[Mlir-commits] [mlir] [MLIR][SCF] Add an API to fuse consumer to a producer within scf loop (PR #88712)

[Oleksandr Alex Zinenko]

================
@@ -131,6 +150,42 @@ def TilingInterface : OpInterface<"TilingInterface"> {
           return failure();
         }]
       >,
+      InterfaceMethod<
+        /*desc=*/[{
+          Method to generate the tiled implementation of an operation from
+          operand tile position.
+
+          Generates the IR that computes the tiled implementation of an
+          operation from operand tile.  The `offsets` and `sizes`
+          describe the tile of the operand required. This is different from
+          `getTiledImplementation` which generates the tiled
+          implementation of the operation given a tile of the
+          iteration space. This method generates a tiled
+          implementation of the operation based on the tile of the
+          operand required. This method enables consumer fusion by using
+          tile and fuse. The method returns failure if the operation
+          can't be tiled to generate the operand tile. In practical terms
+          this implies it cannot be tiled and fused with its producers.
+
+          - `offsets` provides the offset of the tile in the coordinate system
+            of the original iteration space, i.e., if an iteration space
+            dimension had non-zero offset, it must be included in the offset
+            provided here (as opposed to zero-based offset "relative" to the
+            iteration space).
----------------
ftynse wrote:

> Yes, "iteration space" does seem to be referring the coordinate space of the operand here.

Please update the description then. Somebody will be reading it and implementing it.

> From what I understand the non-zero offsets perhaps mean to account for, as an example, the following :
%iv0 and %iv1 loop induction variables in %source [%iv0, %iv1] [32, 32] [1, 1].

Is there a test for this case? 

> @ftynse I dont remember the full context now, but I think this was from a discussion me and you had a few years ago.

Neither do I remember. Could you remind me what the discussion was about?

https://github.com/llvm/llvm-project/pull/88712