diff --git a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp index e83574b734272..04e85c2b337de 100644 --- a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp +++ b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp @@ -373,8 +373,9 @@ void mlir::populateGpuToNVVMConversionPatterns( NVVM::BlockInClusterIdYOp, NVVM::BlockInClusterIdZOp>>( converter, IndexKind::Other, IntrType::Id); patterns.add>(converter, IndexKind::Other, IntrType::Dim); + gpu::ClusterDimBlocksOp, NVVM::ClusterDimBlocksXOp, + NVVM::ClusterDimBlocksYOp, NVVM::ClusterDimBlocksZOp>>( + converter, IndexKind::Other, IntrType::Dim); patterns.add>( converter, IndexKind::Grid, IntrType::Id); diff --git a/mlir/test/Integration/GPU/CUDA/sm90/cga_cluster.mlir b/mlir/test/Integration/GPU/CUDA/sm90/cga_cluster.mlir index 5c11d80178f72..c70c940564a26 100644 --- a/mlir/test/Integration/GPU/CUDA/sm90/cga_cluster.mlir +++ b/mlir/test/Integration/GPU/CUDA/sm90/cga_cluster.mlir @@ -18,7 +18,7 @@ module attributes {gpu.container_module} { return } gpu.module @gpumodule { - gpu.func @kernel_cluster() kernel attributes {gpu.known_block_size = array, gpu.known_grid_size = array} { + gpu.func @kernel_cluster() kernel attributes {gpu.known_block_size = array, gpu.known_grid_size = array} { %cidX = gpu.cluster_id x %cidY = gpu.cluster_id y %cidZ = gpu.cluster_id z