[Mlir-commits] [mlir] [mlir][Vector] Promote buffers accessed via dynamic subviews and memref.copy (PR #217793)

[Andrzej Warzyński]

================
@@ -105,23 +116,39 @@ struct TransferReadOpMemOpModel
                         const SmallPtrSetImpl<OpOperand *> &blockingUses,
                         SmallVectorImpl<OpOperand *> &newBlockingUses,
                         const DataLayout &dataLayout) const {
-    return isWholeBufferTransfer(cast<VectorTransferOpInterface>(op), slot,
-                                 blockingUses);
+    return isPromotableTransfer(cast<VectorTransferOpInterface>(op), slot,
+                                blockingUses);
----------------
banach-space wrote:

I am confused by the fact that no `newBlockingUses` are computed for `xfer_read`. It makes sense for `xfer_write` (it does not return a value), but we should probably add something for `xfer_read`, no?

https://github.com/llvm/llvm-project/pull/217793