diff options
author | 2017-07-26 19:56:14 -0700 | |
---|---|---|
committer | 2017-07-26 20:00:11 -0700 | |
commit | 4404aa7cbc17be245fe11ef85a26beeb63b52b8b (patch) | |
tree | 80def079dae47b5ee329df04d176d6d85bb5cbc2 /tensorflow | |
parent | 43036ac16cc5af2e1ce68d571d83cfacf8fb7cb3 (diff) |
[XLA] Add TODO comment explaining why the IsScalar check exists.
PiperOrigin-RevId: 163292777
Diffstat (limited to 'tensorflow')
-rw-r--r-- | tensorflow/compiler/xla/service/reduce_precision_insertion.cc | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/tensorflow/compiler/xla/service/reduce_precision_insertion.cc b/tensorflow/compiler/xla/service/reduce_precision_insertion.cc index a3079a0c03..7888790e2d 100644 --- a/tensorflow/compiler/xla/service/reduce_precision_insertion.cc +++ b/tensorflow/compiler/xla/service/reduce_precision_insertion.cc @@ -41,6 +41,11 @@ StatusOr<bool> ReducePrecisionInsertion::Run(HloModule* module) { // equivalent behavior can be obtained by adding ReducePrecision // instructions after the instructions that pull the F32 arrays out of // the tuples. + // + // TODO(b/64093391): Remove the IsScalar check once this won't cause + // failures on the GPU backend if the ReducePrecision instruction ends up + // inserted between a scalar constant and the init_value argument of a + // Reduce operation. if (instruction->shape().element_type() == PrimitiveType::F32 && !ShapeUtil::IsScalar(instruction->shape()) && should_reduce_output_precision_(instruction->opcode())) { |