[Mlir-commits] [mlir] [MLIR][GPU] Add gpu.cluster_dim_blocks and gpu.cluster_block_id Ops (PR #95245)

Pradeep Kumar llvmlistbot at llvm.org
Wed Jun 12 23:09:48 PDT 2024


================
@@ -86,6 +86,11 @@ static std::optional<uint64_t> getKnownLaunchDim(Op op, LaunchDims type) {
 
 void ClusterDimOp::inferResultRanges(ArrayRef<ConstantIntRanges>,
                                      SetIntRangeFn setResultRange) {
+  setResultRange(getResult(), getIndexRange(1, kMaxDim));
----------------
schwarzschild-radius wrote:

Unfortunately, ClusterDimOp is a GPU_IndexOp and it requires a `inferResultRanges` function to be defined for these ops that is why I have provided it as weaker constraint

https://github.com/llvm/llvm-project/pull/95245


More information about the Mlir-commits mailing list