diff options
author | Konstantina Mitropoulou <Konstantina.Mitropoulou@amd.com> | 2023-02-17 14:16:39 -0800 |
---|---|---|
committer | Konstantina Mitropoulou <Konstantina.Mitropoulou@amd.com> | 2023-02-22 09:01:33 -0800 |
commit | 944f429b210d0d94171dc5df3068d4f1e8fb5d80 (patch) | |
tree | 17058226214420364419cd804681988f94f0c571 /cmake | |
parent | 3e48c8d75d1ca937ab3595909fb4198226c4ad1d (diff) | |
download | llvm-944f429b210d0d94171dc5df3068d4f1e8fb5d80.tar.gz |
[AMDGPU] Improve the lowering of raw_buffer_load_{i8,i16} and struct_buffer_load_{i8,i16} intrinsics
Currently, raw_buffer_load_{i8,i16} and struct_buffer_load_{i8,i16}
intrinsics are lowered as buffer_load_{u8,u16}. This patch combines
buffer_load_{u8,u16} and sign extension instructions in order to
generate buffer_load_{i8,i16} instructions.
Reviewed By: foad
Differential Revision: https://reviews.llvm.org/D144313
Diffstat (limited to 'cmake')
0 files changed, 0 insertions, 0 deletions