- Generated by
1.9.1
|
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.
|
Classes | |
| class | OperandABC |
| Abstract Base Class for all dimension- and operand-like classes. More... | |
| class | LayerOperand |
| Operand from the layer definition, e.g. More... | |
| class | MemoryOperand |
| Operand from the memory definition, e.g. More... | |
| class | LayerDim |
| (for-loop) dimension of a workload layer (e.g. More... | |
| class | OADimension |
| Operational Array Dimension. More... | |
| class | Constants |
| Store constant objects used throughout ZigZag (instead of hardcoding them) More... | |
Namespaces | |
| zigzag.datatypes | |
Variables | |
| ArrayType = np.ndarray[Any, Any] | |
1.9.1