[Mlir-commits] [mlir] [mlir][sparse] simplify ConvertOp rewriting rules (PR #68350)

[Peiming Liu]

================
@@ -231,21 +231,23 @@ module {
     %c4u_coo = tensor.cast %c4_coo : tensor<4x4xf64> to tensor<*xf64>
     call @printMemrefF64(%c4u_coo) : (tensor<*xf64>) -> ()
 
+    // FIXME: The canonicalizer for tensor.extract_slice does not work with sparse tensors.
----------------
PeimingLiu wrote:

Same here

https://github.com/llvm/llvm-project/pull/68350