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.
zigzag.mapping.utils Namespace Reference

Functions

def get_spatial_loops (CostModelEvaluation cme)
 
def get_temporal_loops (CostModelEvaluation cme)
 
def get_memory_names (CostModelEvaluation cme)
 

Variables

 TypeAlias
 

Function Documentation

◆ get_memory_names()

def zigzag.mapping.utils.get_memory_names ( CostModelEvaluation  cme)
Here is the call graph for this function:
Here is the caller graph for this function:

◆ get_spatial_loops()

def zigzag.mapping.utils.get_spatial_loops ( CostModelEvaluation  cme)
Here is the caller graph for this function:

◆ get_temporal_loops()

def zigzag.mapping.utils.get_temporal_loops ( CostModelEvaluation  cme)
Here is the call graph for this function:
Here is the caller graph for this function:

Variable Documentation

◆ TypeAlias

TypeAlias