X-Authentication-Warning: delorie.com: mailnull set sender to djgpp-bounces using -f
Newsgroups: comp.os.msdos.djgpp
Subject: Re: GCC 3.03 makes slow code
From: no spam <no AT spam DOT com>
References: <Xns9198D540C7BFCgd678bcz5bAA AT 192 DOT 89 DOT 123 DOT 233> <5567-Wed16Jan2002212542+0200-eliz AT is DOT elta DOT co DOT il>
Message-ID: <Xns91997A8DCC34Agd678bcz5bAA@192.89.123.233>
User-Agent: Xnews/4.06.22
Lines: 12
Date: Thu, 17 Jan 2002 09:58:35 GMT
NNTP-Posting-Host: 194.251.251.193
X-Trace: read2.inet.fi 1011261515 194.251.251.193 (Thu, 17 Jan 2002 11:58:35 EET)
NNTP-Posting-Date: Thu, 17 Jan 2002 11:58:35 EET
Organization: Sonera corp Internet services
To: djgpp AT delorie DOT com
DJ-Gateway: from newsgroup comp.os.msdos.djgpp
Reply-To: djgpp AT delorie DOT com

"Eli Zaretskii" <eliz AT is DOT elta DOT co DOT il> wrote in news:5567-
Wed16Jan2002212542+0200-eliz AT is DOT elta DOT co DOT il:
>> I was testing the latest GCC 3.03 (djgpp) and compiled an application
>> using switches -O9 -fomit-frame-pointer -mcpu=pentium -fschedule-insns2
>> -fexpensive-optimizations the code it generated run 10-20% slower (on 
>> Celeron-A CPU) compared to a version compiled with GCC 2.95 (using 
>> identical switches). 
> How does the code fare if you use -O2 instead of -O9?

-O3/-O9 makes slightly faster code than -O3, but the gap isn't big.

So it looks like we have to stick with the GCC 2.9.x for good?