[all-commits] [llvm/llvm-project] dbfc38: [mlir][bufferization] Add `BufferOriginAnalysis` (...

[Matthias Springer via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: dbfc38ed6b3f2a9be0b1a86b2a074aad69eb58a6
      https://github.com/llvm/llvm-project/commit/dbfc38ed6b3f2a9be0b1a86b2a074aad69eb58a6
  Author: Matthias Springer <me at m-sp.org>
  Date:   2024-03-25 (Mon, 25 Mar 2024)

  Changed paths:
    M mlir/include/mlir/Dialect/Bufferization/IR/BufferizationOps.td
    M mlir/include/mlir/Dialect/Bufferization/Transforms/BufferViewFlowAnalysis.h
    M mlir/lib/Dialect/Bufferization/Transforms/BufferDeallocationSimplification.cpp
    M mlir/lib/Dialect/Bufferization/Transforms/BufferViewFlowAnalysis.cpp
    A mlir/test/Dialect/Bufferization/Transforms/OwnershipBasedBufferDeallocation/dealloc-loops.mlir
    M mlir/test/Dialect/Bufferization/Transforms/buffer-deallocation-simplification.mlir

  Log Message:
  -----------
  [mlir][bufferization] Add `BufferOriginAnalysis` (#86461)

This commit adds the `BufferOriginAnalysis`, which can be queried to
check if two buffer SSA values originate from the same allocation. This
new analysis is used in the buffer deallocation pass to fold away or
simplify `bufferization.dealloc` ops more aggressively.

The `BufferOriginAnalysis` is based on the `BufferViewFlowAnalysis`,
which collects buffer SSA value "same buffer" dependencies. E.g., given
IR such as:
```
%0 = memref.alloc()
%1 = memref.subview %0
%2 = memref.subview %1
```
The `BufferViewFlowAnalysis` will report the following "reverse"
dependencies (`resolveReverse`) for `%2`: {`%2`, `%1`, `%0`}. I.e., all
buffer SSA values in the reverse use-def chain that originate from the
same allocation as `%2`. The `BufferOriginAnalysis` is built on top of
that. It handles only simple cases at the moment and may conservatively
return "unknown" around certain IR with branches, memref globals and
function arguments.

This analysis enables additional simplifications during
`-buffer-deallocation-simplification`. In particular, "regular" scf.for
loop nests, that yield buffers (or reallocations thereof) in the same
order as they appear in the iter_args, are now handled much more
efficiently. Such IR patterns are generated by the sparse compiler.



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