[Mlir-commits] [mlir] [mlir][test] Add TD example for peel+vectorize (depthwise conv) (PR #90200)

[Hugo Trachino]

nujaa wrote:

Hi, thanks for the example, very insightful. Nothing to complain really, just wondering if the canonicalization would work in dynamic sizes. 
In opposition to the matmul usecase, you run a canonicalization after decompose. Is it required by decompose ? ( I am not too familiar with the op)

https://github.com/llvm/llvm-project/pull/90200