|
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.
|


Public Member Functions | |
| def | __init__ (self, Multiplier multiplier, dict[OADimension, int] dimensions, dict[str, set[tuple[int,...]]]|None operand_spatial_sharing=None) |
Public Member Functions inherited from OperationalArray | |
| def | __init__ (self, OperationalUnit operational_unit, dict[OADimension, int] dimension_sizes) |
| def | __jsonrepr__ (self) |
| bool | __eq__ (self, Any other) |
Public Member Functions inherited from OperationalArrayABC | |
| def | __init__ (self, dict[OADimension, int] dimension_sizes) |
Public Attributes | |
| multiplier | |
| operand_spatial_sharing | |
Public Attributes inherited from OperationalArray | |
| total_unit_count | |
| total_area | |
| unit | |
| dimension_sizes | |
Public Attributes inherited from OperationalArrayABC | |
| dimension_sizes | |
| def __init__ | ( | self, | |
| Multiplier | multiplier, | ||
| dict[OADimension, int] | dimensions, | ||
| dict[str, set[tuple[int, ...]]] | None | operand_spatial_sharing = None |
||
| ) |
| multiplier |
| operand_spatial_sharing |