Lei Zhang f1db4aec30 [mlir][VectorToGPU] Support transposed+broadcasted 2D MMA load ...

This is loading from 2-D memref, in addition to D139655 where we
load from 1-D memref cases.

Reviewed By: ThomasRaoux

Differential Revision: https://reviews.llvm.org/D140136

2022-12-15 19:34:32 +00:00

..

vector-to-mma-ops-mma-sync.mlir

[mlir][nvgpu] Fix affine maps computing indices for LdMatrixOp srcMemref

2022-12-01 18:26:33 -08:00

vector-to-mma-ops.mlir

[mlir][VectorToGPU] Support transposed+broadcasted 2D MMA load

2022-12-15 19:34:32 +00:00