[all-commits] [llvm/llvm-project] 7f82c9: [mlir][vector] Add support for vector.maskedstore ...

[Han-Chung Wang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 7f82c90621770919dc457d8bb5d12d7f3b29e2e1
      https://github.com/llvm/llvm-project/commit/7f82c90621770919dc457d8bb5d12d7f3b29e2e1
  Author: Han-Chung Wang <hanhan0912 at gmail.com>
  Date:   2023-11-30 (Thu, 30 Nov 2023)

  Changed paths:
    M mlir/lib/Dialect/Vector/Transforms/VectorEmulateNarrowType.cpp
    M mlir/test/Dialect/Vector/vector-emulate-narrow-type.mlir

  Log Message:
  -----------
  [mlir][vector] Add support for vector.maskedstore sub-type emulation. (#73871)

The idea is similar to vector.maskedload + vector.store emulation. What
the emulation does is:

1. Get a compressed mask and load the data from destination.
2. Bitcast the data to original vector type.
3. Select values between `op.valueToStore` and the data from load using
original mask.
4. Bitcast the new value and store it to destination using compressed
masked.