This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: Fwd: gcc instruction scheduling makes things worse?
- From: Alex Turjan <aturjan at yahoo dot com>
- To: He Xiao <xiheasas at gmail dot com>
- Cc: gcc at gcc dot gnu dot org
- Date: Wed, 6 May 2009 01:22:34 -0700 (PDT)
- Subject: Re: Fwd: gcc instruction scheduling makes things worse?
- Reply-to: aturjan at yahoo dot com
> For data dependency cases, I do some jobs in
> the adjust_cost target hook.
Normally the scheduling takes into account the instruction latencies which you have specified: for load 2, for mul 4 and for alu 1.
Why do you need to adjust the sched costs? Did you try simply without adjusting the costs?
> I read THE GNU INSTRUCTION SCHEDULER written by
> Michael D. Tiemann,
This is old work. Meanwhile there is a new scheduler based on finite state machines. You can read in "The finite state automaton based pipeline hazard recognizer and instruction scheduler in GCC" by Vladimir Makarov.