diff options
| author | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2019-07-16 20:06:00 +0000 |
|---|---|---|
| committer | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2019-07-16 20:06:00 +0000 |
| commit | 6e0fa292c22cde726b4ddb53cf1fa8c649384030 (patch) | |
| tree | 0eab7cef5f01384cbbb4618c6be05e2edac66921 /lldb/packages/Python/lldbsuite/test/expression_command/call-function | |
| parent | ccf22ef94c4a94f7598f51a70445fdec8f8a1bc8 (diff) | |
| download | bcm5719-llvm-6e0fa292c22cde726b4ddb53cf1fa8c649384030.tar.gz bcm5719-llvm-6e0fa292c22cde726b4ddb53cf1fa8c649384030.zip | |
[AMDGPU] Change register type for v32 vectors
When it is AReg_1024 this results in unnecessary copying into
AGPRs of a 32 element vectors even though they are not intended
for an mfma instruction.
Differential Revision: https://reviews.llvm.org/D64815
llvm-svn: 366252
Diffstat (limited to 'lldb/packages/Python/lldbsuite/test/expression_command/call-function')
0 files changed, 0 insertions, 0 deletions
