This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: Loop optimizer issues
- From: David Edelsohn <dje at watson dot ibm dot com>
- To: Diego Novillo <dnovillo at redhat dot com>
- Cc: Zdenek Dvorak <rakdver at atrey dot karlin dot mff dot cuni dot cz>, "gcc at gcc dot gnu dot org" <gcc at gcc dot gnu dot org>, Richard Henderson <rth at redhat dot com>, Jason Merrill <jason at redhat dot com>, pop at gauvain dot u-strasbg dot fr, Jan Hubicka <jh at suse dot cz>, Daniel Berlin <dberlin at dberlin dot org>
- Date: Mon, 02 Jun 2003 16:33:06 -0400
- Subject: Re: Loop optimizer issues
>>>>> Diego Novillo writes:
Diego> To avoid duplicate effort, let's just raise our hand whenever we are
Diego> going to get started with something. The initial list that I had in
Diego> mind (at the tree level) includes:
Diego> Induction variable detection
Diego> Array dependency information
Diego> Unswitching
Diego> Peeling
Diego> Interchange
Diego> Fusion
Diego> Fission
Diego> I volunteer to collect suggestions and keep them in the TODO section of
Diego> the project page together with whoever is working on it. If there are
Diego> two proposals for the same analysis/optimization but with different
Diego> approaches, we may want to implement both and then decide which one we
Diego> like best.
The partial list of loop optimizations from a March 2002 public
presentation about XLC compiler optimizations includes:
normalization
scalarization
fusion
nest partitioning
interchange
unroll and jam
I will see if I can provided a more complete and ordered list of TPO
optimizations.
Dan suggested that GCC may get some scalarization implicitly in
its other SSA optimizations.
David