ZigZag - Deep Learning Hardware Design Space Exploration
This repository presents the novel version of our tried-and-tested hardware Architecture-Mapping Design Space Exploration (DSE) Framework for Deep Learning (DL) accelerators. ZigZag bridges the gap between algorithmic DL decisions and their acceleration cost on specialized accelerators through a fast and accurate hardware cost estimation.
MinimalLatencyStage Class Reference

Class that keeps yields only the cost model evaluation that has minimal latency of all cost model evaluations generated by it's substages created by list_of_callables. More...

Inheritance diagram for MinimalLatencyStage:
Collaboration diagram for MinimalLatencyStage:

Public Member Functions

def __init__ (self, list[StageCallable] list_of_callables, *bool reduce_minimal_keep_others=False, **Any kwargs)
 Initialize the compare stage. More...
 
def run (self)
 Run the compare stage by comparing a new cost model output with the current best found result. More...
 
- Public Member Functions inherited from Stage
def __init__ (self, list["StageCallable"] list_of_callables, **Any kwargs)
 
def __iter__ (self)
 
bool is_leaf (self)
 

Public Attributes

 keep_others
 
- Public Attributes inherited from Stage
 kwargs
 
 list_of_callables
 

Detailed Description

Class that keeps yields only the cost model evaluation that has minimal latency of all cost model evaluations generated by it's substages created by list_of_callables.

Constructor & Destructor Documentation

◆ __init__()

def __init__ (   self,
list[StageCallable list_of_callables,
*bool   reduce_minimal_keep_others = False,
**Any  kwargs 
)

Initialize the compare stage.

Member Function Documentation

◆ run()

def run (   self)

Run the compare stage by comparing a new cost model output with the current best found result.

Reimplemented from Stage.

Here is the caller graph for this function:

Member Data Documentation

◆ keep_others

keep_others

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