projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: b3a80e5) | patch
AMDGPU: Improve extract_vector_elt reduction combine
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Wed, 15 Aug 2018 21:34:06 +0000 (21:34 +0000)
committerMatt Arsenault <Matthew.Arsenault@amd.com>
Wed, 15 Aug 2018 21:34:06 +0000 (21:34 +0000)
commita8160737648a51d1de12fcf670591af05d1a1954
treee1b6930b2dd72749edd0f363a371024f2a8e6b5atree | snapshot
parentb3a80e5397d46a50c2ba61b4820a577c17f0198acommit | diff
AMDGPU: Improve extract_vector_elt reduction combine

Handle fmul, fsub and preserve flags.

Also really test minnum/maxnum reductions.
The existing tests were only checking from
minnum/maxnum matched from a fast math compare
and select which is not the same.

llvm-svn: 339820
llvm/lib/Target/AMDGPU/SIISelLowering.cpp diff | blob | history
llvm/test/CodeGen/AMDGPU/fcanonicalize-elimination.ll diff | blob | history
llvm/test/CodeGen/AMDGPU/reduction.ll diff | blob | history
Domain: System / Toolchain;