diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2015-11-24 12:05:03 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2015-11-24 12:05:03 +0000 |
| commit | 4d801cd357c74bb7c2a60fedf4030b9fb5b4827f (patch) | |
| tree | ab89b79da213d3d358dbdaf7b6ba19ba2fe2d994 /llvm/lib/Target/CppBackend | |
| parent | 9d0f44bf8af57cbe992edada1a5351881b1388b2 (diff) | |
| download | bcm5719-llvm-4d801cd357c74bb7c2a60fedf4030b9fb5b4827f.tar.gz bcm5719-llvm-4d801cd357c74bb7c2a60fedf4030b9fb5b4827f.zip | |
AMDGPU: Split x8 and x16 vector loads instead of scalarize
The one regression in the builtin tests is in the read2 test which now
(again) has many extra copies, but this should be solved once the pass
is replaced with a DAG combine.
llvm-svn: 253974
Diffstat (limited to 'llvm/lib/Target/CppBackend')
0 files changed, 0 insertions, 0 deletions
