Hi,
Roland Orre wrote:
> Some days ago Terry Alden <[EMAIL PROTECTED]>
> provided us with a POSIX thread benchmark test, pi.c, for SMP machines
>
> First I have observed that some people have used different optimization
> parameters for gcc, Terry Alden suggested -O but some have used -O6,
> which on my machine gives about twice the performance. For this test
> to give the desired result it is of course essential to have the same
> optimization setup.
I used -O (not -O6) as a optimization parameter, and checked that -O0
(no optimization) gave twice the execution time compared with -O.
But I noticed after reading your mail that -O6 gave no difference in
performance with -O, so my compiler (gcc-2.8.1, compiled and installed
by hand) may have something wrong.
If you mention my result, I have to appologize you to give wrong result.
> Secondly my mailserver reported that there is problem with the mailserver
> at logicalvision, the requester of this benchmark, Terry Alden, may not
> even get our results. I got the message "Relaying denied" when sending
> both to "<[EMAIL PROTECTED]>" as well as <[EMAIL PROTECTED]>
>
> My suggestion is that we STOP sending any more results to Terry Alden and
> to this list, UNTIL Terry can verify that he can recive information and
> that the benchmarks test may still be wanted.
I quite agree with you at this point.
Thank you in advance,
Yasunari OKUDA
-
Linux SMP list: FIRST see FAQ at http://www.irisa.fr/prive/mentre/smp-faq/
To Unsubscribe: send "unsubscribe linux-smp" to [EMAIL PROTECTED]
