lialan f981ee7efc

[MLIR] extend getCompressedMaskOp support in VectorEmulateNarrowType (#116122) ...

Previously when `numFrontPadElems` is not zero, `getCompressedMaskOp`
produces wrong result if the mask generator op is a
`vector.create_mask`.

This patch resolves the issue by including `numFrontPadElems` into the
mask generation.

Signed-off-by: Alan Li <me@alanli.org>

2024-11-19 16:49:05 -08:00

..

Interfaces

[mlir][Vector] Introduce the MaskingOpInterface

2022-10-27 22:54:19 +00:00

IR

[mlir][Vector] Add vector.extract(vector.shuffle) folder (#115105)

2024-11-06 18:17:12 -08:00

TransformOps

[mlir][vector] Add a new TD Op for patterns leveraging ShapeCastOp (#110525)

2024-10-01 10:08:43 +01:00

Transforms

[MLIR] extend getCompressedMaskOp support in VectorEmulateNarrowType (#116122)

2024-11-19 16:49:05 -08:00

Utils

[mlir][vector] Switch to using getNumScalableDims (nfc) (#100806)

2024-07-27 08:11:00 +01:00

CMakeLists.txt

[mlir][Vector] Vector transform skeleton

2022-11-25 04:51:50 -08:00