projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 91e758b) | patch
AMDGPU: Do permlane16 vdst_in discard optimization in InstCombine
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Thu, 16 Jan 2020 14:59:56 +0000 (09:59 -0500)
committerMatt Arsenault <arsenm2@gmail.com>
Thu, 16 Jan 2020 22:27:53 +0000 (17:27 -0500)
commit3ef8cdf6660fc20baeb09eae5008b741f178b624
tree075c645a836b0cde76734606f3311677d1376888tree | snapshot
parent91e758b7329b4ff134684e661af93a85c436a460commit | diff
AMDGPU: Do permlane16 vdst_in discard optimization in InstCombine

There's more potential value to discarding the source value earlier,
since we always know the value of the fi/bc bits.
llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp diff | blob | history
llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll diff | blob | history
Domain: System / Toolchain;