| 1 |
On Wed, Aug 13, 2003 at 04:24:32PM +0200, David Holm wrote: |
| 2 |
> If they really wanted to test the speed why didn't they use more aggressive compiler flags? |
| 3 |
> |
| 4 |
> I think it should be investigated which packages could be compiled by icc since |
| 5 |
> intel are now providing it for free for non-commercial use. I did some tests with it and |
| 6 |
> whetstone (classic fpu benchmark from the 1970's) doubled in speed compared to gcc on a P4, and |
| 7 |
> it was about 75% faster on an Athlon-XP. Now float-point isn't everything but from my experience |
| 8 |
> icc generally produces better optimized code than gcc unless the application has been hand-tuned |
| 9 |
> (like mplayer). |
| 10 |
> I tried installing gentoo with CC=icc once but I had problems with many ebuilds so I dropped |
| 11 |
> that idea. At the moment extremely few ebuilds support icc. |
| 12 |
> |
| 13 |
|
| 14 |
That's because there's no reason each and every ebuild needs to have |
| 15 |
something changed when most of the time 'supporting icc' is just a |
| 16 |
matter of altering the usual environment variables... |
| 17 |
|
| 18 |
At the moment Zadeh and einride are working on ICC integration. einride |
| 19 |
has some excellent ideas about Portage integration, so hopefully that'll |
| 20 |
get us somewhere. |
| 21 |
|
| 22 |
-- |
| 23 |
Jon Portnoy |
| 24 |
avenj/irc.freenode.net |
| 25 |
|
| 26 |
-- |
| 27 |
gentoo-dev@g.o mailing list |
Archives