This is the mail archive of the gcc@gcc.gnu.org mailing list for the GCC project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: compiler performance

From: Richard Guenther <rguenth at tat dot physik dot uni-tuebingen dot de>
To: Dara Hazeghi <dhazeghi at yahoo dot com>
Cc: dewar at gnat dot com, danny at malisoft dot com dot br, gcc at gcc dot gnu dot org
Date: Wed, 11 Feb 2004 20:09:50 +0100
Subject: Re: compiler performance
References: <20040211172228.42274.qmail@web41115.mail.yahoo.com>

Dara Hazeghi wrote:


"C: compiled with gcc -march=pentium4 -msse2
-mfpmath=sse -O3 -s -mno-cygwin to optimize for my
CPU, enable SSE2 extensions for as many math
operations as possible, and link to Windows libraries
instead of Cygwin libraries."

Doubtless it would look even worse were they to use
Intel's compiler...

With gcc 3.3.1 they shouldn't have used -mfpmath=sse and for sure enabled -ffast-math, as probably all other compilers default to optimize for speed rather than correctness. Also adding -funroll-loops and -fomit-frame-pointer would probably help, we don't enable these even at -O3...

Richard.

References:
- Re: compiler performance
  - From: Dara Hazeghi

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]