GPU benchmarks

[savage309]

i tested again under the latest drivers 347.52 and i never get the same results:

2210.219 KPaths/s - 2m13.9s
1450.108 KPaths/s - 2m15.1s
1484.116 KPaths/s - 2m13.3s

does anyone knows what the differences are coming from ?

The KPaths per second we show is not an average value (and some fluctuations there can occure). You have seen its current value of the moment the render has ended. The total render time is what is important here and that deviation is small and completely normal (and is caused by the fact that V-Ray runs on top of OS & GPU driver).

[3LP]

Not sure,
I also got different result each time I render again, it's always quite close though.

[walee]

i tested again under the latest drivers 347.52 and i never get the same results:

2210.219 KPaths/s - 2m13.9s
1450.108 KPaths/s - 2m15.1s
1484.116 KPaths/s - 2m13.3s

does anyone knows what the differences are coming from ?

[3LP]

Just updated your results to the chart, but someone just added a Titan Z!
It's beating my Tri-GTX 970!

I should probably have gone for that one. Price is about the same but uses only 1 pci and has 6Gb in staid of 4.
Next time

[walee]

my score with my GeForce GTX TITAN

nvidia 347.25
V-RAY RT 3.10.03
1503.897 KPaths/s
2m18.2s elapsed

nvidia 347.52
V-RAY RT 3.10.03
1461.614 KPaths/s
2m22.1s elapsed

[3LP]

That's the spirit

[Arjan Jacques]

Yes, added my score and the graph below was auto updated. Nice!

[3LP]

ah ha, just saw I gave the wrong credantials

Try now :

https://docs.google.com/spreadsheets...it?usp=sharing

Cheers

[Arjan Jacques]

GTX 580 / nvidea drivers 347.25 - 3m22,8 sec
Max 2014, vray 3.10.02

I was not able to update the spreadsheet

[3LP]

I quickly jumped in gDocs and did a spreadsheet with the data.
It should be shared and editable by anyone here :
https://docs.google.com/spreadsheets...it?usp=sharing

I think the image should be updated automatically every-time we add info, so this could be a good way to have users input :

Stan

[3LP]

GTX 780 Ti / 340.52 - 2m14
GTX 780 Ti / 340.52 - 1m52 (OC +220Mhz)

I do have one of the best GTX 780 Ti though, the "ZOTAC GeForce GTX 780 Ti OC"
I thought newer cards would actually be better than mine, doesn't seems so, makes me think again about buying those new GTX 9xx.

Stan

[urbanite]

Thanks for the results Peter. I just run the test with my K6000 and the time is 2.41... I wonder what could be the reason of such difference, vray and driver version the same.

[matanov]

Hi there, we have run some tests in the office.

Scene used - http://ftp.chaosgroup.com/support/benchmark_scene.zip with max paths per pixel = 512, so we are looking at the time of completion .
V-Ray version official 3.10.02 for 3ds Max
Note the different times with different driver versions.

Soooo here are the results:
Quadro K2200 / 341.05 - 9m 43,7s
Quadro K6000 / 341.12 - 2m 13s
Quadro K5200 / 341.05 - 3m 9,7s
Quadro K4200 / 341.21 - 4m 54,7s
GTX 550Ti / 340.52 - 11m 25s
GTX 560 / 340.52 - 6m 49,7s
GTX 560 / 335.23 - 6m 48s
GTX 770 / 344.75 - 4m 22,6s
GTX 770 / 340.52 - 5m 17,5s
GTX 770 / 344.60 - 4m
GTX 750 / 340.52 - 8m 55s
GTX 570 / 334.89 - 4m 22s
GTX 980 / 344.16 - 2m 57,7s
GTX 980 / 347.09 - 2m 30,9s
GTX 980M / 344.45 - 4m 32s
GTX 480 / 340.52 - 4m 9.5s
GTX 660Ti / 331.82 - 6m
GTX 660Ti / 344.48 - 5m 45,7s
GTX 690 / 340.52 - 2m 11s
GTX 590 / 334.67 - 5m 12s
Tesla K40 / 332.76 - 3m 10,6s

[werticus]

You know, when we were first looking at GPUs I was looking real hard at the 780ti and I'm kinda wishing we had gone with two of them instead of one Titan Blck (or 4)...we thought the extra RAM would be important, but with the limits to the RT, we're not using the GPU for big scenes like we thought we would...more for product demos and cars, where the scene is usually pretty small (or can be). But having double the cores would really change the game for our render frame rate - for animation demos you could get decent quality renders at like 10 secs a frame if you had 10,000 cores.
Just a word of advice to anyone in the market - worry more about the core count than RAM, at least with the currently supported features, and plan on using RT for object demos/animations, not arch viz or anything with a complex environment (the shader support is just too poor right now).

Interesting... I've never found RT to be useful for complex stuff yet either. Maybe if i built from the ground up for it, but it just seems unstable most of the time.

[werticus]

I did some GPU performance testing on viewport performance:

http://forums.chaosgroup.com/showthr...576#post625576

I also tested a Quadro K5000 in RT and got 14mins or so for the frame :-\