diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2018-05-09 18:37:39 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2018-05-09 18:37:39 +0000 |
| commit | 762d49880876eca14aa75a1bc893eba23ed50788 (patch) | |
| tree | 2d8e059a73d5b7c2f2e60458e71e2503e58dadad /libcxx/include/tgmath.h | |
| parent | 73634e40378fdba2b39c777a871961af2651b4e0 (diff) | |
| download | bcm5719-llvm-762d49880876eca14aa75a1bc893eba23ed50788.tar.gz bcm5719-llvm-762d49880876eca14aa75a1bc893eba23ed50788.zip | |
AMDGPU: Add combine for trunc of bitcast from build_vector
If the truncate is only accessing the first element of the vector,
we can use the original source value.
This helps with some combine ordering issues after operations are
lowered to integer operations between bitcasts of build_vector.
In particular it stops unnecessarily materializing the unused
top half of a vector in some cases.
llvm-svn: 331909
Diffstat (limited to 'libcxx/include/tgmath.h')
0 files changed, 0 insertions, 0 deletions
