[Mlir-commits] [mlir] [MLIR][tensor] Improve `tensor.pack` verifier to catch more cases with unconditional runtime errors (PR #77217)

lorenzo chelini llvmlistbot at llvm.org
Mon Jan 8 08:39:07 PST 2024


chelini wrote:

> I would just drop any notion of UB for the static case: it is invalid for an op to be a partial tile and to not provide a padding value.
> 
> In the dynamic case, we could always require a padding value (if feasible, I forget).

Would it make sense to keep the padding behavior consistent between the static and dynamic behavior, having padding optional in both cases?

https://github.com/llvm/llvm-project/pull/77217


More information about the Mlir-commits mailing list