[Mlir-commits] [mlir] [mlir][gpu] Add Support for Cluster of Thread Blocks in `gpu.launch` (PR #76924)
Adam Paszke
llvmlistbot at llvm.org
Fri Jan 5 02:43:26 PST 2024
================
@@ -660,6 +661,8 @@ void LaunchOp::build(OpBuilder &builder, OperationState &result,
// Add grid and block sizes as op operands, followed by the data operands.
result.addOperands({gridSizeX, gridSizeY, gridSizeZ, getBlockSizeX,
getBlockSizeY, getBlockSizeZ});
+ if (clusterSizeX && clusterSizeY && clusterSizeZ)
----------------
apaszke wrote:
This doesn't seem resolved yet? I would change the condition to use `||` instead of `&&`
https://github.com/llvm/llvm-project/pull/76924
More information about the Mlir-commits
mailing list