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.
|
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 |