experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Allow index inside dimension tensors.

Browse Source 
Ever since https://reviews.llvm.org/rG3dceb6d2460550ef8c2e53df2181c8a11a7e6730 MLIR now allows `index` type inside tensors, addressing this longstanding TODO.

PiperOrigin-RevId: 306391413
Change-Id: I797623de02ff031b9ffabfaee81afba91ead6692
This commit is contained in:
Sean Silva 2020-04-14 01:00:05 -07:00 committed by TensorFlower Gardener
parent 242129341e
commit b2418b7fee
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
tensorflow/compiler/mlir/xla/ir/hlo_ops_base.td
View File

@ -55,11 +55,10 @@ def HLO_Tuple : NestedTupleOf<[HLO_Tensor, HLO_Token]>;
def HLO_TensorOrTuple : AnyTypeOf<[HLO_Tensor, HLO_Tuple]>; def HLO_TensorOrTuple : AnyTypeOf<[HLO_Tensor, HLO_Tuple]>;
// Dynamic representation of a shape vector as a tensor. Ideally this would be // Dynamic representation of a shape vector as a tensor.
// an index type (as it stores indices) but that is currently disallowed in
// MLIR.
def HLO_DimensionTensor : ShapedContainerType< def HLO_DimensionTensor : ShapedContainerType<
[AnySignlessInteger], And<[IsTensorTypePred, HasAnyRankOfPred<[1]>]>, [Index, AnySignlessInteger],
And<[IsTensorTypePred, HasAnyRankOfPred<[1]>]>,
"a 1D tensor of dimensions">; "a 1D tensor of dimensions">;
// In general, static shaped tensor constraints should be avoided unless // In general, static shaped tensor constraints should be avoided unless