Daniel Hernandez-Juarez 1fd1f65569

[mlir] Refactor LegalizeToF32 to specify extra supported float types and target type as arguments (#108815) ...

Instead of hardcoding all fp smaller than 32 bits are unsupported we
provide a way to pass supported floating point types as well as the
target type. fp64 and fp32 are implicitly supported.

CC: @krzysz00 @manupak

2024-09-27 10:02:16 -05:00

..

AlgebraicSimplification.cpp

[mlir] Move casting calls from methods to function calls

2023-05-12 11:21:25 +02:00

CMakeLists.txt

[mlir] Refactor LegalizeToF32 to specify extra supported float types and target type as arguments (#108815)

2024-09-27 10:02:16 -05:00

ExpandPatterns.cpp

[mlir][math] lower rsqrt to sqrt + fdiv (#91344)

2024-05-13 10:15:39 +02:00

ExtendToSupportedTypes.cpp

[mlir] Refactor LegalizeToF32 to specify extra supported float types and target type as arguments (#108815)

2024-09-27 10:02:16 -05:00

PolynomialApproximation.cpp

[mlir] Construct SmallVector with ArrayRef (NFC) (#101896)

2024-08-04 11:43:05 -07:00

UpliftToFMA.cpp

[mlir][math] Uplift from arith to math.fma

2023-06-18 17:11:21 +02:00