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.
|
Classes | |
class | MinimalEnergyStage |
Class that keeps yields only the cost model evaluation that has minimal energy of all cost model evaluations generated by it's substages created by list_of_callables. More... | |
class | MinimalLatencyStage |
Class that keeps yields only the cost model evaluation that has minimal latency of all cost model evaluations generated by it's substages created by list_of_callables. More... | |
class | MinimalEDPStage |
Class that keeps yields only the cost model evaluation that has minimal EDP of all cost model evaluations generated by it's substages created by list_of_callables. More... | |
class | SumStage |
Class that keeps yields only the sum of all cost model evaluations generated by its substages created by list_of_callables. More... | |
Variables | |
logger = logging.getLogger(__name__) | |
logger = logging.getLogger(__name__) |