diff options
| author | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2018-11-08 00:16:23 +0000 |
|---|---|---|
| committer | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2018-11-08 00:16:23 +0000 |
| commit | 6cc8b2fc6580e5889f0807d2a85296a676f201e1 (patch) | |
| tree | dd2b911011e7c676d674bb2c5876a58cc939da7d /llvm/lib/Analysis/AssumptionCache.cpp | |
| parent | 3a58d89819389488df9fb5155f6d73ddd60e4816 (diff) | |
| download | bcm5719-llvm-6cc8b2fc6580e5889f0807d2a85296a676f201e1.tar.gz bcm5719-llvm-6cc8b2fc6580e5889f0807d2a85296a676f201e1.zip | |
[AMDGPU] Extend promote alloca vectorization
Promote alloca can vectorize a small array by bitcasting it to a
vector type. Extend vectorization for the case when alloca is
already a vector type. We still want to replace GEPs with an
insert/extract element instructions in this case.
Differential Revision: https://reviews.llvm.org/D54219
llvm-svn: 346376
Diffstat (limited to 'llvm/lib/Analysis/AssumptionCache.cpp')
0 files changed, 0 insertions, 0 deletions
