[Mlir-commits] [mlir] [mlir][NVVM] Add support for barrier0-reduction operation (PR #167036)

[Valentin Clement バレンタイン クレメン]

================
@@ -991,6 +1008,9 @@ def NVVM_BarrierOp : NVVM_Op<"barrier", [AttrSizedOperandSegments]> {
     - `numberOfThreads`: Specifies the number of threads participating in the barrier. 
       When specified, the value must be a multiple of the warp size. If not specified, 
       all threads in the CTA participate in the barrier.
+    - `reductionOp`: specifies the reduction operation (`popc`, `and`, `or`).
+    - `reductionPredicate`: specifies the predicate to be used with the
----------------
clementval wrote:

Renamed

https://github.com/llvm/llvm-project/pull/167036