2.7 Viewport benchmark

Hi,

thanks to @Thanzex who found the benchmark and lapineige who fixed the benchmark to work with 2.7, here’s a viewport benchmark to have an idea of how graphic cards handle viewport.

EDIT : the benchmark has been updated by elvios : https://db.tt/yVWaXC58

Please post your results as this :

CPU :
GPU :
Screen resolution :
Overall score :
Overall Time :

I don’t know how CPU is important for display when we have a GPU.

My results :

CPU : i7 980x
GPU : GTX 580 3Gb
Screen resolution : 1920 x 1150
Overall score : 7.2
Overall Time : 2’31"

On my laptop :

CPU : U4100 @1,3 Ghz
GPU : -
Screen resolution : 1365 x 678
Overall score : 0.7
Overall Time : 28’6"

Hi. :

CPU : i5 3570K
GPU : GTX 760 4 GB
Screen resolution : 1919 x 997
Overall score : 8.4
Overall Time : 2’10"

It make not much difference if you set VBO on or off, why?

Cheers, mib

CPU : [email protected]
GPU : GT 630 1GB
Screen resolution : 1919 x 1052
Overall score : 8.5
Overall Time : 1m50s

screenshot


Hi

CPU : i7 4770
GPU : GTX 780 ti SC
Screen resolution : 1901 x 959
Overall score : 11.0
Overall Time : 1 min 28 sec

Cheers, Wayne

CPU : i7 4930K @ 4.5GHz
GPU : GTX 760 4 GB
Screen resolution : 1919 x 1095
Overall score : 10.6
Overall Time : 1’ 31"


CPU : i7 3930K @4.2GHz
GPU : GTX 580 3GB
Screen resolution : 1919 x 990
Overall score : 7.2
Overall Time : 2 min 27 sec

What surprises me is the Sculpt mode Matcap is twice faster than the Solid Mode (19.41 fps vs 10.94fps). I thought matcap was slower than OpenGL lights?

CPU :i5-2500k
GPU : radeon 7850
Screen resolution : 1917 x 1149
Overall score : 7.1
Overall Time : 2 min 6 sec

not many amds here

cpu: Core i7-860 @ 2.8Ghz
gpu: ATI Radeon HD 4850 (512MB)
Screen resolution : 1838 x 1037

Overall score : 15.9

Overall Time (to run the benchmark): 2 min 1 sec

CPU : i7 Q 720 @1.60 GHz
GPU : AMD Mobility Radeon HD 5000 Series (1GB)
Screen resolution : 1599 x 820
Overall score : 16.0
Overall Time : 2 min 14 sec

Looks like AMD GPU wins in OpenGL. Would like to see a result from somebody with a professional Nvidia card like Quadro or Tesla, because these should perform well in OpenGL

I did not know there was a benchmark for the viewport, great!

Well, I knew that I have the worst nvidia GT 430 in the market (Biostar), but I did not expect my integrated intel HD4000 is much better. So, I’ll have to research about how to solve some problems that I have with intel (Blender closes with segmentation fault when selecting objects)

nvidia

OS: Kubuntu 14.04
CPU : i7 3770
GPU : GT 430 1GB - nvidia 331.38
Screen resolution : 1919 x 994
Overall score : 6.4
Overall Time : 3 min 6 sec

intel

OS: Kubuntu 14.04
CPU : i7 3770
GPU : iGPU HD4000
Screen resolution : 1919 x 994
Overall score : 10.7
Overall Time : 1 min 58 sec

Edit:
So, Are these benchmarks ok? Curious results in ATI vs nvidia on viewport, particularly those in ATI where they get high scores with no really good time. :eyebrowlift2:

Edit 2:
I solved the intel problem by restoring Blender settings.

benchmarked again with “double sided” off

CPU : [email protected]
GPU : GT 630 1GB

double sided on:
Screen resolution : 1919 x 1052
Overall score : 8.5
Overall Time : 1m50s

double sided off:
Screen resolution : 1919 x 1052
Overall score : 14.5
Overall Time : 1m18s

screenshot:


My results :

Core i7 950
GTX 780
16go of ram

BLENDER VIEWPORT BENCHMARK

Blender Version: (2, 71, 5)
Platform: b’Windows:64bit’

RESULTS
Screen resolution : 2559 x 1341

Overall score : 7.5

Object mode, Solid | Score: 11.0
50k faces: 59.98 fps
50k faces, with subsurf, 2 levels: 10.22 fps
750k faces: 13.48 fps

Object mode, Wireframe | Score: 7.0
50k faces: 59.97 fps
50k faces, with subsurf, 2 levels: 17.72 fps
750k faces: 56.99 fps

Edit mode, Solid | Score: 7.5
50k faces: 29.77 fps
50k faces, with subsurf, 2 levels: 8.52 fps
750k faces: 2.03 fps

Edit mode, Wireframe | Score: 10.2
50k faces: 58.84 fps
750k faces: 4.00 fps

Sculpt mode, Solid | Score: 4.5
4 levels multires (750k faces): 15.29 fps
5 levels(2.5mln faces): 3.68 fps

Sculpt mode, Matcap | Score: 4.7
4 levels multires (750k faces): 23.39 fps

VBOs: True
Draw Method: AUTOMATIC
Overall Time (to run the benchmark): 2 min 20 sec

CPU : Intel i7 3930K @ 3.20 Ghz
GPU : NVIDIA GTX 580 | 3 GB RAM
Screen resolution : 1919 x 1026
Overall score : 7.4
Overall Time : 2’ 29"

BLENDER VIEWPORT BENCHMARK

Blender Version: (2, 71, 0)
Platform: b’Linux:64bit’

RESULTS
Screen resolution : 1919 x 1026

Overall score : 7.4

Object mode, Solid | Score: 9.9
50k faces: 60.02 fps
50k faces, with subsurf, 2 levels: 9.62 fps
750k faces: 11.33 fps

Object mode, Wireframe | Score: 8.3
50k faces: 60.01 fps
50k faces, with subsurf, 2 levels: 27.17 fps
750k faces: 58.70 fps

Edit mode, Solid | Score: 8.3
50k faces: 31.45 fps
50k faces, with subsurf, 2 levels: 10.08 fps
750k faces: 2.10 fps

Edit mode, Wireframe | Score: 10.6
50k faces: 60.12 fps
750k faces: 4.40 fps

Sculpt mode, Solid | Score: 3.2
4 levels multires (750k faces): 10.67 fps
5 levels(2.5mln faces): 2.60 fps

Sculpt mode, Matcap | Score: 4.0
4 levels multires (750k faces): 19.85 fps

VBOs: True
Draw Method: AUTOMATIC
Overall Time (to run the benchmark): 2 min 29 sec

CPU : i7 Q 720 @1.60 GHz
GPU : AMD Mobility Radeon HD 5000 Series (1GB)
Screen resolution : 1599 x 820
Overall score : 16.0
Overall Time : 2 min 14 sec

Looks like AMD GPU wins in OpenGL. Would like to see a result from somebody with a professional Nvidia card like Quadro or Tesla, because these should perform well in OpenGL

This is what I would like to see as well; along with some more AMD / FireGL cards.

CPU : i7 [email protected]
GPU : AMD Radeon HD6950
Screen resolution : 1679 x 960
Overall score : 46.7
Overall Time : 1 min 3 sec

VBOs: True
Draw Method: OVERLAP_FLIP

Blender 2.71 64bit

This test is useless, I am sorry to say:

  • on Nvidia cards the FPS is capped at 60fps by the driver, artificially lowering the results. For example, on my 7970 I get 517fps on the 50k faces Solid. Any Nvidia card gets ~60fps on this test.
  • in edit mode the CPU is taxed much more than the GPU, making it impossible to make useful comparisons in regards to GPU performance between systems.
  • the tests include models with active subsurf modifiers, which slow down Blender, and are not GPU optimized at all. They should be applied before testing.
  • some of us may have anti-aliasing activated in Blender, again skewing the results.
  • the draw method should be identical for everyone, but some of us use a different draw method while testing.
  • version 2.71 beta runs faster on average in this test than version 2.70. Especially in edit mode 2.71 seems faster.
  • there is no textured model mode test with bitmap textures at varying sizes. That would be a telling test. For real world work at least one textured semi-complex model should be included in a GPU test.

The 60fps cap alone completely invalidates any comparison between Nvidia and AMD cards.

The bolts scene, for example: when I add a subdivide modifier set to 3 (3,110,544 faces) runs at 2.72FPS. When applied it runs at a healthy 80fps on my system (without anti-aliasing). The subd modifier should be kept out of ANY GPU test in Blender.

All in all, this test is fundamentally flawed on so many levels it is not really worth our time. Which, I believe, I already stated when it was posted on these forums the first time. It tells us a lot about the caveats in Blender’s performance on different levels, but tells us nothing useful about the GPU performance on different systems.

I appreciate the effort, though. Someone should come up with a well-thought out one.

herbert123 is right - there should be some rules what is enabled and what not

anyway - with sync to vblank off

CPU : [email protected]
GPU : GT 630 1GB

sync to vblank: on
double sided on:
Screen resolution : 1919 x 1052
Overall score : 8.5
Overall Time : 1m50s

sync to vblank: on
double sided: off
Screen resolution : 1919 x 1052
Overall score : 14.5
Overall Time : 1m18s

sync to vblank: off
double sided: off
Screen resolution : 1919 x 1052
Overall score : 20.7
Overall Time : 1m07s

screenshot:


edit:

window draw method: full
sync to vblank: off
double sided: off
Screen resolution : 1919 x 1052
Overall score : 24.7
Overall Time : 1m05s

… ^^

I think maybe it is as you say. With intel I get better scores than nvidia, but when normal blender usage the viewport works really slow with intel (linux). Furthermore, with the systems in similar conditions and with the same graphics card, sometimes I get different results ​​when running the benchmarak.
I do not know…

Edit:
So, now I do not know if what I said above is correct, you see the two subsequent messages

disable vsync
disable “double sided” for the 3 meshes (is off by default but not in the bench) - object data -> normals
run in fullscreen mode alt+f11

Disabling VSync in nvidia-settings I win only a few seconds. But disabling double sided now I get:
Overall score : 11.8
Overall Time : 1 min 24 sec

Before I got:
Overall score : 6.4
Overall Time : 3 min 6 sec

So “double sided” was the culprit, regarding the difference I noticed when using blender with nvidia compared with intel in relation to the results I got before.

Thanks.