Benjamin Kramer 2d76274b99 [mlir][VectorOps] Loosen restrictions on vector.reduction types ...

LLVM can deal with any integer or float type, don't arbitrarily restrict
it to f32/f64/i32/i64.

Differential Revision: https://reviews.llvm.org/D88010

2020-09-21 12:45:23 +02:00

..

EDSC

…

CMakeLists.txt

…

VectorOps.cpp

[mlir][VectorOps] Loosen restrictions on vector.reduction types

2020-09-21 12:45:23 +02:00

VectorTransforms.cpp

[mlir] [VectorOps] Improve SIMD compares with narrower indices

2020-09-03 21:43:38 -07:00

VectorUtils.cpp

…