Han-Chung Wang

What is the status of removing `iree-llvmgpu-test-combine-layout-transformation` flag? I got few questions about that offline, and it'd be good to remove the flag if it is no longer needed.

Can you update https://github.com/iree-org/iree/issues/20530#issuecomment-2852302024? Either mark them resolved or say that it is no longer needed.

cc @banach-space @mub-at-arm this is breaking IREE, so we reverted it on our llvm-project fork. We'll need some help to land it to IREE. Can we revert the upstream commit...

Thanks thanks, and sorry for bothering you when you're traveling. I think we can land the change with dropping the local revert LLVM commit. It could need additional permission, so...

cc @banach-space @nujaa the llvm commit is breaking IREE, so we reverted it in our llvm-project fork. We'll need some help to land it to IREE. Can we revert the...

The upstream commit is reverted in https://github.com/llvm/llvm-project/pull/97652, closing the issue.

> Splat constants are the non-canonical form for codegen, we instead prefer fills for 2 reasons: > > 1. Consistency with dynamic shapes > 2. Fills are tilable and compose...

> I found this test: > > https://github.com/iree-org/iree/blob/1e155cc4b72e75e1fc1776d406cbdbe48d194e5c/compiler/src/iree/compiler/Codegen/LLVMGPU/test/nvvm_pipeline_test.mlir#L874 > > which uses a splat as the destination of a generic, hence this change. Even if we fix this at the...

The top_k becomes sort ops, do we really not convert it to linalg_ext.top_k op? The difference is that in passing.mlir version, two readwrite buffers are passed and used by the...

Here is the IR before and after ConvertDispatchRegionsToWorkgroupsPass; the readonly tensor is introduced by the pass. https://gist.github.com/hanhanW/ed9aa991eb72527b42b58f1d9e268190