On Tuesday 28 October 2003 11:59 pm, Javier Villavicencio wrote:
Hi, and sorry, but as I said, in that moment I wasn't sure about the
CFLAGS, the correct one is: -frename-registers
And you can see it in the benchmark in the next mails of this thread.
OK, i tried using the -frename-registers;
On Tuesday 28 Oct 2003 20:47, Javier Villavicencio wrote:
-O2 -frename-regs = FASTER than -O2
I'll post my complete benchmarked results ASAP. It includes many more
CFLAGS (but for my architecture only, an AMD Athlon-XP).
Hmmm, I tried:
CFLAGS=-march=athlon-xp -O2 -frename-regs
Hi, and sorry, but as I said, in that moment I wasn't sure about the CFLAGS, the
correct one is:
-frename-registers
And you can see it in the benchmark in the next mails of this thread.
On Wed, 29 Oct 2003 07:31:12 +
Peter Ruskin [EMAIL PROTECTED] wrote:
On Tuesday 28 Oct 2003 20:47,
]
Subject: Re: [gentoo-user] gcc optimizations
On Tuesday 28 Oct 2003 20:47, Javier Villavicencio wrote:
-O2 -frename-regs = FASTER than -O2
I'll post my complete benchmarked results ASAP. It includes many more
CFLAGS (but for my architecture only, an AMD Athlon-XP).
Hmmm, I tried:
CFLAGS=-march
http://forums.gentoo.org/viewtopic.php?t=97809sid=f02545b072e69dbe7cf020e5e2034c0f
[...]
It could be a good idea to have some users running a
bash script that uploads the results+CFLAGS to some server so we could
have something to see and be able to compare flags / archs.
Something like gentoo
On Wednesday 29 October 2003 16:54, Van Eps, Nathan D. (James Tower)
wrote:
Just as a FYI, -fomit-frame-pointer is included in -O -O2 -O3 -Os
according to:
http://gcc.gnu.org/onlinedocs/gcc-3.3.2/gcc/Optimize-Options.html;.
Only if it does not affect debugging. In x86 it does so it is NOT
: [gentoo-user] gcc optimizations
On Wednesday 29 October 2003 16:54, Van Eps, Nathan D. (James Tower)
wrote:
Just as a FYI, -fomit-frame-pointer is included in -O -O2 -O3 -Os
according to:
http://gcc.gnu.org/onlinedocs/gcc-3.3.2/gcc/Optimize-Options.html;.
Only if it does not affect
with debugging.
From the document you linked.
-Original Message-
From: Sami Näätänen [mailto:[EMAIL PROTECTED]
Sent: Wednesday, October 29, 2003 11:15 AM
To: [EMAIL PROTECTED]
Subject: Re: [gentoo-user] gcc optimizations
On Wednesday 29 October 2003 16:54, Van Eps, Nathan D
OK, so some folks swear by -O3 optimizations, but alot of what I've
read suggests -O2 produces faster binaries.
I have a Pentium III (coppermine) @ 900MHz with 512M RAM and 1G swap.
What CFLAGS do I want? (questionably unstable optimizations that do
produce better results are OK)
-chris
--
http://gcc.gnu.org/onlinedocs/
Chris Graves wrote:
OK, so some folks swear by -O3 optimizations, but alot of what I've
read suggests -O2 produces faster binaries.
I have a Pentium III (coppermine) @ 900MHz with 512M RAM and 1G swap.
What CFLAGS do I want? (questionably unstable optimizations
Chris Graves wrote:
OK, so some folks swear by -O3 optimizations, but alot of what I've
read suggests -O2 produces faster binaries.
I was always under the impression that -O3 was so much better than -O2. Well, the other
day, I switched from -O3 to -O2. Not only does everything compile *so* much
-O3 (finline-functions to be exact) might create useless code that will
polute cache and throws away the advantages of using trace caches.
I use -O2 and this works fine for me.
Kind regards,
Joao Seabra
On Tue, 28 Oct 2003, Chris Graves wrote:
OK, so some folks swear by -O3 optimizations,
On Tuesday 28 October 2003 11:52 am, Chris Graves wrote:
OK, so some folks swear by -O3 optimizations, but alot of what I've
read suggests -O2 produces faster binaries.
I have a Pentium III (coppermine) @ 900MHz with 512M RAM and 1G swap.
What CFLAGS do I want? (questionably unstable
Joao Seabra wrote:
-O3 (finline-functions to be exact) might create useless code that will
polute cache and throws away the advantages of using trace caches.
I use -O2 and this works fine for me.
Kind regards,
Joao Seabra
On Tue, 28 Oct 2003, Chris Graves wrote:
OK, so some folks swear by
These are the results of benchmarking gcc optimizations compiling povray
(www.povray.org) using the benchmark.ini and the skyvase.pov from the unofficial
benchmarks pages.
Of course that this isn't so accurate about timings (I should have used some more time
consuming render, but I liked this
PLEASE NOTE (i forgot to tell this 8+|!!!)
these CFLAGS ARE NOT SAFE TO BUILD GENTOO WITH
SPECIALLY THESE:
-malign-double (after compiling mc with this, every file showed a size of 16384Gb 8+)
-maccumulate-outgoing-args (changes calling conventions, you have to build EVERYTHING
from scratch
Javier Villavicencio wrote:
PLEASE NOTE (i forgot to tell this 8+|!!!)
these CFLAGS ARE NOT SAFE TO BUILD GENTOO WITH
SPECIALLY THESE:
-malign-double (after compiling mc with this, every file showed a size of 16384Gb 8+)
That's nice to know. I'd just added it my CFLAGS. Luckily, I wasn't about
On Tue, 28 Oct 2003 22:59:46 +0100
Redeeman [EMAIL PROTECTED] wrote:
this is interresting, so i emerged povray, and did like you, but i
couldnt find the benchmark.ini you talk about, so i just did the command
u used, in the dir with the file u use, and this is result:
real0m2.568s
Redeeman wrote:
i've got an athlon xp 1800+, and a geforce2 intergrated GPU :-)
Just to avoid confusion, POV-Ray only uses your CPU for rendering.
Rick
Kitty5 NewMedia http://Kitty5.com
POV-Ray News Resources http://Povray.co.uk
TEL : +44 (01270) 501101 - ICQ : 15776037
PGP Public Key
Since were at it could you please have the kindness to look at my post:
http://forums.gentoo.org/viewtopic.php?t=97809highlight=benchmarksid=fc862184f192d314050a62c7f8fe9f55
Kind Regards,
Joao Seabra
On Tue, 28 Oct 2003, Javier Villavicencio wrote:
CFLAGS= -O3 -march=athlon-xp
20 matches
Mail list logo