ONE - On-device Neural Engine
Loading...
Searching...
No Matches
luci::FuseMulToFullyConnectedWeightsPass Struct Referencefinal

Class to fuse Mul into following FullyConnected. More...

#include <FuseMulToFullyConnectedWeightsPass.h>

Collaboration diagram for luci::FuseMulToFullyConnectedWeightsPass:

Public Member Functions

const char * name (void) const final
 
bool run (loco::Graph *g) final
 Run the pass.
 
- Public Member Functions inherited from logo::Pass
virtual ~Pass ()=default
 

Detailed Description

Class to fuse Mul into following FullyConnected.

Definition at line 28 of file FuseMulToFullyConnectedWeightsPass.h.

Member Function Documentation

◆ name()

const char * luci::FuseMulToFullyConnectedWeightsPass::name ( void  ) const
inlinefinalvirtual

Reimplemented from logo::Pass.

Definition at line 30 of file FuseMulToFullyConnectedWeightsPass.h.

30{ return "luci::FuseMulToFullyConnectedWeightsPass"; }

◆ run()

bool luci::FuseMulToFullyConnectedWeightsPass::run ( loco::Graph graph)
finalvirtual

Run the pass.

Returns
false if there was nothing changed

Implements logo::Pass.

Definition at line 104 of file FuseMulToFullyConnectedWeightsPass.cpp.

105{
106 bool changed = false;
107 for (auto node : loco::active_nodes(loco::output_nodes(g)))
108 {
109 auto fc = dynamic_cast<luci::CircleFullyConnected *>(node);
110 if (not fc)
111 continue;
112
113 if (fuse_fc_with_mul(fc))
114 changed = true;
115 }
116
117 return changed;
118}
FULLY_CONNECTED in Circle.
std::set< loco::Node * > active_nodes(const std::vector< loco::Node * > &roots)
Enumerate all the nodes required to compute "roots".
std::vector< Node * > output_nodes(Graph *)
Definition Graph.cpp:101

References loco::active_nodes(), and loco::output_nodes().

Referenced by package.infer.session::inference().


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