This is an archive of the discontinued LLVM Phabricator instance.

Show First 20 Lines • Show All 54 Lines • ▼ Show 20 Lines	let description = [{
`bufferization.alloc_tensor` is a tensor value that can be used like any		`bufferization.alloc_tensor` is a tensor value that can be used like any
other tensor value. In practice, it is often used as the "out" operand of		other tensor value. In practice, it is often used as the "out" operand of
another op. Sparse tensor allocations should always be used in a local		another op. Sparse tensor allocations should always be used in a local
construction operation and never escape the function boundary directly.		construction operation and never escape the function boundary directly.

Example:		Example:

```mlir		```mlir
%c = bufferization.alloc_tensor [%d1, %d2] : tensor<?x?xf32, #SparseMatrix>		%c = bufferization.alloc_tensor(%d1, %d2) : tensor<?x?xf32, #SparseMatrix>
		aartbikUnsubmitted Done Reply Inline Actions Good catch! Given the roundtrip behavior, I think you can even remove the space, i.e. bufferization.alloc_tensor(%d1, %d2) aartbik: Good catch! Given the roundtrip behavior, I think you can even remove the space, i.e.
%0 = linalg.matmul		%0 = linalg.matmul
ins(%a, %b: tensor<?x?xf32, #SparseMatrix>, tensor<?x?xf32, #SparseMatrix>)		ins(%a, %b: tensor<?x?xf32, #SparseMatrix>, tensor<?x?xf32, #SparseMatrix>)
outs(%c: tensor<?x?xf32, #SparseMatrix>) -> tensor<?x?xf32, #SparseMatrix>		outs(%c: tensor<?x?xf32, #SparseMatrix>) -> tensor<?x?xf32, #SparseMatrix>
return %0 : tensor<?x?xf32, #SparseMatrix>		return %0 : tensor<?x?xf32, #SparseMatrix>
```		```
}];		}];

let arguments = (ins Variadic<Index>:$dynamic_sizes,		let arguments = (ins Variadic<Index>:$dynamic_sizes,
▲ Show 20 Lines • Show All 346 Lines • Show Last 20 Lines

This is an archive of the discontinued LLVM Phabricator instance.

[mlir][bufferization] fix typo in example code for bufferization.alloc_tensorClosedPublic

Details

Diff Detail

Event Timeline

Revision Contents

Diff 458783

mlir/include/mlir/Dialect/Bufferization/IR/BufferizationOps.td

[mlir][bufferization] fix typo in example code for bufferization.alloc_tensor
ClosedPublic