commit	b5acec1f79deaae964b981a52ce8ed2ce3a01359	[log] [tgz]
author	Matt Arsenault <Matthew.Arsenault@amd.com>	Sun Aug 12 08:42:54 2018 +0000
committer	Matt Arsenault <Matthew.Arsenault@amd.com>	Sun Aug 12 08:42:54 2018 +0000
tree	a667a04b05b5103e6253c0e8b4c06c163eed9d99
parent	3ead7d73893dd6544651dc5cf6989abd7fe4f4bb [diff]

AMDGPU: Use splat vectors for undefs when folding canonicalize

If one of the elements is undef, use the canonicalized constant
from the other element instead of 0.

Splat vectors are more useful for other optimizations, such
as matching vector clamps. This was breaking on clamps
of half3 from the undef 4th component.

llvm-svn: 339512

llvm/lib/Target/AMDGPU/SIISelLowering.cpp[diff]
llvm/test/CodeGen/AMDGPU/clamp.ll[diff]
llvm/test/CodeGen/AMDGPU/fcanonicalize.f16.ll[diff]

3 files changed

tree: a667a04b05b5103e6253c0e8b4c06c163eed9d99

clang/
clang-tools-extra/
compiler-rt/
debuginfo-tests/
libclc/
libcxx/
libcxxabi/
libunwind/
lld/
lldb/
llgo/
llvm/
openmp/
parallel-libs/
polly/
README.md

README.md

Low Level Virtual Machine (LLVM)

This directory and its subdirectories contain source code for LLVM, a toolkit for the construction of highly optimized compilers, optimizers, and runtime environments.