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.
SpatialMappingInternal Member List

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

__init__(self, SpatialMappingPerMemLvl spatial_mapping_dict, "LayerNode" layer_node)SpatialMappingInternal
__jsonrepr__(self)SpatialMappingInternal
__repr__(self)SpatialMappingInternal
__str__(self)SpatialMappingInternal
arch_levelSpatialMappingInternal
calc_data_serve_scope(self)SpatialMappingInternal
calc_mem_bw_boost_factor(self)SpatialMappingInternal
calc_unit_count(self)SpatialMappingInternal
calc_unroll_size(self)SpatialMappingInternal
data_serve_scopeSpatialMappingInternal
get_unrolling(self, LayerOperand op, int level)SpatialMappingInternal
get_unrolling_all(self, LayerOperand op, int min_level)SpatialMappingInternal
layer_nodeSpatialMappingInternal
mapping_dict_originSpatialMappingInternal
mem_bw_boostSpatialMappingInternal
save_spatial_loop_dim_size(self)SpatialMappingInternal
unit_countSpatialMappingInternal
unit_duplicateSpatialMappingInternal
unit_uniqueSpatialMappingInternal
unroll_size_irSpatialMappingInternal
unroll_size_rSpatialMappingInternal
unroll_size_totalSpatialMappingInternal