Article: Parallelism at HotPar 2010
By: Mark Roulo (nothanks.delete@this.xxx.com), August 3, 2010 8:22 am
Room: Moderated Discussions
Michael S (already5chosen@yahoo.com) on 8/3/10 wrote:
---------------------------
>Well, there is at least one case in which I'd easily believe in 100x gain - case
>of your algorithm using texture interpolation.
>According to my understanding of HESS article they used texture units for efficient caching but not for interpolation.
>
Well, me, too.
If the paper says, "Hey, or GPU implementation crushes the CPU because we found a way to use the dedicated GPU hardware," then I'm fine. I also know that if my problem *can't* use this H/W, then the claimed speedups won't apply to my problems.
Without using the dedicated GPU H/W, though, I'm back to my basic claim: Showing a speedup greater than the extra available compute I find dubious without an explanation.
-Mark Roulo
---------------------------
>Well, there is at least one case in which I'd easily believe in 100x gain - case
>of your algorithm using texture interpolation.
>According to my understanding of HESS article they used texture units for efficient caching but not for interpolation.
>
Well, me, too.
If the paper says, "Hey, or GPU implementation crushes the CPU because we found a way to use the dedicated GPU hardware," then I'm fine. I also know that if my problem *can't* use this H/W, then the claimed speedups won't apply to my problems.
Without using the dedicated GPU H/W, though, I'm back to my basic claim: Showing a speedup greater than the extra available compute I find dubious without an explanation.
-Mark Roulo
