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 Directory Reference

Directories

directory  cacti
 
directory  cost_model
 
directory  hardware
 
directory  mapping
 
directory  opt
 
directory  parser
 
directory  stages
 
directory  visualization
 
directory  workload
 

Files

file  __init__.py
 
file  __main__.py
 
file  api.py
 
file  datatypes.py
 
file  utils.py