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 | onnx |
Files | |
file | __init__.py |
file | accelerator_factory.py |
file | accelerator_validator.py |
file | arguments.py |
file | mapping_factory.py |
file | mapping_validator.py |
file | upgraded_validator.py |
file | workload_factory.py |
file | workload_validator.py |