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.
|
Files | |
file | __init__.py |
file | data_movement.py |
file | mapping.py |
file | mapping_assist_funcs.py |
file | spatial_mapping.py |
file | spatial_mapping_internal.py |
file | temporal_mapping.py |
file | utils.py |