diff options
| author | Lorenzo Chelini <l.chelini@icloud.com> | 2022-09-19 12:34:49 +0200 |
|---|---|---|
| committer | Lorenzo Chelini <l.chelini@icloud.com> | 2022-09-19 12:50:27 +0200 |
| commit | 3718082e2b11cd1c66317bc067aac7cb094226cc (patch) | |
| tree | 422df0069362270627e05bc0c58a7e545aa97baa /llvm/lib/Transforms/Utils/LoopRotationUtils.cpp | |
| parent | 21a9abc1cebfd5022eb4eec754c257342d032d30 (diff) | |
| download | llvm-3718082e2b11cd1c66317bc067aac7cb094226cc.zip llvm-3718082e2b11cd1c66317bc067aac7cb094226cc.tar.gz llvm-3718082e2b11cd1c66317bc067aac7cb094226cc.tar.bz2 | |
[MLIR][Linalg] introduce batch-reduce GEMM
The batch-reduce GEMM kernel essentially multiplies a sequence of input tensor
blocks (which form a batch) and the partial multiplication results are reduced
into a single output tensor block.
See: https://ieeexplore.ieee.org/document/9139809 for more details.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D134163
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopRotationUtils.cpp')
0 files changed, 0 insertions, 0 deletions