os that rather uses the gpu?

JD jd1008 at gmail.com
Fri Jul 16 03:22:37 UTC 2010


  On 07/15/2010 05:58 PM, Robert Myers wrote:
>
>
> On Thu, Jul 15, 2010 at 8:12 PM, JD <jd1008 at gmail.com 
> <mailto:jd1008 at gmail.com>> wrote:
>
>     .
>     >
>     "There he goes again"
>     I did not choose any position. I merely stated a fact and you
>     concocted
>     from that, that I am taking a position on the issue.
>     I am an old timer by the average age of this list's subscribers. I was
>     around when the pdp 8 and pdp 11 were  used to teach
>     assembly language programming.
>
>
> Quoting you:
>
> "This is the kind of technology that is needed to solve huge mathematical
> problems."
>
> Highly questionable.  Mostly wrong.  Ok?
>
> Bandwidth.  Bandwidth.  Bandwidth.
>
> And it's a big problem for GPU's which are really, really good at 
> pounding the living daylights out of small datasets, but of marginal 
> usefulness for "huge mathematical problems," except for a small subset 
> of such problems, like linpack.  I've argued this over and over again 
> publicly.  People who actually control budgets already know what I 
> have to say.  The most interesting problems are bandwidth-bound, not 
> compute-bound.
>
> If I could have a Fermi, would I?  You bet, because I want to play 
> with one.  Do I expect it to open up new ground that in any way 
> reflects naive measures of its computational power?  No, I don't.
>
> Robert.
>
Listen Robert, you can disagree on the usefulness
and utilization for solving large problems.
But that hardly grants you the license to disparage
another member of this list.
If you do not think your comment:
 > If you think flops is a good measure of the science you can do, you
 > should probably be in a different business.
is at least disparaging, if not outright nasty.
Please refrain from making them.



More information about the users mailing list