[PATCH] D148159: [mlir][TransformDialect] Simplify the lowering of pack/unpack when these are just pad/unpad

[Mahesh Ravishankar via Phabricator via llvm-commits]

mravishankar added inline comments.


================
Comment at: mlir/test/Dialect/Linalg/transform-lower-pack.mlir:41
+  //      CHECK: %[[EMPTY:.*]] = tensor.empty() : tensor<1x1x1x1x136x64x16x16xf32>
+  //      CHECK: %[[RES:.*]] = tensor.insert_slice %[[PAD]] into %[[EMPTY]]
+  // offsets.
----------------
I wondering if we even want to have an `insert_slice` here? we could just do a `reshape` here. In which case the only difference is whether there is a transpose or not? If we can teach bufferization to handle this reshape without introducing additional buffers, that'd be very useful (we used to have a `memref.reshape` to just change the indexing, wonder if we still have that).


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D148159/new/

https://reviews.llvm.org/D148159