This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: some profiling numbers
- From: Devang Patel <dpatel at apple dot com>
- To: Steven Bosscher <s dot bosscher at student dot tudelft dot nl>
- Cc: graydon hoare <graydon at redhat dot com>, gcc at gcc dot gnu dot org
- Date: Thu, 26 Jun 2003 08:54:43 -0700
- Subject: Re: some profiling numbers
- References: <3EF9DE6D.3030605@redhat.com> <3EFA3488.5060406@student.tudelft.nl>
On Wednesday, June 25, 2003, at 4:47 PM, Steven Bosscher wrote:
One thing you point out is that the slowdown is more or less a result
of GCC just getting bigger. Does that mean that the extra passes over
the whole chain of insns or trees may be blamed for much of the
slowdown? Is there any way to measure how many times different GCC
versions walks large chains of insns/trees, and where? (Maybe the
number of cache misses per function or something like that???)
I would be curious to see how mainline does, too...
http://gcc.gnu.org/ml/gcc/2002-09/msg00215.html
We have made progress in removing redundant tree chain walks exposed in
right hand side of the graph. But you can see as compilation continues,
it touches more and more memory pages to access nodes in tree chain.
-Devang