[Mlir-commits] [mlir] [mlir][scf] Refactor and improve ParallelLoopFusion (PR #179284)

[llvmlistbot at llvm.org]

================

----------------
fabrizio-indirli wrote:

I made it much more general now:
- it supports both `vector.store` and `vector.transfer_write`
- it supports vectors of arbitrary rank
- it supports also memref.loads that are not part of scf.for loops, and they don't necessarily have to load all the elements of the vector

https://github.com/llvm/llvm-project/pull/179284