Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-18 Thread Martin Cracauer
In [EMAIL PROTECTED], Adrian Chadd wrote: Its squid's DNS routines, not the shared libraries. heck the squid-dev archies on http://www.squid-cache.org/, as someone found the lines of asm which are wrongly generated. I'd welcome a more specific place. I just don't have the time to search the

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-18 Thread Adrian Chadd
On Tue, Apr 18, 2000, Martin Cracauer wrote: In [EMAIL PROTECTED], Adrian Chadd wrote: Its squid's DNS routines, not the shared libraries. heck the squid-dev archies on http://www.squid-cache.org/, as someone found the lines of asm which are wrongly generated. I'd welcome a more

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-17 Thread Martin Cracauer
In [EMAIL PROTECTED], Adrian Chadd wrote: On Mon, Apr 10, 2000, Ville-Pertti Keinonen wrote: [EMAIL PROTECTED] (Kris Kennaway) writes: Can you say "gimmick"? :-) gcc often produces demonstrably broken code for optimisation levels higher than -O. That -O is safe seems to be a

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-17 Thread Martin Cracauer
In [EMAIL PROTECTED], Alexey N. Dokuchaev wrote: Hi! AFAIK, Linux Mandrake has it's kernel and userland highly optimized for Pentium architecture. However, they have additional gcc optimization flags turned on by default, including -O3 and -mfast_math. That they care for -mfast-math in

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-17 Thread Adrian Chadd
On Mon, Apr 17, 2000, Martin Cracauer wrote: j I have exactly the same problem hacking squid code under 4.0-CURRENT and 5.0-CURRENT. Basically, inside the dns routines a variable would be corrupted between a couple of non-relevant lines, and cause squid to segfault after trying to resolve

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-10 Thread Ville-Pertti Keinonen
[EMAIL PROTECTED] (Kris Kennaway) writes: Can you say "gimmick"? :-) gcc often produces demonstrably broken code for optimisation levels higher than -O. That -O is safe seems to be a persistent myth. GCC also produces broken code for -O and no optimization in some cases, sometimes while

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-10 Thread Adrian Chadd
On Mon, Apr 10, 2000, Ville-Pertti Keinonen wrote: [EMAIL PROTECTED] (Kris Kennaway) writes: Can you say "gimmick"? :-) gcc often produces demonstrably broken code for optimisation levels higher than -O. That -O is safe seems to be a persistent myth. GCC also produces broken code

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-09 Thread Martin Minkus
A very quick example of why big -O3 gcc optimizations are a bad thing? my /etc/make.conf has USA_RESIDENT=NO CFLAGS=-O3 -pipe -mcpu=pentiumpro -march=pentiumpro -fomit-frame-pointer NOPROFILE=true (NOPROFILE=true because profiled libraries fail to build with no frame pointer) now, cd

What are the best gcc optimization options for Pentium 200 MMX

2000-04-08 Thread Alexey N. Dokuchaev
Hi! AFAIK, Linux Mandrake has it's kernel and userland highly optimized for Pentium architecture. However, they have additional gcc optimization flags turned on by default, including -O3 and -mfast_math. I'm trying to achive maximum performance of my FreeBSD 4.0-RELEASE box, and going to

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-08 Thread Pedro F. Giffuni
FWIW, I understand that they carry pgcc (http://www.goof.com) which may be very risky under Linux. Linus doesn't even recommend the latest gcc because he likes to keep his kernel dependent on the old (non-standard) features. Look in the archives, I recall someone benchmarked the new gcc on this

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-08 Thread Matthew Dillon
:On Sat, 8 Apr 2000, Alexey N. Dokuchaev wrote: : : AFAIK, Linux Mandrake has it's kernel and userland highly optimized for : Pentium architecture. However, they have additional gcc optimization : flags turned on by default, including -O3 and -mfast_math. : :Can you say "gimmick"? :-) gcc often

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-08 Thread Kenneth Wayne Culver
Why exactly whould you not touch the -march options? I have had no problems using them, and my system (5.0-CURRENT) seems a little faster with -march=i686. I could be wrong though as I havn't done any exact tests... it just seems a bit more responsive..

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-08 Thread Matthew Dillon
: :Why exactly whould you not touch the -march options? I have had no :problems using them, and my system (5.0-CURRENT) seems a little faster :with -march=i686. I could be wrong though as I havn't done any exact :tests... it just seems a bit more responsive.. :

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-08 Thread David Malone
On Sat, Apr 08, 2000 at 09:25:16PM +0700, Alexey N. Dokuchaev wrote: I'm trying to achive maximum performance of my FreeBSD 4.0-RELEASE box, and going to recompile kernel and world using -Os -pipe options. Is there any additional flags I might consider turning on (like -mfast_math) to make

Re: What are the best gcc optimization options for Pentium 200 MMX

2000-04-08 Thread Kenneth Wayne Culver
Thanks :-) = | Kenneth Culver | FreeBSD: The best OS around.| | Unix Systems Administrator | ICQ #: 24767726 | | and student at The | AIM: muythaibxr | | The University of