diff options
| author | Mirko Brkusanin <Mirko.Brkusanin@amd.com> | 2020-10-06 15:20:29 +0200 |
|---|---|---|
| committer | Mirko Brkusanin <Mirko.Brkusanin@amd.com> | 2020-10-08 10:17:15 +0200 |
| commit | 7c88d13fd1c1a864124d96224996c62192d431f2 (patch) | |
| tree | 818b81b7eb772bcf349230b7ddad311dce02703d /llvm/tools/llvm-readobj/llvm-readobj.cpp | |
| parent | 380087e6c9a226b28c24de3b18e202e20d430765 (diff) | |
| download | llvm-7c88d13fd1c1a864124d96224996c62192d431f2.zip llvm-7c88d13fd1c1a864124d96224996c62192d431f2.tar.gz llvm-7c88d13fd1c1a864124d96224996c62192d431f2.tar.bz2 | |
[AMDGPU] Prefer SplitVectorLoad/Store over expandUnalignedLoad/Store
ExpandUnalignedLoad/Store can sometimes produce unnecessary copies to
temporary stack slot. We should prefer splitting vectors if possible.
Differential Revision: https://reviews.llvm.org/D88882
Diffstat (limited to 'llvm/tools/llvm-readobj/llvm-readobj.cpp')
0 files changed, 0 insertions, 0 deletions