Michael Platings 18ecdbfe6c

[mlir][vector-to-gpu]: Lower transposed strided transfer_read ...

Add support for lowering vector.transfer_read to
gpu.subgroup_mma_load_matrix with transpose permutation_map
with non-minor dimensions e.g. (d0, d1, d2) -> (d2, d0)

2026-02-05 16:40:59 +00:00

..

CMakeLists.txt

…

VectorToGPU.cpp

[mlir][vector-to-gpu]: Lower transposed strided transfer_read

2026-02-05 16:40:59 +00:00