Skip to content

Commit ff0ab1f

Browse files
committed
Update attr documentation
1 parent 45b0b32 commit ff0ab1f

File tree

1 file changed

+3
-3
lines changed

1 file changed

+3
-3
lines changed

llvm/docs/AMDGPUUsage.rst

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1645,9 +1645,9 @@ The AMDGPU backend supports the following LLVM IR attributes.
16451645
reduced by heuristics.
16461646

16471647
"amdgpu-max-num-workgroups"="x,y,z" Specify the maximum number of work groups for the kernel dispatch in the
1648-
X, Y, and Z dimensions. Generated by the ``amdgpu_max_num_work_groups``
1649-
CLANG attribute [CLANG-ATTR]_. Clang only emits this attribute when all
1650-
the three numbers are >= 1.
1648+
X, Y, and Z dimensions. Each number must be >= 1. Generated by the
1649+
``amdgpu_max_num_work_groups`` CLANG attribute [CLANG-ATTR]_. Clang only
1650+
emits this attribute when all the three numbers are >= 1.
16511651

16521652
"amdgpu-no-agpr" Indicates the function will not require allocating AGPRs. This is only
16531653
relevant on subtargets with AGPRs. The behavior is undefined if a

0 commit comments

Comments
 (0)