Jump to content

Better OpenGL benchmarking, GioFX OpenMark


DiaboliK
 Share

87 posts in this topic

Recommended Posts

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)

 

post-14143-1174322912_thumb.jpg

X1300Pro.R1.OpenMark.result.txt

 

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 :poster_oops:)

Link to comment
Share on other sites

couple more of my cards:

 

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

 

post-14143-1174394227_thumb.jpg

Diabolik.7600GS.Fanless.OpenMarkresult.txt

 

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

 

post-14143-1174394532_thumb.jpg

Diabolik.X1600Pro.512.OpenMarkresult.txt

 

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

Link to comment
Share on other sites

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 OpenMark_result.txt

 

post-77533-1175070331_thumb.jpg

Link to comment
Share on other sites

:) 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.

post-57474-1175163458_thumb.jpg

post-57474-1175163701_thumb.jpg

post-57474-1175163747_thumb.jpg

post-57474-1175163765_thumb.jpg

Link to comment
Share on other sites

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.

 

post-57247-1175531394_thumb.jpg

Link to comment
Share on other sites

:blink: 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.

 

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

Link to comment
Share on other sites

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.

 

 

Link to comment
Share on other sites

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 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

Link to comment
Share on other sites

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 {censored}?

Link to comment
Share on other sites

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? :P

Link to comment
Share on other sites

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? :thumbsup_anim:

 

 

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.

Link to comment
Share on other sites

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.

post-57474-1175611950_thumb.jpg

post-57474-1175611971_thumb.jpg

post-57474-1175611986_thumb.jpg

Link to comment
Share on other sites

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 :D 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.

Link to comment
Share on other sites

 Share

×
×
  • Create New...