diff options
| author | Shoreshen <372660931@qq.com> | 2025-08-27 09:48:42 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-08-27 09:48:42 +0800 |
| commit | 7fff93db50bad40548fa08895844629f1d40e715 (patch) | |
| tree | a53121378bb99c08af5c2bea6574e48e2418eed1 /clang/lib/CodeGen/CodeGenModule.cpp | |
| parent | e3823a625aa55ea93dbe50d76a845aed5ac66e31 (diff) | |
| download | llvm-7fff93db50bad40548fa08895844629f1d40e715.zip llvm-7fff93db50bad40548fa08895844629f1d40e715.tar.gz llvm-7fff93db50bad40548fa08895844629f1d40e715.tar.bz2 | |
[AMDGPU] Set GRANULATED_WAVEFRONT_SGPR_COUNT of compute_pgm_rsrc1 to 0 for gfx10+ (#154666)
According to `llvm-project/llvm/docs/AMDGPUUsage.rst::L5212` the
`GRANULATED_WAVEFRONT_SGPR_COUNT`, which is `compute_pgm_rsrc1[6:9]` has
to be 0 for gfx10+ arch
---------
Co-authored-by: Matt Arsenault <Matthew.Arsenault@amd.com>
Diffstat (limited to 'clang/lib/CodeGen/CodeGenModule.cpp')
0 files changed, 0 insertions, 0 deletions