Module melior::dialect::ods::tensor

tensor dialect.

The tensor dialect is intended to hold core tensor creation and manipulation ops, which are not strongly associated with any particular other dialect or domain abstraction. The aim for ops in this dialect is that they make sense for any tensor element type. When this is not the case, the op is left to live in other dialects. Examples of element types that could be supported by the tensor dialect include:

• representing large, dense aggregations of primitive types, suitable for high-performance numerical computing.
• representing shapes in the shape dialect, which consist of small 1D tensors of index data type.
• representing aggregations of strings or “variant” types.
• representing large, sparse aggregations of primitive types, suitable for high-performance numerical computing.

Because of this broad element type support and because of the existence of more dedicated dialects, such as the sparse_tensor and linalg dialects, we prefer for now to keep the tensor dialect as small as possible. The expectation is that at some point in the future, the tensor dialect’s scope may be broadened through a careful discussion of the tradeoffs.

On the tensor type itself, note that it is actually a builtin type (it lives in the builtin dialect), and does not live in this dialect. Furthermore, a tensor is an immutable object. For example, this means that a copy will always be made of the tensor object when it is passed to the dest operand used by some ops in this dialect. As an optimization, an implementation can eliminate these copies during lowering when they are redundant and perform in-place mutation, see the Destination-Passing Style documentation for more information.

Structs

• BitcastOperation
  A bitcast operation. Tensor bitcast operation.
• BitcastOperationBuilder
  A builder for a bitcast operation.
• CastOperation
  A cast operation. Tensor cast operation.
• CastOperationBuilder
  A builder for a cast operation.
• CollapseShapeOperation
  A collapse_shape operation. Operation to produce a tensor with a smaller rank.
• CollapseShapeOperationBuilder
  A builder for a collapse_shape operation.
• ConcatOperation
  A concat operation. Tensor concatenation operation.
• ConcatOperationBuilder
  A builder for a concat operation.
• DimOperation
  A dim operation. Dimension index operation.
• DimOperationBuilder
  A builder for a dim operation.
• EmptyOperation
  An empty operation. Empty tensor operation.
• EmptyOperationBuilder
  A builder for an empty operation.
• ExpandShapeOperation
  An expand_shape operation. Operation to produce a tensor with a higher rank.
• ExpandShapeOperationBuilder
  A builder for an expand_shape operation.
• ExtractOperation
  An extract operation. Element extraction operation.
• ExtractOperationBuilder
  A builder for an extract operation.
• ExtractSliceOperation
  An extract_slice operation. Extract slice operation.
• ExtractSliceOperationBuilder
  A builder for an extract_slice operation.
• FromElementsOperation
  A from_elements operation. Tensor from elements operation..
• FromElementsOperationBuilder
  A builder for a from_elements operation.
• GatherOperation
  A gather operation. Gather a subset of a tensor at specified indices.
• GatherOperationBuilder
  A builder for a gather operation.
• GenerateOperation
  A generate operation. Creates a dynamically sized tensor from elements.
• GenerateOperationBuilder
  A builder for a generate operation.
• InsertOperation
  An insert operation. Element insertion operation.
• InsertOperationBuilder
  A builder for an insert operation.
• InsertSliceOperation
  An insert_slice operation. Insert_slice operation.
• InsertSliceOperationBuilder
  A builder for an insert_slice operation.
• PackOperation
  A pack operation. Tensor pack operation.
• PackOperationBuilder
  A builder for a pack operation.
• PadOperation
  A pad operation. Tensor pad operation.
• PadOperationBuilder
  A builder for a pad operation.
• ParallelInsertSliceOperation
  A parallel_insert_slice operation. Specify the tensor slice update of a single thread of a parent ParallelCombiningOpInterface op. .
• ParallelInsertSliceOperationBuilder
  A builder for a parallel_insert_slice operation.
• RankOperation
  A rank operation. Rank operation.
• RankOperationBuilder
  A builder for a rank operation.
• ReshapeOperation
  A reshape operation. Tensor reshape operation.
• ReshapeOperationBuilder
  A builder for a reshape operation.
• ScatterOperation
  A scatter operation. Scatter a tensor into a destination tensor at specified indices.
• ScatterOperationBuilder
  A builder for a scatter operation.
• SplatOperation
  A splat operation. Tensor splat or broadcast operation.
• SplatOperationBuilder
  A builder for a splat operation.
• UnPackOperation
  An unpack operation. Tensor unpack operation.
• UnPackOperationBuilder
  A builder for an unpack operation.
• YieldOperation
  A yield operation. Yield a value from a region.
• YieldOperationBuilder
  A builder for a yield operation.

Functions

• bitcast
  Creates a bitcast operation.
• cast
  Creates a cast operation.
• collapse_shape
  Creates a collapse_shape operation.
• concat
  Creates a concat operation.
• dim
  Creates a dim operation.
• empty
  Creates an empty operation.
• expand_shape
  Creates an expand_shape operation.
• extract
  Creates an extract operation.
• extract_slice
  Creates an extract_slice operation.
• from_elements
  Creates a from_elements operation.
• gather
  Creates a gather operation.
• generate
  Creates a generate operation.
• insert
  Creates an insert operation.
• insert_slice
  Creates an insert_slice operation.
• pack
  Creates a pack operation.
• pad
  Creates a pad operation.
• parallel_insert_slice
  Creates a parallel_insert_slice operation.
• rank
  Creates a rank operation.
• reshape
  Creates a reshape operation.
• scatter
  Creates a scatter operation.
• splat
  Creates a splat operation.
• unpack
  Creates an unpack operation.
• yield
  Creates a yield operation.