GTX580 floating point performance

Discussion of ArrayFire using CUDA or OpenCL.

Moderator: pavanky

GTX580 floating point performance

Postby Lars1 » Fri Dec 03, 2010 7:33 am

Hi.

I have just finalized some floating point performance test of the GeForce GTX580. As expected it was the fastest single precision performance I have ever measured. The peak single precision performance was 849 GFlops, and peak double precision performance was 193 GFlops. For comparison the Tesla C2050 delivered 550 GFlops single precision peak performance, and 250 GFlops in double precision performance.

Single precision:
i7x975_GTX580_flopsSGeMMjkt_W7J160.jpg
i7x975_GTX580_flopsSGeMMjkt_W7J160.jpg (182.74 KiB) Viewed 3150 times



Double precision:
i7x975_GTX580_flopsDGeMMjkt_W7J160.jpg
i7x975_GTX580_flopsDGeMMjkt_W7J160.jpg (180.08 KiB) Viewed 3150 times


I hope the results may be useful. I will soon upload it to Torben's Corner - but it will likely have to wait for my Christmas holidays.

Torben
--
Editor of "Torben's Corner" - http://wiki.accelereyes.com/wiki/index.php/Torben's_Corner
Cluster: 2 x X5670 + 20 x X5570 | 18 x C2070 & 15 x GTX580
Colfax CXT2000i: GTX465 & GTX580 | FX3800 & 4000 | C1060 & C2050
Lars1
 
Posts: 140
Joined: Thu Jul 23, 2009 7:28 am

Re: GTX580 floating point performance

Postby gallagher.pryor » Fri Dec 03, 2010 1:17 pm

Wow - that's really impressive. Is it then correct to compare these results to the charts @ http://wiki.accelereyes.com/wiki/index.php/MTIMES_Benchmarks ?

Are these still up to date? Here are the charts themselves... (wow the img tag worked! awesome!)

Image

Image
User avatar
gallagher.pryor
 
Posts: 562
Joined: Wed Jun 11, 2008 10:54 am

Re: GTX580 floating point performance

Postby Lars1 » Fri Dec 03, 2010 1:26 pm

Yes, I believe you can compare.

Below find we a couple of different GPUs for comparison.

Single precision:
specialPlot_SP.jpg
specialPlot_SP.jpg (265.16 KiB) Viewed 3137 times



Double precision:
specialPlot_DP.jpg
specialPlot_DP.jpg (262.36 KiB) Viewed 3137 times



Torben
--
Editor of "Torben's Corner" - http://wiki.accelereyes.com/wiki/index.php/Torben's_Corner
Cluster: 2 x X5670 + 20 x X5570 | 18 x C2070 & 15 x GTX580
Colfax CXT2000i: GTX465 & GTX580 | FX3800 & 4000 | C1060 & C2050
Lars1
 
Posts: 140
Joined: Thu Jul 23, 2009 7:28 am

Re: GTX580 floating point performance

Postby rollyng » Tue Feb 01, 2011 2:21 am

Hi, the above benchmarks seem verified the claim of deliberate reduction of double precision floating point performance of the GForce series...
http://forums.nvidia.com/index.php?showtopic=164417

Anyway, in terms of Cash/Performance ratio, GTX580 is still better than Tesla series :mrgreen:
rollyng
 
Posts: 30
Joined: Fri Jan 14, 2011 11:30 am
Location: HKSAR

Re: GTX580 floating point performance

Postby malcolm » Tue Feb 01, 2011 11:11 am

Jacket 1.7 is in the works and will be using CUDA 3.2. In our experiments, we found that CUBLAS matrix multiply performance went down for certain sizes. We benchmarked cublasSgemm on a Tesla C1060 using the 260.x driver and just switching the toolkit library between cuda3.1 and cuda3.2. The new version using MAGMA is still a big improvement in consistency! It's very tough to get such stable trendlines (blue).
cublas_comparison.png
cublasSgemm comparison in GFLOPs
cublas_comparison.png (17.41 KiB) Viewed 2916 times
James Malcolm (malcolm@accelereyes.com)
User avatar
malcolm
 
Posts: 600
Joined: Sat Jun 14, 2008 11:00 pm


Return to Programming & Development with ArrayFire