Francesca Palumbo
ABSTRACT
Massively Parallel Systems-on-chip represent the new frontier of integrated computing systems for general purpose computing. The integration of a huge number of cores poses several issues such as the efficiency and flexibility of the interconnection network in order to serve in the best way the different traffic patterns that can arise.
In this paper we present the CYBER architecture, an advanced Network-on-Chip (NoC) for concurrent hybrid switching with prioritized best effort Quality of Service. Compared to similar architectures, CYBER allows the simultaneous exploitation of packet switching and circuit switching, providing two different priorities to packets in order to be able to transmit urgent messages (e.g. signalling) while long-lasting transactions and huge packets congestion are present. In terms of the typical NoC metrics, evaluated on synthetic traffic representative of several application categories, their standard trend is degraded while serving both circuit and packet switching simultaneously but the architecture preserves a predictable behaviour. A CMOS 90nm implementation reveals a maximum operating frequency of about 1GHz.
- B. Ahamad, A. Erdogan, and S. Khawarm. Architecture of a dynamically reconfigurable NoC for adaptive reconfigurable MPSoC. In Proc. of the first NASA/ESA Conf. on Adaptive Hardware and Systems (AHS'06), 2006. Google Scholar
Digital Library
- F. Angiolini and S. Murali. Communication Architectures for Systems-on-Chip, chapter 4 - Quality-of-Service in NoCs, pages 127--157. CRC Press, 2011.Google Scholar
- N. Banerjee, P. Vellanki, and K. S. Chatha. A power and performance model for network-on-chip architectures. In DATE '04: Proceedings of the conference on Design, automation and test in Europe, 2004. Google ScholarDigital Library
- T. Bjerregaard and J. Sparsø. A router architecture for connection-oriented service guarantees in the MANGO clockless network-on-chip. In Proceedings of Design, Automation and Testing in Europe Conference 2005 (DATE05). IEEE, 2005. Google ScholarDigital Library
- E. Bolotin, I. Cidon, R. Ginosar, and A. Kolodny. QNoC: QoS architecture and design process for network on chip. Journal of Systems Architecture, special issue on Network on Chip, 50:105--128, 2004. Google ScholarDigital Library
- T. Caohuu, T. T. Le, M. Glesner, and J. Becker. Dynamically reconfigurable reduced crossbar: A novel approach to large scale switching. In FPL '99: Proceedings of the 9th International Workshop on Field-Programmable Logic and Applications, pages 507--513, London, UK, 1999. Springer-Verlag. Google ScholarDigital Library
- C.-H. O. Chen, N. Agarwal, T. Krishna, K.-H. Koo, L.-S. Peh, and K. C. Saraswat. Physical vs. virtual express topologies with low-swing links for future many-core nocs. Networks-on-Chip, International Symposium on, pages 173--180, 2010. Google ScholarDigital Library
- W. Dally and B. Towles. Principles and Practices of Interconnection Networks. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 2003. Google ScholarDigital Library
- J. Diemer and R. Ernst. Back suction: Service guarantees for latency-sensitive on-chip networks. Networks-on-Chip, International Symposium on, pages 155--162, 2010. Google ScholarDigital Library
- F. Gilabert, M. E. Gomez, S. Medardoni, and D. Bertozzi. Improved utilization of noc channel bandwidth by switch replication for cost-effective multi-processor systems-on-chip. Networks-on-Chip, International Symposium on, pages 165--172, 2010. Google ScholarDigital Library
- K. Goossens, J. Dielissen, and A. Radulescu. The Æthereal network on chip: Concepts, architectures, and implementations. IEEE Design and Test of Computers, 22(5):21--31, 2005. Google ScholarDigital Library
- K. Goossens and A. Hansson. The Æthereal network on chip after ten years: Goals, evolution, lessons, and future. In Proc. Design Automation Conference (DAC), June 2010. Google ScholarDigital Library
- B. Grot, J. Hestness, S. W. Keckler, and O. Mutlu. Kilo-noc: a heterogeneous network-on-chip architecture for scalability and service guarantees. In Proceedings of the 38th annual international symposium on Computer architecture, ISCA '11, pages 401--412, New York, NY, USA, 2011. ACM. Google ScholarDigital Library
- S. Hsu, Y. Lin, and J. Jou. Design of a dual-mode noc router integrated with network interface for amba-based ips. In Proc. IEEE Asian Solid-State Circuits Conf., pages 211--214, 2006.Google ScholarCross Ref
- N. D. E. Jerger, L.-S. Peh, and M. H. Lipasti. Circuit-switched coherence. In NOCS '08: Proc. of the Second International Symposium on Networks-on-Chip, pages 193--202, 2008. Google ScholarDigital Library
- M. Livingston and Q. Stout. Parallel allocation algorithms for hypercubes and meshes. In Proc. 4th Conf. Hypercube Concurrent Comput. Applications, pages 59--66, 1989.Google Scholar
- M. Millberg, E. Nilsson, R. Thid, S. Kumar, and A. Jantsch. The nostrum backbone-a communication protocol stack for networks on chip. In VLSI Design, 2004. Proceedings. 17th International Conference on, pages 693 -- 696, 2004. Google ScholarDigital Library
- U. Y. Ogras, J. Hu, and R. Marculescu. Key research problems in noc design: A holistic perspective. In International Conference on Hardware - Software Codesign and System Synthesis, September 2005. Google ScholarDigital Library
- F. Palumbo, D. Pani, L. Raffo, and S. Secchi. A surface tension and coalescence model for dynamic distributed resources allocation in massively parallel processors on-chip. In NICSO '07: Proc of the International Workshop on Nature Inspired Cooperative Strategies for Optimization, pages 335--345. 2007.Google Scholar
- F. Palumbo, S. Secchi, D. Pani, and L. Raffo. A novel non-exclusive dual-mode architecture for mpsocs-oriented network on chip designs. In SAMOS08: Proc. of the 8th international workshop on Embedded Computer Systems, pages 96--105, Berlin, Heidelberg, 2008. Springer-Verlag. Google ScholarDigital Library
- D. Pani, F. Palumbo, and L. Raffo. A fast mpi-based parallel framework for cycle-accurate HDL multi-parametric simulations. Int. J. High Perform. Syst. Archit., 2:187--202, August 2010. Google ScholarDigital Library
- picoArray. picoChip company. http://www.picochip.com/, web.Google Scholar
- A. D. Rast, X. Jin, F. Galluppi, L. A. Plana, C. Patterson, and S. Furber. Scalable event-driven native parallel processing: the SpiNNaker neuromimetic system. In Proceedings of the 7th ACM international conference on Computing frontiers, pages 21--30, 2010. Google ScholarDigital Library
- S. Sathe, D. Wiklund, and D. Liu. Design of a switching node (router) for on-chip networks. Proceedings of the 5th International Conference on ASIC, pages 75--78, 2003.Google ScholarCross Ref
- Y. H. Song and T. M. Pinkston. A progressive approach to handling message-dependent deadlock in parallel computer systems. IEEE Transactions on Parallel and Distributed Systems, 14(3):259--275, 2003. Google ScholarDigital Library
- W. Stallings. Operating Systems (5th Edition). 2004. Google ScholarDigital Library
- Tilera. The tile64 chip. http://www.tilera.com/, web.Google Scholar
- F. Trivino, J. L. Sanchez, F. J. Alfaro, and J. Flich. Virtualizing network-on-chip resources in chip-multiprocessors. Microprocessors and Microsystems, In Press, 2010. Google ScholarDigital Library
- F. Wu, C.-C. Hsu, and L.-P. Chou. Processor allocation in the mesh multiprocessors using the leapfrog method. IEEE Trans. Parallel Distrib. Syst., 14(3):276--289, 2003. Google ScholarDigital Library
Index Terms
- Concurrent hybrid switching for massively parallel systems-on-chip: the CYBER architecture
Recommendations
Streamlined network-on-chip for multicore embedded architectures
ARCS'12: Proceedings of the 25th international conference on Architecture of Computing SystemsMPSoCs are becoming complex systems incorporating a large number of compute cores as well as various accelerators and application specific units. To handle the communication in MPSoCs, the Network-on-Chip (NoC) concept has been proposed as a versatile ...
Analysis and Implementation of Hybrid Switching
The switching scheme of a point-to-point network determines how packets flow through each node, and is a primary element in determining the network's performance. In this paper, we present and evaluate a new switching scheme called hybrid switching. ...
Design of AXI bus based MPSoC on FPGA
ASID'09: Proceedings of the 3rd international conference on Anti-Counterfeiting, security, and identification in communicationWhile the computational core is becoming faster and faster, the communication efficiency between the processors has become a bottleneck which limits the performance of multiprocessor system-on-chip (MPSoC). This paper focuses on design and ...
Comments