Access the full text.
Sign up today, get DeepDyve free for 14 days.
I. Fujiwara, M. Koibuchi (2013)
Mapping Non-trivial Network Topologies Onto Chips2013 IEEE 7th International Symposium on Embedded Multicore Socs
S. Kaushik, Ashutosh Singh, T. Srikanthan (2011)
Computation and communication aware run-time mapping for NoC-based MPSoC platforms2011 IEEE International SOC Conference
A. Barto, R. Sutton, C. Anderson (1983)
Neuronlike adaptive elements that can solve difficult learning control problemsIEEE Transactions on Systems, Man, and Cybernetics, SMC-13
Peng Chen, Weichen Liu, Hui Chen, Shiqing Li, Mengquan Li, Lei Yang, Nan Guan (2021)
Reduced Worst-Case Communication Latency Using Single-Cycle Multihop Traversal Network-on-ChipIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 40
Vijeta Rathore, Vivek Chaturvedi, Ashutosh Singh, T. Srikanthan, M. Shafique (2019)
Life Guard: A Reinforcement Learning-Based Task Mapping Strategy for Performance-Centric Aging Management2019 56th ACM/IEEE Design Automation Conference (DAC)
Wei Quan, Andy Pimentel (2015)
A Hybrid Task Mapping Algorithm for Heterogeneous MPSoCsACM Transactions on Embedded Computing Systems (TECS), 14
Hui Chen, Peng Chen, Jun Zhou, Luan Duong, Weichen Liu (2020)
ArSMART: An Improved SMART NoC Design Supporting Arbitrary-Turn TransmissionIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 41
Ashutosh Singh, W. Jigang, A. Prakash, T. Srikanthan (2009)
Efficient Heuristics for Minimizing Communication Overhead in NoC-based Heterogeneous MPSoC Platforms2009 IEEE/IFIP International Symposium on Rapid System Prototyping
Shoukat Ali, H. Siegel, Muthucumaru Maheswaran, D. Hensgen, Sahra Ali (2000)
Task execution time modeling for heterogeneous computing systemsProceedings 9th Heterogeneous Computing Workshop (HCW 2000) (Cat. No.PR00556)
A. Krishnakumar, Samet Arda, A. Goksoy, Sumit Mandal, U. Ogras, A. Sartor, R. Marculescu (2020)
Runtime Task Scheduling Using Imitation Learning for Heterogeneous Many-Core SystemsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 39
Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Quoc Le (2018)
MnasNet: Platform-Aware Neural Architecture Search for Mobile2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Ting-Ru Lin, Drew Penney, M. Pedram, Lizhong Chen (2020)
A Deep Reinforcement Learning Framework for Architectural Exploration: A Routerless NoC Case Study2020 IEEE International Symposium on High Performance Computer Architecture (HPCA)
W. Thies, Saman Amarasinghe (2010)
An empirical characterization of stream programs and its implications for language and compiler design2010 19th International Conference on Parallel Architectures and Compilation Techniques (PACT)
Ashutosh Singh, T. Srikanthan, Akash Kumar, W. Jigang (2010)
Communication-aware heuristics for run-time task mapping on NoC-based MPSoC platformsJ. Syst. Archit., 56
M. Palesi, Rickard Holsmark, Shashi Kumar, V. Catania (2006)
A methodology for design of application specific deadlock-free routing algorithms for NoC systemsProceedings of the 4th International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS '06)
Xianfu Chen, Honggang Zhang, Celimuge Wu, S. Mao, Yusheng Ji, Medhi Bennis (2018)
Optimized Computation Offloading Performance in Virtual Edge Computing Systems Via Deep Reinforcement LearningIEEE Internet of Things Journal, 6
Xianmin Chen, N. Jha (2016)
Reducing Wire and Energy Overheads of the SMART NoC Using a Setup Request NetworkIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 24
Chaochao Feng, Zhonghai Lu, A. Jantsch, Jinwen Li, Minxuan Zhang (2010)
A reconfigurable fault-tolerant deflection routing algorithm based on reinforcement learning for network-on-chip
Marcelo Mandelli, Alexandre Amory, Luciano Ost, F. Moraes (2011)
Multi-task dynamic mapping onto NoC-based MPSoCs
Hui Chen, Peng Chen, Jun Zhou, Duong H. K. Luan, Weichen Liu (2020)
ArSMART: An improved SMART NoC design supporting arbitrary-turn transmissionarXiv preprint arXiv:2011.09261 (2020).
Gamal Abd El-Nasser A. Said, Abeer M. Mahmoud, El-Sayed M. El-Horbaty (2014)
A comparative study of meta-heuristic algorithms for solving quadratic assignment problemarXiv preprint arXiv:1407.4863 (2014).
B. Khumawala, Marvin Arostegui (1997)
An empirical comparison of tabu search, simulated annealing, and genetic algorithms for facilities location problemsInternational Journal of Production Economics, 103
Jingcao Hu, R. Marculescu (2004)
DyAD - smart routing for networks-on-chipProceedings. 41st Design Automation Conference, 2004.
Quintin Fettes, Mark Clark, Razvan Bunescu, Avinash Karanth, A. Louri (2019)
Dynamic Voltage and Frequency Scaling in NoCs with Supervised and Reinforcement Learning TechniquesIEEE Transactions on Computers, 68
C. Chen, Sunghyun Park, T. Krishna, Suvinay Subramanian, A. Chandrakasan, L. Peh (2013)
SMART: A single-cycle reconfigurable NoC for SoC applications2013 Design, Automation & Test in Europe Conference & Exhibition (DATE)
I. Witten (1977)
An Adaptive Optimal Controller for Discrete-Time Markov EnvironmentsInf. Control., 34
Anish Krishnakumar, Samet E. Arda, A. Alper Goksoy, Sumit K. Mandal, Umit Y. Ogras, Anderson L. Sartor, Radu Marculescu (2020)
Runtime task scheduling using imitation learning for heterogeneous many-core systemsarXiv preprint arXiv:2007.09361 (2020).
Samarth Kaushik, Amit Kumar Singh, Thambipillai Srikanthan (2011)
Computation and communication aware run-time mapping for NoC-based MPSoC platforms2011 IEEE International SOC Conference. IEEE, 2011
É. Taillard (1991)
Robust taboo search for the quadratic assignment problemParallel Comput., 17
Shengkai Chen, Shuiliang Fang, Renzhong Tang (2018)
A reinforcement learning based approach for multi-projects scheduling in cloud manufacturingInternational Journal of Production Research, 57
Richard S. Sutton, Andrew G. Barto (2018)
Reinforcement learning: An introductionMIT press
Lei Yang, Weichen Liu, Peng Chen, Nan Guan, Mengquan Li (2017)
Task mapping on SMART NoC: Contention matters, not the distance2017 54th ACM/EDAC/IEEE Design Automation Conference (DAC)
Shoukat Ali, Howard Jay Siegel, Muthucumaru Maheswaran, Debra Hensgen, Sahra Ali (2000)
Task execution time modeling for heterogeneous computing systemsProceedings of the Heterogeneous Computing Workshop
Chen-Ling Chou, R. Marculescu (2008)
User-Aware Dynamic Task Allocation in Networks-on-Chip2008 Design, Automation and Test in Europe
P. Hölzenspies, Timon Braak, J. Kuper, G. Smit, J. Hurink (2010)
Run-time Spatial Mapping of Streaming Applications to Heterogeneous Multi-Processor SystemsInternational Journal of Parallel Programming, 38
Yashar Asgarieh, Bill Lin (2019)
Smart-Hop Arbitration Request PropagationACM Transactions on Design Automation of Electronic Systems (TODAES), 24
Chia Hsin Owen Chen, Sunghyun Park, Tushar Krishna, Suvinay Subramanian, Anantha P. Chandrakasan, Li Shiuan Peh (2013)
SMART: A single-cycle reconfigurable NoC for SoC applicationsProceedings-Design
Peng Chen, Weichen Liu, Mengquan Li, Lei Yang, Nan Guan (2020)
Contention Minimized Bypassing in SMART NoC2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC)
Ge-Ming Chiu (2000)
The Odd-Even Turn Model for Adaptive RoutingIEEE Trans. Parallel Distributed Syst., 11
Sunghyun Park, T. Krishna, C. Chen, Bhavya Daya, A. Chandrakasan, L. Peh (2012)
Approaching the theoretical limits of a mesh NoC with a 16-node chip prototype in 45nm SOIDAC Design Automation Conference 2012
Heterogeneous computing systems (HCSs), which consist of various processing elements (PEs) that vary in their processing ability, are usually facilitated by the network-on-chip (NoC) to interconnect its components. The emerging point-to-point NoCs which support single-cycle-multi-hop transmission, reduce or eliminate the latency dependence on distance, addressing the scalability concern raised by high latency for long-distance transmission and enlarging the design space of the routing algorithm to search the non-shortest paths. For such point-to-point NoC-based HCSs, resource management strategies which are managed by compilers, scheduler, or controllers, e.g., mapping and routing, are complicated for the following reasons: (i) Due to the heterogeneity, mapping and routing need to optimize computation and communication concurrently (for homogeneous computing systems, only communication). (ii) Conducting mapping and routing consecutively cannot minimize the schedule length in most cases since the PEs with high processing ability may locate in the crowded area and suffer from high resource contention overhead. (iii) Since changing the mapping selection of one task will reconstruct the whole routing design space, the exploration of mapping and routing design space is challenging. Therefore, in this work, we propose MARCO, the mapping and routing co-optimization framework, to decrease the schedule length of applications on point-to-point NoC-based HCSs. Specifically, we revise the tabu search to explore the design space and evaluate the quality of mapping and routing. The advanced reinforcement learning (RL)algorithm, i.e., advantage actor-critic, is adopted to efficiently compute paths. We perform extensive experiments on various real applications, which demonstrates that the MARCO achieves a remarkable performance improvement in terms of schedule length (+44.94% ∼ +50.18%) when compared with the state-of-the-art mapping and routing co-optimization algorithm for homogeneous computing systems. We also compare MARCO with different combinations of state-of-the-art mapping and routing approaches.
ACM Transactions on Embedded Computing Systems (TECS) – Association for Computing Machinery
Published: Sep 22, 2021
Keywords: Mapping
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.