| 1 |
On Fri, 18 Jul 2008 10:24:58 -0400 (EDT) |
| 2 |
Adam Stylinski <stylinae@××××××××.edu> wrote: |
| 3 |
> GCC 4.3 is catching up, but they are no where near utilizing SSE4 or |
| 4 |
> SSE5 instructions. |
| 5 |
> |
| 6 |
> http://blog.alphagemini.org/2008/03/icc-vs-gcc-43.html |
| 7 |
> |
| 8 |
> He concludes that it's not worth pursuing, but I beg to differ. |
| 9 |
> Those are signifcant differences for a processor. |
| 10 |
|
| 11 |
He doesn't establish whether the code in question is highly cpu-bound |
| 12 |
or not when run on his system. For a lot of memory- and i/o-bound code, |
| 13 |
there's little practical difference between gcc with optimisations |
| 14 |
turned off and gcc with -frice-my-shorts except that the former |
| 15 |
compiles an order of magnitude faster. |
| 16 |
|
| 17 |
The more interesting question, then, is whether users run any |
| 18 |
non-trivial cpu-bound programs. We know the applied science types do, |
| 19 |
but they tend to be the ones who're doing clever things with icc |
| 20 |
anyway. What about normal users? |
| 21 |
|
| 22 |
-- |
| 23 |
Ciaran McCreesh |
Archives