Neuron grouping and mapping methods for 2D-mesh NoC-based DNN accelerators

Deep Neural Networks (DNNs) have gained widespread adoption in various fields; however, their computational cost is often prohibitively high due to the large number of layers and neurons communicating with each other. Furthermore, DNNs can consume a significant amount of energy due to the large volu...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of parallel and distributed computing Ročník 193; s. 104949
Hlavní autori: Nacar, Furkan, Cakin, Alperen, Dilek, Selma, Tosun, Suleyman, Chakrabarty, Krishnendu
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Inc 01.11.2024
Predmet:
Accelerators
Deep Neural Network (DNN)
Integer Linear Programming (ILP)
Mapping
Network-on-Chip (NoC)
Simulated Annealing (SA)
Deep Neural Network (DNN)
Mapping
Accelerators
Integer Linear Programming (ILP)
Network-on-Chip (NoC)
Simulated Annealing (SA)
ISSN:0743-7315
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Deep Neural Networks (DNNs) have gained widespread adoption in various fields; however, their computational cost is often prohibitively high due to the large number of layers and neurons communicating with each other. Furthermore, DNNs can consume a significant amount of energy due to the large volume of data movement and computation they require. To address these challenges, there is a need for new architectures to accelerate DNNs. In this paper, we propose novel neuron grouping and mapping methods for 2D-mesh Network-on-Chip (NoC)-based DNN accelerators considering both fully connected and partially connected DNN models. We present Integer Linear Programming (ILP) and simulated annealing (SA)-based neuron grouping solutions with the objective of minimizing the total volume of data communication among the neuron groups. After determining a suitable graph representation of the DNN, we also apply ILP and SA methods to map the neurons onto a 2D-mesh NoC fabric with the objective of minimizing the total communication cost of the system. We conducted several experiments on various benchmarks and DNN models with different pruning ratios and achieved an average of 40-50% improvement in communication cost. •Novel methodologies proposed for efficient 2D-mesh NoC-based DNN accelerators.•ILP and SA-based neuron grouping and mapping methods to minimize communication cost.•The proposed methods can be used for both fully connected and partially pruned DNNs.•Performance validation on diverse DNN benchmark applications.
ISSN:0743-7315
DOI:10.1016/j.jpdc.2024.104949