(j3.2006) IEEE and the GPU world

[Dick Hendrickson]

On Wed, Jun 23, 2010 at 2:38 PM, Keith Bierman <khbkhb at gmail.com> wrote:

> Should the Standard really prescribe that deeply?
>
> On  a GPU that observes only the bit patterns but nothing else, I'd hope
> that whether the IEEE stuff "worked" was a compiler option .. because
> clearly anyone trying to do careful numerical reasoning is going to want
> "no" and people who are more relaxed might want a different answer so they
> could keep their source code "the same".
>
> Future GPUs might have better support, at least for some features, and then
> it's more like what Dick suggests ;>
>
> The current GPU situation is vaguely akin to the early array processors
> (FPS, et al) we didn't craft special definitions for them, the market moved
> on, and better integrated solutions won the day (and made for an easier
> model for the Standard ;>).
>

I think Keith hit the nail on the head here.  It's too early to decide what
to do (don't just do something, stand there!).

My previous suggestion still has merit.  I think it's exactly similar to
REAL*4HENRY.  When many compilers see that, they issue a message saying
approximately "your program is non-standard, we'll try to guess what you
mean and continue."  And it works, the vendors have a vested interest in
doing the right thing.  I think the same process will work with IEEE and
GPU.  Moderately non-portable, but for now people can get used to not having
IEEE features work on a line-by-line basis.

Dick Hendrickson

>
> History doesn't always repeat, but it is often the way to bet ;>
>
>
> Keith Bierman
> khbkhb at gmail.com
> kbiermank AIM
> 303 997 2749
>
>
>
>> _______________________________________________
>> J3 mailing list
>> J3 at j3-fortran.org
>> http://j3-fortran.org/mailman/listinfo/j3
>>
>>
>
> _______________________________________________
> J3 mailing list
> J3 at j3-fortran.org
> http://j3-fortran.org/mailman/listinfo/j3
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://j3-fortran.org/pipermail/j3/attachments/20100623/81844f55/attachment.htm>