Alright kids,

i hate xbench's opengl and other graphics tests, cause it dependent on the monitor's resolution and refresh rate, change that and your results change!

so some people here at : GioFX , created OpenMark : OpenGl benchmarking for Mac OS X

with that said and done lets post some results.

heres my ATi x1300Pro 256 pci-e with NatitX1300(R1) and 1049 ATi kexts:
(you need to convert the .tga to something uploadable to attach here)

Click to view attachment
Click to view attachment

i will post my other cards when im done actually using them, to pull a few benches off them.
-DiaboliK

(if this program crahses your system or locks it up, you have a problem with your OpenGL )

couple more of my cards:

XFX 7600GS fanless 256mb pci-e: natit dual v02, unedited nvidia 1049 kexts

Click to view attachment
Click to view attachment

Sapphire X1600Pro 512mb pci-e: NatitX1600 (R1v3), edited atiradeonx1000.kext and 10.4.5 atindrv.kext , all other ati kexts are 1049

Click to view attachment
Click to view attachment

Ive got a couple more cards but they are agp and i cant use agpgart so ill post anyway but i have to get that machine updated:P

lets see some more benches so we can have a nice comparison!
-DiaboliK

GF 6600 TC on 10.4.9 kernel 8.9.1, I am curious how this benchmark is depended on CPU I have celeron 2.53GHz

this doesnt bech your cpu just your gpu and opengl.

Hackintosh specs:
AMD Athlon 64 x2 4200
1GB Corsair Ram
Gigabyte K8N Pro SLi
(1) XFX Geforce 7900GT Overclocked

OSX 10.4.8
Semethex 8.8.1 kernel
Natit Universal Installer


Click to view attachment

GMA950 @ 1600x1200x32 = 609 Points... yeah it suxx bigtime

GMA950 @ 1024x768x32 = 720
Nvidia 6200 PCI @ 1280x1024x32 = 5807

Both on a Asrock conroe 945G-DVI with a C2D 1.87GHz E6300 and 1Gb Ram.

Can't run the bench at any other resolutions other than 1152x870x32 (crashes when switching to fullscreen), my desktop is at 1280x1024x32. Everything works fine otherwise, the app scared me. Natit Dual v.02 with 10.4.9 kexts, more at sig.

Palit Geforce 7600GT 256MB PCIe
Openmark Score: 16040 Click to view attachment

Click to view attachment

Pentium 4 3Ghz HTT
2GB DDR
200GB HDD
10.4.8[8.8.1]
1680x1050x32 res
7900GS stock

I'm surprised to see 7600GTs scoring higher then 7900GS' and very close to 7900GTs, I suspect something is very unwell with kext's responsible for 7900s.


All benchies below were run at stock speeds.... Good old 9800, still pulling it's weight, damn that was a good card.

Sapphire Ati Radeon x1600xt 256MB DDR3

Although i couldn't run the bench on my EIZO CRT, i changed monitors and on my Mitsubishi CRT i got the following results
Graphics = Gainward 7600GS passive Stock speed

ATI MSI x1950xtx stock
SCORE : 16040

Well this makes me feel a bit better about my 7900 GTO. xBench had it running at around 160, which is quite a bit slower than my buddy's x1600 in his Macbook Pro. I'll be interested to see what his card gets in OpenMark. My result was a 23,557.

Click to view attachment

I was running the benchmark in 1680x1050 resolution. The 7600GT was running in 1100x700 or something like that.

i really don't understand these numbers.

in consolation's post there is a 7600GT with a score of 16,040
and a 7600GS with a score of 10,396

but the GT was at 9 FPS
and theGS was 363 FPS


here is the part i don't understand, how does the GT get higher score
running 9FPS? that just doesn't make sense.

The FPS probably dropped when the screenshot was taken...

the bottom fps is just the fps thats currently going. if you used the tga that it output it would usally be 9fps.
screenshots will vary

So could we normalize the results somehow?
Normalized Result = (Width x Height x Depth x Score)/1000000000
Using that formula would give the following:

DaxTsurugi 7900GS
(1680 x 1050 x 32 x 15769)/1000000000
= 890

consolation 7600GT
(1440 x 900 x 32 x 16040)/1000000000
= 665

My Nvidia 6200 PCI
(1280 x 1024 x 32 x 5807)/1000000000
= 243

SA22C 7900 GTO
(1280 x 1024 x 32 x 23557)/1000000000
= 988

Does this make sense or am I talking crap?

That seems reasonable...

That makes more sense now.

How about trying this out, also includes a nifty utility:

OpenGL Extensions Viewer

It would make things easier IMHO, and it's not as buggy/picky with GioFX's fullscreen problems. I can run the included benchmarks in all resolutions, also has AA/AF tests and GPU capabilities.

Maybe a better Better OpenGL Benchmarking app?

Multi-Render tests will crash on some hackies using OG Extension viewer, I think it's still affected by screen resolution (display mode selection) + lod/aa settings it would be even more of a pita to standardize. We could all agree to bench @ a lowest common denominator (1024x768) or a common resolution (1280x1024). First option will work on any display, but gives old/low end card a deceptive advantage, second may not be possible on all displays. Ritalin's normalization method seems to provide results approximate to what you see in the real world.

if you are interested in how these compare to PPC macs

mid-range

high-end

-you will need to register for the SDs site, but it's well worth the hassle.

Actually - OpenMark seems reasonably resistant to resolution change, I benched at different resolutions:

1024x640= 655360pixels 16313
1440x900= 1296000pixels 16040
1280*1024=1310720pixels 16040

Doubling the pixels resulted in only a 1.7% drop; so the benchmarks at different resolutions are comparable.

So I guess it doesn't really matter what resolution you bench it on, it just calculates pure GPU processing power. Nice.

I'm liking this bench more. Let's forget about me suggesting OpenGL Extensions Viewer And considering that the 7600GTs returned almost the same results (16040), makes it much more reliable than the other GPU benchmarks I know, even at different resolutions.

Don't get me wrong, I like OGLE Viewer - it allows you a far more detailed look at your card's abilities than OM; especially in separating the abilities of newer and older cards etc etc... It's just that, for a "quick'n'dirty" overview of raw speed, it's a bit of an over-kill, IMHO.

I'd be interested to see the OGLE Viewer results for 7900s with high LOD/AA vs 7600GTs at same settings. I suspect the high core speed of the 7600GTs lets you draw a lot of relatively simple polygons but, once it has to process them more it should fall off relatively to the slower but more sophisticated high-end cards. That, or the kext just doesn't take advantage of those cards as it should - I'm speculating here...

P.S. A page I found very useful for card specs is:
http://users.erols.com/chare/video.htm

Kind of offtopic, but here's a screen I took of my results with my 7900 GS in the OGLE Viewer.

Hmm... that's rather poor.

this is my 7600gt



Could you rerun your test with the following settings:

1280X1024X32 (60Hz) Display Mode
Tick multisample set to 4
Untick LOD, set slider to 0
Anistropy set to 16
Tick Use Fog

This the same GT with those settings

That's a lot more like the results you would expect.

So the kexts aren't unbalanced then?

I think they probably use the same kexts, I thought that maybe they are not taking full advantage of your card. Seem like they are; just that the 7600GT is really good at churning out simple polygons. But the (relative) small number of pixel/vertex shaders shows when you start processing the output more.

This is the Benchmarks of my Hackintosh:

Display Card: Leadtek/Winfast PX7900GS TDH

1280X1024X32 (60Hz) Display Mode
Tick multisample set to 4
Untick LOD, set slider to 0
Anistropy set to 16
Tick Use Fog

Here's the results for my 7900 GTO 512 MB.

Test settings:
1280X1024X32 (60Hz) Display Mode
Tick multisample set to 4
Untick LOD, set slider to 0
Anistropy set to 16
Tick Use Fog

Click to view attachment

Interesting that the results are basically the same as the 7900GS in this test, but that my card pulls away quite handily in the OpenMark test, posting a score that is approximately 50% faster.

x1900xt crossfire edition, 512MB

Click to view attachment

using the settings established above for OpenGL Extensions Viewer:

Display Mode: 1280 x 1024 x 33bpp (60Hz)
Framebuffer: Standard

untick Multisample set slider to 4
untick LOD Bias set slider to 0
tick Antisotropy set slider to 16
tic Use Fog

my results are:



i have nVidia GeForce 7600 GT with 256 VRAM

you are supposed to tick Multisample ;-)

These are my results:

stock conditions

score 294 with Open GL

fsb=166

score 373 with Open GL

My stupid question:changing the fsb at the boot influences the performance on the entire system as indicated , or the becnhmarks results are not real at all , 'cause the time is not set correctly ? ( I mean the clocktime is going slower)

oops, thanks.
here are the real ones i guess:

yep that's the one. The bios sets your fsb, not the fsb=xxx switch. That only tells OS X what fsb it's running on. Now, if the real time is faster than the reported time, the benchmark will think the card did more "work" in a shorter period = inflated results.

thanks consolation for clarification!
ok a bit OT ,
Is it possible overclock from inside xp virtual (parallels) and after switch off it , having in the osx running a real overclock?

parallels runs a virtual machine, XP won't see your real hardware.

The rigg is the computer in my signature.
GPU430/ MEM860Mhz clocked and voltmodded 1,4V
Click to view attachment

wohoo! new card!

XFX 7600GT Fatal1ty Fanless : natit dual v02 and 10.4.9 nvidia kexts all stock

openmark bench : 18000

Click to view attachment

Pretty fast card, a clear 2000 points over a stock 7600GT. What is it clocked at default? And it's even fanless... sweet.

I think stock core clock is 560mhz or 580mhz : and this cards core clock is 650mhz

the card's cooling is quite nice and adiquate but im gonna be lapping and polishing that it up to be a bit cooler.

This is my first time to do this test.So is this result ok and is higher FPS better or not?
Graphic card : ATI X1950XTX 512RAM but this test see my card as X1900 series.

Could it be that the ATI drivers perform much better in OSX right now than Nvidia Drivers?

Here are my NVIDIA 7900 GTO results - I'm using a Dual Screen Setup, 1st mon: 1280x1024@85, 2nd mon: 1440x900@60hz.



Still, the ATI results MacIntelrator posted are mucho better.

Also, I've been trying Maya on OSX86 and it's unbearably slow. Marking Menus take about 0.25 to 0.50 seconds to accept, nothing is instant, it just feels totally sluggish.

Specs are in my sig. 7900GTX flashed to Quadro FX 5500:

Radeon X800 Stock
OpenMark final score: 9750

Sorry for no screenshot. It beach-balls at the end and never takes it.