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.
|
Pipeline stage that calls a cost model to evaluate a mapping on a HW config. More...
Public Member Functions | |
def | __init__ (self, list[StageCallable] list_of_callables, *Accelerator accelerator, LayerNode layer, SpatialMappingInternal spatial_mapping, SpatialMappingInternal spatial_mapping_int, TemporalMapping temporal_mapping, bool access_same_data_considered_as_no_access=True, **Any kwargs) |
def | run (self) |
Run the cost model stage by calling the internal zigzag cost model with the correct inputs. More... | |
bool | is_leaf (self) |
![]() | |
def | __init__ (self, list["StageCallable"] list_of_callables, **Any kwargs) |
def | __iter__ (self) |
Public Attributes | |
accelerator | |
layer | |
spatial_mapping | |
spatial_mapping_int | |
temporal_mapping | |
access_same_data_considered_as_no_access | |
![]() | |
kwargs | |
list_of_callables | |
Pipeline stage that calls a cost model to evaluate a mapping on a HW config.
def __init__ | ( | self, | |
list[StageCallable] | list_of_callables, | ||
*Accelerator | accelerator, | ||
LayerNode | layer, | ||
SpatialMappingInternal | spatial_mapping, | ||
SpatialMappingInternal | spatial_mapping_int, | ||
TemporalMapping | temporal_mapping, | ||
bool | access_same_data_considered_as_no_access = True , |
||
**Any | kwargs | ||
) |
bool is_leaf | ( | self | ) |
Reimplemented from Stage.
def run | ( | self | ) |
Run the cost model stage by calling the internal zigzag cost model with the correct inputs.
Reimplemented from Stage.
accelerator |
access_same_data_considered_as_no_access |
layer |
spatial_mapping |
spatial_mapping_int |
temporal_mapping |