[all-commits] [llvm/llvm-project] 17bb2d: [ExpandReductions] Don't push all intrinsics to th...

[topperc via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 17bb2d7c803db4cc52ebfb95e627b92eeccf302a
      https://github.com/llvm/llvm-project/commit/17bb2d7c803db4cc52ebfb95e627b92eeccf302a
  Author: Craig Topper <craig.topper at intel.com>
  Date:   2019-11-14 (Thu, 14 Nov 2019)

  Changed paths:
    M llvm/lib/CodeGen/ExpandReductions.cpp

  Log Message:
  -----------
  [ExpandReductions] Don't push all intrinsics to the worklist. Just push reductions.

We were previously pushing all intrinsics used in a function to the
worklist. This is wasteful for memory in a function with a lot of
intrinsics.

We also ask TTI if we should expand every intrinsic, but we only
have expansion support for the reduction intrinsics. This just
wastes time for the non-reduction intrinsics.

This patch only pushes reduction intrinsics into the worklist and
skips other intrinsics.

Differential Revision: https://reviews.llvm.org/D69470