Please make sure that this is a feature request. As per our GitHub Policy, we only address code/doc bugs, performance issues, feature requests and build/installation issues on GitHub. tag:feature_template

System information

• TensorFlow version (you are using): master
• Are you willing to contribute it (Yes/No): yes

Describe the feature and the current behavior/state.

https://github.com/tensorflow/tensorflow/blob/master/tensorflow/compiler/xla/service/hlo_instruction.h#L1315
Only kFusion is considered in this code, modify to the following code to consider other instructions that has a called_computation.

if (!hlo.called_computations().empty()) {
  for (auto* comp : hlo.called_computations()) {
    h = H::combine(std::move(h), *comp);
  }
}

if (hlo.opcode() == HloOpcode::kFusion) {
  h = H::combine(std::move(h), hlo.fusion_kind(), 
                 hlo.fused_instruction_count(),
                 hlo.fused_parameters().size());
}

Will this change the current api? How?
No

Who will benefit with this feature?
Everyone who is using the hash value to distinguish different computations.

Any Other info.