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.
SpatialMappingHint Member List

This is the complete list of members for SpatialMappingHint, including all inherited members.

__contains__(self, Any key)LayerAttribute
__eq__(self, object other)LayerAttribute
__getitem__(self, OADimension key)SpatialMappingHint
zigzag::workload::layer_attribute::LayerAttribute.__getitem__(self, Any key)LayerAttribute
__hash__(self)LayerAttribute
__init__(self, dict[OADimension, set[LayerDim]] data)SpatialMappingHint
zigzag::workload::layer_attribute::LayerAttribute.__init__(self, Any data)LayerAttribute
__iter__(self)LayerAttribute
__jsonrepr__(self)LayerAttribute
__len__(self)LayerAttribute
__repr__(self)LayerAttribute
__str__(self)LayerAttribute
clear_invalid_hits(self, list[LayerDim] valid_layer_dims)SpatialMappingHint
complete_with_defaults(self, dict[OADimension, int] oa_dim_sizes, list[LayerDim] layer_dims)SpatialMappingHint
dataSpatialMappingHint
empty()SpatialMappingHintstatic