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

Han-Chung Wang llvmlistbot at llvm.org
Mon Jan 8 09:57:36 PST 2024


hanhanW wrote:

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

+1 on keeping the padding behavior consistent between static and dynamic cases. It is valid to me. I don't have a specific use case, but I think user can allocate big enough buffer based on inner_tile_sizes.

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


More information about the Mlir-commits mailing list