Thanks, Andreas. You are right in that fully peeling a loop is done by a different code path (peel_loops_completely() and earlier in the tree unroller).
Teresa On Fri, Dec 2, 2011 at 12:54 AM, Andreas Krebbel <kreb...@linux.vnet.ibm.com> wrote: > On Thu, Dec 01, 2011 at 11:39:36PM -0800, Teresa Johnson wrote: >> To do this I leveraged the existing TARGET_LOOP_UNROLL_ADJUST target >> hook, which was previously only defined for s390. I added one >> additional call to this target hook, when unrolling for constant trip >> count loops. Previously it was only called for runtime computed trip >> counts. Andreas, can you comment on the effect for s390 of this >> additional call of the target hook, since I can't measure that? > > Limiting the unrolling of loops with constant iterations makes also > sense for s390. However, the limitations are only relevant if it > actually stays a loop. If the loop gets completely peeled into a > sequential instruction stream there should be no limitation. But as I > understand it this will be done by different code paths. > > So I think the change should be ok for s390 as well. It will take some > time to get measurements on that. I'll try to keep that in mind until > then. > > Bye, > > -Andreas- > -- Teresa Johnson | Software Engineer | tejohn...@google.com | 408-460-2413