maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/mlir
History
Lei Zhang f0c93fd4ca [mlir][vector] Merge accumulator/result transpose into contract 
This commit adds a pattern to merge accumulator and result
`vector.transpose` ops into `vector.contract`. This kind of
pattern can be generated for NCHW convolution vectorization,
where we use transposes to convert the 1-D NCW convolution
into NWC during vectorization. Merging the transpose would
mean we can avoid materialize vector extract/insert for
transposes and it makes further vector level transformations
easier.

Reviewed By: ThomasRaoux

Differential Revision: https://reviews.llvm.org/D135496
 		2022-10-08 00:43:45 +00:00
..
benchmark/python
…
cmake/modules [CMake] Avoid `LLVM_BINARY_DIR` when other more specific variable are better-suited, part 2 2022-09-14 15:48:58 -04:00
docs [mlir][doc] Remove trailing whitespace (NFC) 2022-10-07 09:05:49 -07:00
examples [mlir][mlir-translation] patch for standalone-translation command line description missing. 2022-10-04 09:14:40 +08:00
include [mlir][arith] Expose dedicated API for expanding ceil/floor division 2022-10-07 19:51:59 +00:00
lib [mlir][vector] Merge accumulator/result transpose into contract 2022-10-08 00:43:45 +00:00
python [mlir][tensor][NFC] Rename linalg.init_tensor to tensor.empty 2022-10-04 17:25:35 +09:00
test [mlir][vector] Merge accumulator/result transpose into contract 2022-10-08 00:43:45 +00:00
tools [mlir][llvmir] Import intrinsics with attributes from LLVMIR. 2022-10-07 14:30:30 +03:00
unittests [mlir][sparse] Favors synthetic tensor over other undefined tensors 2022-10-06 20:51:38 +00:00
utils [vscode-mlir] Bump to version 0.0.11 2022-09-28 02:50:24 -07:00
.clang-format
…
.clang-tidy
…
CMakeLists.txt
…
LICENSE.TXT
…
README.md
…

README.md

Multi-Level Intermediate Representation

See https://mlir.llvm.org/ for more information.