diff options
| author | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2022-03-31 16:17:01 -0700 |
|---|---|---|
| committer | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2022-04-08 17:46:49 -0700 |
| commit | fced87d457d39d94cf7b396d8200dcb4e171003d (patch) | |
| tree | 7a7208285a43d51d88bb0c298a98e132eff137b0 /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 833882b32701ce3713c9dd9afdedf1126db691f0 (diff) | |
| download | llvm-fced87d457d39d94cf7b396d8200dcb4e171003d.zip llvm-fced87d457d39d94cf7b396d8200dcb4e171003d.tar.gz llvm-fced87d457d39d94cf7b396d8200dcb4e171003d.tar.bz2 | |
[AMDGPU] Fix regression with vectorization limiting
D67148 has removed TTI::getNumberOfRegisters(bool Vector) and
started to call TTI::getNumberOfRegisters(unsigned ClassID) from
the LoopVectorize. This has resulted in an unrestricted vectorization
on AMDGPU blowing up register pressure.
Differential Revision: https://reviews.llvm.org/D122850
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions