[Mlir-commits] [mlir] [mlir][Linalg] Remove implicit zero rank vectors in vectorization (PR #116069)

Diego Caballero llvmlistbot at llvm.org
Wed Nov 13 08:52:21 PST 2024


dcaballe wrote:

I don't have a strong concern here but I'm curious about the motivation to prioritize a 0-D vector over a scalar. Is this mostly to preserve a 0-D tensor input?

https://github.com/llvm/llvm-project/pull/116069


More information about the Mlir-commits mailing list