This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: Performance of Integer Multiplication on PIII (gcc-2.95.2 onP6)
- To: Jan Hubicka <jh at suse dot cz>
- Subject: Re: Performance of Integer Multiplication on PIII (gcc-2.95.2 onP6)
- From: pete at ltoi dot iap dot physik dot tu-darmstadt dot de
- Date: Mon, 5 Nov 2001 17:19:11 +0200 (MEST)
- Cc: Kevin Atkinson <kevin at atkinson dot dhs dot org>, Tim Prince <tprince at computer dot org>, <gcc at gcc dot gnu dot org>
And now something completely different:
gcc-2.95.2 (haifa) on PII (P6 Modell II)-400
(SuSE-6.1, glibc-2.0.7, GNU ld version 2.9.1 (with BFD 2.9.1.0.22),
unmodified)
gcc -O2 -march=i686 -s -o imul imul.c read_empty.c read.c
Loop: 1.93, Code: 3.13
Clocks: 23.32
-ffplfj=2:= -fomit-frame-pointer -malign-loops=2 -malign-functions=2
-malign-jumps=2
gcc -O2 -march=i686 -ffplfj=2 -s -o imul imul.c read_empty.c read.c
Loop: 1.18, Code: 3.48
Clocks: 25.93
-flfj=2:= -fomit-frame-pointer -malign-loops=2 -malign-functions=2
-malign-jumps=2
gcc -O2 -march=i686 -flfj=2 -s -o imul imul.c read_empty.c read.c
Loop: 1.92, Code: 3.12
Clocks: 23.24
... read_[i]asm.s ... will not work with intel_syntax ... (Tex motto
applies: user can work it out ...)
Thus, it seems, we are at status quo ante?
Peter