[Mlir-commits] [mlir] [mlir][VectorOps] Extend vector.constant_mask to support 'all true' scalable dims (PR #66638)
Cullen Rhodes
llvmlistbot at llvm.org
Tue Sep 19 01:29:51 PDT 2023
================
@@ -1003,7 +1007,7 @@ func.func @contraction_masked_scalable(%A: vector<3x4xf32>,
%C: vector<3x[8]xf32>,
%M : vector<3x[8]x4xi1>) -> vector<3x[8]xf32> {
// CHECK: vector.mask %[[M]] { vector.contract {indexing_maps = [#{{.*}}, #{{.*}}, #{{.*}}], iterator_types = ["parallel", "parallel", "reduction"], kind = #vector.kind<add>} %[[A]], %[[B]], %[[C]] : vector<3x4xf32>, vector<4x[8]xf32> into vector<3x[8]xf32> } : vector<3x[8]x4xi1> -> vector<3x[8]xf32>
- %0 = vector.mask %M { vector.contract #matmat_trait %A, %B, %C : vector<3x4xf32>, vector<4x[8]xf32> into vector<3x[8]xf32> }
+ %0 = vector.mask %M { vector.contract #matmat_trait %A, %B, %C : vector<3x4xf32>, vector<4x[8]xf32> into vector<3x[8]xf32> }
----------------
c-rhodes wrote:
unrelated change?
https://github.com/llvm/llvm-project/pull/66638
More information about the Mlir-commits
mailing list