diff options
| author |  A. Unique TensorFlower <gardener@tensorflow.org> | 2018-06-21 15:26:20 -0700 |
|---|---|---|
| committer | TensorFlower Gardener <gardener@tensorflow.org> | 2018-06-21 15:29:18 -0700 |
| commit | adb956fe62a52c089a7df8b0867bff1e7741ea8e (patch) | |
| tree | 26606265f104ed9fd223e78083db68b3e1f195a8 /tensorflow/compiler/xla/service/shape_inference.cc | |
| parent | 4ff57a1098fa5353fa19d6994e76280465cc3fb4 (diff) | |
[TF:XLA] Add Xor HLO operation.
This avoids lowering xor in terms of other bitwise ops and all backends have instructions for it anyway.
PiperOrigin-RevId: 201597493
Diffstat (limited to 'tensorflow/compiler/xla/service/shape_inference.cc')
| -rw-r--r-- | tensorflow/compiler/xla/service/shape_inference.cc | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/tensorflow/compiler/xla/service/shape_inference.cc b/tensorflow/compiler/xla/service/shape_inference.cc index 4606d8f202..bbc95f8630 100644 --- a/tensorflow/compiler/xla/service/shape_inference.cc +++ b/tensorflow/compiler/xla/service/shape_inference.cc @@ -885,6 +885,7 @@ ShapeInference::InferDegenerateDimensionBroadcastShape(HloOpcode operation, } case HloOpcode::kAnd: case HloOpcode::kOr: + case HloOpcode::kXor: if (lhs.element_type() != PRED && !primitive_util::IsIntegralType(lhs.element_type())) { return InvalidArgument( |