projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: b8e7887) | patch
[ARM] Use Cortex-A57 sched model for Cortex-A72
authorSam Parker <sam.parker@arm.com>
Thu, 25 Oct 2018 15:08:29 +0000 (15:08 +0000)
committerSam Parker <sam.parker@arm.com>
Thu, 25 Oct 2018 15:08:29 +0000 (15:08 +0000)
commita16667e79be9164943dd76235d5406ae519b9042
tree8433d048538fa26cffe855bc4b73087c427f1fc9tree | snapshot
parentb8e7887f33290b48918bc2dd1640cbeb69c42ef8commit | diff
[ARM] Use Cortex-A57 sched model for Cortex-A72

This mirrors what we already do for AArch64 as the cores are similar.
As discussed in the review, enabling the machine scheduler causes
more variations in performance changes so it is not enabled for now.
This patch improves LNT scores by a geomean of 1.57% at -O3.

Differential Revision: https://reviews.llvm.org/D53562

llvm-svn: 345272
llvm/lib/Target/ARM/ARM.td diff | blob | history
llvm/test/Transforms/LoopUnroll/ARM/loop-unrolling.ll diff | blob | history
Domain: System / Toolchain;