Article: Parallelism at HotPar 2010
By: anon (anon.delete@this.anon.com), August 2, 2010 3:32 am
Room: Moderated Discussions
AM (myname4rwt@jee-male.com) on 8/2/10 wrote:
---------------------------
>David Kanter (dkanter@realworldtech.com) on 7/29/10 wrote:
>---------------------------
>...
>>When I hear crap like "the only interesting workloads are amenable to GPUs", it's
>>quite annoying. Ditto for claimed 100X speed ups.
>
>Weren't you provided with a link some months ago (or perhaps last year) to where
>you can find many original sources of GPU-related work which you can study?
>
>Wasn't it suggested to you that should you (or anyone else, for that matter) choose
>to dispute results obtained by particular researchers, it should better be done
>by referencing the work and showing why quoted results are misleading, downright wrong etc.?
>
>And since you are apparently calling crap all 100x and higher speedups, it's reasonable
>to ask if you have any proof wrt every piece of published research with such results.
>I don't think you have any though.
I didn't see this, could you point it out to me? This is an apples to apples comparison, of optimized and parallelized (simd and mimd) code on both GPUs versus contemporary CPUs of today, right?
---------------------------
>David Kanter (dkanter@realworldtech.com) on 7/29/10 wrote:
>---------------------------
>...
>>When I hear crap like "the only interesting workloads are amenable to GPUs", it's
>>quite annoying. Ditto for claimed 100X speed ups.
>
>Weren't you provided with a link some months ago (or perhaps last year) to where
>you can find many original sources of GPU-related work which you can study?
>
>Wasn't it suggested to you that should you (or anyone else, for that matter) choose
>to dispute results obtained by particular researchers, it should better be done
>by referencing the work and showing why quoted results are misleading, downright wrong etc.?
>
>And since you are apparently calling crap all 100x and higher speedups, it's reasonable
>to ask if you have any proof wrt every piece of published research with such results.
>I don't think you have any though.
I didn't see this, could you point it out to me? This is an apples to apples comparison, of optimized and parallelized (simd and mimd) code on both GPUs versus contemporary CPUs of today, right?