[Mlir-commits] [mlir] [mlir][linalg] Propagate filter tensor encoding in im2col (PR #160099)

[Andrzej Warzyński]

================
@@ -124,6 +125,10 @@ rewriteInIm2Col(RewriterBase &rewriter, linalg::Conv2DNhwcHwcfOp convOp) {
   auto filterType = cast<ShapedType>(convOp.getInputs()[1].getType());
   auto outputType = cast<ShapedType>(convOp.getOutputs()[0].getType());
 
+  if (!convOp.hasPureTensorSemantics())
+    return rewriter.notifyMatchFailure(
+        convOp, "expected op to have pure tensor semantics");
+
----------------
banach-space wrote:

Thanks for checking!

Would you mind adding a high-level comment somewhere + negative tests for MemRef (you could just modify an existing test on Tensors). That would be much appreciated 🙏🏻 Note, we prefix negative tests with `@negative_`: https://mlir.llvm.org/getting_started/TestingGuide/#test-naming-convention

https://github.com/llvm/llvm-project/pull/160099