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.
stages Directory Reference

Directories

directory  evaluation
 
directory  mapping
 
directory  parser
 
directory  results
 

Files

file  __init__.py
 
file  exploit_data_locality_stages.py
 
file  main.py
 
file  run_opt_stages.py
 
file  stage.py
 
file  workload_iterator.py