core 2 Duo than a massively overclocked one, but any comparison would be great to see.

I don't have a Atom 330 Processor to benchmark, but from it's specs and based on other benchmarks on the web of the 330, I can tell you a Atom 330 will get thumped in MAME by even a E4300 at stock clock speeds. The Atom is a great little CPU, but it's designed for power saving and not preformace. 
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Charles4400 on February 14, 2009, 07:06:11 pm
This might be a dumb question but when you buy a case aby itself, does it come with the screws needed to mount the MB or do you have to get that separately?

Also Taz is the case really important in the OC pursuits? I don't care what they look like since it will be put in the cab, but BECAUSE it is being put in the cab is there a preferred one to use in consideration of the air flow etc...?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: drventure on February 14, 2009, 09:11:56 pm
Usually, no, you don't get mounting screws with the mobo, you often get them with a new case, though.

Of course, once you've been doing this a while, you end up with boxes and boxes of those screws, standoffs, nuts and whatnot :)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on February 14, 2009, 10:52:17 pm
This might be a dumb question but when you buy a case aby itself, does it come with the screws needed to mount the MB or do you have to get that separately?

As drventure said, the screws and motherboard risers you need to fit your motherboard are almost always include with the case. Case manufactures generally give you more risers than you need to mount you motherboard, but they also have an annoying habit of include risers with two different internal threads, some risers accept the finer thread CD-Rom type screws, while most accept the standard HDD and Case screw thread.

Also Taz is the case really important in the OC pursuits? I don't care what they look like since it will be put in the cab, but BECAUSE it is being put in the cab is there a preferred one to use in consideration of the air flow etc...?

Short answer yes, keeping your system cool is key to stable overclocking, a computer case has a relatively small internal volume for the amount of heat pumped into it from you CPU and other harware.
A good case design allows for plenty of air flow through the case, allowing the hot air inside to be rapidly exchanged with cooler air from outside the case, thus keeping the internal tempature as close to that of the air in the room around it as possible.
The easiest way to do this is with good front to back airflow, cases with open mesh fronts and large rear exhaust fans work best, too many fans pointed in random direction will actual hurt airflow, they tend to just swirl the hot air around inside the case.

That said if your going to put the system in a cabinet and don't intended to use it for anything else, I'd forget the case and just mount the motherboard directly to the inside of the cabinet, the case is just there to protect the computer hardware from physical damage and to sheild it from EMI, and to shield other devices from any EMI the PC might give off.
Having no case means more air volume around the computer hardware, which in term means the air will be cooler, but I do suggest that you make sure you cabinet is well vented at the top so heat can escape, and has vents near the bottom to allow it to draw in cool air.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Charles4400 on February 15, 2009, 12:23:04 am
Great thanks alot guys appreciate the help!

The project will be coming up soon, just thinking of waiting untill the e8700 becomes available for the price drop of the e8600 or even getting the e8700 to OC that chip!

btw saw this on ebay and was wondering how this guy got a e8500 to 4.24! I'm not getting this auction but do you think its stable and will have a 'long' life?
http://cgi.ebay.com/Overclocked-Core-2-duo-4-24GHz-Gaming-PC-w-HD-4870-1GB_W0QQitemZ280310121412QQcmdZViewItemQQptZDesktop_PCs?hash=item280310121412&_trksid=p3286.c0.m14&_trkparms=72%3A1205%7C66%3A2%7C65%3A12%7C39%3A1%7C240%3A1318%7C301%3A1%7C293%3A1%7C294%3A50 (http://cgi.ebay.com/Overclocked-Core-2-duo-4-24GHz-Gaming-PC-w-HD-4870-1GB_W0QQitemZ280310121412QQcmdZViewItemQQptZDesktop_PCs?hash=item280310121412&_trksid=p3286.c0.m14&_trkparms=72%3A1205%7C66%3A2%7C65%3A12%7C39%3A1%7C240%3A1318%7C301%3A1%7C293%3A1%7C294%3A50)

Once again appreciate the help and advice!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on February 15, 2009, 08:22:58 pm
I run my E8500 at 4250 MHz  (8.5 x 500) with 1.38 vcore, I hear they are safe up to 1.45 vcore for everyday use.  At this speed I've tested orthos, prime95, and memtest for over 2 hours each. I can even run at 4500 MHz but it starts to run hot in orthos. I'm using a Zalman 8700 NT heatsink, which is probably holding me back a little.

That auction on ebay, if you dont care about a fancy case or a bleeding edge video card, or a 1TB hard drive, you could probably put that same system together for like $700.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Charles4400 on February 16, 2009, 01:40:17 am
Man OCing seems the way to go...I mean WOW if you can supe it up that much I'm really anxious to see how far the e8700 will go....

But wondering still, is it a good idea to OC that much if the computer gets left on for possibly 6-7+ hours a day?

Since its going in the cab, sometimes that gets left on if nobody remembers to turn it off which happens more often than not...Well I suppose even if it does get burn out before its average life span (hopefully will survive for more than 3 years!?) it still might be worth it!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: jombee on March 02, 2009, 05:37:58 pm
This is a great post, thanks for all the info!

I am going to upgrade the computer in my cabinet (P4 3.0ghz), and I would like to be able to play most of the MAME CHD games.  I am currently running about 30 emulators (including MAME) and my OS is Windows XP (32).  In the earlier posts the frame rates for WinXP32 appear playable and I really would prefer to stay with WinXP 32 if possible.  If I need to go to 64bit, I would really like to use WinXP64 instead of Vista64.

Here are my questions:

1.  A Core2Quad Q8300 and a Core2Duo E8500 are currently the same price.  Which would be my best choice assuming I will be Over Clocking it to 4 ghz?

2.  Will either of these processors give me nice playable speeds for most CHD games with WinXP32?

3.  If not, is the Core2Quad/Duo compatible with WindowsXP 64?  If I need to go to a 64bit OS I would strongly prefer XP but It does not list those processors as supported as far as I can see.

4.  A bunch of CPU coolers are mentioned in this post, which one do you currently think would be my best choice?

Any help would be greatly appreciated, Thanks!



Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 03, 2009, 03:04:25 am
1.  A Core2Quad Q8300 and a Core2Duo E8500 are currently the same price.  Which would be my best choice assuming I will be Over Clocking it to 4 ghz?

The E0 stepping E8500 is easy overclock to 4ghz and will hit 4.5ghz with the right setup, on the other hand the your pushing it to get Q8300 to 4ghz due to low 7.5x multiplier and it's low binning.

2.  Will either of these processors give me nice playable speeds for most CHD games with WinXP32?

You are lossing a lot of preformance running 32bit MAME in WinXP 32bit, on the order of 20% compaired with 64bit, I suggest trying a 64bit OS before you exclude the idea, compatiblity is not really an issue unless the software your running is only 16bit (in which case it will not work), lack of lightgun support is the only real drawback to 64bit OS.

3.  If not, is the Core2Quad/Duo compatible with WindowsXP 64?  If I need to go to a 64bit OS I would strongly prefer XP but It does not list those processors as supported as far as I can see.

You will have no issue running WinXP 64bit on any of the Core2 family. XP 64bit pre-dates the Core2Duo release, thus they are not listed.
I will warn you though that Windows XP 64bit has atiny install base and thus it's well supported, Vista 64bit on the other hand is getting more and more popular, and is very well supported now.

4.  A bunch of CPU coolers are mentioned in this post, which one do you currently think would be my best choice?

The Sunbeam Core Contact Freezer offers great value for money, but if you want to go all out get a Thermalright True Black 120 and a couple of Scythe SFF21F 1600rpm fans.




Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Todd H on March 03, 2009, 08:28:25 am
Well, my cab is now finished with the exception of the PC. Anybody got any CPU/motherboard reccomendations? Like jombee above, I'm looking at the E8500 CPU. What's a good mother board to go with this processor? I'm planning on overclocking to 4Ghz or higher. I'm also going to need a good video card that will let me play modern PC games like the upcoming Street Fighter IV. The motherboard will be mounted inside the cabinet instead of a case. What about a beefy power supply? Any particular model?

I've been out of the PC building scene for a while since I started using Mac's. The last time I built a PC was during the Pentium 3 years. So any help would be greatly appreciated. Thanks.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: jombee on March 03, 2009, 05:55:12 pm
1.  A Core2Quad Q8300 and a Core2Duo E8500 are currently the same price.  Which would be my best choice assuming I will be Over Clocking it to 4 ghz?

The E0 stepping E8500 is easy overclock to 4ghz and will hit 4.5ghz with the right setup, on the other hand the your pushing it to get Q8300 to 4ghz due to low 7.5x multiplier and it's low binning.

2.  Will either of these processors give me nice playable speeds for most CHD games with WinXP32?

You are lossing a lot of preformance running 32bit MAME in WinXP 32bit, on the order of 20% compaired with 64bit, I suggest trying a 64bit OS before you exclude the idea, compatiblity is not really an issue unless the software your running is only 16bit (in which case it will not work), lack of lightgun support is the only real drawback to 64bit OS.

3.  If not, is the Core2Quad/Duo compatible with WindowsXP 64?  If I need to go to a 64bit OS I would strongly prefer XP but It does not list those processors as supported as far as I can see.

You will have no issue running WinXP 64bit on any of the Core2 family. XP 64bit pre-dates the Core2Duo release, thus they are not listed.
I will warn you though that Windows XP 64bit has atiny install base and thus it's well supported, Vista 64bit on the other hand is getting more and more popular, and is very well supported now.

4.  A bunch of CPU coolers are mentioned in this post, which one do you currently think would be my best choice?

The Sunbeam Core Contact Freezer offers great value for money, but if you want to go all out get a Thermalright True Black 120 and a couple of Scythe SFF21F 1600rpm fans.


Thanks so much Taz-nz, your input is truly appreciated and answered all my questions!

Take care!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: jombee on March 03, 2009, 06:02:06 pm
Well, my cab is now finished with the exception of the PC. Anybody got any CPU/motherboard reccomendations? Like jombee above, I'm looking at the E8500 CPU. What's a good mother board to go with this processor? I'm planning on overclocking to 4Ghz or higher. I'm also going to need a good video card that will let me play modern PC games like the upcoming Street Fighter IV. The motherboard will be mounted inside the cabinet instead of a case. What about a beefy power supply? Any particular model?

I've been out of the PC building scene for a while since I started using Mac's. The last time I built a PC was during the Pentium 3 years. So any help would be greatly appreciated. Thanks.

Todd, here is the motherboard that I am most likely going to buy.  I will be running a single ArcadeVGA2 PCIe card, so the single PCIe slot will not be a problem for me.

GIGABYTE GA-EP45C-UD3R intel p45 chipset ATX form factor 1xPCI-E(x16)/3xPCI-E(x1)/3xpci/4xddr2/2xddr3 w/sata2 raid,lan(gb),1394,usb 2.0 & audio (cpu type:intel - socket 775)





Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 03, 2009, 10:13:42 pm
Well, my cab is now finished with the exception of the PC. Anybody got any CPU/motherboard reccomendations? Like jombee above, I'm looking at the E8500 CPU. What's a good mother board to go with this processor? I'm planning on overclocking to 4Ghz or higher. I'm also going to need a good video card that will let me play modern PC games like the upcoming Street Fighter IV. The motherboard will be mounted inside the cabinet instead of a case. What about a beefy power supply? Any particular model?

I've been out of the PC building scene for a while since I started using Mac's. The last time I built a PC was during the Pentium 3 years. So any help would be greatly appreciated. Thanks.

To get most out of your E8500 i suggest a Gigabyte GA-EP45-UD3R  (http://www.newegg.com/Product/Product.aspx?Item=N82E16813128359), I'm not a fan of the dual memory type GA-EP45C-UD3R that jombee suggested, the single memory type boards tend to be more stable,  my abvice is stick to DDR2 for a Core2 , leave DDR3 to the Core i7.

Graphics card wise it depends on what you want to spend, but currently for PC gaming I'd suggest either a ATI Radeon HD4870 (http://www.newegg.com/Product/Product.aspx?Item=N82E16814125256) or HD4870x2 (http://www.newegg.com/Product/Product.aspx?Item=N82E16814125233).

Power supply, it depends which graphics card you go with and what else you plan to have in the system, but a good brand name (Seasonic, Enermax or similar)600w for the HD4870 and at least a 750w for a system with a HD4870x2.



Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Todd H on March 04, 2009, 08:16:40 am
Well, my cab is now finished with the exception of the PC. Anybody got any CPU/motherboard reccomendations? Like jombee above, I'm looking at the E8500 CPU. What's a good mother board to go with this processor? I'm planning on overclocking to 4Ghz or higher. I'm also going to need a good video card that will let me play modern PC games like the upcoming Street Fighter IV. The motherboard will be mounted inside the cabinet instead of a case. What about a beefy power supply? Any particular model?

I've been out of the PC building scene for a while since I started using Mac's. The last time I built a PC was during the Pentium 3 years. So any help would be greatly appreciated. Thanks.

To get most out of your E8500 i suggest a Gigabyte GA-EP45-UD3R  (http://www.newegg.com/Product/Product.aspx?Item=N82E16813128359), I'm not a fan of the dual memory type GA-EP45C-UD3R that jombee suggested, the single memory type boards tend to be more stable,  my abvice is stick to DDR2 for a Core2 , leave DDR3 to the Core i7.

Graphics card wise it depends on what you want to spend, but currently for PC gaming I'd suggest either a ATI Radeon HD4870 (http://www.newegg.com/Product/Product.aspx?Item=N82E16814125256) or HD4870x2 (http://www.newegg.com/Product/Product.aspx?Item=N82E16814125233).

Power supply, it depends which graphics card you go with and what else you plan to have in the system, but a good brand name (Seasonic, Enermax or similar)600w for the HD4870 and at least a 750w for a system with a HD4870x2.





Just what I needed to know. Thanks. Any particular CPU cooler I should look at?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: joeH on March 04, 2009, 11:41:16 am
Well, my cab is now finished with the exception of the PC. Anybody got any CPU/motherboard reccomendations? Like jombee above, I'm looking at the E8500 CPU. What's a good mother board to go with this processor? I'm planning on overclocking to 4Ghz or higher. I'm also going to need a good video card that will let me play modern PC games like the upcoming Street Fighter IV. The motherboard will be mounted inside the cabinet instead of a case. What about a beefy power supply? Any particular model?

I've been out of the PC building scene for a while since I started using Mac's. The last time I built a PC was during the Pentium 3 years. So any help would be greatly appreciated. Thanks.

The Gigabyte board is a good board.  I'm running my E8400 clocked to 4.0ghz on an Asus P5Q Pro. May want to check that one out as well.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 05, 2009, 12:05:38 am
Any particular CPU cooler I should look at?

To quote myself.

The Sunbeam Core Contact Freezer offers great value for money, but if you want to go all out get a Thermalright True Black 120 and a couple of Scythe SFF21F 1600rpm fans.

There are more extremem options but they aren't really needed with the E0 stepping E8500s.

Title: Beware! Quadzilla!
Post by: ghettodish on March 05, 2009, 12:41:12 am
I got this emailed from Tiger Direct today:

http://www.tigerdirect.com/applications/searchtools/item-Details.asp?EdpNo=4492004&sku=B69-0029&SRCCODE=WEM1865CU&cm_mmc=Email-_-Main-_-WEM1865-_-barebone
Title: Re: Beware! Quadzilla!
Post by: taz-nz on March 05, 2009, 04:21:10 am
I got this emailed from Tiger Direct today:

http://www.tigerdirect.com/applications/searchtools/item-Details.asp?EdpNo=4492004&sku=B69-0029&SRCCODE=WEM1865CU&cm_mmc=Email-_-Main-_-WEM1865-_-barebone

Look like a good deal if you after a media storage box, probably not the most suitable setup for MAME and for the same money you can build budget MAME monster.

I wouldn't trust the no name power supply either (even if it does have a brand). Of the first 5 customer review for it, 3 complain about the sata connector not fitting, 1 talks about how his earlier unit of the same brand failed, and the 5th and only all good review was comparing it to one of those dell 200watt gutless wonders that they put in there pc's.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Silverwind on March 08, 2009, 06:05:06 pm
I run my E8500 at 4250 MHz  (8.5 x 500) with 1.38 vcore, I hear they are safe up to 1.45 vcore for everyday use.  At this speed I've tested orthos, prime95, and memtest for over 2 hours each. I can even run at 4500 MHz but it starts to run hot in orthos. I'm using a Zalman 8700 NT heatsink, which is probably holding me back a little.

That auction on ebay, if you dont care about a fancy case or a bleeding edge video card, or a 1TB hard drive, you could probably put that same system together for like $700.



Any games that do not run smooth on  that?  I have an E0 E8500 on the way.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on March 08, 2009, 09:44:43 pm
The most demanding games I've tried would be games like San Francisco Rush and NFL Blitz. When I use MameUI .121 (64-bit) they run real smooth. As far as regular PC games, I'm only limited by my graphics card as of right now.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: savj14 on March 11, 2009, 01:29:42 pm
I'd love to be able to play Blitz and NBA Showtime on my machine. Has anyone test NBA Showtime? I assume it will run just fine though.

I recently upgraded my Motheboard, and I am really considering getting a new CPU and anything else I need so I can play Blitz and NBA Showtime. I am a noob when it comes to Overclocking, so below are my machine specs. I am hoping someone can tell me if this can be done and what I'll need.

My Motherboard: http://www.msicomputer.com/product/p_spec.asp?model=G31M3-F&class=mb (http://www.msicomputer.com/product/p_spec.asp?model=G31M3-F&class=mb)
RAM: http://www.directron.com/kvr667d2n5k22g.html (http://www.directron.com/kvr667d2n5k22g.html)
PS: http://www.directron.com/w0070ruc.html (http://www.directron.com/w0070ruc.html)

I was looking to get the following CPU: http://www.directron.com/bx80570e8400a.html (http://www.directron.com/bx80570e8400a.html)

I only have the generic heatsink/fan, so I assume I would need something better? What do you suggest I get?

Will I be able to do this with my machine?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 12, 2009, 02:44:00 am
I'd love to be able to play Blitz and NBA Showtime on my machine. Has anyone test NBA Showtime? I assume it will run just fine though.

I recently upgraded my Motheboard, and I am really considering getting a new CPU and anything else I need so I can play Blitz and NBA Showtime. I am a noob when it comes to Overclocking, so below are my machine specs. I am hoping someone can tell me if this can be done and what I'll need.

My Motherboard: http://www.msicomputer.com/product/p_spec.asp?model=G31M3-F&class=mb (http://www.msicomputer.com/product/p_spec.asp?model=G31M3-F&class=mb)
RAM: http://www.directron.com/kvr667d2n5k22g.html (http://www.directron.com/kvr667d2n5k22g.html)
PS: http://www.directron.com/w0070ruc.html (http://www.directron.com/w0070ruc.html)

I was looking to get the following CPU: http://www.directron.com/bx80570e8400a.html (http://www.directron.com/bx80570e8400a.html)

I only have the generic heatsink/fan, so I assume I would need something better? What do you suggest I get?

Will I be able to do this with my machine?

Sorry to say the odds are stacked against you on this one, chipsets with intergated graphics are limited in the amount you can overclock them before the onboard graphics start to give you grief, the G31 chipset is not know for it's overclockablity, and due to the entry level nature of the board it's probably going to be harder to get stable.

On top of that your ram is DDR2-667 which mean if you fit a E8400 CPU with a 1333 (333mhz) FSB  the ram will be running and it maximum factory spec before you even start to overclock the CPU, which means you will have to overclock the RAM as well, which increase the difficulty of getting the system stable.

The Power supply should be fine as long as you don't add a half dozen Hard Drives of a Radeon HD4870 to the system.

If you are going to try and overclock on this board I'd suggest you get a Core 2 Duo E7500  (http://www.directron.com/bx80571e7500.html) , with it's lower 1066 (266Mhz) FSB and high 11x multiply, you will be able to get a high CPU Clock speed without the need to crank the FSB to high (which is likely to cause you issues with the motherboard and RAM you have).

Since you like to shop at Directon, I'd suggest you get the Cooler Master Hyper 212 (http://www.directron.com/rrcchlb12gp.html) Heatsink fan, otherwise I'd suggest the Sunbeam Core Contact Freezer (http://www.newegg.com/Product/Product.aspx?Item=N82E16835207004).

But the best advice I can give is to save some extra cash and upgrade the motherboard and RAM at the same time as the CPU.




Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on March 12, 2009, 04:41:54 am
I just tried showtime out on my rig and it runs damn near perfect. I am on the other hand having emulation issues though, the game does have weird lock up issues where the music just plays and the screen is frozen.

specs of machine

Gigabyte g31m-es2l
Core2 e8400 3.0 ( @ 3.96ghz ) w/ stock fan heatsinks 33c idle 57c peak load.
2gb 1ghz ram
xp x64
wd black 640gb hdd
Radeon x850 xt ( running soft 15khz)

On a side note a new heatsink would be nice but I am officially out of money. I will have to come back to this part in a bit. I don't really ever max this out right now unless I am running prime95.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: savj14 on March 12, 2009, 08:16:41 am
@Taz, first off thanks for the nice reply, very very helpful.

I do have an older Radeon Video card......it's a ATI Radeon X300 SE, it's decent for running MAME games right now. As I have used Powerstrip to add some custom resolutions for my Arcade monitor.

Do I need to upgrade my Video Card? I was thinking about getting an Arcade VGA, not sure if that is good enough.

I just bought the Motherboard/Ram not too long ago, but I suppose I could upgrade them. Is there any way I could just upgrade the RAM and be able to pull this off? If so what RAM do you suggest?

If not what Motherboard and RAM should I purchase from Directron?

I'll post what Video card I havel, to see if that needs to be upgraded as well.

Thanks again for the help
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: massive88 on March 12, 2009, 10:17:55 am
Mame doesnt use any 3d acceleration, so even base level cards will work fine.

The deal with the onboard video is that it creates problems when overclocking, not that it is insufficient for Mame.

A dedicated card you can keep at the AGP bus speed (separate from the FSB) and thus you take it out as a mode of failure for overclocking.

That said I recently snagged a 9800 GTX+ so that I can run PS2 games on my arcade machine  =D
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: savj14 on March 12, 2009, 01:19:08 pm
@uprightbass360

How far into the game were you able to get before it locked up? Did it lock up every time you played(in the same spot)?

Sounds like it might be an issue with the ROM itself........Has anyone else tried playing NBA Showtime?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on March 12, 2009, 01:28:39 pm
Mame doesnt use any 3d acceleration, so even base level cards will work fine.

Wrong, and has been wrong since 0.107.  Mame does use 3d acceleration, just not for game emulation.  Scaling res, scaling color depth, rotating screen image, overlay & artwork, scanlines, and other video stuff are all done in the 3d card now.

Quote
The deal with the onboard video is that it creates problems when overclocking, not that it is insufficient for Mame.

Yup, that's the deal.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Goatz18 on March 12, 2009, 01:34:18 pm
How would say a quad core 1.8 Mhz pc do for playing games in Mame64 on either XP x64 or Vista x64? Overclocked of course to whatever she can handle. Just speculating out loud for future cab pc prospects.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: massive88 on March 12, 2009, 03:22:14 pm
Wrong, and has been wrong since 0.107.  Mame does use 3d acceleration, just not for game emulation.  Scaling res, scaling color depth, rotating screen image, overlay & artwork, scanlines, and other video stuff are all done in the 3d card now.

Well ok, but any direct3d/ddraw card should be able to to handle those, you dont need a beefy GPU for that, that was my point.

Its not like Dreamcast, N64, PSX or PS2 emulation, where your GPU is likely to be a bottleneck.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on March 12, 2009, 07:30:40 pm
@uprightbass360

How far into the game were you able to get before it locked up? Did it lock up every time you played(in the same spot)?

Sounds like it might be an issue with the ROM itself........Has anyone else tried playing NBA Showtime?

I don't doubt that it could be a rom issue ( I did get the chd from a torrent site so that could be so ) The issue is usually when you go to start a game, after you pick your characters. It doesn't happen every time, but when it does you have to re set the rom.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on March 13, 2009, 02:05:11 pm
Wrong, and has been wrong since 0.107.  Mame does use 3d acceleration, just not for game emulation.  Scaling res, scaling color depth, rotating screen image, overlay & artwork, scanlines, and other video stuff are all done in the 3d card now.

Well ok, but any direct3d/ddraw card should be able to to handle those, you dont need a beefy GPU for that, that was my point.

You don't need a beefy GPU; I didn't mean to imply that. 

But intel's current onboard video chip does slow down mame under most modern setups (LCD widescreen 19" or bigger, with mame's default settings).  AFAIK, as of xmas, only one onboard chip was strong enough to not be a slow down (until the res got 1080p class or bigger, that is, where no onboard was strong enough, but that's the same with some cards).

So it's not "any" direct3d chip, not even "any" directX 9.0 chip, anymore.  Sure, almost any card, and (unless it's changed) only one onboard chip, at most resolutions, won't make a difference.  I know, lots of qualifiers, but that's the point.

Quote
Its not like Dreamcast, N64, PSX or PS2 emulation, where your GPU is likely to be a bottleneck.

True 'dat.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: savj14 on March 18, 2009, 04:19:51 pm
Would any of these bundles be good for overclocking and making a nice MAME macine?

http://www.directron.com/spring-motherboard-combo-6.html (http://www.directron.com/spring-motherboard-combo-6.html)

http://www.directron.com/holidaycombo2.html (http://www.directron.com/holidaycombo2.html)

http://www.directron.com/holidaycombo8.html (http://www.directron.com/holidaycombo8.html)

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Silverwind on March 18, 2009, 11:46:01 pm
Upgrade arrived!
Core voltage is 1.280v.

(http://valid.canardpc.com/cache/screenshot/530032.png)
http://valid.canardpc.com/show_oc.php?id=530032
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Iron Maiden on March 19, 2009, 12:58:38 am
Hey peoples. I got myself a couple of goodies for my new MAME rig..

Core 2 Duo E8400
Gigabyte GA-EP35-DS3R rev2.1
Gskill 2 Gig 800Mhz (might get 2 gig of 1066Mhz cuz I stole this from my main PC)
8500GT PCIe

My question is 1: will the 8500GT be ok? It should be right? I'll overclock the CPU to 4GHz so...? And 2: is 800Mhz ram ok cuz I'll just try and keep it at stock speed so as not to disrupt the overclock.  My aim is to play all the MAME games that work at the moment..
Cheers
Steve

PS Great thread BTW  :applaud:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 19, 2009, 04:49:47 am
Would any of these bundles be good for overclocking and making a nice MAME macine?

Not really, almost any system can be overclocked to some degree, but to get a good overclock you need to get the basics right, that means a good motherboard, CPU, RAM and heatsink.

If your shopping a Directron I suggest the following:

Intel Core 2 Duo E7400 (http://www.directron.com/bx80571e7400.html)
Cooler Master Hyper 212 (http://www.directron.com/rrcchlb12gp.html)
Gigabyte GA-P45-DS3L motherboard  (http://www.directron.com/gaep45ds3l.html)
Corsair DDR2-800 2x1gb kit. (http://www.directron.com/twin2x20486400.html)

Total $297 less $13 mail in rebate on the ram brings you to $284, not as cheap as any of the combos but a better base for overclocking. You can use the old X300 you talked about in your earlier post for graphics, it should do the trick for MAME, but probably isn't Vista ready.


Upgrade arrived!
Core voltage is 1.280v.

Very nice Volts, and great overclock too, probably has a more to give with a little more voltage.  :applaud: :cheers:
I've really got to replace my old engineering sample C0 stepping E8500, it's likes the volts a little to much and I'd really want to be at 4.5ghz+ stable at sane voltage on a day to day basis.

Hey peoples. I got myself a couple of goodies for my new MAME rig..

Core 2 Duo E8400
Gigabyte GA-EP35-DS3R rev2.1
Gskill 2 Gig 800Mhz (might get 2 gig of 1066Mhz cuz I stole this from my main PC)
8500GT PCIe

My question is 1: will the 8500GT be ok? It should be right? I'll overclock the CPU to 4GHz so...? And 2: is 800Mhz ram ok cuz I'll just try and keep it at stock speed so as not to disrupt the overclock.  My aim is to play all the MAME games that work at the moment..

1) The 8500GT will run MAME no issues.

2) The DDR3-800 ram will be an issue unless you want to overclock it too, to get your E8400 with it's 9x multiplier to 4ghz you'll need to run a FSB of 445Mhz, which mean your RAM will end up running at 890mhz or DDR2-890, so I'd suggest the getting the DDR2-1066 ram, that way you don't have to run your ram out of spec to get to 4ghz and it also mean you can look at running a 500Mhz FSB with the CPU multiplier at 8x to gain a some more FSB preformance.

What heatsink are you planning on running ?


Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Iron Maiden on March 19, 2009, 05:12:10 am
Hey peoples. I got myself a couple of goodies for my new MAME rig..

Core 2 Duo E8400
Gigabyte GA-EP35-DS3R rev2.1
Gskill 2 Gig 800Mhz (might get 2 gig of 1066Mhz cuz I stole this from my main PC)
8500GT PCIe

My question is 1: will the 8500GT be ok? It should be right? I'll overclock the CPU to 4GHz so...? And 2: is 800Mhz ram ok cuz I'll just try and keep it at stock speed so as not to disrupt the overclock.  My aim is to play all the MAME games that work at the moment..

1) The 8500GT will run MAME no issues.

2) The DDR3-800 ram will be an issue unless you want to overclock it too, to get your E8400 with it's 9x multiplier to 4ghz you'll need to run a FSB of 445Mhz, which mean your RAM will end up running at 890mhz or DDR2-890, so I'd suggest the getting the DDR2-1066 ram, that way you don't have to run your ram out of spec to get to 4ghz and it also mean you can look at running a 500Mhz FSB with the CPU multiplier at 8x to gain a some more FSB preformance.

What heatsink are you planning on running ?


[/quote]
Thanks very much for your help.. Yes, I was unsure about the overclocking of the RAM as this Asus MB that I have as my main PC ( Asus P5N32-e SLI) allows me to run the RAM and the CPU at independent speeds. I've got my Q6600 Quad running at 4Ghz and I can run the Gskill 800 at 800Mhz... So this Gigabyte board is different in that respect? I have tried this Gskill ram right up to 910 but it does have the occasional lockup with it that high.. 890 is still a little high so I  just leave it at 800 and have the timings at 4,4,3,5... Anywho....I'll look at some 1066Mhz stuff then.. Any brand will do seeing as I wont be overclocking it yeah? I was thinking of running a Cooler Master Geminii S Universal CPU Cooler. What do you think? At the moment I have the stock intel cooler from my Quad core bolted on.. Its a little bigger than a stock intel Dual Core cooler and has a bigger copper footprint, but as yet I havn't fired anything up cuz I'm waiting on the 8500GT...
Again, cheers for the help.  I've been pointing many newbies to this thread... I think it should be put up on a pedestal.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 19, 2009, 06:49:29 am

Thanks very much for your help.. Yes, I was unsure about the overclocking of the RAM as this Asus MB that I have as my main PC ( Asus P5N32-e SLI) allows me to run the RAM and the CPU at independent speeds. I've got my Q6600 Quad running at 4Ghz and I can run the Gskill 800 at 800Mhz... So this Gigabyte board is different in that respect? I have tried this Gskill ram right up to 910 but it does have the occasional lockup with it that high.. 890 is still a little high so I  just leave it at 800 and have the timings at 4,4,3,5... Anywho....I'll look at some 1066Mhz stuff then.. Any brand will do seeing as I wont be overclocking it yeah? I was thinking of running a Cooler Master Geminii S Universal CPU Cooler. What do you think? At the moment I have the stock intel cooler from my Quad core bolted on.. Its a little bigger than a stock intel Dual Core cooler and has a bigger copper footprint, but as yet I havn't fired anything up cuz I'm waiting on the 8500GT...
Again, cheers for the help.  I've been pointing many newbies to this thread... I think it should be put up on a pedestal.

The Intel 3 & 4 series chipsets have a minium FSB to RAM frequency RATIO of 1:1, so you can't run your RAM at a slower rate than you FSB. You may well find you can get more out of your memory on the Intel chipset, the Nvidia 680i SLI chipset has the single worst memory controller in the history of computing in my books, any motherboard with that chipset should have come bundled with memory that had been individually tested for compatibly with that board.

Any brand of DDR2-1066 will do, but I suggest sticking to a good brand name or memory modules on compatible list for the motherboard.

The Cooler Master Geminii series coolers are great for making quiet systems, but aren't that great for overclocking, a CPU will run about 5+ Deg C hotter with a Geminii S cooling it, than the same CPU cooled with a Sunbeam Core Contact  Freezer for example.

Yeah, the old Pentium-D style copper cored coolers that came with the early Core 2 Duo's are much better, than the shortened all aluminum heasinks you get with the later Core 2 Duos, but I wouldn't recommend using one to cool a heavily overclocked CPU.

No Problem. Yeah this thread has taken on a like of it own, I remember posting it and thinking I'd be lucky if it got a couple of hundred views and a dozen replies at best before it dropped off the first page and was forgotten, but now some 36000+ views and 380 odd posts later it still going strong.




Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Iron Maiden on March 20, 2009, 08:21:36 pm

Thanks very much for your help.. Yes, I was unsure about the overclocking of the RAM as this Asus MB that I have as my main PC ( Asus P5N32-e SLI) allows me to run the RAM and the CPU at independent speeds. I've got my Q6600 Quad running at 4Ghz and I can run the Gskill 800 at 800Mhz... So this Gigabyte board is different in that respect? I have tried this Gskill ram right up to 910 but it does have the occasional lockup with it that high.. 890 is still a little high so I  just leave it at 800 and have the timings at 4,4,3,5... Anywho....I'll look at some 1066Mhz stuff then.. Any brand will do seeing as I wont be overclocking it yeah? I was thinking of running a Cooler Master Geminii S Universal CPU Cooler. What do you think? At the moment I have the stock intel cooler from my Quad core bolted on.. Its a little bigger than a stock intel Dual Core cooler and has a bigger copper footprint, but as yet I havn't fired anything up cuz I'm waiting on the 8500GT...
Again, cheers for the help.  I've been pointing many newbies to this thread... I think it should be put up on a pedestal.


The Intel 3 & 4 series chipsets have a minium FSB to RAM frequency RATIO of 1:1, so you can't run your RAM at a slower rate than you FSB. You may well find you can get more out of your memory on the Intel chipset, the Nvidia 680i SLI chipset has the single worst memory controller in the history of computing in my books, any motherboard with that chipset should have come bundled with memory that had been individually tested for compatibly with that board.

Any brand of DDR2-1066 will do, but I suggest sticking to a good brand name or memory modules on compatible list for the motherboard.

The Cooler Master Geminii series coolers are great for making quiet systems, but aren't that great for overclocking, a CPU will run about 5+ Deg C hotter with a Geminii S cooling it, than the same CPU cooled with a Sunbeam Core Contact  Freezer for example.

Yeah, the old Pentium-D style copper cored coolers that came with the early Core 2 Duo's are much better, than the shortened all aluminum heasinks you get with the later Core 2 Duos, but I wouldn't recommend using one to cool a heavily overclocked CPU.

No Problem. Yeah this thread has taken on a like of it own, I remember posting it and thinking I'd be lucky if it got a couple of hundred views and a dozen replies at best before it dropped off the first page and was forgotten, but now some 36000+ views and 380 odd posts later it still going strong.




Mate, I have to say..Thank you for all your help with my questions and with this whole  entire thread. As I've said before I don't think there is a place on the net with this much information dealing with the system specs required for a good MAME rig. You showed me the ingredients that I needed to make my MAME machine a winner and to put a huge smile on mine and my 7 year old sons face.
  My 8500GT came in the mail yesterday.. It was the last peice of the puzzle that I needed before I could fire this thing up.. I ripped the box open and shoved the card into the PCIe slot, as it was all ready and waiting for the card to come.
  I fired it up and bang, it came to life... I went straight to the Bios to check on everything and found that the board had been running at 2.8Ghz before me...So I know its had a nice easy life. Everything had been found, and was running as spec.. After setting it to 3Ghz I rebooted..
  I then installed Windows Vista 64.. The OS of choice ( until windows 7 is good to go. The benchmarks I've seen from windows 7 shows a 50 to 70% increase in speed over Vista and a 150% over XP with rock solid stability.. And thats just a beta..Anyway).. after the install was complete, I did a basic setup of windows to set it up the way I like it, then installed the video, chipset and audio drivers. Then opened up Everest to see what I had under the bonnet....VERY NICE, VERY NICE INDEED...
  Then, onto MAME... I run MAMEUIFX64 as my MAME of choice. Now at this point I have to say that my e8400 is not overclocked.. it's still running at the stock 3Ghz..The next fastest machine that I've played MAME games up until now is on may main PC which is a q6600 quad running at 2.4Ghz (but sometimes overclocked to 4Ghz with watercooling)..I can say right away that this dual core running at 3Ghz with its 6meg of L2 cache is faster than my q6600 running at 3Ghz.. I put this down to the lack of L2 cache.. 2meg..
  I started out playing MAME games over 10 years ago with a celeron 300Mhz overcloed to 450MHZ (arr the good ol days). a Riva TNT2 Ultra card, and 512meg of sdram. Games were choppy, and chads didn't exist...For the fact that the consumer didn't have access to technology to run chds yet...
  Iv'e spent alot of money over the years, upgrading and upgrading.. Hoping that "that next upgrade" will see me playing all the games available to us. 1.3Ghz Durons, 1.8Ghz Seprons, 3 Ghz P4s etc etc etc... UNTIL NOW
  On this day, I can say that I can play the larrgest amount of MAME games than I ever been able to play before.. and I know with overclocking I have even more overhead to play with.
Mate, you are a legend.. If I see you in the street.. I'll buy you a beer. These are good times indeed.
My Machine:
CPU: Intel E8400 Core 2 Duo
Motherboard: Gigabyte GA-EP35-DS3R Motherboard rev2.1 LGA 775
RAM: 2G Gskill DDR2 800Mhz (but may upgrade to some 1066Mhz peices as these may not suit an overclock)
Video card: nVidia 8500GT PCIe
Power Supply: Codegen 550w
CPU heatsink: Stock Intel Quad core. (they are larger than the stock intel dual core items..)But this will change with overclocking as this heatsink my not be good enough.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Iron Maiden on March 21, 2009, 02:26:20 am
Welp, with a quick attempt at an overclock 4GHz seems to be out of the reach of the RAM as the only option is to run 800Mhz at 890Mhz and I kept getting blue screens on load up of windows.. The PC boots, but won't load windows.... Backing the FSB off a little 3.7Ghz is running quite easily.. 3.7Ghz over the stock 3Ghz makes a world of difference to games like Sanfran Rush and Guantlet.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on March 23, 2009, 05:04:08 am
What multiplier are you using?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Iron Maiden on March 23, 2009, 05:37:01 am
2x for the ram and 9x for the cpu. 2 x 445Mhz gives you 890 for the ram and 9 x 445 gives you the 4Ghz for the CPU. 2x is the lowest setting I can choose for ram so i think I'll need 1066Mhz ram to do the job right.. 890 for 800Mhz ram is to unstable..
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Iron Maiden on March 23, 2009, 09:45:51 am
@Taz-nz. Whats your opinion of these two CPU coolers. I'm still in the market for one.

Cooler Master Eclipse
http://www.virtual-hideout.net/reviews/Coolermaster_Eclipse/index.shtml

and

ThermalRight Ultra 120 eXtreme
http://www.frostytech.com/articleview.cfm?articleID=2244
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Silverwind on March 23, 2009, 12:14:40 pm
@Taz-nz. Whats your opinion of these two CPU coolers. I'm still in the market for one.

Cooler Master Eclipse
http://www.virtual-hideout.net/reviews/Coolermaster_Eclipse/index.shtml

and

ThermalRight Ultra 120 eXtreme
http://www.frostytech.com/articleview.cfm?articleID=2244

I hear a lot of good things about thermalright 120's.  Very popular HSF.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Silverwind on March 23, 2009, 01:43:26 pm

Very nice Volts, and great overclock too, probably has a more to give with a little more voltage.  :applaud: :cheers:
I've really got to replace my old engineering sample C0 stepping E8500, it's likes the volts a little to much and I'd really want to be at 4.5ghz+ stable at sane voltage on a day to day basis.


Forgot to list my parts.

Gigabyte GA-G33M-DS2R mATX motherboard
E0 E8500
Swiftech MCX159-CU Northbridge HSF
Alpha PRE9060T CPU HSF  (It is one heavy sucker) http://www.frozencpu.com/products/1398/cpu-alp-05/Alpha_PRE9060T_-_Socket_775.html (http://www.frozencpu.com/products/1398/cpu-alp-05/Alpha_PRE9060T_-_Socket_775.html)
2 x 2GB Mushkin ascent ram
corsair HX620

I am using an old school case.. Inwin Q500 full tower, bought originally for a celeron 300A. :)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 23, 2009, 09:09:57 pm
@Taz-nz. Whats your opinion of these two CPU coolers. I'm still in the market for one.

Cooler Master Eclipse
http://www.virtual-hideout.net/reviews/Coolermaster_Eclipse/index.shtml

and

ThermalRight Ultra 120 eXtreme
http://www.frostytech.com/articleview.cfm?articleID=2244

I've running a Thermalright Ultra 120 extreme myself, so you can guess which one I recommend, but I suggest getting the newer Thermalright True Black (http://www.crazypc.com/products/true-black-50984.html) version, if for no other reason than that it comes with two sets of fan mounts, so you can run a dual fan push pull setup, saves running a single noisy High RPM fan.

Forgot to list my parts.

Gigabyte GA-G33M-DS2R mATX motherboard
E0 E8500
Swiftech MCX159-CU Northbridge HSF
Alpha PRE9060T CPU HSF  (It is one heavy sucker) http://www.frozencpu.com/products/1398/cpu-alp-05/Alpha_PRE9060T_-_Socket_775.html (http://www.frozencpu.com/products/1398/cpu-alp-05/Alpha_PRE9060T_-_Socket_775.html)
2 x 2GB Mushkin ascent ram
corsair HX620


If your still running the intergrated graphics your doing well, from all accounts I've seen the intergrated graphics normally cries blood murder somewhere in the mid four hundred FSB range, and going my your clock speed your running a 450mhz FSB, so your probably almost at the point where you'll need a standalone graphics card to go any faster. Still a great overclock and really nice volts.

Hows your heatsink hold up under a burnin test like orthos ?, while MAME isn't as good at heating up your CPU as Orthos and alike, there are a number of ROM that will happily pin both cores to a 100%, so you need good cooling to make sure the system is stable in MAME and not just on the desktop. Your low volts are possibly your saving grace on this one, but I'd be interested to know what temps you are getting.

I am using an old school case.. Inwin Q500 full tower, bought originally for a celeron 300A. :)

Celeron 300A now that's old school overclocking, my mates still runs his old 300A overclocked to 450Mhz as a internet gateway and print server, The system is on it's second or third power supply and about it's forth hard drive but the CPU it just keeps going and going.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Silverwind on March 24, 2009, 10:44:01 pm
If your still running the intergrated graphics your doing well, from all accounts I've seen the intergrated graphics normally cries blood murder somewhere in the mid four hundred FSB range, and going my your clock speed your running a 450mhz FSB, so your probably almost at the point where you'll need a standalone graphics card to go any faster. Still a great overclock and really nice volts.

Hows your heatsink hold up under a burnin test like orthos ?, while MAME isn't as good at heating up your CPU as Orthos and alike, there are a number of ROM that will happily pin both cores to a 100%, so you need good cooling to make sure the system is stable in MAME and not just on the desktop. Your low volts are possibly your saving grace on this one, but I'd be interested to know what temps you are getting.


For graphics I currently have an ATI 1800xt 512mb.

IDLE is normally around 27C depending on ambient temp.  After a couple hours of Team Fortress 2 it is about 43C.  Orthos gets it up to about 50C, higher if it is hot in the room.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Iron Maiden on March 30, 2009, 05:23:40 am
Welp, with a quick attempt at an overclock 4GHz seems to be out of the reach of the RAM as the only option is to run 800Mhz at 890Mhz and I kept getting blue screens on load up of windows.. The PC boots, but won't load windows.... Backing the FSB off a little 3.7Ghz is running quite easily.. 3.7Ghz over the stock 3Ghz makes a world of difference to games like Sanfran Rush and Guantlet.
Soooo I ended up buying some Team Xtreem DDR2 PC-8500 1066 5-5-5-15 2x1Gb RAM and the 1066Mhz speed did the trick.. Even on the stock quad core intel cooler I acheived 4Ghz first pop. It seems that because of the limits of the multplier for the RAM with this Motherboard, running 800Mhz at the lowest speed of 890Mhz (with 2x multiplied FSB ) was just to much for the ram... But the CPU runs fine at 4Ghz and probably will go higher... Now.. Just for a cooler... What do you think of this one  IceAge 90 CPU Cooler ?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on March 30, 2009, 06:45:55 am
Soooo I ended up buying some Team Xtreem DDR2 PC-8500 1066 5-5-5-15 2x1Gb RAM and the 1066Mhz speed did the trick.. Even on the stock quad core intel cooler I acheived 4Ghz first pop. It seems that because of the limits of the multplier for the RAM with this Motherboard, running 800Mhz at the lowest speed of 890Mhz (with 2x multiplied FSB ) was just to much for the ram... But the CPU runs fine at 4Ghz and probably will go higher... Now.. Just for a cooler... What do you think of this one  IceAge 90 CPU Cooler ?

Nice RAM, I find overclocking RAM is far more hit and miss than overclocking CPUs, I've seen cheap DDR2-800 hit DDR2-1200 with only a little extra voltage, but I've also seen expensive DDR2-1066 kits that called it quits at DDR2-1100, it's why I prefer to avoid overclocking memory if I can, and with current memory prices there is little reason not to buy the fast stuff and keep life simple.

Welcome to the 4ghz club, just watch your temps until you replace the stock heatsink, hate to see you cook your CPU.

As for what I think of the Iceage 90 cooler, if have a space restriction that limits you to a 92mm FAN heatsink then it's probably ok, otherwise I'd say it's so so, the larger Iceage 120 result are 3 deg hotter than a Sunbeam Core contact freezer, so if you scale the cooling preformance down to the 92mm fan and heatsink and allow foronly 3 heatpipes vs the larger versions 4, your going to see a noticable drop in cooling preformance compared to a larger solution like the core contact freezer. It will still be better than the stock item your using now, but I prefer to keep CPU tempatures as low as possible when overclocking, it gives you a larger safety margin for loss of heatsink preformance due to dust, hot days, etc.



Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Iron Maiden on March 30, 2009, 09:39:46 am

Nice RAM, I find overclocking RAM is far more hit and miss than overclocking CPUs, I've seen cheap DDR2-800 hit DDR2-1200 with only a little extra voltage, but I've also seen expensive DDR2-1066 kits that called it quits at DDR2-1100, it's why I prefer to avoid overclocking memory if I can, and with current memory prices there is little reason not to buy the fast stuff and keep life simple.

Yes, thats my thoughts exactly. And if you look at overclocked RAM the performance vs stability is not worth the hastle..

Welcome to the 4ghz club, just watch your temps until you replace the stock heatsink, hate to see you cook your CPU.

Cheers mate. It's good to be up here  :) .I'd hate to see me cook it also... I've read that 65 would be the max limit yeah? Would that be for each core reading, or the overal CPU (in everest )


As for what I think of the Iceage 90 cooler, if have a space restriction that limits you to a 92mm FAN heatsink then it's probably ok, otherwise I'd say it's so so, the larger Iceage 120 result are 3 deg hotter than a Sunbeam Core contact freezer, so if you scale the cooling preformance down to the 92mm fan and heatsink and allow foronly 3 heatpipes vs the larger versions 4, your going to see a noticable drop in cooling preformance compared to a larger solution like the core contact freezer. It will still be better than the stock item your using now, but I prefer to keep CPU tempatures as low as possible when overclocking, it gives you a larger safety margin for loss of heatsink preformance due to dust, hot days, etc.

Well lucky I didn't win the auction on ebay then. On reading your reply, Ive decided to pull my Thermaltake Bigwater 735 cooling system out of my main PC (Q6600) and do swapsies. I haven't overclocked this old girl for a month or more so this 3 radiator system (ya need multi radiators with these quads.. especially at 1.7v) needs to be put to good use. The intel fan thats on the e8400 is the stock one from this q6600 so it gets to go back to its daddy.

I should see some pretty high numbers in doing it this way I think. Especially now with the 1066Mhz RAM.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Todd H on March 31, 2009, 02:10:29 pm
Which would be better...Vista 64 or XP 64? I have Vista 64 already installed but I can get a copy of XP 64 for free (one of the perks of being a MCT). I have yet to install MAME and the other game software as I haven't yet mounted my monitor. Would there be a speed difference between the two?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on March 31, 2009, 03:12:17 pm
The biggest difference is the windows shell. Speed is pretty much the same, but you can completely hide the xp shell and replace it with the frontend of your choice. You can't really do that with vista.
I'd use either this post: http://forums.maximusarcade.com/viewtopic.php?f=1&t=506 or mala instant sheller.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: massive88 on March 31, 2009, 05:18:32 pm
Which would be better...Vista 64 or XP 64? I have Vista 64 already installed but I can get a copy of XP 64 for free (one of the perks of being a MCT). I have yet to install MAME and the other game software as I haven't yet mounted my monitor. Would there be a speed difference between the two?

Personally I noticed no speed difference in Mame between XP64 and Vista64 in my benchmarking.  If you already have one and are happy with it, I would just stay with it.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Iron Maiden on March 31, 2009, 07:32:15 pm
Which would be better...Vista 64 or XP 64? I have Vista 64 already installed but I can get a copy of XP 64 for free (one of the perks of being a MCT). I have yet to install MAME and the other game software as I haven't yet mounted my monitor. Would there be a speed difference between the two?

About the biggest thing you'll find is the lack of driver support for XP 64. I went from XP 32 to XP 64 (for one day) then on to Vista 64.. It's the drivers that let you down with XP. No drivers for my SOund Blaster Live sound card was the biggy, but then there were others...

XP is a smaller OS and will take less space on your HD. It loads faster, and uses less ram to operate. If you have 2 gig of RAM vista will put some of itself into your ram, and the other part into the swap file.. If you have 4 gig, vista will load all of itself into ram (for you as a courtesy from Microsoft) and use 1.6gig straight up. Speed wise in MAME, pretty much the same... I just put my MAME emulator .exe in the start folder and when I turn on the cab at the wall the PC turns on and auto loads into MAMEUIFX64 and there is my list of games. Sure I can see it's windows but it's only for 10 seconds or so..

They each have their pros and cons. If it's free for you, I'd try XP and see if you have any issues... Then hold out for Windows 7. If your stuck, try Vista. 8).
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Ortizimo on April 08, 2009, 04:50:44 pm
Ok, as I see, there are no AVGA 64bit drivers so what can I do if I'm running xp64? Can I run XP32 and just run MAME64? Please clarify...if ne1 has the xp64 AVGA drivers please contact me...thnx!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on April 08, 2009, 07:54:01 pm
Man, I have been trying for ever to get win 7. I really wanna see what my 4ghz monster can do with it. I really don't wanna go for an old torrent. I do have a serial for the x64 ultimate thought that microsoft sent me, but they just do not host the files any longer.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on April 08, 2009, 08:25:31 pm
Ok, as I see, there are no AVGA 64bit drivers so what can I do if I'm running xp64? Can I run XP32 and just run MAME64? Please clarify...if ne1 has the xp64 AVGA drivers please contact me...thnx!

The Arcade VGA is basically a ATI radeon 7000 or 9200 graphics card with a custom BIOS, and tweaked drivers. ATI only supplies 64bit drivers for the Radeon 9500 and newer graphics chips, so your probably out of luck.
 
No you can't run MAME64 on 32bit XP , 64bit apps can only be run on a 64bit OS.

Try contacting Andy at Ultimarc andy@ultimarc.com just incase he has some 64bit drivers tucked away. 

There are Vista 64bit Drivers for the Arcade VGA2 which you can download here: www.ultimarc.com/avga2_vista.zip (http://www.ultimarc.com/avga2_vista.zip)

If you can't get 64bit drivers you have three options:
- Stick to 32bit windows and MAME32. (not really a solution, more like putting ones head in the sand)
- Sell your old Arcade VGA to someone here that's happy to stick to the older MAME versions and replace it with a newer Arcade VGA2 (and run Vista 64bit if needed)
- Buy a cheap entry level ATI graphics card that is atleast a radeon 9500 or newer which has 64bit driver support, and run Soft-15Khz (http://files.arianchen.de/soft15khz/soft15khz.zip) to get the required screen resolutions & refresh rates for your arcade monitor.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on April 08, 2009, 11:51:42 pm
Man, I have been trying for ever to get win 7. I really wanna see what my 4ghz monster can do with it. I really don't wanna go for an old torrent. I do have a serial for the x64 ultimate thought that microsoft sent me, but they just do not host the files any longer.

Microsoft closed the public beta and took down the file about a while back, Windows 7 RC1 will be out in a few more weeks. If you can't find someone local with a copy you can burn , your ony choices are slow torrents, or a News Group server with 200 day binary retention.

Note it is a beta and is a little broken here and there, and if you have an Nvidia graphics card the beta drivers were totally broken last time i looked, so I'd probably wait until Microsoft post the Release Candidate and then grab a copy of that.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DiskTwo on June 08, 2009, 05:21:25 pm
I currently have an Intel Pentium D 940 sl94q 3.2 ghz CPU. Could anyone advice me on weather or not this is a decent chip to be able to Overclock to 4.0 with the correct cooling? To be able to play things like Gauntlet legends, and Blitz properly like the other chips. And possibly suggest a good Motherboard to go with it?

Thanks for any advice.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: massive88 on June 08, 2009, 06:02:28 pm
It wont matter with a Pentium D.

The Core 2 Duo is much faster for Mame per MHZ, that is the processor you need at 4ghz to run those games.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DiskTwo on June 08, 2009, 07:12:00 pm
ah ok thanks ill ditch this one and get a core 2 duo
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Ummon on June 08, 2009, 10:45:08 pm
Yeah, just like that, huh?
ah ok thanks ill ditch this one and get a core 2 duo

Yeah, just like that, huh?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: retrometro on June 17, 2009, 12:12:01 am
Does anyone have recent numbers with i7's?

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: ivwshane on June 17, 2009, 01:55:34 am
Does anyone have recent numbers with i7's?



Give me a couple of weeks >:D
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on June 17, 2009, 06:46:34 am
Yeah I just built an i7 machine with 12 gb ram and 4 tb hdd space. The payment will be to let me bench out mame. I wish there was a batch util I could run.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: massive88 on June 17, 2009, 10:11:07 am
Yeah I just built an i7 machine with 12 gb ram and 4 tb hdd space. The payment will be to let me bench out mame. I wish there was a batch util I could run.

...Just make your own batch file, start it running and come back in a few hours.

Id post the one I used but Im not at home.

Edit:  Duh, the first post in this thread gives you the commands to test it against Taz's numbers.  Just copy and paste that string several times in a batch file, and test it on some demanding Roms.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: BASS! on June 17, 2009, 07:34:39 pm
Duhh, Yeah. Thanks man. I'll report back. This thing is a freaking beast. Its a 2.9 8core or 4 2core chip I cant tell, with water cooling and a geforce gtx 285. He even had me put dual blueray burners in the thing. Lets see what this puppy can do  ;D
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: KissMyWookie on June 25, 2009, 08:20:33 am
...
If you can't get 64bit drivers you have three options:
- Stick to 32bit windows and MAME32. (not really a solution, more like putting ones head in the sand)
- Sell your old Arcade VGA to someone here that's happy to stick to the older MAME versions and replace it with a newer Arcade VGA2 (and run Vista 64bit if needed)
- Buy a cheap entry level ATI graphics card that is atleast a radeon 9500 or newer which has 64bit driver support, and run Soft-15Khz (http://files.arianchen.de/soft15khz/soft15khz.zip) to get the required screen resolutions & refresh rates for your arcade monitor.

Unfortunately, Soft-15kHz does not work with Vista. So the closest option is to use XP 64-bit.
From what I've read, SailorSat said the same problem continues under Windows 7 too.

Steve
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Pete4321 on September 07, 2009, 05:43:06 pm
Can someone benchmark naomi  games. Are they playable at 4.0 Ghz??
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Neverending Project on September 18, 2009, 11:25:03 am
I'm looking for some tips on the following system (I have been pouring over the recommended setups here on the forums - thanks taz-nz and everyone!). I have never overclocked before, so my goal is to hit something as fast as I can but I don't need 4+ GHz. I also want to keep the costs down as much as possible, preferably under $400 if possible (although I don't see how that is possible considering Vista 64 is $100). I already have an HD.

COOLER MASTER Elite 330 RC-330-KKN1-GP Black SECC ATX Mid Tower Computer Case - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16811119115)$40
ENERMAX Tomahawk ETK405AST 405W ATX12V V2.2 AirGuard, Speed Guard and Safe Guard Power Supply - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16817194037)$45
GIGABYTE GA-EP45-UD3L LGA 775 Intel P45 ATX Intel Motherboard - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16813128372)$95
Intel Core2 Duo E7500 Wolfdale 2.93GHz LGA 775 65W Dual-Core Processor Model BX80571E7500 - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16819115056)$120
CORSAIR XMS2 2GB (2 x 1GB) 240-Pin DDR2 SDRAM DDR2 800 (PC2 6400) Dual Channel Kit Desktop Memory Model TWIN2X2048-6400 - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16820145590)$50
GIGABYTE GV-R435OC-512I Radeon HD 4350 512MB 64-bit GDDR2 PCI Express 2.0 x16 HDCP Ready CrossFire Supported Low Profile ... - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16814125251)$35
LITE-ON Black SATA DVD-ROM Drive Model iHDS118-04 - OEM (http://www.newegg.com/Product/Product.aspx?Item=N82E16827106276)$20
Sunbeam CR-CCTF 120 mm Core-Contact Freezer CPU Cooler W/TX-2 - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16835207004)$40
Microsoft Windows Vista Home Premium SP1 64-bit for System Builders - OEM (http://www.newegg.com/Product/Product.aspx?Item=N82E16832116488)$100
Total$545

Any tips for reducing costs? Can I just mount all the components on the inside of the arcade cabinet and forget the case, or will this adversely affect cooling? Yes, no.

Edit: Oh, and this will be for MAME only - no PC games or other emus. Kthanksbye.
Edit again: Just reread this previous post (http://forum.arcadecontrols.com/index.php?topic=72776.msg939961#msg939961) answering my question about the case (not necessary). Coolio.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on September 18, 2009, 03:22:23 pm
Can someone benchmark naomi  games. Are they playable at 4.0 Ghz??

Hah, ah no. Approx. 25% at 3.5Ghz.  RB's DRC for the SH4 should help but 100% full playability may only come when we transition to GPU assisted emulation.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: clok on September 21, 2009, 01:24:09 pm
I'm looking for some tips on the following system (I have been pouring over the recommended setups here on the forums - thanks taz-nz and everyone!). I have never overclocked before, so my goal is to hit something as fast as I can but I don't need 4+ GHz. I also want to keep the costs down as much as possible, preferably under $400 if possible (although I don't see how that is possible considering Vista 64 is $100). I already have an HD.

COOLER MASTER Elite 330 RC-330-KKN1-GP Black SECC ATX Mid Tower Computer Case - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16811119115)$40
ENERMAX Tomahawk ETK405AST 405W ATX12V V2.2 AirGuard, Speed Guard and Safe Guard Power Supply - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16817194037)$45
GIGABYTE GA-EP45-UD3L LGA 775 Intel P45 ATX Intel Motherboard - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16813128372)$95
Intel Core2 Duo E7500 Wolfdale 2.93GHz LGA 775 65W Dual-Core Processor Model BX80571E7500 - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16819115056)$120
CORSAIR XMS2 2GB (2 x 1GB) 240-Pin DDR2 SDRAM DDR2 800 (PC2 6400) Dual Channel Kit Desktop Memory Model TWIN2X2048-6400 - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16820145590)$50
GIGABYTE GV-R435OC-512I Radeon HD 4350 512MB 64-bit GDDR2 PCI Express 2.0 x16 HDCP Ready CrossFire Supported Low Profile ... - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16814125251)$35
LITE-ON Black SATA DVD-ROM Drive Model iHDS118-04 - OEM (http://www.newegg.com/Product/Product.aspx?Item=N82E16827106276)$20
Sunbeam CR-CCTF 120 mm Core-Contact Freezer CPU Cooler W/TX-2 - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16835207004)$40
Microsoft Windows Vista Home Premium SP1 64-bit for System Builders - OEM (http://www.newegg.com/Product/Product.aspx?Item=N82E16832116488)$100
Total$545

Any tips for reducing costs? Can I just mount all the components on the inside of the arcade cabinet and forget the case, or will this adversely affect cooling? Yes, no.

Edit: Oh, and this will be for MAME only - no PC games or other emus. Kthanksbye.
Edit again: Just reread this previous post (http://forum.arcadecontrols.com/index.php?topic=72776.msg939961#msg939961) answering my question about the case (not necessary). Coolio.

PSU is a bit weak, I cant underestimate how important a good one is. I must admit you are working with a failry bare system (as in not a big video card sucking power) But I hate to say it. I just wouldnt go with anything less then a 500. Your system should use about 300watts (most OC's will take some voltage tweaking, and yess 300 watts is a bit high, but I would rather guess high then to low) so at 80% efficency thats 320 watts... you are right on the edge, so your PSU will be working at its 100% load (almost). I know most will do that just fine, and Enermax is a good enough PSU brand. I would guess my figures are worst case and that PSU would probebly last forever, but a few more watts would really give you a much more overhead.  I work and build systems (how I make my money) and PSU are one of the worst headaches to find, fix on unstable systems. Again, it looks like a nice build to me, looks like you are going rebate crazy (so price will be even better then your list when you get um all back). I have a E7500 but have yet to play with it, I do know the 8400 are wonderfull to OC and mine have been rocks. I build more "gameing" systems with 8400's then anything else and almost always get an OC of 4Ghz out of them with close to stock voltage (personal machine for gaming is runing 4.2 at stock (but its the excpetion, not the rule)).

Again, I think you are fine, but I would bump the PSU for peace of mind (but you may just be fine).  Really looks like you ahve done your research to me. Great Bang for Buck!!!!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Neverending Project on September 21, 2009, 02:02:38 pm
PSU is a bit weak, I cant underestimate how important a good one is. I must admit you are working with a failry bare system (as in not a big video card sucking power) But I hate to say it. I just wouldnt go with anything less then a 500. Your system should use about 300watts (most OC's will take some voltage tweaking, and yess 300 watts is a bit high, but I would rather guess high then to low) so at 80% efficency thats 320 watts... you are right on the edge, so your PSU will be working at its 100% load (almost). I know most will do that just fine, and Enermax is a good enough PSU brand. I would guess my figures are worst case and that PSU would probebly last forever, but a few more watts would really give you a much more overhead.  I work and build systems (how I make my money) and PSU are one of the worst headaches to find, fix on unstable systems. Again, it looks like a nice build to me, looks like you are going rebate crazy (so price will be even better then your list when you get um all back). I have a E7500 but have yet to play with it, I do know the 8400 are wonderfull to OC and mine have been rocks. I build more "gameing" systems with 8400's then anything else and almost always get an OC of 4Ghz out of them with close to stock voltage (personal machine for gaming is runing 4.2 at stock (but its the excpetion, not the rule)).

Again, I think you are fine, but I would bump the PSU for peace of mind (but you may just be fine).  Really looks like you ahve done your research to me. Great Bang for Buck!!!!

Excellent. Thanks for the response and advice. What would be the difference in a $32 RAM and the $50 RAM I listed above, in terms of overclocking? Like:
OCZ System Elite 2GB (2 x 1GB) 240-Pin DDR2 SDRAM DDR2 800 (PC2 6400) Dual Channel Kit Desktop Memory Model OCZ2SE8002GK - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16820227238) $32

Oh, and I seldom account for the rebates when I am pricing anything. They are such a pain to get and take so long that I usually don't even consider the rebated price when making my budget. Then when/if the rebate does come it's like free cash to me.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: clok on September 21, 2009, 02:38:24 pm
The cheaper stuff is older OCZ, i notice there is no warrenty info listed, possilby only throuhg OCZ on that stuff? Older OCZ memory is known to be fussy. That memory has older specs (lower voltage) so its possilbe it wont work in your board. It should but.... Its slower all around but for waht you are doping that shouldnt matter. I use gigbyte boards myslef for my peresonal machines(for OC and customer rigs, have had great luck). But I did have some OCZ memory (older stuff actually) that didnt work in one of my boards.  if you are looking to save a buck... great reviews and cheap.

http://www.newegg.com/Product/Product.aspx?Item=N82E16820148163
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Neverending Project on October 02, 2009, 01:52:30 am
I placed an order with Newegg for my shopping list above. Three longs days later I was like a kid in a candy store with all my new parts. I was hoping that this post would be about my benchmark results, but instead it was mid-assembly when I noticed that the CPU cooler was missing the mounting bracket for the 775 motherboard. And it wasn't until after I liberal applied the thermal paste that I realized this. I would have continued without the cooler for now until I could get a replacement delivered, but then I found a problem with the hard drive (I already had one) that I thought I was going to use.

So I'm stuck with a mostly assembled machine. Once I get the correct mounting bracket I am sure I will need to remove the old thermal paste and apply new again. Argh. The frustration begins.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: John IV [MameUI64] on October 02, 2009, 02:36:20 am
Recent bench pass completed at 3.5Ghz w/ some new games:

http://www.mameui.info/Bench.htm
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Neverending Project on October 06, 2009, 04:19:11 pm
After I got the hang of getting my BIOS settings correct, I was able to get my above setting to 3.6GHz with the stock cooler and almost NO tweaking even necessary.

I am having a hard time with the Core-Contact Freezer CPU cooler because I received it without the retaining ring. I have left four messages (on four separate days) with Sunbeam Tech at their "customer service" and RMA number so far without a single response. I can return the cooler to NewEgg and have a new one sent, but that is going to cost me another $8 for return shipping, which is an additional 20% of the original price. I just don't feel I should have to pay extra because they screwed up and sent me an incomplete package. So I installed the stock Intel cooler for now.

On OC news, all I did was set the frontside bus to 400MHz, multiplier to 9X, and voltage to 1.3725 I think. The trick I was having was in getting the memory setting correct. Once I got the memory to a 1:1 ratio and set at 400MHz with a multiplier at 2, all was golden. I ran Prime95 at 3.6GHz and hit temperatures in the mid to high 50's at full load. I think this is highly do-able, since in all practical use both cores will not be at 100% load for hours at a time.

Once I get the new cooler situated I will bump the multiplier to 10X and see if I can get 4GHz stable. That is my goal.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Neverending Project on October 26, 2009, 11:19:01 am
Well, I am almost there. I got my new cooler installed (thanks to NewEgg for stepping up and paying for the return shipping) and began incrementing the multiplier and voltage. I got 3.8GHz stable (400MHz 9.5X) but couldn't hit the magic 4GHz with a 10X multiplier. First shot it gave me a BSOD at boot. I bumped the voltage a little and got it to boot, but it gave a BSOD after a few minutes. Bumped the voltage a little more and got it to seem stable. Then I ran Prime, but it quit after about 15 minutes. One more bump to the voltage and got Prime to run for over 2 hours with both CPUs between 45-55C (according to CoreTemp). But alas, when I woke up this morning, it had crashed with a BSOD. The CPU voltage under load as reported by CPU-Z was 1.424V.

So my questions: should I bump the voltage a little more and go for the gold at a 400MHz 10X multiplier? Or try to get 500MHz at 8X stable? If it is the latter, I couldn't get it to even boot - so something was funky with either my voltage setting, memory timings, or both. If I try 500MHz, how do I set the memory timing (DDR2 PC6400)?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Neverending Project on October 27, 2009, 10:35:58 am
OK, I went ahead and bumped the voltage one more tick, and I am now a member of the 4GHz club.  :)

I tested last night for 10 hours using the Prime Blend test and the temperatures were very reasonable, and the voltage under load was at 1.454. I am going to call that good enough for me!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: isucamper on October 27, 2009, 12:20:39 pm
Tomorrow, this thread will officially be 2 years old.  Am I to believe that getting a core 2 duo and overclocking it to 4Ghz is still the only way to get max performance in MAME?  Has there been no advance in processor technology in the last 2 years for running a nearly single threaded application like MAME?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Neverending Project on October 28, 2009, 11:31:22 am
Tomorrow, this thread will officially be 2 years old.  Am I to believe that getting a core 2 duo and overclocking it to 4Ghz is still the only way to get max performance in MAME?  Has there been no advance in processor technology in the last 2 years for running a nearly single threaded application like MAME?

I can't speak for everyone, but I went with the Core 2 Duo because it is cheap. I bought an E7500, which came out at the beginning of the year. The introduction of the "i" line of chips helped drive down the price. For my 4GHz rig I spent under $400 (excluding OS) and was able to overclock it fairly easily. 2 years ago it would have cost twice that, and been significantly more difficult to overclock the same.

These days processors are all headed to more cores, and MAME is still being developed to take better advantage of this. Some might say MAME will never be optimized for many cores, while others think it is just a matter of time.

My guess is that in 2 more years we won't see anything with fewer than 4 cores in it, and MAME development work will be heading in that direction also (more than it is already).
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: mlalena on October 28, 2009, 07:32:19 pm
For MAME, the next best thing after the Core 2 Duo is the Core i7. While these are faster, they are MUCH more expensive. The chips are $500, the motherboards start at $250, they use triple channel RAM... Intel is just now coming out with the lower end i5 & i3 chips which will eventually phase out the Core 2 line by the end of 2010.

Since there is so much knowledge about overclocking the Core 2 Duo, I think it is still the way to go today. Note that Intel keeps improving these processors and model numbers have changed over the past 2 years. They are not the same exact chips and they overclock better than they did 2 years ago.

If you were to wait 6 months to a year, you will want to go with one of the i5 processors. Right now, they are too new for me. The chips themselves might not be expensive but motherboard costs are higher. If you want to look at the i5, check out this link: http://www.tomshardware.com/reviews/core-i5-750-overclock,2438.html (http://www.tomshardware.com/reviews/core-i5-750-overclock,2438.html)

Like the previous poster, I got to 4GHz with an E8500 very easily and spent about $400 for the whole system after rebates. I could probably push to 4.4GHz, but right now I don't have a reason to. I'm only running the CPU .00625V above stock and all the MAME games that I play run fine. What I really need is a good DirectX 10 video card for SF IV for PC. I have a crap video card (MAME doesn't care) and with everything turned off I only get 30 FPS (15 FPS with everything maxed out).
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on October 29, 2009, 02:20:01 pm
For MAME, the next best thing after the Core 2 Duo is the Core i7. While these are faster, they are MUCH more expensive. The chips are $500, the motherboards start at $250, they use triple channel RAM... Intel is just now coming out with the lower end i5 & i3 chips which will eventually phase out the Core 2 line by the end of 2010.

Just small correction:
Core i7 9xx series is triple channel,
Core i7 8xx & Core i5 are double channel. 
Xeons based on the i7 9xx sersies can do either triple or double channel (or if you eff up the memory stick matching, single or a mix of double and single).

And yes, the triple change MBs run in the $200 range, but the double channel i5/i7 8xx MBs are cheaper (betwween $100 & $200).


I'm looking at getting the i7 860 as a Chrismas present to myself, ATM.  Even if it runs mame about the same speed as a Core 2 @ same Hz (based on one poster's i7 920 benchmarks), the i5/i7 will compile faster, the new i7 8xx/i5 7xx have better "turbo" than the i7 9xx.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: mlalena on October 29, 2009, 07:26:05 pm
Sorry, didn't mean to imply that the i5 was also triple channel.

While I wont bother going i7 for MAME until there are much newer games that demand it (latest Golden Tee would be cool), I would love to have one for work - also for the faster compile times.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: u_rebelscum on October 30, 2009, 01:47:30 pm
the Core i7 ... use triple channel RAM...
Sorry, didn't mean to imply that the i5 was also triple channel.

Err, I was trying to say that some i7's are not triple channel also, and share the same (cheaper) MBs as i5s.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Expressline99 on November 15, 2009, 12:41:26 pm
Anyone have some input on which motherboard to use with c2d 4ghz setup? Was thinking a Asus P5Q version.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: J.Max on November 16, 2009, 11:19:42 am
Tomorrow, this thread will officially be 2 years old.  Am I to believe that getting a core 2 duo and overclocking it to 4Ghz is still the only way to get max performance in MAME?  Has there been no advance in processor technology in the last 2 years for running a nearly single threaded application like MAME?

Well, there's the E8500 and E8600...

Anyone tried OCing an E8600?  Just wondering if it can get past 4 Ghz, since it starts at 3.33 anyway.

EDIT: This topic should really be stickied.  It seems to come up a lot.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DillonFoulds on November 21, 2009, 03:19:37 am
@Neverending Project: I'm debating dropping the coin on an e7500 for my cab this xmas. How does your cab handle the gauntlets, and how much ram do you have in your machine?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Neverending Project on November 22, 2009, 01:07:50 am
@Neverending Project: I'm debating dropping the coin on an e7500 for my cab this xmas. How does your cab handle the gauntlets, and how much ram do you have in your machine?

I have 2GB RAM, and it handles all the Gauntlets fine. I can play SF Rush too. And on my previous 1.8GHz Core 2 Duo games like Cruisin USA and Cruisin World would stutter - now they are great.

I hit 3.6GHz pretty easily with the stock Intel cooler, but this wasn't quite good enough for these games. It wasn't until I put on the Core Contact cooler and pushed it to 4GHz that they stopped stuttering. And I had to set it to a slightly higher voltage to hit 4GHz - but now it is very stable. And I don't really know what I am doing, so there may be a way to get the voltage lower. It works great for me, and I am happy.

Edit: Make sure you make the jump to a 64-bit OS and recompile MAME. It will give you a 10% boost, or more.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DillonFoulds on November 22, 2009, 02:56:23 am
recompile mame? Isn't there a 64bit version on mamedev?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Silly Burrito on December 07, 2009, 06:21:50 pm
So what would currently be the easiest chip to overclock and hit 4Ghz? The E8400 seems to be the biggest bang for the buck chip, but if the E7500 can do the same with the same type of cooler, is there any reason to spend the extra $50?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Expressline99 on December 08, 2009, 04:48:18 pm
Well I'm about to setup my e6300 (wolfdale 2.8ghz)with a coolermaster V8 to see if I can get 4ghz out of it. Will be my first OC'ing experience.
Should be fun. Will report setup of course.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Hyperfan on December 08, 2009, 05:56:26 pm
Been reading this but im a bit confused.

Im looking to build a new mame machine. I was going to get this cpu  Intel Core i5 750 2.66GHz Socket LGA1156 8MB L3 Cache

Is this a good move or should i get a duel core?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DillonFoulds on December 08, 2009, 06:42:22 pm
@ihmedia: benchmarks are your best bet. Tom's Hardware Guide (http://www.tomshardware.com/charts/2009-desktop-cpu-charts/3DMark-Vantage-1.0.2,1396.html) will be an invaluable resource to you. In the List i linked, find your CPU, and it will be paired with a score, compare the score between CPUs, and you'll have an idea of how it ranks at the task given it.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Silly Burrito on December 29, 2009, 03:15:40 pm
I'm looking for some tips on the following system (I have been pouring over the recommended setups here on the forums - thanks taz-nz and everyone!). I have never overclocked before, so my goal is to hit something as fast as I can but I don't need 4+ GHz. I also want to keep the costs down as much as possible, preferably under $400 if possible (although I don't see how that is possible considering Vista 64 is $100). I already have an HD.

COOLER MASTER Elite 330 RC-330-KKN1-GP Black SECC ATX Mid Tower Computer Case - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16811119115)$40
ENERMAX Tomahawk ETK405AST 405W ATX12V V2.2 AirGuard, Speed Guard and Safe Guard Power Supply - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16817194037)$45
GIGABYTE GA-EP45-UD3L LGA 775 Intel P45 ATX Intel Motherboard - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16813128372)$95
Intel Core2 Duo E7500 Wolfdale 2.93GHz LGA 775 65W Dual-Core Processor Model BX80571E7500 - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16819115056)$120
CORSAIR XMS2 2GB (2 x 1GB) 240-Pin DDR2 SDRAM DDR2 800 (PC2 6400) Dual Channel Kit Desktop Memory Model TWIN2X2048-6400 - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16820145590)$50
GIGABYTE GV-R435OC-512I Radeon HD 4350 512MB 64-bit GDDR2 PCI Express 2.0 x16 HDCP Ready CrossFire Supported Low Profile ... - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16814125251)$35
LITE-ON Black SATA DVD-ROM Drive Model iHDS118-04 - OEM (http://www.newegg.com/Product/Product.aspx?Item=N82E16827106276)$20
Sunbeam CR-CCTF 120 mm Core-Contact Freezer CPU Cooler W/TX-2 - Retail (http://www.newegg.com/Product/Product.aspx?Item=N82E16835207004)$40
Microsoft Windows Vista Home Premium SP1 64-bit for System Builders - OEM (http://www.newegg.com/Product/Product.aspx?Item=N82E16832116488)$100
Total$545

Any tips for reducing costs? Can I just mount all the components on the inside of the arcade cabinet and forget the case, or will this adversely affect cooling? Yes, no.

Edit: Oh, and this will be for MAME only - no PC games or other emus. Kthanksbye.
Edit again: Just reread this previous post (http://forum.arcadecontrols.com/index.php?topic=72776.msg939961#msg939961) answering my question about the case (not necessary). Coolio.

Thanks for posting this list. I ended up buying any of the same items as you (especially the motherboard and the cooler, although I did buy the E8400), and I was shocked by how easy it was to overclock to 4Ghz even though I had never overclocked before. I probably could have bumped it up to anywhere from 4.2-4.8Ghz on air cooling (and judging by how many people have done it, it shouldn't be that difficult), but I just wanted 4 with reasonable voltage/temperatures. My only real problem came when the motherboard had my RAM voltage too low. Setting it to 2.1 (the recommended manufacturer setting) had it working in no time, and 27 hours of Prime95 (with no errors) later, I'm running a 4.05Ghz PC w/4GB of RAM for $466 (not counting rebates). :applaud: Not too shabby at all.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Truecade on March 29, 2010, 10:52:57 am
Well everyone, its been a few months and there are new processors out there for benchmarking.  Specifically, the Core i5/i3 processors built on Intel's 32nm process.  I am particularly interesting in the Core i5 since the stock clock speeds seem to be pretty high and with the 'turbo' ability to push even higher. 

So has anyone had a chance to see how MAME runs on one of the new Core i5 processors? 

ProcessorCoreUn-coreGPUMax Mem ClockCores / ThreadsL3 CacheMax Turbo
Intel Core i5-670   3.46GHz   2.40GHz   733MHz   1333MHz   2 / 4   4MB   3.76GHz   
Intel Core i5-6603.33GHz2.40GHz733MHz1333MHz2 / 4 4MB3.60GHz
Intel Core i5-6503.20GHz2.40GHz733MHz1333MHz2 / 44MB3.46GHz
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on May 29, 2010, 02:25:48 am
Ok so it's been over a year since I've posted anything in this thread, but I'm back a happy to annouce I have some new toys to play with for a few days in the form or the Intel Core i5 655K and Core I7 875K unlocked CPUs.

My kitchen table currently looks like this:

(http://i302.photobucket.com/albums/nn111/taz-nz/tabletop.png)

Currently I have the I5 655K running stablily at 4.6 GHZ.  >:D

(http://i302.photobucket.com/albums/nn111/taz-nz/i5655k46Ghz.png)

So the question is now people what do you want benchmarked?  My copy of MAME is way out of date, but that's easily fixed, and I can soon undate a rom set of two dozen, so what do what to see, make it fast the CPU have to be back at work on monday :)

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Red on May 29, 2010, 12:27:27 pm
Benchmarks for all the NFL Blitz games.  Thanks.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DillonFoulds on May 29, 2010, 01:56:11 pm
Gauntlet Legends, and play through the entire first world!!!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Epyx on May 30, 2010, 09:53:58 pm
Quote
So the question is now people what do you want benchmarked?

Dealer's Choice :)

You started the thread and must have a list of games that you have been itching to "get revenge" on with a faster processor...start with those  :cheers:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: SlayerAlex on May 31, 2010, 12:29:53 am
heo yea! all the big dawgs if possible. Blitz, gauntlet,  and maybe even Tekken 3 in Ling Xiaoyu stage with the Merry go round in the back. oh and a DDR if you have the CHD. :D
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: taz-nz on May 31, 2010, 05:24:29 am
All Benchmarks were run on MAMEUI 64bit version 0.138u1 in Windows 7 64bit.

First set of benchmark I ran were using the same Roms & setting as John IV (http://www.mameui.info/Bench.htm).

I ran the benchmark set three times, once with the I5 655k @ 4.6ghz, then again at 4.8ghz, and then with the I7 875K @ 4.0ghz.

(http://i302.photobucket.com/albums/nn111/taz-nz/i7875k40Ghz.png)

The Command Line was as follows:
MAMEUI64.EXE -str 90 -nothrottle -norc -mt -nosleep -view standard [Rom Name]

ROM              i5 @ 4.6ghz    i5 @ 4.8ghz    i7 @4.0ghz
19425294.06%5656.39%5049.09%
Blitz211.76%219.89%247.23%
Dolphin33.44%35.91%29.27%
Gauntleg295.30%300.43%322.49%
Gradius4163.59%169.82%182.35%
Propcycl159.75%159.93%203.97%
Radikalb199.64%209.44%159.87%
Scud119.33%124.38%115.24%
Starsldr139.56%144.96%120.40%

I ran another benchmark set with a large set of ROMs on the I5 655K @ 4.6ghz using my old command line.

MAMEUI64.EXE -noautoframeskip -frameskip 0 -seconds_to_run 240 -nothrottle -nosleep -video ddraw -skip_gameinfo -effect none -nowaitvsync -noreadconfig -m [Rom Name]


ROM                 Result
19425300.81%
Airco22b165.88%
Alpinerd106.31%
Blitz201.74%
Blitz99210.60%
Cybrcycc222.12%
Dolphin34.44%
Gauntleg330.59%
Gradius4156.53%
Hyperdriv240.46%
Propcycl162.43%
Radikalb193.13%
Raveracw153.87%
Ridgerac184.33%
Scud115.35%
Sidebs2219.05%
Starblad168.09%
Starsldr137.76%
Stunrun886.06%
Surfplnt177.45%

Sorry I didn't get a chance to do more, but I only had a limited amount of time with the CPU's.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Epyx on May 31, 2010, 04:30:33 pm
Would be neat to see how these scale every 100mhz compared to your original set of benchmarks which you said at the time were pretty linear with each additional 100mhz.

Also, was there still sound stuttering on Gauntlet Legends or was that finally smooth?

Thanks for posting these!  :cheers:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: kronic24601 on June 02, 2010, 11:49:07 am
Would be neat to see how these scale every 100mhz compared to your original set of benchmarks which you said at the time were pretty linear with each additional 100mhz.

Also, was there still sound stuttering on Gauntlet Legends or was that finally smooth?

Thanks for posting these!  :cheers:

I don't have any stats to post, but I have a i5 oc'd to 4.52 Ghz running W7 64x and Gauntlet Legends runs pretty smooth with an occasional voice glitch in heavy battle. HOWEVER, that game is pretty buggy, 4 out of 5 times it will freeze on me when trying to run up the first set of stairs. I noticed it is a logged bug in MAME. Gauntlet Legends DL works better... but same problem with occasional voice glitch during massive battles. I think the ideal CPU speed would be around 5Ghz ... but that's a guess.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DillonFoulds on June 02, 2010, 06:24:39 pm
When you say it runs fine, how far have you got on it, if you don't mind me asking?

Edit: "has you got"? Guess my Albertan is sticking out...
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: kronic24601 on June 02, 2010, 06:49:35 pm
I haven't played with it too much but this was my exp.

GL (1st level -easy) ... You can run around kill guys, grab treasure etc... but MOST of the time running up the stairs it will freeze. One time I went straight for the stairs and made it past there and was able to finish the level. Didn't try any others.

GL DL (1st level easy) Didn't experience any problems, finished the first level and warped out.

That's it so far I've been too busy setting things up to test it too much more. I also haven't tried things with 4 players ... not sure what effect that will have on things.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Epyx on June 03, 2010, 12:19:38 am
Ah so even with the right overclock it sounds like im not missing much if it is that buggy still :(

Thanks for the heads up, good to know.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: kronic24601 on June 03, 2010, 10:43:47 am
ya ... it's kinda gay considering how much $$ I plunked down on the upgrade. I was hoping for full GL playback, it works pretty smooth, but there is that one bug that'll just butcher the fun-factor.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DillonFoulds on June 03, 2010, 10:50:03 am
HAHA! That one tiny bug of not being able to go up stairs!

I guess rather than dump my money on an upgrade to my MAME PCs, I'll have to settle for a dedicated GL cab :D Girlfriend's gonna be REAL happy when that one shows up in the kitchen! >:D
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: juksu on August 05, 2010, 10:55:14 am
i5-670 is crazy processor. With air cooled it can get to 5.4Ghz =P. I wonder if it can run all the 3D-mame games..
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Havok on August 05, 2010, 11:04:50 am
Let's see that toaster benchmarked!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: dosmame on January 06, 2011, 05:01:42 pm
some good numbers there, i only get 1279.61% on 1941 using the -bench option and 2.6GHz Q6700

http://dosmame.mameworld.info/index.php/Special_Blog?cmd=post&id=21 (http://dosmame.mameworld.info/index.php/Special_Blog?cmd=post&id=21)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Truecade on January 20, 2011, 12:09:18 pm
Time to dig up this thread, I just upgraded to the new Intel Sandy Bridge processor and did some very preliminary testing last night. 

Here is what I have:
Core i5-2500 (3.3 Ghz stock)
Intel DH67CF Mini ITX board
4 GB Ram
MSI HD 5670 video card
Windows XP 32 bit SP3

I only tested a couple games, but everything ran really good.

I fired up Mace: the Dark Age and played it through to the end.  The framerates never dropped below 100% and game ran perfectly. 

Next up, Gauntlet Legends.  The game played very well with only a couple frame rate drop to 90ish% on the first stage of the mountain world.  For some reason I didn't have sound effects (the music worked fine), but that may have been due to the older version of MAME I was using or mismatched CHD/ROM files.  I will get a newer version of MAME tonight and do some more testing. 

I would have done more benchmarking, but I was having too much fun playing Mace the Dark Age.   ;D  So my very early thoughts are that the new Sandy Bridge CPUs are going to finally make almost all of those CHD games playable without overclocking.  With an unlocked Sandy Bridge CPU, overclocking is as easy as just changing the CPU multiplier in the BIOS.  So far the tech sites are saying 4.0 Ghz OC can be achieved very easily on air with the stock Intel cooler.  These are the perfect CPUs for MAME and with 64-bit Windows MAME performance would be even better. 

Nest up, I need to find a PCI-e vid card that is compatible with Soft 15Khz so I can test games running at their native resolutions with my NEC XM29.   :cheers:
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on June 09, 2011, 11:55:08 am
Sorry to drag up an old thread, but I've tied reading this thread in a linear fashion and I just got confused  :dizzy:

My current setup is running a P4 3.0 HT, and plays most chd games ok. Gauntlet and Blitz are still kind of not there yet.

I'd like to drop in something overclocked to the 4.0 GHz range. I've read that the E8400 is a nice choice, but I don't know what motherboard and RAM to get.

Should I try getting my hands on a core i5 2500k? Is there a motherboard that will handle both chips, or are they different sockets?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: scofthe7seas on June 09, 2011, 12:55:11 pm
Since the thread is already back from the dead; Yes, those are different socket types. I'm pretty sure all of the core2blah processors are 775. there might be some newer ones that are not, but I have a core2quad, my mobo broke and I had kind of a hassle finding an "older"  ::) motherboard that would work with it, and DDR2 ram.
Having never seen the chart above, I find it interesting that blitz runs slower than gauntlet on the OPs PC. I get a lot more playability out of blitz.

As for ram, ddr2 or ddr3 won't make a huge impact on arcade gaming. None of the games are doing things that require heavy ram processing. (actually, most things on Pcs don't need that, but let's not go there.) 64bit is one of the best and easiest choices for a significant speed boost!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: newmanfamilyvlogs on June 09, 2011, 02:24:02 pm
As for ram, ddr2 or ddr3 won't make a huge impact on arcade gaming. None of the games are doing things that require heavy ram processing. (actually, most things on Pcs don't need that, but let's not go there.) 64bit is one of the best and easiest choices for a significant speed boost!

Has this ever been proven/disproven with actual benchmarks? If you're running the program, you're in ram, and as I understand it, for CPU intensive things like emulation, I would imagine that waiting for the ram could cause wasted cycles.

Edit: Ran a benchmark on 1942 with the above procedures on a P4 3.0Ghz machine with the same capacities of DDR226 and DDR400 with identical results. Perhaps I'm wrong, after all.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Goalies Rule on June 09, 2011, 09:19:08 pm
As for ram, ddr2 or ddr3 won't make a huge impact on arcade gaming. None of the games are doing things that require heavy ram processing. (actually, most things on Pcs don't need that, but let's not go there.) 64bit is one of the best and easiest choices for a significant speed boost!

Has this ever been proven/disproven with actual benchmarks? If you're running the program, you're in ram, and as I understand it, for CPU intensive things like emulation, I would imagine that waiting for the ram could cause wasted cycles.

Edit: Ran a benchmark on 1942 with the above procedures on a P4 3.0Ghz machine with the same capacities of DDR226 and DDR400 with identical results. Perhaps I'm wrong, after all.

Thats not really much of a comparison between 2 speeds of ddr ram. You would want something along the lines of an AMD AM2 cpu with a built in memory controller that supports both ddr2 and ddr3.

Even then, I would still think it'd be a small difference.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: scofthe7seas on June 10, 2011, 11:32:11 am
I'm sure you might get some small boost on the games that you're already getting 1000 fps on, but for all of the newer games that would currently require the ridiculous super computers people are building for them, the extra bandwidth in DDR3 isn't going to show any beneficial results. The emulation just isn't optimized enough to require a faster speed coming from the memory. There's a big big CPU "bottleneck". It's more of an emulation bottleneck, actually.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on June 10, 2011, 02:58:21 pm
Ah, to hell with it. I went ahead and sprung for the i7 2600K. After I get the system up and running, I'll report back with results.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Charles4400 on June 12, 2011, 05:30:12 pm
Time to dig up this thread, I just upgraded to the new Intel Sandy Bridge processor and did some very preliminary testing last night. 

Here is what I have:
Core i5-2500 (3.3 Ghz stock)
Intel DH67CF Mini ITX board
4 GB Ram
MSI HD 5670 video card
Windows XP 32 bit SP3

I only tested a couple games, but everything ran really good.

I fired up Mace: the Dark Age and played it through to the end.  The framerates never dropped below 100% and game ran perfectly. 

Next up, Gauntlet Legends.  The game played very well with only a couple frame rate drop to 90ish% on the first stage of the mountain world.  For some reason I didn't have sound effects (the music worked fine), but that may have been due to the older version of MAME I was using or mismatched CHD/ROM files.  I will get a newer version of MAME tonight and do some more testing. 

I would have done more benchmarking, but I was having too much fun playing Mace the Dark Age.   ;D  So my very early thoughts are that the new Sandy Bridge CPUs are going to finally make almost all of those CHD games playable without overclocking.  With an unlocked Sandy Bridge CPU, overclocking is as easy as just changing the CPU multiplier in the BIOS.  So far the tech sites are saying 4.0 Ghz OC can be achieved very easily on air with the stock Intel cooler.  These are the perfect CPUs for MAME and with 64-bit Windows MAME performance would be even better. 

Nest up, I need to find a PCI-e vid card that is compatible with Soft 15Khz so I can test games running at their native resolutions with my NEC XM29.   :cheers:

Very cool and good to hear...did you get a chance to test out any of the other heavy  dudty games like Blitz?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Charles4400 on June 12, 2011, 05:31:04 pm
Ah, to hell with it. I went ahead and sprung for the i7 2600K. After I get the system up and running, I'll report back with results.

Let us know how thaty performs...I expect very well!

When are you getting it in?

Look forward to the results!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Charles4400 on June 12, 2011, 05:42:13 pm
BTW does anyone know if they fixed the major stairs bug in Gauntlet Legends on the latest release of mame?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DillonFoulds on June 14, 2011, 05:45:30 pm
http://maws.mameworld.info/maws/ (http://maws.mameworld.info/maws/) and search for "gauntleg", the mame changelog is posted under "additional information"
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Silverwind on July 25, 2011, 11:28:14 pm
Ah, to hell with it. I went ahead and sprung for the i7 2600K. After I get the system up and running, I'll report back with results.

How's the 2600K been running?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on July 27, 2011, 07:34:08 am
Not at all. I haven't had a motherboard for it.

Just picked one up on Friday night on feeBay, so I'll work on some RAM and then I can start some benchmarking.

*lazy*

 >:D
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on September 02, 2011, 12:41:48 pm
STILL planning on getting to this....I just picked up the last two pieces of hardware I need to test this rig this week: a SSD hard drive and a CoolerMaster Hyper 212 Air cooler.

As soon as the cooler arrives, it's GO time.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DillonFoulds on October 13, 2011, 01:04:47 am
still itching to hear about the 2600k!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on October 13, 2011, 10:22:37 am
Thanks for the prod. I'll start putting some parts together tonight and see if I can get XP 64bit up and running.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: scofthe7seas on October 13, 2011, 07:57:33 pm
I tried to go with Windows XP 64, but it was super unstable. Freezing up. I went to Windows 7 64 and haven't had any trouble. I just don't know if the 64 bit architecture was fully implemented into Windows XP, or just tacked on.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: SNAAKE on October 14, 2011, 02:48:22 am
time crisis randomly lags on my 6core lol.. ???
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: newmanfamilyvlogs on October 14, 2011, 05:45:40 am
I tried to go with Windows XP 64, but it was super unstable. Freezing up. I went to Windows 7 64 and haven't had any trouble. I just don't know if the 64 bit architecture was fully implemented into Windows XP, or just tacked on.

I think the issue of stability fully comes from whatever drivers you're running, and not from WinXP64 itself. I've been running it on different machines (both work and MAME) for 4-5 years now and never had an issue with stability. The only time I was having stability issues, it turned out to be a failing hardware issue.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: scofthe7seas on October 21, 2011, 02:05:41 pm
The hardware is definitely not failing, but a lot of brand new stuff that obviously wasn't around when Windows XP came out.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: equlizer on October 21, 2011, 11:01:40 pm
is mame setup for multiple cores?  I think its just about the speed of the cpu.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on December 01, 2011, 12:42:19 pm
Regardless of whether or not you're using multiple cores, with the i7 2600k, you've got 4 pipelines to work with, so even if MAME is running in a single one, the rest of the cores can handle all of the other OS activities going on. And you can OC each of the cores separately.

I'm about to do some formal benchmarking on my i7 2600k soon.

First blush reports show MK4 running for 180 seconds at an average of 89% with the chip clocked to 4.5ghz.

I'm putting the finishing touches on my test rig and I'm hoping to get 5.1ghz stable on air cooling. Then I'll start my benchmark tests.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on February 25, 2012, 02:28:50 pm
Alright, finally some results. My core i7 gets pretty flaky after 4.8ghz, so I chose to keep it there for now.

5346.38% - 1942
735.65%  - Area 51
352.60%  - gauntleg12
272.67%  - Blitz
387.44%  - Gradius4
177.67%  - Propcycl
142.97%  - radikalb
121.86%  - starsldr

Not too shabby :)

My system setup: ASUS P8P67M-Pro, 8 Gigs Ripjaw 12800 RAM,  64GB SATA III SSD, I7 2600k clocked to 4.8 on air, NVIDIA GeForce 8500 GT 256mb PCIe, running XP 64bit.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: brad808 on February 25, 2012, 04:17:41 pm
Alright, finally some results. My core i7 gets pretty flaky after 4.8ghz, so I chose to keep it there for now.

5346.38% - 1942
735.65%  - Area 51
327.25%  - gauntleg
272.67%  - Blitz
387.44%  - Gradius4
177.67%  - Propcycl
142.97%  - radikalb
121.86%  - starsldr

Not too shabby :)

My system setup: ASUS P8P67M-Pro, 8 Gigs Ripjaw 12800 RAM,  64GB SATA III SSD, I7 2600k clocked to 4.8 on air, NVIDIA GeForce 8500 GT 256mb PCIe, running XP 64bit.


I've been curious about this actually. When you have benchmark numbers like that on games such as gauntlet legends and blitz are you able to play them without any sound stuttering?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on February 25, 2012, 07:34:54 pm
Both games play perfectly with no audio issues. I played a full half of football in Blitz and it plays perfectly.

Gauntlet legends crashes randomly after I start gameplay. My cpu is nowhere near maxed out - the game is running in 4 out of 8 cores, and each of them is at best 60% utilized.

Is Gauntlet Legends emulated properly in MAME?

EDIT: I tried version 1.2 of Gauntlet Legends, and it plays perfectly. Wow, fun game. I'll have to get a few guys together and beat the crap out of that one :)

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DillonFoulds on February 26, 2012, 03:03:37 pm
PLEASE DO! Since it's nearly impossible for me to get my hands on a dedicated, I'd love to know how far you get through this!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on February 28, 2012, 09:43:45 am

Gauntlet legends crashes randomly after I start gameplay. My cpu is nowhere near maxed out - the game is running in 4 out of 8 cores, and each of them is at best 60% utilized.


Have you tried disabling hyperthreading?  My i3-560 runs mame better without HT -- I would bet that your benchmarks (and perhaps GL gameplay) would be better with HT disabled.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on February 28, 2012, 10:00:37 am

Gauntlet legends crashes randomly after I start gameplay. My cpu is nowhere near maxed out - the game is running in 4 out of 8 cores, and each of them is at best 60% utilized.


Have you tried disabling hyperthreading?  My i3-560 runs mame better without HT -- I would bet that your benchmarks (and perhaps GL gameplay) would be better with HT disabled.

I did - it didn't make a difference. Gauntlet Legends actually plays perfectly. The problem was that I was using version 1.6, which has known crashing issues (see mamedev.org) but 1.2 works perfectly. No stutters, no speed issues, no sound issues.

Later this week I'm going to try and play through the whole game with a friend so I can be sure that multiplayer will work without issues.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: tommyinajar on February 28, 2012, 02:14:21 pm
I remember not too long ago, it was thought you'd need a 8 or 9 Ghz CPU to be able to play Legends. :)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on February 28, 2012, 04:07:40 pm
Considering I can see MAME64 running in two of my eight cores @ 4.8ghz each, I can see where a single core CPU would need to run close that speed in order to keep up.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on February 28, 2012, 04:13:01 pm
It would be interesting to see if you needed all 4.8ghz to run these games or if they are able to run at, say, 4.2 or 4.3.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on February 28, 2012, 04:22:18 pm
Yeah, that's an interesting point to consider. Since I was overclocking for the pure purpose to see how high I could push my chip and still remain stable, I'm not inclined to mess with my settings now that I've got it locked in stable at 4.8.

I would, however, be happy to bench test any other games that folks would like to see benchmarked.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on February 28, 2012, 04:28:11 pm
Considering I can see MAME64 running in two of my eight threads @ 4.8ghz each, I can see where a single core CPU would need to run close that speed in order to keep up.



I am curious -- while your benchmark is running how many of your threads are at 100% -- 2 or 4?  If only 2 of 8 are at 100% then shouldn't you be able to disable HT to get a higher benchmark (mame would then use 2 of 4)?  I'm going to try this out on my Clarkdale when I get home...for some reason I can't shake the notion that HT negatively affects mame performance.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on February 28, 2012, 04:32:32 pm
Considering I can see MAME64 running in two of my eight threads @ 4.8ghz each, I can see where a single core CPU would need to run close that speed in order to keep up.



I am curious -- while your benchmark is running how many of your threads are at 100% -- 2 or 4?  If only 2 of 8 are at 100% then shouldn't you be able to disable HT to get a higher benchmark (mame would then use 2 of 4)?  I'm going to try this out on my Clarkdale when I get home...for some reason I can't shake the notion that HT negatively affects mame performance.

My motherboard has a lot to do with how well my i7 performs. It does a very good job with the voltage during TurboBoost. I had CPU-Z running during my benching, and the board did a very good job ratcheting up the core speeds from 3.4 (stock) to 4.8ghz when under load. AFAIK the turbo boost mode overclocks all 8 cores, so they're all running at 4.8 regardless of whether or not a process is running in that core or not.

I believe MAME64 v145 only uses 2 cores at most. I could be wrong. I'll shoot urebelscum a PM and ask.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on February 29, 2012, 01:59:34 am
OK so I was able to spend some time tinkering.  Got my i3-560 up to 4.2ghz (going higher would require more time than I was willing to invest) and ran some benchmarks with and without HT.  I am running mame64 in windows 7 (ultimate 64 bit) with 8 gb of RAM.  I had a limited selection of roms but I was able to benchmark the following:

galaga (no HT): 5415
galaga (HT): 3973

1943 (no HT): 4124
1943 (HT): 4114

1942 (no HT): 5175
1942 (HT): 5209

gauntleg (no HT): 275
gauntleg (HT): 263

So it looks like 1942 and 1943 are pushes, galaga runs significantly faster (?!) and gauntleg has about a 4.5% advantage with no HT.  I took a closer look while running the gauntleg bench 90 and my CPU has a slightly higher overall utilization when HT is turned off.

These limited results don't indicate that turning off HT gives a significant advantage but they do indicate that turning on HT doesn't benefit mame64.  I will therefore be leaving HT off (which will lower temps and allow for a higher overclock).

Out of curiosity I fired up gauntleg and it ran just fine until it crashed while I was on the stairs (known issue).  I didn't have blitz handy but I will pull it out tomorrow and post results.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on February 29, 2012, 07:12:52 am
gauntleg and it ran just fine until it crashed while I was on the stairs (known issue)

Did you run version 1.6 or version 1.2?

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on February 29, 2012, 11:18:57 am
Not sure -- I will check it out tonight.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DillonFoulds on February 29, 2012, 11:14:08 pm
If I'm not mistaken...

gauntleg = 1.6
gauntleg12 = 1.2

You can also confirm the version on the title screen (or is it the credits?). It's listed in the bottom left corner of the screen.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on March 01, 2012, 12:39:09 am
ok, so I dug out blitz, and here are my results:

blitz (no HT): 192
blitz (HT): 179

7% advantage with HT disabled.

Same settings as yesterday -- i3 560 (Clarkdale) @4.2ghz.  I am not using onboard graphics -- I am running an ATI 5570.

With HT disabled I was able to play blitz flawlessly (@100%).  My legends version is 1.6 and plays flawlessly (@99.97%) until crash.  I don't have version 1.2.

I could push my Clarkdale further but I see no need when GL and blitz runs smooth @4.2ghz (cruise control) with room to spare.  I am guessing that a sandy bridge i5@4.2ghz would eat my clarkdale for breakfast.

Can someone please remind me why C2Ds are so highly regarded for running mame?

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: MacGyver on March 01, 2012, 03:21:09 am
You guys are costing me money. :)  After reading the new additions to this thread and the fact that you got everything up to %100 speed, I decided to finally spend the money on an upgraded CPU, so I bought an i5 2500K, an ASUS z68, 8gb of 1333 RAM, and a 128gb SSD.  Wish me luck.  Oh, and I swear I plan on building the cabinet now, the monitor was the real thing holding me up (Germany and 200lb crates don't work well), so I found this and bought it:
(http://ecx.images-amazon.com/images/I/41yP70jfmZL._SL500_AA300_.jpg)
http://www.amazon.com/I-Inc-IH283HPB-Class-Widescreen-Monitor/dp/B0050HZ2SS (http://www.amazon.com/I-Inc-IH283HPB-Class-Widescreen-Monitor/dp/B0050HZ2SS)
it was $249, so I couldn't help it, I just hope it is more like a real monitor in shape than a 16:9 TV.  Now off to find some black pica vinyl.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on March 02, 2012, 07:12:46 am

I could push my Clarkdale further but I see no need when GL and blitz runs smooth @4.2ghz (cruise control) with room to spare.  I am guessing that a sandy bridge i5@4.2ghz would eat my clarkdale for breakfast.

Can someone please remind me why C2Ds are so highly regarded for running mame?

Well, they were so highly regarded for running MAME cause they were doing what your now doing about 4 years ago. My Core2Duo E8500 @ 4.27Ghz runs blitz without a hitch (room to spare), and even a more challenging game San Francisco Rush, with very few hiccups (while fraps is recording), I posted a video in this thread a few years ago (September 2008 I believe). I had my E8500 clocked at 4.5GHz for the first year I had it, then I decided to clock it down slightly (to 4.27GHz) and use more comfortable almost stock voltage, cause I knew it was a great CPU and I wanted it to last many years.  .

Here's a refresher, this video is over 3 years old now...

MAME San Francisco Rush (Track 1) (http://www.youtube.com/watch?v=dldHlHhlG_4#)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on March 02, 2012, 09:55:46 am
Nicely done.  I am going to dig for that rom and try to run it tonight at my current settings.  Did you figure out a way to permanently solve the sound issue or are you still having to do your work-around?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: kahlid74 on March 02, 2012, 11:50:20 am
This is a rig I've been using for a lot of my Cabs but I've never tested with Blitz/Gauntleg so I'll try to test with those this weekend and report on what my performance levels are.

(http://i157.photobucket.com/albums/t54/Kahlid74/Cab6/ArcComp.jpg)
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on March 02, 2012, 03:25:58 pm
If I'm not mistaken...

gauntleg = 1.6
gauntleg12 = 1.2

You can also confirm the version on the title screen (or is it the credits?). It's listed in the bottom left corner of the screen.

Out of curiosity, what is gauntdl and is it the same as gauntleg?  If not, how is it different?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on March 02, 2012, 03:32:20 pm
 ;D

I couldn't resist.


http://lmgtfy.com/?q=what+is+gauntdl+on+mame%3F (http://lmgtfy.com/?q=what+is+gauntdl+on+mame%3F)

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on March 02, 2012, 05:13:41 pm
Nicely done.  I am going to dig for that rom and try to run it tonight at my current settings.  Did you figure out a way to permanently solve the sound issue or are you still having to do your work-around?

Last I checked, the SF Rush sound issue was fixed, I forgot what version of MAME it was cause it's been a while. Playing the game with a PS2 controller isn't the best, and is very hard to configure, if I owned a high quality steering wheel, I'd be addicted to the game again.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on March 02, 2012, 05:22:58 pm
;D

I couldn't resist.


http://lmgtfy.com/?q=what+is+gauntdl+on+mame%3F (http://lmgtfy.com/?q=what+is+gauntdl+on+mame%3F)



ok, so maybe I deserved that, but to get more specific, if gauntdl contains everything gauntleg does (+more) why are we benchmarking gauntleg and not gauntdl?  I played gauntdl on my system last night and there was no freezing...

I ran a -bench 90 on gauntdl and it benched a lot higher than gauntleg -- I can't remember what the number was but I can bench it again when I get home...
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on March 02, 2012, 05:23:50 pm
I chose gauntlet legends because that's what the OP used.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DillonFoulds on March 02, 2012, 07:06:19 pm
If gauntdl benches higher than gauntleg, then you want to be benching gauntleg, as that's a harder task...
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on March 02, 2012, 08:17:20 pm
Fair enough.  So besides locating version 1.2 and taking a look at sfrush, is there any other game out there that folks would like to see me try to run on my Clarkdale?
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on March 02, 2012, 08:53:06 pm
Fair enough.  So besides locating version 1.2 and taking a look at sfrush, is there any other game out there that folks would like to see me try to run on my Clarkdale?

There's a lot of games I'd love to see and play, but most are marked as "NOT WORKING" unfortunately.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on March 04, 2012, 10:23:41 am
ok so i tried sfrush and it plays at just under 99%.  The game stutters a bit on the track selection screen but is perfect after that (car selection and gameplay were perfect).
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Bigtymer781 on March 04, 2012, 06:47:33 pm
This used to be true, I haven't tried the latest versions of MAME so I'm not sure anymore, but when I'd use Mame32 .121 (64-bit), I'd get like a 10% performance boost in SF Rush, but you have to do the sound work around when using .121, and it's hard to find now I think. I got it sitting around somewhere though.

Another tweak I'd do to the sound is, since the arcade machine had 4 channel sound, It doesn't sound quite right in MAME (with 2 channels), I'd set the sound to 50% in channels 1 and 3 (if I remember correctly), or it could be channels 0 and 2 (I'm going off memory) and it would sound more like the arcade machine when you turned the sound up.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Hockeyboy on July 23, 2012, 10:10:45 pm
So...reading in the Main Forum CPU FAQ led me to here (apparently way outdated, started in '03), and I'm curious about my proposed equipment for my upcoming cabinet:

Gigabyte GA-EP45-DS3L motherboard
Intel® Core™2 Quad Processor Q9450 (12M Cache, 2.66 GHz, 1333 MHz FSB)
Kingston DDR2 800 MHz SDRAM, 4x1GB sticks for a total of 4GB RAM
CORSAIR Builder Series CX500 V2 500W ATX12V v2.3 80 PLUS Certified Active PFC Power Supply
EVGA 01G-P3-N988-TR GeForce 9800 GT HDMI 1GB 256-bit DDR3 PCI Express 2.0 x16 HDCP Ready SLI Support Video Card
DVD-ROM drive
Hard drive - use either spare SATA 250GB or purchase new 60GB SSD w/SATA II

I'm planning on using my MAME version 0.103u2 (Jan 11 '06) and also putting DAPHNE on to run Dragon's Lair, Dragon's Lair II, Space Ace, and Cliff Hanger. Now I'm hearing about Gauntlet Legends -- will the above setup be able to play it or will I have some serious issues and not worry about it? Thanks in advance for the advice.
Title: Re: Re: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: brad808 on July 23, 2012, 10:58:38 pm
So...reading in the Main Forum CPU FAQ led me to here (apparently way outdated, started in '03), and I'm curious about my proposed equipment for my upcoming cabinet:

Gigabyte GA-EP45-DS3L motherboard
Intel® Core™2 Quad Processor Q9450 (12M Cache, 2.66 GHz, 1333 MHz FSB)
Kingston DDR2 800 MHz SDRAM, 4x1GB sticks for a total of 4GB RAM
CORSAIR Builder Series CX500 V2 500W ATX12V v2.3 80 PLUS Certified Active PFC Power Supply
EVGA 01G-P3-N988-TR GeForce 9800 GT HDMI 1GB 256-bit DDR3 PCI Express 2.0 x16 HDCP Ready SLI Support Video Card
DVD-ROM drive
Hard drive - use either spare SATA 250GB or purchase new 60GB SSD w/SATA II

I'm planning on using my MAME version 0.103u2 (Jan 11 '06) and also putting DAPHNE on to run Dragon's Lair, Dragon's Lair II, Space Ace, and Cliff Hanger. Now I'm hearing about Gauntlet Legends -- will the above setup be able to play it or will I have some serious issues and not worry about it? Thanks in advance for the advice.

I have two similar processors, q6600 and q8200, and neither are close to playing gauntlet legends. You would probably need a pretty serious overclock to get it running full speed.

Sent from my Desire HD
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: kahlid74 on July 24, 2012, 10:46:04 am
So...reading in the Main Forum CPU FAQ led me to here (apparently way outdated, started in '03), and I'm curious about my proposed equipment for my upcoming cabinet:

Gigabyte GA-EP45-DS3L motherboard
Intel® Core™2 Quad Processor Q9450 (12M Cache, 2.66 GHz, 1333 MHz FSB)
Kingston DDR2 800 MHz SDRAM, 4x1GB sticks for a total of 4GB RAM
CORSAIR Builder Series CX500 V2 500W ATX12V v2.3 80 PLUS Certified Active PFC Power Supply
EVGA 01G-P3-N988-TR GeForce 9800 GT HDMI 1GB 256-bit DDR3 PCI Express 2.0 x16 HDCP Ready SLI Support Video Card
DVD-ROM drive
Hard drive - use either spare SATA 250GB or purchase new 60GB SSD w/SATA II

I'm planning on using my MAME version 0.103u2 (Jan 11 '06) and also putting DAPHNE on to run Dragon's Lair, Dragon's Lair II, Space Ace, and Cliff Hanger. Now I'm hearing about Gauntlet Legends -- will the above setup be able to play it or will I have some serious issues and not worry about it? Thanks in advance for the advice.

From what I remember reading, you'd need to be somewhere in the 5-8 Ghz range for Gauntlet legends/NFL Blitz 99.  So I don't think you'll get smooth Gauntlet Legends play on your current rig.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on July 24, 2012, 10:52:01 am
So...reading in the Main Forum CPU FAQ led me to here (apparently way outdated, started in '03), and I'm curious about my proposed equipment for my upcoming cabinet:

Gigabyte GA-EP45-DS3L motherboard
Intel® Core™2 Quad Processor Q9450 (12M Cache, 2.66 GHz, 1333 MHz FSB)
Kingston DDR2 800 MHz SDRAM, 4x1GB sticks for a total of 4GB RAM
CORSAIR Builder Series CX500 V2 500W ATX12V v2.3 80 PLUS Certified Active PFC Power Supply
EVGA 01G-P3-N988-TR GeForce 9800 GT HDMI 1GB 256-bit DDR3 PCI Express 2.0 x16 HDCP Ready SLI Support Video Card
DVD-ROM drive
Hard drive - use either spare SATA 250GB or purchase new 60GB SSD w/SATA II

I'm planning on using my MAME version 0.103u2 (Jan 11 '06) and also putting DAPHNE on to run Dragon's Lair, Dragon's Lair II, Space Ace, and Cliff Hanger. Now I'm hearing about Gauntlet Legends -- will the above setup be able to play it or will I have some serious issues and not worry about it? Thanks in advance for the advice.

From what I remember reading, you'd need to be somewhere in the 5-8 Ghz range for Gauntlet legends/NFL Blitz 99.  So I don't think you'll get smooth Gauntlet Legends play on your current rig.

Not true. See my quote below, from earlier in this thread. Both Blitz and GL play perfectly on my 4.8ghz rig.


Alright, finally some results. My core i7 gets pretty flaky after 4.8ghz, so I chose to keep it there for now.

5346.38% - 1942
735.65%  - Area 51
352.60%  - gauntleg12
272.67%  - Blitz
387.44%  - Gradius4
177.67%  - Propcycl
142.97%  - radikalb
121.86%  - starsldr

Not too shabby :)

My system setup: ASUS P8P67M-Pro, 8 Gigs Ripjaw 12800 RAM,  64GB SATA III SSD, I7 2600k clocked to 4.8 on air, NVIDIA GeForce 8500 GT 256mb PCIe, running XP 64bit.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: DillonFoulds on July 24, 2012, 11:01:21 am
I think one of the big things is gauntleg12 (Gauntlet Legends 1.2) vs gauntleg (Gauntlet Legends 1.6). Apparently the emulation is MUCH better overall in 1.2. Even to the point that you can actually even finish the first level!
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on July 24, 2012, 05:43:41 pm
So...reading in the Main Forum CPU FAQ led me to here (apparently way outdated, started in '03), and I'm curious about my proposed equipment for my upcoming cabinet:

Gigabyte GA-EP45-DS3L motherboard
Intel® Core™2 Quad Processor Q9450 (12M Cache, 2.66 GHz, 1333 MHz FSB)
Kingston DDR2 800 MHz SDRAM, 4x1GB sticks for a total of 4GB RAM
CORSAIR Builder Series CX500 V2 500W ATX12V v2.3 80 PLUS Certified Active PFC Power Supply
EVGA 01G-P3-N988-TR GeForce 9800 GT HDMI 1GB 256-bit DDR3 PCI Express 2.0 x16 HDCP Ready SLI Support Video Card
DVD-ROM drive
Hard drive - use either spare SATA 250GB or purchase new 60GB SSD w/SATA II

I'm planning on using my MAME version 0.103u2 (Jan 11 '06) and also putting DAPHNE on to run Dragon's Lair, Dragon's Lair II, Space Ace, and Cliff Hanger. Now I'm hearing about Gauntlet Legends -- will the above setup be able to play it or will I have some serious issues and not worry about it? Thanks in advance for the advice.

Out of curiosity are you pretty much set on the above specs?  If you already have the machine you might as well start running tests to see what you can do (and how much you are able to overclock).  If you don't already have the components there are probably better options out there in terms of CPU's (for mame) -- one example earlier on this page has a Core 2 Duo overclocked to 4ghz, and I was running an i3-560 overclocked to 4.2 and was able to run all of these games (nfl blitz, gauntdl).  

If you are set on a socket 775 motherboard, Core 2 duos tend to overclock better than the core 2 quads because the extra cores and cache of the quads generate more heat.

If you go Sandy Bridge you don't need 4.8ghz to run these games.  I have a 2500k @ 4.2 and it runs these games with room to spare.  I just happen to be assembling a new system based on an i5-2400 (Sandy bridge @3.1 ghz) and can try to run these games when I get home tonight if you want.  

I agree that there appears to be emulation issues in gauntleg, so you will want to try to run either gauntleg12 or gauntdl.





Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on July 24, 2012, 05:46:47 pm
I just bought an i5 3570k Ivy Bridge today - I'll be swapping this into my rig to run more tests. Once I get the overclock stable on it, I'll benchmark a few more games again.

Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on July 24, 2012, 05:57:31 pm
I just bought an i5 3570k Ivy Bridge today - I'll be swapping this into my rig to run more tests. Once I get the overclock stable on it, I'll benchmark a few more games again.



It would be interesting to see if your 3570k is able to run these games at stock settings -- I suspect that it might be able to.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: smalltownguy on July 24, 2012, 05:58:32 pm
That'll be my first test, actually.
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Hockeyboy on July 25, 2012, 03:35:46 am
So...reading in the Main Forum CPU FAQ led me to here (apparently way outdated, started in '03), and I'm curious about my proposed equipment for my upcoming cabinet:

Gigabyte GA-EP45-DS3L motherboard
Intel® Core™2 Quad Processor Q9450 (12M Cache, 2.66 GHz, 1333 MHz FSB)
Kingston DDR2 800 MHz SDRAM, 4x1GB sticks for a total of 4GB RAM
CORSAIR Builder Series CX500 V2 500W ATX12V v2.3 80 PLUS Certified Active PFC Power Supply
EVGA 01G-P3-N988-TR GeForce 9800 GT HDMI 1GB 256-bit DDR3 PCI Express 2.0 x16 HDCP Ready SLI Support Video Card
DVD-ROM drive
Hard drive - use either spare SATA 250GB or purchase new 60GB SSD w/SATA II

I'm planning on using my MAME version 0.103u2 (Jan 11 '06) and also putting DAPHNE on to run Dragon's Lair, Dragon's Lair II, Space Ace, and Cliff Hanger. Now I'm hearing about Gauntlet Legends -- will the above setup be able to play it or will I have some serious issues and not worry about it? Thanks in advance for the advice.

Out of curiosity are you pretty much set on the above specs?  If you already have the machine you might as well start running tests to see what you can do (and how much you are able to overclock).  If you don't already have the components there are probably better options out there in terms of CPU's (for mame) -- one example earlier on this page has a Core 2 Duo overclocked to 4ghz, and I was running an i3-560 overclocked to 4.2 and was able to run all of these games (nfl blitz, gauntdl).  

If you are set on a socket 775 motherboard, Core 2 duos tend to overclock better than the core 2 quads because the extra cores and cache of the quads generate more heat.

If you go Sandy Bridge you don't need 4.8ghz to run these games.  I have a 2500k @ 4.2 and it runs these games with room to spare.  I just happen to be assembling a new system based on an i5-2400 (Sandy bridge @3.1 ghz) and can try to run these games when I get home tonight if you want.  

I agree that there appears to be emulation issues in gauntleg, so you will want to try to run either gauntleg12 or gauntdl.


I quoted the above specs because that's what I have as my "spare" PC that I'm going to build my MAME cabinet with. I could go out and buy a new set of computer components, but I'd really rather not spend the money -- it's been enough of a fight just to get my wife to let me build a cabinet in this smaller house that she claims has no space available. As for not being able to run Gauntlet Legends, although that's a loss, it's not a huge deal, but I admit it would have been nice to play one of my favorite families of games with Gauntlet. Right now my main concern is being able to play most of the arcade games -- I can always upgrade the PC later after the cab is built.  ;D
Title: Re: 4Ghz Core 2 Duo vs M.A.M.E. 0.120 (benchmark results)
Post by: Diet_Pepsi on July 25, 2012, 06:23:52 am

 Right now my main concern is being able to play most of the arcade games -- I can always upgrade the PC later after the cab is built.  ;D

Absolutely no worries in that regard -- your system is plenty powerful for that, even at stock settings.