A Customized NoC Architecture to Enable Highly Localized Computing-on-the-Move DNN Dataflow
- 13 December 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 69 (3) , 1692-1696
Abstract
The ever-increasing computation complexity of fast-growing Deep Neural Networks (DNNs) has requested new computing paradigms to overcome the memory wall in conventional Von Neumann computing architectures. The emerging Computing-In-Memory (CIM) architecture has been a promising candidate to accelerate neural network computing. However, data movement between CIM arrays may still dominate the total power consumption in conventional designs. This brief proposes a flexible CIM processor architecture named Domino and “Computing-On-the-Move” (COM) dataflow, to enable stream computing and local data access to significantly reduce data movement energy. Meanwhile, Domino employs customized distributed instruction scheduling within Network-on-Chip (NoC) to implement inter-memory computing and attain mapping flexibility. The evaluation with prevailing DNN models shows that Domino achieves 1.77-to- $2.37\times $ power efficiency over several state-of-the-art CIM accelerators and improves the throughput by 1.28-to- $13.16\times $ .
Keywords
All Related Versions
Funding Information
- Major Scientific Research Project of Zhejiang Lab (2019KC0AD02)
- National Natural Science Foundation of China (U19B2043)
- National Key Research and Development Program of China (2020AAA0109002)
This publication has 15 references indexed in Scilit:
- 29.1 A 40nm 64Kb 56.67TOPS/W Read-Disturb-Tolerant Compute-in-Memory/Digital RRAM Macro with Active-Feedback-Based Read and In-Situ Write Verification2021
- CASCADE2019
- Eyeriss v2: A Flexible Accelerator for Emerging Deep Neural Networks on Mobile DevicesIEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2019
- Squeeze-and-Excitation Networks2018
- Efficient Processing of Deep Neural Networks: A Tutorial and SurveyProceedings of the IEEE, 2017
- Scaling equations for the accurate prediction of CMOS device performance from 180 nm to 7 nmIntegration, 2017
- A 0.5-V 28-nm 256-kb Mini-Array Based 6T SRAM With Vtrip-Tracking Write-AssistIEEE Transactions on Circuits and Systems I: Regular Papers, 2017
- Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks2016
- Cycle-Accurate Network on Chip Simulation with NoximACM Transactions on Modeling and Computer Simulation, 2016
- Deep Residual Learning for Image Recognition2016