xla::TransposeFolding Class Reference

#include <transpose_folding.h>

Inherits HloPassInterface.

Public Member Functions
StatusOr< bool >	Run (HloModule *module) override
	entry point of xla::TransposeFolding pass More...

Detailed Description

HLO pass that folds transpose operators into Dot operators, where the Dot operator is implemented by a GEMM kernel that can transpose its inputs.

Member Function Documentation

Run()

StatusOr< bool > xla::TransposeFolding::Run ( HloModule *  module )

override

entry point of xla::TransposeFolding pass

Find all folding opportunities(dots and convolutions) and then fold it.

Here is the call graph for this function:

---

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

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