diff options
author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2018-07-18 19:55:19 +0000 |
---|---|---|
committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2018-07-18 19:55:19 +0000 |
commit | d4b82da1136ff60df4ba9da99aa260a2d7f02de1 (patch) | |
tree | 04207f8d337b8ada3834c2ac27cc1d6d35d4c41b /clang/lib/CodeGen/CodeGenModule.cpp | |
parent | 4915d3a1ec3e7d3542aafd05487f7e8246460f4a (diff) | |
download | bcm5719-llvm-d4b82da1136ff60df4ba9da99aa260a2d7f02de1.tar.gz bcm5719-llvm-d4b82da1136ff60df4ba9da99aa260a2d7f02de1.zip |
[X86][SSE] Canonicalize scalar fp arithmetic shuffle patterns
As discussed on PR38197, this canonicalizes MOVS*(N0, OP(N0, N1)) --> MOVS*(N0, SCALAR_TO_VECTOR(OP(N0[0], N1[0])))
This returns the scalar-fp codegen lost by rL336971.
Additionally it handles the OP(N1, N0)) case for commutable (FADD/FMUL) ops.
Differential Revision: https://reviews.llvm.org/D49474
llvm-svn: 337419
Diffstat (limited to 'clang/lib/CodeGen/CodeGenModule.cpp')
0 files changed, 0 insertions, 0 deletions