I did some experiments with my current GPUs and I'm becoming more and more interested of the OpenCL platform. I am in scientific computing (so: matrices, geometrical algorithms, etc.)
However, I'm yet to get my hands on a high powered ATI card (like 5870/5970). I was intrigued by the incoming nVidia Fermi/Tesla. But the relative pricing and the stats of the nvidia seems mismatched if we compare to the ATI option.
From stats gathered on the net, I get for Gflops
- GTX280: single=622 double=78
- 5970: single=4600 double=928
- (Current) tesla C1060: single=933 double=78
- (New) GTX480: single=1344 double=168 [EDIT]
- (Future) tesla C2070: single=N/A double=630
Approx pricing: GTX280=450, 5970=650, tesla=1700
In the past, I was kind of partial toward nVidia... but these number are totally ludicrous!
I know this is only theoretical throughtput and real-life OpenCL code will not touch those, but even then... I would simply say wow to the 5970 (and its way cheaper than any Tesla).
Am I missing anything obvious here? did I get a stat wrong? is double-precision performance on ATI "that good" ?
Is there a catch? something like: on ATI the memory accesses would need to be coalesced perfectly (whereas, on GT200, the coalesced restrictions were lowered, in comparison to G80)