[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 23:11:13 PDT 2024


================
@@ -95,6 +100,12 @@ void ClusterIdOp::inferResultRanges(ArrayRef<ConstantIntRanges>,
   setResultRange(getResult(), getIndexRange(0, max - 1ULL));
 }
 
+void ClusterBlockIdOp::inferResultRanges(ArrayRef<ConstantIntRanges>,
+                                         SetIntRangeFn setResultRange) {
+  uint64_t max = kMaxClusterDim;
+  setResultRange(getResult(), getIndexRange(0, max - 1ULL));
----------------
schwarzschild-radius wrote:

Right, I was planning to update it in the subsequent PR when I introduced the non_portable_cluster_size attribute. I can update it in the PR as well

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


More information about the Mlir-commits mailing list