[all-commits] [llvm/llvm-project] f215a6: [mlir][linalg][vector] Refine create{Read|Write}Or...

[Andrzej Warzyński via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: f215a61891b0368d2d7e329bc994c9053dc3fac9
      https://github.com/llvm/llvm-project/commit/f215a61891b0368d2d7e329bc994c9053dc3fac9
  Author: Andrzej Warzyński <andrzej.warzynski at arm.com>
  Date:   2025-04-15 (Tue, 15 Apr 2025)

  Changed paths:
    M mlir/include/mlir/Dialect/Vector/Utils/VectorUtils.h
    M mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp
    M mlir/lib/Dialect/Vector/Utils/VectorUtils.cpp

  Log Message:
  -----------
  [mlir][linalg][vector] Refine create{Read|Write}OrMasked{Read|Write} (nfc) (#135350)

The semantics of `createReadOrMaskedRead` and `createWriteOrMaskedWrite`
are currently a bit inconsistent and not fully documented:

* The input vector sizes are passed as `readShape` and
  `inputVectorSizes`, respectively — inconsistent naming.

* Currently, the input vector sizes in `createWriteOrMaskedWrite` are
  not required to be complete: any missing trailing sizes are inferred
  from the destination tensor. This only works when the destination
  tensor is statically shaped.

* Unlike `createReadOrMaskedRead`, the documentation for
  `createWriteOrMaskedWrite` does not specify that write offsets are
  hard-coded to 0.

This PR only updates the documentation and unifies the naming. As such,
it is NFC.

A follow-up PR will generalize and unify the implementation to support,
for example, dynamically shaped destination tensors — a requirement for
enabling scalable vectorization of `linalg.pack` and `linalg.unpack`.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications