Article: Parallelism at HotPar 2010
By: anon (anon.delete@this.anon.com), August 5, 2010 4:47 am
Room: Moderated Discussions
AM (myname4rwt@jee-male.com) on 8/5/10 wrote:
---------------------------
>anon (anon@anon.com) on 8/4/10 wrote:
>---------------------------
>>AM (myname4rwt@jee-male.com) on 8/4/10 wrote:
>>---------------------------
>>>David Kanter (dkanter@realworldtech.com) on 8/3/10 wrote:
>>>---------------------------
>>>BS (nice try though). Read his post again (bw and FP advantage,
>>
>>You think that is BS? Then what is your number for BW and FP advantages of GPUs?
>
>BS is the GPGPU part. The poster doesn't narrow down his analysis to any particular class of workloads.
Huh??? Apparently everybody but you knows what GPGPU means. So either catch up or stay out of the conversation.
>>Which papers are claiming 100x? Are they also stating which CPUs were compared
>>against, and that they were comparing equivalent code and using all the parallelism
>>in the CPU? Please point out those papers.
>
>A short list in my other reply.
The list from the NVIDIA PR guy where every one I looked at seems dubious in one way or another? You didn't even read them let alone try to understand them yourself, did you? Otherwise you wouldn't be posting such drivel that backs up Kanter's arguments.
>>Stop going off topic.
>
>No off-topic.
Yes it is. Pull your head out of your ass and stop acting like a demented fanboy with no intellect of your own, or stop posting. End of story.
---------------------------
>anon (anon@anon.com) on 8/4/10 wrote:
>---------------------------
>>AM (myname4rwt@jee-male.com) on 8/4/10 wrote:
>>---------------------------
>>>David Kanter (dkanter@realworldtech.com) on 8/3/10 wrote:
>>>---------------------------
>>>BS (nice try though). Read his post again (bw and FP advantage,
>>
>>You think that is BS? Then what is your number for BW and FP advantages of GPUs?
>
>BS is the GPGPU part. The poster doesn't narrow down his analysis to any particular class of workloads.
Huh??? Apparently everybody but you knows what GPGPU means. So either catch up or stay out of the conversation.
>>Which papers are claiming 100x? Are they also stating which CPUs were compared
>>against, and that they were comparing equivalent code and using all the parallelism
>>in the CPU? Please point out those papers.
>
>A short list in my other reply.
The list from the NVIDIA PR guy where every one I looked at seems dubious in one way or another? You didn't even read them let alone try to understand them yourself, did you? Otherwise you wouldn't be posting such drivel that backs up Kanter's arguments.
>>Stop going off topic.
>
>No off-topic.
Yes it is. Pull your head out of your ass and stop acting like a demented fanboy with no intellect of your own, or stop posting. End of story.