[mlir][sparse] Fix getUnorderedCOOFromType for rank 1 tensor.

[bixia]

Summary

Previously, it used DimLevelType::SingletonNo to represent an unorder COO
tensor of rank 1 while it should use DimLevelType::CompressedNuNo.

[bixia]

Push the fill op inside if (rank > 1)

[wrengr]

mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorRewriting.cpp

139

If I'm reading things right, shouldn't this TODO apply to the CompressedNu(No) level rather than the SingletonNuNo levels?

[bixia]

Rebase.

[aartbik]

LGTM

mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorRewriting.cpp

 // TODO: The dim level property of the COO type relies on input tensors, the
 // shape relies on the output tensor
 // Helpers to setup a COO type.
 static RankedTensorType getUnorderedCOOFromType(RankedTensorType src) {
   auto *ctx = src.getContext();
   auto rank = src.getRank();
   SmallVector<DimLevelType, 4> dims;
 
-  // An unordered and non-unique compressed dim at beginning unless the tensor
-  // is a 1D tensor.
-  if (rank > 1)
-    dims.push_back(DimLevelType::CompressedNuNo);
+  // An unordered and non-unique compressed dim at beginning.
 
+  if (rank > 1) {
     // TODO: it is actually ordered at the level for ordered input.
     // Followed by unordered non-unique n-2 singleton levels.
-  std::fill_n(std::back_inserter(dims), rank - 2, DimLevelType::SingletonNuNo);
+    std::fill_n(std::back_inserter(dims), rank - 2,
+                DimLevelType::SingletonNuNo);
     // TODO: only if all the inputs (for concatentate) are unique at the last
     // level should the COO has a unique level at the end. Ends by a unordered
-  // unique singleton level.
+    // unique singleton level unless the tensor rank is 1.
     dims.push_back(DimLevelType::SingletonNo);
+  }
   SparseTensorEncodingAttr encSrc = getSparseTensorEncoding(src);
   // TODO: Maybe pick the bitwidth based on input/output tensors (probably the
   // largest one among them) in the original operation instead of using the
   // default value.
   auto enc = SparseTensorEncodingAttr::get(
       ctx, dims, AffineMap::getMultiDimIdentityMap(rank, ctx), AffineMap(),
       encSrc.getPointerBitWidth(), encSrc.getIndexBitWidth());
   return RankedTensorType::get(src.getShape(), src.getElementType(), enc);