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.
|
Represents the sum of multiple CMEs. More...
Public Member Functions | |
def | __init__ (self) |
def | __str__ (self) |
![]() | |
def | core (self) |
"CumulativeCME" | __add__ (self, "CostModelEvaluationABC" other) |
def | __mul__ (self, int number) |
dict[str, float] | __simplejsonrepr__ (self) |
Simple JSON representation used for saving this object to a simple json file. More... | |
def | __jsonrepr__ (self) |
JSON representation used for saving this object to a json file. More... | |
Public Attributes | |
accelerator | |
Represents the sum of multiple CMEs.
This class only contains attributes that make sense for cumulated CMEs
def __init__ | ( | self | ) |
Reimplemented from CostModelEvaluationABC.
def __str__ | ( | self | ) |
accelerator |