anonymous (no@spam.com) on 8/4/10 wrote:
---------------------------
>>>I got an even better reality check for you: tell me the SPECint and SPECfp.
>>>
>>>I have yet to see GPGPU work well for problems that aren't parallel math.
>>>
>>>Like uhm, you know... the bulk of the code that people are dealing with.
>>
>>You should probably read at least a few posts up the thread before posting. The claims made were
>>
>>a) reported 100x [and above] speedups are crap (Kanter).
>>
>>b) *real* performance advantage of GPUs is 2.5x-5x if compared against well-optimized CPU code (Mark Roulo).
>>
>>While both *may* be true indeed (very easily for codes utilizing a very small portion
>>of GPU's hw), both are infinetely far from being a universal truth.
>
>Hence my suggestion w.r.t. SPECint and SPECfp.
>
>If GPGPUs pride themselves with the GP part, then they need to demonstrate
>actual GP performance rather than just parallel math performance.
>
>IMO they haven't so far... and won't, ever.

Suggest running SpecInt and SpecFP to people who argue that e.g. GPU is better than CPU at everything. I object to a couple of ridiculous claims mentioned above.