[prev in list] [next in list] [prev in thread] [next in thread] 

List:       gcc
Subject:    Re: cache misses in gcc 3.3
From:       law () redhat ! com
Date:       2003-02-10 18:18:51
[Download RAW message or body]

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

[prev in list] [next in list] [prev in thread] [next in thread]