diff options
| author |  David Majnemer <majnemer@google.com> | 2018-05-09 23:21:19 -0700 |
|---|---|---|
| committer |  TensorFlower Gardener <gardener@tensorflow.org> | 2018-05-09 23:24:14 -0700 |
| commit | 11574c3b5aa8dbb9d7dbaf0e1b20ad3ae5a4bb46 (patch) | |
| tree | 096f2c288fc4ad0986f742263bfe22fc80449a26 /tensorflow/compiler/xla/service/hlo_graph_dumper.cc | |
| parent | 8c747a1a8f8c78475c5d5d99d95509c836684dcf (diff) | |
[XLA] Add log1p/expm1
A new HLO seems prudent as it allows implementations to use fancy techniques to
compute accurate results for small inputs.
PiperOrigin-RevId: 196078115
Diffstat (limited to 'tensorflow/compiler/xla/service/hlo_graph_dumper.cc')
| -rw-r--r-- | tensorflow/compiler/xla/service/hlo_graph_dumper.cc | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/tensorflow/compiler/xla/service/hlo_graph_dumper.cc b/tensorflow/compiler/xla/service/hlo_graph_dumper.cc index 55911acc28..8dc3b83eee 100644 --- a/tensorflow/compiler/xla/service/hlo_graph_dumper.cc +++ b/tensorflow/compiler/xla/service/hlo_graph_dumper.cc @@ -925,6 +925,7 @@ ColorScheme HloDotDumper::GetInstructionColor(const HloInstruction* instr) { case HloOpcode::kDivide: case HloOpcode::kEq: case HloOpcode::kExp: + case HloOpcode::kExpm1: case HloOpcode::kFloor: case HloOpcode::kGe: case HloOpcode::kGt: @@ -932,6 +933,7 @@ ColorScheme HloDotDumper::GetInstructionColor(const HloInstruction* instr) { case HloOpcode::kIsFinite: case HloOpcode::kLe: case HloOpcode::kLog: + case HloOpcode::kLog1p: case HloOpcode::kLt: case HloOpcode::kMaximum: case HloOpcode::kMinimum: |