THanks Nicolas for the explanation. Code looks fine to me. Still think that this is effectively adding promotion during tiling and doing this on tensors only is strange. Just trying to see if there is a more commonality between buffers and tensors so as to reuse things instead of completely new paths. Lets land and experiment. I understand how this would subsume promotion though.

In D95149#2518130, @nicolasvasilache wrote:

It should be easy to extend promotion to abort if it doesnt figure out the static sizes when "promotion" is applied to ops with tensor semantics.

The fact that promotion tries to create static buffers is very much due to history and needs to go away.

Here is what happens concretely today to inject static sizes in the memory pipeline:

1. Promotion creates alloc + fill + copy after some best effort local analysis to try and create a static buffer.
2. Fingers are crossed so that vectorization succeeds.
3. After vectorization, LinalgCopyVTRForwardingPattern and LinalgCopyVTWForwardingPattern are applied with a best effort dependence analysis to undo 1. and replace by vector.transfer.
4. Later masked/unmasked vector.transfer splitting is performed to isolate parts.

In contrast, thanks to the progress on transformations on tensors we can:

1. Tile on tensors with padding at the level(s) we are interested in.
2. Hoist, as we wish to create and amortize packing.
3. Decide which packed tensors materialize in memory, which ones turn into simple subview + control flow and which ones turn into vector transfers.

The implications of padding at the tiling on tensor level are far reaching as you have already seen in IREE, phases are being reordered and Promotion is a bystanding casualty.
See the followup https://reviews.llvm.org/D95243 to get a better idea how things look like after padding + packing.
I would not be surprised that Promotion just gets deleted / becomes part of some bufferization in a not too distant future: the ease with which we can perform transformations thanks to SSA use-def chains is just a no-brainer.

Promotion is guaranteed to alloc and copy but is not guaranteed to create static shapes.
This in contrast has no guarantees of alloc/copy and is guaranteed to create static shapes.

Closed by commit 6e8ef3b76ab65960edd6ee99f387e75564d8d9db

Rebase and adress comments

Rebase

This feels like it is promotion on tensors with the linalg.simple_pad (for now and linalg.pad later) being used instead of the alloc(...) ; copy(...) method. So the tensor "promotion" and buffer promotion are living in entirely different places. Ill go deeper into this code, but my read of the tests informs this comment.

Removing errant function.

Rebase on top of enhancements to LinalgDependenceGraph allowing
dependence tracking through results.

Rebase on top of change to LinalgDependenceGraph that accounts for
tracking dependence through result values.

Oh thanks for fixing this. I did see the Kernel capability requirement. Got confused about it not being valid for Shader

Rebase

Adding test for tiling of fill op on tensor

In D94819#2502142, @silvas wrote:

LGTM, but ot sounds like you might want to add some more testing as well. A payload that returns an argument of the enclosing function would be enough.

Add a test

Address comments.

Rebase

Rebase

Address comments

Address comments

Rebase

Catching up on the discussion after break here. I agree the design is flawed. The strides are wrong of the result memref. As defined right now that would mean that lowering the memref will need to look at where the memref is coming from which is really wrong. You could return a memref with the strides embedded into the memref type so that it works fine, but I dont think that fully works either. I think Hanhan had a fix to this shortly. Thanks for the feedback!

In D93076#2480253, @nicolasvasilache wrote:

Going through my unreviewed stack, note that with the revamp of linalg on tensors @pifon2a sent a diff today that implements the functionality with out tensors,

Rebase and add extra test

Rebase

Fix build errors

Address comments

Addressed remaining minor comments

Minor comment addressed

Rebase

Rebase

Rebase

Rebase

Rebase

Rebase

Rebase

Rebase

Rebase

Rebase

Dont need this anymore. Abondoning.

In D93724#2469920, @hanchung wrote:

This patch also move "invalid" tests to roundtrip.mlir file, which is not related to patch description. Could we split it into two patches?

Rebase on chnages to linalg on tensors

Rebase

Rebase