| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
[mlir][linalg] Implement patterns for reducing rank of named linalg contraction ops (#95710) This patch introduces pattern rewrites for reducing the rank of named linalg contraction ops with unit spatial dim(s) to other named contraction ops. For example linalg.batch_matmul with batch size 1 -> linalg.matmul and linalg.matmul with unit LHS spatial dim -> linalg.vecmat, etc. These patterns don't support reducing the rank along reduction dimension as those don't convert to other named contraction ops. | 1 年前 | |
[mlir][linalg] Switch to use OpOperand* in ControlPropagationFn. (#96697) It's not easy to determine whether we want to propagate pack/unpack ops because we don't know the (producer, consumer) information. The revisions switch it to OpOperand*, so the control function can capture the (producer, consumer) pair. E.g., Operation *producer = opOperand->get().getDefiningOp(); Operation *consumer = opOperand->getOwner(); | 1 年前 | |
[mlir][Affine][NFC] Wrap dialect in "affine" namespace This cleanup aligns the affine dialect with all the other dialects. Differential Revision: https://reviews.llvm.org/D148687 | 3 年前 | |
Apply clang-tidy fixes for modernize-use-equals-default in TestLinalgDropUnitDims.cpp (NFC) | 2 年前 | |
[mlir][linalg] Enable CollapseLinalgDimensions to collapse linalg::CopyOp (#68526) | 2 年前 | |
[NFC] Clean up TestLinalgGreedyFusion (#94430) Linalg fusion-on-memrefs are removed in dc37dc824aabbbe. There is nothing being inserted in the erase set. Remove the useless code. | 2 年前 | |
[mlir][linalg] Implement patterns for reducing rank of named linalg contraction ops (#95710) This patch introduces pattern rewrites for reducing the rank of named linalg contraction ops with unit spatial dim(s) to other named contraction ops. For example linalg.batch_matmul with batch size 1 -> linalg.matmul and linalg.matmul with unit LHS spatial dim -> linalg.vecmat, etc. These patterns don't support reducing the rank along reduction dimension as those don't convert to other named contraction ops. | 1 年前 | |
[mlir][linalg] Decompose winograd operators (#96183) Convert Linalg winograd_filter_transform, winograd_input_transform, and winograd_output_transform into nested loops with matrix multiplication with constant transform matrices. Support several configurations of Winograd Conv2D, including F(2, 3), F(4, 3) and F(2, 5). These configurations show that the implementation can support different kernel size (3 and 5) and different output size (2 and 4). Besides symetric kernel size 3x3 and 5x5, this patch also supports 1x3, 3x1, 1x5, and 5x1 kernels. The implementation is based on the paper, Fast Algorithm for Convolutional Neural Networks. (https://arxiv.org/abs/1509.09308) Reviewers: ftynse, Max191, GeorgeARM, nicolasvasilache, MaheshRavishankar, dcaballe, rengolin Reviewed By: ftynse, Max191 Pull Request: https://github.com/llvm/llvm-project/pull/96183 | 1 年前 | |
[mlir][Affine][NFC] Wrap dialect in "affine" namespace This cleanup aligns the affine dialect with all the other dialects. Differential Revision: https://reviews.llvm.org/D148687 | 3 年前 |