diff options
| author | Krzysztof Drewniak <Krzysztof.Drewniak@amd.com> | 2022-07-06 20:37:30 +0000 |
|---|---|---|
| committer | Krzysztof Drewniak <Krzysztof.Drewniak@amd.com> | 2022-08-04 19:42:33 +0000 |
| commit | 63295622491a31eaccb6c534ba5caa836beb843f (patch) | |
| tree | 79c761eca8b335e7f25781ab1be5222198584858 /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 35cc1738468e62453611fcb5d88d212da7022768 (diff) | |
| download | llvm-63295622491a31eaccb6c534ba5caa836beb843f.zip llvm-63295622491a31eaccb6c534ba5caa836beb843f.tar.gz llvm-63295622491a31eaccb6c534ba5caa836beb843f.tar.bz2 | |
[mlir][AMDGPU] Explicitly truncate memory addresses in buffer ops
As a percaution, truncate memory addresses passed to kernels to 48 bits,
since bits 48-63 of the buffer descriptor are used for the stride field
and, on gfx10, to control swizzling.
Reviewed By: ThomasRaoux
Differential Revision: https://reviews.llvm.org/D131016
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions