Address the comment.

BufferAssignmentPlacer is removed, and comments are addressed.

Thanks.

Address the comments.

@rupprecht I am investigating the downstream issue.

Resolve the failure

Reopen to resolve the failure.

Resolve the minor comment before landing

Resolving comments

Resolve comments, change setResultConversionKind to a mapping (i.e. setResultConversionKind<RankedTensorType, MemRefType>(AppendToArguementList)), and introduce addDecomposeTypeConversion.

Address the comments.

@rriddle Thanks for the comments. They will be fixed in the upcoming PR for the copy removal.

@bondhugula Yes, I am working on it.
@rriddle @mehdi_amini We have started to provide a detailed document for BA.

The following points are addressed:

• The remaining comments are resolved.
• CopyOpInterface is introduced and added to linalg.copy.
• Make this pass generic for all copies.
• The pass is moved to mlir/lib/transforms.
• copy-removal.mlir is moved to mlir/test/transforms.

Add another copy removal condition and a few more test cases.

Address the multiple deallocation issue.

@mehdi_amini Is there any generic copy interface available? The other problem would be in test files that how we can specify the copy operation class for the pass. @herhut suggested that since it is going to be a dialect independent and unique copy at the end, we can start with linalg.copy and generalize it later on.
In summary, what we'd like to achieve is to remove %to value and the Copy operation, and replace all its uses with %from value. In both of these examples, if we remove %to and the copy operation, and replace it with %from, the logic of the program will change.

Comments are addressed.

Thanks for suggesting to use the Pass option. I made TestBufferPlacementPreparationPass a template struct due to the fact that registerTestBufferPlacementPreparationPass and registerTestPreparationPassWithAllowedMemrefResults are two passes for only test purposes which shouldn't be publicly seen.

Correct the position of registerTestPreparationPassWithAllowedMemrefResults.

Address the comments.

Resolve the comments.

Removing unnecessary mapping.

Change walk return type to WalkResult and move BlockAndValueMapping before adding new arguments to the new block.

Addressed the comments.

Change Assert to emitError and add a test case for the generated error.

BufferAssignmentPlacer now fails in cases that function returns buffers already. A note has also been added to the description of BufferPlacement.cpp about not supporting these cases. The related TODO in TensorsToBuffers.cpp has also been removed.

Add description and indent.

Addressing the comments.

Address the comments.

In D78996#2007630, @ftynse wrote:

lib/Conversion is intended to for conversions from dialect A to dialect B to ensure it can depend on both without creating unnecessary dependencies A->B or B->A. Since this transformation stays within Linalg, it should go to lib/Dialect/Linalg/Transforms. Beyond being cleaner library-wise, it can have a more meaningful name than "linalg to linalg", e.g. "TensorsToBuffers" or "BufferAssignment".

Address the comments.

Taking Context and ConversionTarget out of the scope of function walk.