Re: Performance of Integer Multiplication on PIII

["Tim Prince" <tprince at computer dot org>]

I am confused myself as to which architecture is meant by -march=i686,
but I didn't think it was P-III.  I thought -march=pentiumpro was the one
for P-II/P-III.  However, wouldn't many people wonder whether you mean P4
when you talk about "faster Pentiums?" Some of us would not go out of our
way to slow down the P4 by asking for imul on code meant to run on a
variety of CPU's, although some would like to have -Os favor the use of
imul.  It might be interesting to have a separate table of the penalties
used in each version of gcc for each architecture selection, rather than
having to peruse source.
----- Original Message -----
From: "Kevin Atkinson" <kevin@atkinson.dhs.org>
To: <gcc@gcc.gnu.org>
Sent: Friday, November 02, 2001 10:45 AM
Subject: Performance of Integer Multiplication on PIII


> Trying to teach some my self x86 assembly language as was playing
around
> with hand coding a functions which encodes an array of integers (with
> limited range) into a number for direct referencing and I discovered
that
> my hand coded code that does not do any fancy tricks is roughly 50%
faster
> than Gcc code which attempts to avoid imul by using shifts and adds.
Here
> are the results I get.