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.
|
Links LayerOperand to MemoryOperand. More...
Public Member Functions | |
def | __init__ (self, dict[LayerOperand, MemoryOperand] data) |
MemoryOperand | layer_to_mem_op (self, LayerOperand layer_op) |
LayerOperand | mem_to_layer_op (self, MemoryOperand mem_op) |
Given a MemoryOperand, return the linked LayerOperand. More... | |
def | layer_and_mem_ops (self) |
bool | contains_layer_op (self, LayerOperand layer_op) |
bool | contains_mem_op (self, MemoryOperand mem_op) |
def | copy (self) |
def | __str__ (self) |
![]() | |
def | __init__ (self, Any data) |
int | __len__ (self) |
Iterator[Any] | __iter__ (self) |
def | __getitem__ (self, Any key) |
bool | __contains__ (self, Any key) |
def | __repr__ (self) |
Any | __jsonrepr__ (self) |
def | __eq__ (self, object other) |
def | __hash__ (self) |
Public Attributes | |
data | |
layer_operands | |
mem_operands | |
![]() | |
data | |
Links LayerOperand to MemoryOperand.
def __init__ | ( | self, | |
dict[LayerOperand, MemoryOperand] | data | ||
) |
def __str__ | ( | self | ) |
Reimplemented from LayerAttribute.
bool contains_layer_op | ( | self, | |
LayerOperand | layer_op | ||
) |
bool contains_mem_op | ( | self, | |
MemoryOperand | mem_op | ||
) |
def copy | ( | self | ) |
def layer_and_mem_ops | ( | self | ) |
MemoryOperand layer_to_mem_op | ( | self, | |
LayerOperand | layer_op | ||
) |
LayerOperand mem_to_layer_op | ( | self, | |
MemoryOperand | mem_op | ||
) |
Given a MemoryOperand, return the linked LayerOperand.
data |
layer_operands |
mem_operands |