An Overview of Efficient Interconnection Networks for Deep Neural Network Accelerators
Open Access
- 9 September 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 10 (3), 268-282
- https://doi.org/10.1109/jetcas.2020.3022920
Abstract
Deep Neural Networks (DNNs) have shown significant advantages in many domains, such as pattern recognition, prediction, and control optimization. The edge computing demand in the Internet-of-Things (IoTs) era has motivated many kinds of computing platforms to accelerate DNN operations. However, due to the massive parallel processing, the performance of the current large-scale artificial neural network is often limited by the huge communication overheads and storage requirements. As a result, efficient interconnection and data movement mechanisms for future on-chip artificial intelligence (AI) accelerators are worthy of study. Currently, a large body of research aims to find an efficient on-chip interconnection to achieve low-power and high-bandwidth DNN computing. This paper provides a comprehensive investigation of the recent advances in efficient on-chip interconnection and design methodology of the DNN accelerator design. First, we provide an overview of the different interconnection methods on the DNN accelerator. Then, the interconnection methods on the non-ASIC DNN accelerator will be discussed. On the other hand, with the flexible interconnection, the DNN accelerator can support different computing flow, which increases the computing flexibility. With this motivation, reconfigurable DNN computing with flexible on-chip interconnection will be investigated in this paper. Finally, we investigate the emerging interconnection technologies (e.g., in/near-memory processing) for the DNN accelerator design. This paper systematically investigates the interconnection networks in modern DNN accelerator designs. With this article, the readers are able to: 1) understand the interconnection design for DNN accelerators; 2) evaluate DNNs with different on-chip interconnection; 3) familiarize with the trade-offs under different interconnections.Keywords
Funding Information
- Ministry of Science and Technology Taiwan (MOST 109-2221-E-110-062)
This publication has 120 references indexed in Scilit:
- A scalable processing-in-memory accelerator for parallel graph processingPublished by Association for Computing Machinery (ACM) ,2015
- RENOPublished by Association for Computing Machinery (ACM) ,2015
- Spin-Transfer Torque Magnetic Memory as a Stochastic Memristive Synapse for Neuromorphic SystemsIEEE Transactions on Biomedical Circuits and Systems, 2015
- Fixed latency on-chip interconnect for hardware spiking neural network architecturesParallel Computing, 2013
- Spin-transfer torque magnetic random access memory (STT-MRAM)ACM Journal on Emerging Technologies in Computing Systems, 2013
- Advancing interconnect density for spiking neural network hardware implementations using traffic-aware adaptive network-on-chip routersNeural Networks, 2012
- Fast and Scalable CPU/GPU Collision Detection for Rigid and Deformable SurfacesComputer Graphics Forum, 2010
- SPIKING NEURAL NETWORKSInternational Journal of Neural Systems, 2009
- The missing memristor foundNature, 2008
- On-line algorithms for path selection in a nonblocking networkPublished by Association for Computing Machinery (ACM) ,1990