projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: a8d63dc) | patch
[X86][SSE] Reuse zeroable element mask instead of regenerating it. NFCI
authorSimon Pilgrim <llvm-dev@redking.me.uk>
Sat, 5 Nov 2016 16:40:20 +0000 (16:40 +0000)
committerSimon Pilgrim <llvm-dev@redking.me.uk>
Sat, 5 Nov 2016 16:40:20 +0000 (16:40 +0000)
commit1af0fc1103591c35cca8048dae9776a6c329ecd1
tree0ca70076d0c57aaa2d237140f09ab2ef76bf4ad1tree | snapshot
parenta8d63dc2896a555a5efa19dea312f245fdf10ba2commit | diff
[X86][SSE] Reuse zeroable element mask instead of regenerating it. NFCI

We are repeatedly calling computeZeroableShuffleElements in many shuffle lowering calls for the same shuffle mask/inputs.

This is a first step towards reusing the zeroable result, initially just for lowerVectorShuffleAsShift calls.

llvm-svn: 286037
llvm/lib/Target/X86/X86ISelLowering.cpp diff | blob | history
Domain: System / Toolchain;