[Mlir-commits] [mlir] [MLIR][XeGPU] Allow some nd ops to have argument shapes mismatch for … (PR #120566)

[Petr Kurapov]

kurapov-peter wrote:

Seems like there's consensus on going with the option 2 now. We can merge this then unless there're additional comments.

> This argument is not clear to me. Are you saying that sg_map must be present even after the SIMT distribution? That seems like an unnecessary demand because after SIMT we don't really need sg_map.

By the way, this validation relies on `sg_map` to check the shapes. There is currently no other source of information to validate the shapes.

https://github.com/llvm/llvm-project/pull/120566