diff options
| -rw-r--r-- | mlir/lib/Target/LLVMIR/Dialect/ROCDL/ROCDLToLLVMIRTranslation.cpp | 2 | ||||
| -rw-r--r-- | mlir/test/Target/LLVMIR/rocdl.mlir | 2 |
2 files changed, 2 insertions, 2 deletions
diff --git a/mlir/lib/Target/LLVMIR/Dialect/ROCDL/ROCDLToLLVMIRTranslation.cpp b/mlir/lib/Target/LLVMIR/Dialect/ROCDL/ROCDLToLLVMIRTranslation.cpp index a230ead..0cbb3da 100644 --- a/mlir/lib/Target/LLVMIR/Dialect/ROCDL/ROCDLToLLVMIRTranslation.cpp +++ b/mlir/lib/Target/LLVMIR/Dialect/ROCDL/ROCDLToLLVMIRTranslation.cpp @@ -99,7 +99,7 @@ public: if (!llvmFunc->hasFnAttribute("amdgpu-flat-work-group-size")) { llvmFunc->addFnAttr("amdgpu-flat-work-group-size", "1,256"); } - llvmFunc->addFnAttr("amdgpu-implicitarg-num-bytes", "256"); + } // Override flat-work-group-size // TODO: update clients to rocdl.flat_work_group_size instead, diff --git a/mlir/test/Target/LLVMIR/rocdl.mlir b/mlir/test/Target/LLVMIR/rocdl.mlir index f831d7b..3c9c707 100644 --- a/mlir/test/Target/LLVMIR/rocdl.mlir +++ b/mlir/test/Target/LLVMIR/rocdl.mlir @@ -489,7 +489,7 @@ llvm.func @rocdl_8bit_floats(%source: i32, %stoch: i32) -> i32 { llvm.return %source5 : i32 } -// CHECK-DAG: attributes #[[$KERNEL_ATTRS]] = { "amdgpu-flat-work-group-size"="1,256" "amdgpu-implicitarg-num-bytes"="256" } +// CHECK-DAG: attributes #[[$KERNEL_ATTRS]] = { "amdgpu-flat-work-group-size"="1,256" } // CHECK-DAG: attributes #[[$KERNEL_WORKGROUP_ATTRS]] = { "amdgpu-flat-work-group-size"="1,1024" // CHECK-DAG: attributes #[[$KNOWN_BLOCK_SIZE_ATTRS]] = { "amdgpu-flat-work-group-size"="128,128" // CHECK-DAG: ![[$RANGE]] = !{i32 0, i32 64} |