llvm-project/mlir
Diego Caballero eaf2588a51 [mlir][Linalg] Add support for min/max reduction vectorization in linalg.generic
This patch extends Linalg core vectorization with support for min/max reductions
in linalg.generic ops. It enables the reduction detection for min/max combiner ops.
It also renames MIN/MAX combining kinds to MINS/MAXS to make the sign explicit for
floating point and signed integer types. MINU/MAXU should be introduce din the future
for unsigned integer types.

Reviewed By: pifon2a, ThomasRaoux

Differential Revision: https://reviews.llvm.org/D110854
2021-10-05 22:47:20 +00:00
..
cmake/modules [mlir][python] Simplify python extension loading. 2021-09-03 00:43:28 +00:00
docs [mlir][doc] fix typos. 2021-10-04 13:15:51 -07:00
examples [mlir] Add value_begin/value_end methods to DenseElementsAttr 2021-09-21 01:57:43 +00:00
include [mlir][Linalg] Add support for min/max reduction vectorization in linalg.generic 2021-10-05 22:47:20 +00:00
lib [mlir][Linalg] Add support for min/max reduction vectorization in linalg.generic 2021-10-05 22:47:20 +00:00
python [mlir][python] Provide more convenient constructors for std.CallOp 2021-10-04 11:45:29 +02:00
test [mlir][Linalg] Add support for min/max reduction vectorization in linalg.generic 2021-10-05 22:47:20 +00:00
tools [mlir] Add an 'cppNamespace' field to availability 2021-10-05 09:38:09 -04:00
unittests [mlir] Tighten strided layout specification. 2021-10-04 10:37:05 +00:00
utils [mlir][spirv] Fix path in define_enum.sh script 2021-10-05 09:32:01 -04:00
.clang-format
.clang-tidy NFC: .clang-tidy: Inherit configs from parents to improve maintainability 2021-06-08 08:25:59 -07:00
CMakeLists.txt MLIR can't support -Bsymbolic link option, fail at CMake time with a helpful message instead of broken runtime 2021-09-26 00:36:31 +00:00
LICENSE.TXT
README.md

README.md

Multi-Level Intermediate Representation

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