[all-commits] [llvm/llvm-project] 214d32: Support for dynamic dimensions in 'tensor.splat' (...

[Rafael Ubal via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 214d32ccd2be05262a328563d3792ec0d36404b0
      https://github.com/llvm/llvm-project/commit/214d32ccd2be05262a328563d3792ec0d36404b0
  Author: Rafael Ubal <rubal at mathworks.com>
  Date:   2023-12-15 (Fri, 15 Dec 2023)

  Changed paths:
    M mlir/include/mlir/Dialect/Tensor/IR/TensorOps.td
    M mlir/lib/Dialect/Tensor/IR/TensorOps.cpp
    M mlir/test/Dialect/Tensor/bufferize.mlir
    M mlir/test/Dialect/Tensor/canonicalize.mlir
    M mlir/test/Dialect/Tensor/invalid.mlir
    M mlir/test/Dialect/Tensor/ops.mlir

  Log Message:
  -----------
  Support for dynamic dimensions in 'tensor.splat' (#74626)

This feature had been marked as `TODO` in the `tensor.splat`
documentation for a while. This MR includes:

- Support for dynamically shaped tensors in the return type of
`tensor.splat` with the syntax suggested in the `TODO` comment.

- Updated op documentation.

- Bufferization support.

- Updates in op folders affected by the new feature.

- Unit tests for valid/invalid syntax, valid/invalid folding, and
lowering through bufferization.

- Additional op builders resembling those available in `tensor.empty`.