Reconfigurable Network-on-Chip for 3D Neural Network Accelerators
2018 (English)In: 2018 12th IEEE/ACM International Symposium on Networks-on-Chip, NOCS 2018, Institute of Electrical and Electronics Engineers Inc. , 2018Conference paper, Published paper (Refereed)
Abstract [en]
Parallel hardware accelerators for large-scale neural networks typically consist of several processing nodes, arranged as a multi- or many-core system-on-chip, connected by a network-on-chip (NoC). Recent proposals also benefit from the emerging 3D memory-on-logic architectures to provide sufficient bandwidth for neural networks. Handling the heavy traffic between neurons and memory and also the multicast-based inter-neuron traffic, which often varies over time, is the most challenging design consideration for the networks-on-chip in such accelerators. To address these issues, a reconfigurable network-on-chip architecture for 3D memory-on-logic neural network accelerators is presented in this paper. The reconfigurable NoC can adapt its topology to the on-chip traffic patterns. It can be also configured as a tree-like structure to support multicast-based neuron-to-neuron and memory-to-neuron traffic of neural networks. The evaluation results show that the proposed architecture can better manage the multicast-based traffic of neural networks than some state-of-the-art topologies and considerably increase throughput and power efficiency.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2018.
Series
International Symposium on Networks-on-Chip, ISSN 2474-3739
Keywords [en]
Network-on-Chip, Neural Networks, Hardware Accelerator, Reconfiguration
National Category
Computer Systems
Identifiers
URN: urn:nbn:se:mdh:diva-41506DOI: 10.1109/NOCS.2018.8512170ISI: 000759131800018Scopus ID: 2-s2.0-85057297781ISBN: 9781538648933 (print)OAI: oai:DiVA.org:mdh-41506DiVA, id: diva2:1268527
Conference
12th IEEE/ACM International Symposium on Networks-on-Chip, NOCS 2018, Torino, Italy, 4-5 October 2018
2018-12-062018-12-062022-11-23Bibliographically approved