Unigine Heaven 4.0 Benchmark! Updated 14.02.2013 + BIG GPU test

[kdtt]

Mountain Lion DP2, gtx260

[Regi Yassin]

Gigabyte GTX 580 Stock Clock

 

is this very good, good enough, not good or no at all?

 

10.7.3 Mac OS X Lion

[mitch_de]

Mountain Lion DP2, gtx260

Maybe a bit low - but we dont have any other GTX 260 to compare + your res isnt listed to .

Your gpu should give at least 2,5 * of the result of my 9600 GT (look my score screenshoots first post) which means score = > 2500 , using: 800x600 windowed, FSAA * 2, SHaders = High, Ani =4

Resoulution= + FSAA= + shaders= has the most effect on the score results - so if they are different to already listed results, its not possible to compare.

Different Ani filter and other parameters have less effect and so different settings here can compared even if the users used different settings in that parameters.

 

@ GTX 580:

Same here : your combination of res (1440x900) + 8* FSAA isnt already listed to compare.

But there are some GTX 570, GTX 460/470 results with other res / other FSAA settings. You could try to use similar settinsg and compare then.

 

HINT: Because the different possible settings (especially RES + FSAA + SHADERS) makes it hard to compare already benched GPUs,

PLEASE post also 800x600 windowed, FSAA * 2, Shaders = High, Ani =4 Result beside your other (for sure also interesting) full screen high res + 4* FSAA results.

[kdtt]

MountainLion dp2 gtx260

I guess score is bit low.

[mitch_de]

Yep indeed , to low compared to 9600 GT / 512 MB running "our" same comparable 800x600 settings.

[kdtt]

I newly installed Lion 10.7.3

but I guess score is still bit low. Do you think it's my graphics card's problem?

[Aivarz]

ML DP2

 

[mitch_de]

1920x1080 + FSAA * 2 may run (near) out of VRAM (not really but starts swapping VRAM RAM) if

You may reduce Textures Details (=corresponds 1:1 to VRAM usage, if enough MEDIUM vs HIGH doesnt matter in FPS speed) to MEDIUM (insted of HIGH) and bench again.

If much diff (>> 10%) VRAM was a bit to less for 1920x1080 + FSAA*2. Diff may occur more in the diff of Min FPS than Max FPS in that case.

[Thireus]

Gigabyte GTX 580 Stock Clock

 

is this very good, good enough, not good or no at all?

 

10.7.3 Mac OS X Lion

 

Wow very impressive. Anything special to do to have these incredible results?

What about your AGPM.kext?

 

Edit: Damn, once again I've been trolled by the screen resolution... nevermind, forget about it.

Edited March 19, 2012 by Thireus

[Aivarz]

Textures: high

 

Textures: medium

[mitch_de]

If Textures high vs medium give near same results, then VRAM was enough.

So 1900x1080 , FSSA*2 can be done with 512 MB without significant VRAM swapping.

[Graebags]

@Aivarz, These may make your day:

 

dp1 dp2

 

 

Edit:

My geekbench score was round 9500 for both Lion 10.7.3 (9483) and ML DP2 (9557).

[mitch_de]

@Graebags :

Really huge diff between DP1 + DP2! Did you use same AGPM settings/patches in both?

Also check if the cpu stepping (up) is working same way (geekbench will show you that!) , because also CPU MHz diff (by not working stepping) may give such an bad result in DP2.

[Aivarz]

My scores with DP1/DP2 was ~the same. And I have ATI card.

[mitch_de]

So, even some minor FPS diff (

[mitch_de]

Then the huge fps drop cames from drivers or not working AGPM (i prefer guessing).

Also it may happen that the drivers are OK but OpenGL benchmark has problems with it = fps lost.

Have you test Cinebench on DP2 vs 10.7.3 ? If also huge diff : drivers / AGPM if normal diff : Unique has problems.

[Graebags]

@mitch_de

With Cinebench 11.5 on Lion 10.7.3 I get 29.09, and on DP2 30.51.

With Galaxies on Lion 10.7.3 I get 646 GFlops, and on DP2 621.

With Luxmark v2 on Lion 10.7.3 I get 958, and on DP2 1096, for the default render.

 

With OpenGL Extensions Viewer my scores for the basic Cube range from 6718 to 7309 with Lion, and 731 to 749 with ML DP2, ie a HUGE drop.

 

Is this a Fermi and later Nvidia gpu problem?

[mitch_de]

OK - so we found out thats not the cpu clock and not the gpu clock - otherwise Cinebench would also be much slower in DP2.

So the DP2 drivers seems to be an problem for some OpenGL apps - but not for all. Some functions an OpenGL App uses / other not or the way it is using them gives problem or not.

It can be a bug in the drivers OR the problematic OpenGL Apps have some OpenGL code which isnt good for that OPenGL driver (Nvidia ) but not in general (, AMD seems not affected, also other Nvidia gputypes may not affected).

 

I also have NVIDIA (9600GT) and tested DP2:

For me NO FPS lost by DP2 vs DP1 - near same results as DP1 (which is also near 10.7.3).

So your FPS lost must be not an general problem with Nvida drivers but may come by your gpu type.

HINT: After clicking RUN (benchmark) you see SETTINGS menue : You could try to disable sound (its musc in the bench)- perhaps thats the problem?

Also check if you setup windowed (disable fullscreen!!) - perhaps somethings changed by VSYNC problems. In windowed mode vsync never matters. In fullscreen VSYNC does matter - even if OpenGL App has an setup for no vsyc . The drivers may NOT disable such in App disabled VSYNC if tehre is some bug in their vsyc driver part.

Also OpenGLExtensionsviewer works MUCH different in speed if VSYNC is working - to avoid vsync problems use window mode.

 

For me it doesnt matter sound on/off near same fps.

PIC shows usual 800x600, windowed, FSSA*2 , Shader = High, OS X ML DP2

[surfcaster]

I think that you liked mich_de

 

I would like to see the punctuation of something like if run on OS X

[oSxFr33k]

I deleted my post a few up since those screenshots where attachments and made screenshots this time. Very unhappy with my results. I had to delete AGPM because I was getting random freezing. 800 x 600 gives me the best scores!!

[mitch_de]

I would not change so much settings like Shaders M/H or Ani beside resolution and FSAA - last parameters are the main FPS parameters-

Leave Shaders always at HIgh and Ani at 4* - otherwise we have even more different settings to compare. Different res + different FSAA is enough to bench

 

Would also interesting_

Bench you results in non FSAA + windowed mode (800x600 or 1280x1024) vs same res but fullsreen.

Normally both sould run near same speed - otherwise vsync (only happens in fullscreen modes) limits FPS.

But normally vsync is switched off in such benchmarks - but may handled wrong by some gpu / driver combinations.

[^Andy^]

@Aivarz, These may make your day:

 

dp1 dp2

 

 

Edit:

My geekbench score was round 9500 for both Lion 10.7.3 (9483) and ML DP2 (9557).

 

 

I get similar results with my GTX570 DP1 v DP2 - Unigine scores in DP2 is roughly half the score i get in DP1. Cinebench and GLViewer reults are pretty much identical between DP1 and DP2 though (run GLViewer in full screen - for some reason it defaults to windowed on DP2?).

[mitch_de]

Can you compare windowed 800x600 no FSAA against 800x600 no FSAA fullscreen for DP2 ?

(Or FSAA *2 if you have benched 800x600 in DP1 already to compare also DP1)

So we can see if vsync handling may be the fps down (in fullscreen mode).

If ysync is off normally windowed vs fullscreen (same 800x600!) should not give much differences.

Also compare GLViewer results fullscreen vs windowed (same res!). Also should give not much diff if vsync is off .

[oSxFr33k]

I tried as you suggested and I saw no difference between windowed and full screen.

 

After many many benchmarks scenarios I realize where I start to suffer from FPS loss. In my case its screen resolution and not so much FSAA.

 

I am using 10.7.3 clean install and my graphics card is Mobile. I don't see any benchmarks other than mine on Mobile. It seems like most of the benchmark results posted so far are from Desktop Graphics Cards.

 

Even the GTX 460 I thought at first was mobile is why I was unhappy with my original results. I should be happy with these results I suppose unless I see someone post there mobile GTX460M with better results over my GTX560M. I doubt that will be the case though.

[^Andy^]

Can you compare windowed 800x600 no FSAA against 800x600 no FSAA fullscreen for DP2 ?

(Or FSAA *2 if you have benched 800x600 in DP1 already to compare also DP1)

So we can see if vsync handling may be the fps down (in fullscreen mode).

If ysync is off normally windowed vs fullscreen (same 800x600!) should not give much differences.

Also compare GLViewer results fullscreen vs windowed (same res!). Also should give not much diff if vsync is off .

 

I'll do this when i get some time but i know off hand that windowed glviewer results in dp2 are way way slower than fullscreen. I cant remember the exact figures but in Windowed mode the results are less than 1000 whilst in fullscreen they are over 5000.