diff options
author | Sanjay Patel <spatel@rotateright.com> | 2015-02-20 16:55:27 +0000 |
---|---|---|
committer | Sanjay Patel <spatel@rotateright.com> | 2015-02-20 16:55:27 +0000 |
commit | 1b53f74c4cd9f7028292cce860f56066b961991e (patch) | |
tree | 0d4b103a6b32b015a9bb31bba7a6a43dbbf57a9c /clang/lib/Serialization/ModuleManager.cpp | |
parent | d50f33d9966c380299779be48550a3ef9788af67 (diff) | |
download | llvm-1b53f74c4cd9f7028292cce860f56066b961991e.zip llvm-1b53f74c4cd9f7028292cce860f56066b961991e.tar.gz llvm-1b53f74c4cd9f7028292cce860f56066b961991e.tar.bz2 |
canonicalize a v2f64 blendi of 2 registers
This canonicalization step saves us 3 pattern matching possibilities * 4 math ops
for scalar FP math that uses xmm regs. The backend can re-commute the operands
post-instruction-selection if that makes register allocation better.
The tests in llvm/test/CodeGen/X86/sse-scalar-fp-arith.ll cover this scenario already,
so there are no new tests with this patch.
Differential Revision: http://reviews.llvm.org/D7777
llvm-svn: 230024
Diffstat (limited to 'clang/lib/Serialization/ModuleManager.cpp')
0 files changed, 0 insertions, 0 deletions