llvm-project/mlir
Christian Sigg be1aeb818c Remove NaN constant from arith.minf, arith.maxf expansion
If any of the operands is NaN, return the operand instead of a new constant.

When the rhs operand is a constant, the second arith.cmpf+select ops will be folded away.

https://reviews.llvm.org/D117010 marks the two ops commutative, which will place the constant on the rhs.

Reviewed By: herhut

Differential Revision: https://reviews.llvm.org/D117011
2022-01-12 20:56:40 +01:00
..
cmake/modules Fix exported MLIR_TABLEGEN_EXE 2022-01-09 23:27:08 -08:00
docs Add a `qualified` directive to the Op, Attribute, and Type declarative assembly format 2022-01-11 01:30:19 +00:00
examples Fix clang-tidy issues in mlir/ (NFC) 2021-12-20 20:25:01 +00:00
include [mlir][vector] Add folding for extract + extract/insert_strided 2022-01-12 11:48:35 -08:00
lib Remove NaN constant from arith.minf, arith.maxf expansion 2022-01-12 20:56:40 +01:00
python [mlir][linalg] Improve pooling op iterator order consistency 2022-01-11 17:49:22 +00:00
test Remove NaN constant from arith.minf, arith.maxf expansion 2022-01-12 20:56:40 +01:00
tools [mlir][Linalg] Pattern to fuse pad operation with elementwise operations. 2022-01-11 13:37:25 -08:00
unittests [MLIR][NFC] Move PresburgerSet to Presburger/ directory 2022-01-08 15:39:40 +05:30
utils Update mlir GDB printers 2022-01-06 22:20:25 +01:00
.clang-format
.clang-tidy Enable readability-redundant-smartptr-get in MLIR local clang-tidy config 2022-01-08 20:07:11 +00:00
CMakeLists.txt [CMake] Factor out config prefix finding logic 2022-01-07 20:16:18 +00:00
LICENSE.TXT
README.md

README.md

Multi-Level Intermediate Representation

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