- 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 | LayerEquation |
| "! core computation equation, e.g. More... | |
| class | LayerDimSizes |
| Contains the size of each computation loop as defined in the workload, e.g. More... | |
| class | LayerOperandPrecision |
| Contains the bit precision of each layer operand. More... | |
| class | MemoryOperandLinks |
| Links LayerOperand to MemoryOperand. More... | |
| class | LayerDimRelation |
| For the operand dimension that is not directly a loop dimension, a relation equations between them(operand dimension) and the loop dimension is required. More... | |
| class | LayerTemporalOrdering |
| Represents a user-defined temporal ordering. More... | |
| class | LayerPadding |
Namespaces | |
| zigzag.workload.layer_attributes | |
Variables | |
| logger = logging.getLogger(__name__) | |
| TypeAlias | |
1.9.1