xla::ReducePrecisionInsertion Class Reference

#include <reduce_precision_insertion.h>

Inherits HloPassInterface.

Public Types
enum	PassTiming

Static Public Member Functions
static bool	AddPasses (HloPassPipeline *pipeline, const DebugOptions &debug_options, const PassTiming pass_timing)

Detailed Description

Google docs:

HLO pass which inserts reduce-precision instructions into the HLO graph, for purposes of experimenting with the effects of reduced-precision storage of intermediate values.

Member Enumeration Documentation

PassTiming

enum xla::ReducePrecisionInsertion::PassTiming

strong

Enumeration to control which passes should be added.

Member Function Documentation

AddPasses()

bool xla::ReducePrecisionInsertion::AddPasses ( HloPassPipeline *  pipeline, const DebugOptions &  debug_options, const PassTiming  pass_timing  )

static

Google docs:

Add ReducePrecisionInsertion passes to an HloPassPipeline based on the list of HloReducePrecisionOptions in a DebugOptions proto. Returns true if any passes were added.

Here is the call graph for this function:

Here is the caller graph for this function:

---

The documentation for this class was generated from the following files:

• tensorflow/tensorflow/compiler/xla/service/reduce_precision_insertion.h
• tensorflow/tensorflow/compiler/xla/service/reduce_precision_insertion.cc