This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: cache misses in gcc 3.3
- From: law at redhat dot com
- To: Geoff Keating <geoffk at geoffk dot org>
- Cc: Andi Kleen <ak at muc dot de>, gcc at gcc dot gnu dot org, mszick at goquest dot com
- Date: Mon, 10 Feb 2003 11:18:51 -0700
- Subject: Re: cache misses in gcc 3.3
- Reply-to: law at redhat dot com
In message <jmwuk83tu8.fsf@desire.geoffk.org>, Geoff Keating writes:
>Andi Kleen <ak@muc.de> writes:
>
>> > One thing that is really important in going after speed improvements is
>> > to have really accurate profiling information that shows where the time
>> > is being spent. Otherwise you will chase phantoms.
>>
>> My -O2 test case was spending 10% in the parser, according to the standard
>timing
>> output. This was in the top three, with only CSE being slower. This was on
>an
>> Athlon.
>
>You should be aware that last time I looked, "parser" really meant
>"all the time that wasn't allocated to some other part of the compiler".
Yes. I've tripped over this as well. Let's say it was rather surprising
to see time for computing dominance frontiers for the SSA builder showing
up as "parser" time :-)
Jeff