[PATCH] D157111: AMDGPU: Try to select fmul by power of 2 to ldexp

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fmul.mir:277
+
+...
----------------
foad wrote:
> Need some tests with negated powers of two. I don't see how the patch handles these.
this is just to demonstrate the patterns do actually import, the actual testing should be the IR test (I'm just working around the failure to import)


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D157111/new/

https://reviews.llvm.org/D157111