[Mlir-commits] [mlir] [mlir][xegpu] Add support for `vector.multi_reduction` and `vector.shape_cast` SIMT distribution. (PR #157560)

[Charitha Saumya]

charithaintc wrote:

> @charithaintc Just as a side note, couldn't `shape_cast` part of that PR still go through? It looked largely complete. Either way, it's fine to have it here too if it's better, easier etc..

We found that shape cast also need to access xegpu layouts in most cases. So we can not reply on vector distribution infra (plus the pattern there is naive, does not fit our use cases). The shape cast here has high pattern benefit, so it should go first. I think we will have to adopt this approach until we have something working.

https://github.com/llvm/llvm-project/pull/157560