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]

Re: Multiplications on Pentium 4

To: Frank Klemm <pfk at fuchs dot offl dot uni-jena dot de>
Subject: Re: Multiplications on Pentium 4
From: Torbjorn Granlund <tege at swox dot com>
Date: 10 Sep 2001 11:11:13 +0200
Cc: Jan Hubicka <jh at suse dot cz>, gcc at gcc dot gnu dot org
References: <20010827121624.D8568@atrey.karlin.mff.cuni.cz><20010827143032.C636@fuchs.offl.uni-jena.de><20010827173025.F11402@atrey.karlin.mff.cuni.cz><20010901202854.A7713@fuchs.offl.uni-jena.de><20010902000000.C27182@atrey.karlin.mff.cuni.cz><20010902024104.F7713@fuchs.offl.uni-jena.de><20010903171717.E13574@atrey.karlin.mff.cuni.cz><20010904215156.C438@fuchs.offl.uni-jena.de><007001c1358e$6f53b6f0$7edd18ac@amr.corp.intel.com><20010905134405.G15564@atrey.karlin.mff.cuni.cz><20010907200403.A5281@fuchs.offl.uni-jena.de>

Frank Klemm <pfk@fuchs.offl.uni-jena.de> writes:

  The Pentim 4 is so different from all other CPUs so I must write a special
  Code Choice Generator. Some Examples:

I don't know what a Code Choice Generator is, but I know that
multiply-by-constant code generation is controlled by the *COSTS
macros.  If you set these up properly for Pentium 4, you should get
code sequences that use fewer shifts and more adds.

(It isn't going to become perfect since this code understands nothing
about scheduling.)

-- 
Torbjörn

Follow-Ups:
- Re: Multiplications on Pentium 4
  - From: Jan Hubicka

References:
- mul + div with 64 bit signed ints on IA32
  - From: Frank Klemm
- Re: mul + div with 64 bit signed ints on IA32
  - From: Tim Prince
- Re: mul + div with 64 bit signed ints on IA32
  - From: Jan Hubicka
- Multiplications on Pentium 4
  - From: Frank Klemm

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