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.
LayerDim Class Reference

(for-loop) dimension of a workload layer (e.g. More...

Inheritance diagram for LayerDim:
Collaboration diagram for LayerDim:

Public Member Functions

def __init__ (self, str name)
 
"LayerDim" create_r_version (self)
 Create a new LayerDim instance with is tagged relevant and can be distinguished from non-tagged LayerDims. More...
 
"LayerDim" create_ir_version (self)
 Create a new LayerDim instance with is tagged irrelevant and can be distinguished from non-tagged LayerDims. More...
 
- Public Member Functions inherited from OperandABC
def name (self)
 Protect the class variable from reassignment (as this would invalidate the stored hash value) More...
 
def __eq__ (self, "OperandABC" other)
 
def __hash__ (self)
 Optimize performance by statically storing the hash. More...
 
def __str__ (self)
 
def __repr__ (self)
 
def __lt__ (self, "OperandABC" other)
 
def __ge__ (self, "OperandABC" other)
 
def __jsonrepr__ (self)
 

Detailed Description

(for-loop) dimension of a workload layer (e.g.

K, C)

Constructor & Destructor Documentation

◆ __init__()

def __init__ (   self,
str  name 
)

Reimplemented from OperandABC.

Member Function Documentation

◆ create_ir_version()

"LayerDim" create_ir_version (   self)

Create a new LayerDim instance with is tagged irrelevant and can be distinguished from non-tagged LayerDims.

Here is the call graph for this function:

◆ create_r_version()

"LayerDim" create_r_version (   self)

Create a new LayerDim instance with is tagged relevant and can be distinguished from non-tagged LayerDims.

Here is the call graph for this function:

The documentation for this class was generated from the following file: