Date: Mon, 17 May 1999 00:38:51 +0200
To: pgcc AT delorie DOT com
Subject: Re: Benchmark PGCC vs EGCS on a K6-2
Message-ID: <19990517003851.L10291@cerebro.laendle>
Mail-Followup-To: pgcc AT delorie DOT com
References: <373F3AA2 DOT A446D611 AT informatik DOT hu-berlin DOT de>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
In-Reply-To: <373F3AA2.A446D611@informatik.hu-berlin.de>; from Jens-Uwe Rumstich on Sun, May 16, 1999 at 09:37:38PM +0000
X-Operating-System: Linux version 2.2.7 (root AT cerebro) (gcc driver version pgcc-2.93.09 19990221 (gcc2 ss-980929 experimental) executing gcc version 2.7.2.3) 
From: Marc Lehmann <pcg AT goof DOT com>
Reply-To: pgcc AT delorie DOT com
X-Mailing-List: pgcc AT delorie DOT com
X-Unsubscribes-To: listserv AT delorie DOT com
Precedence: bulk

On Sun, May 16, 1999 at 09:37:38PM +0000, Jens-Uwe Rumstich wrote:
> - even on the K6 PGCC creates better code with PentiumPro-option than
> with K6-Option, but there is an improvement with enabled K6-optimizing.
> - both compilers create worser code with O4 than with O3

Your results are bogus. egcs does NOT make any difference between -O3 and
-O4.  If you tests show a difference then its not compiler related.

> PS: aehm, are there any reasons, why the def_align in i386.c for the K6
> is set to 0 instead of 5 (32 bytes cache alignment) or atleast 4 ??

pgcc uses an adaptive alignment, which is available with newer versions of
binutils (2.9.x)

--  
      -----==-                                             |
      ----==-- _                                           |
      ---==---(_)__  __ ____  __       Marc Lehmann      +--
      --==---/ / _ \/ // /\ \/ /       pcg AT goof DOT com      |e|
      -=====/_/_//_/\_,_/ /_/\_\       XX11-RIPE         --+
    The choice of a GNU generation                       |
                                                         |