xla::HloModule Class Reference

#include <hlo_module.h>

Collaboration diagram for xla::HloModule:

Public Member Functions
std::vector< HloComputation * >	MakeNonfusionComputations () const

Detailed Description

Describes a compilation unit at the HLO level.

A HLO module contains one or more HLO computations. The module contains one "entry" computation which produces the result. The module also includes any embedded computations used by instructions such as "map" and "reduce". All computations are owned by the module.

Member Function Documentation

MakeNonfusionComputations()

std::vector< HloComputation * > xla::HloModule::MakeNonfusionComputations

(

)

const

Gets the computations in this module which aren't for fusion nodes.

Each computation has a filed points to the corresponding fusion instruction. So if it is non-fusion computation, then the pointer will be null

Here is the caller graph for this function:

---

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

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