Abstract
The paper concerns new communication solutions for hierarchical Chip Multiprocessor (CMP) systems composed of many CMP modules interconnected by a global data exchange network. New architectural solutions for internal module data communication are presented in the presence of hierarchical data caches in CMP modules. Inside CMP modules, dynamic shared memory core clusters are organized around L1–L2 data cache busses. Such clusters enable a group-oriented data communication based on reads on the fly to L1 banks of data present on the busses by many cores at a time. Dynamic switching of cores between such L1–L2 busses is done with porting data in core’s L1 caches. Together with data reads on the fly, it provides a very efficient intercluster “communication on the fly,” especially useful for transfers of strongly shared data. It provides fast cache to cache group data transmissions and eliminates standard transactions based on shared memory in the system. Comparative experimental results based on automatic scheduling of program data flow graphs and execution in a simulator of the proposed architecture evaluate the assumed architectural solutions. The multi-CMP system structure is assessed while taking into account technological limitations of the size of the single CMP module.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Adriahantenaina et al (2003) SPIN: a scalable, packet switched on-chip micro-network. In: Proceedings of the design, automation and test in Europe, DATE’03, Munich, March, vol 2, pp 2070–2081
Dally W, Towles B (2001) Route packets, not wires: on-chip interconnection networks. In: 38-th DAC, Las Vegas, June, pp 684–689
Hossain H et al (2008) Improving support for locality and fine-grain sharing in chip multiprocesors. In: PACT’08, Toronto. ACM Press, New York, pp 155–165
Hsu L et al (2005) Exploring the cache design space for large scale CMPs. SIGARCH Comput Archit News 33(4), November
Huh J (2007) A NUCA substrate for flexible CMP cache sharing. IEEE Trans Parallel Distrib Syst 18(8):1028–1040
Kundu S, Peh LS (2007) On-chip interconnects for multicores. In: IEEE MICRO, Sept–Oct, pp 3–5
Lepere R, Trystram D, Woeginger GJ (2001) Approximation algorithms for scheduling malleable tasks under precedence constraints. In: 9th annual European symposium on algorithms. LNCS, vol 2161. Springer, Berlin, pp 146–157
Masko L, Tudruj M (2008) Task scheduling for SoC-based dynamic SMP clusters with communication on the fly. In: 7th int symp on parallel and distributed computing, ISPDC 2008, Krakow, pp 99–106
Masko L et al (2005) Scheduling moldable tasks for dynamic SMP clusters in SoC technology, parallel processing and applied mathematics. In: PPAM 2005, Poznań, Poland, Sept 2005. LNCS, vol 3911. Springer, Berlin, pp 879–887
Milenkovic, Milutinovic V (2000) Cache injection: a novel technique for tolerating memory latency in bus-based SMPs. In: Proceedings of the euro-par. LNCS, vol 1900. Springer, Berlin
Owens JD et al (2007) Research challenges for on-chip interconnection networks. In: IEEE MICRO, Sept–Oct, pp 96–108
Parisha S, Dutt N, Ben-Romdhane M (2008) Fast exploration of bus-based communication architectures at CCATB abstraction. ACM Trans Embed Comput Syst 7(2)
Terry TY et al (2004) Packetization and routing analysis of on-chip multiprocessor networks. J Systems Archit 50:81–104
Tudruj M, Masko L (2004) Dynamic SMP clusters with communication on the fly in NoC technology for very fine grain computations. In: 3rd int symp on parallel and distributed computing, ISPDC 2004, Cork, July, pp 97–104
Tudruj M, Masko L (2005) Towards massively parallel computations based on dynamic SMP clusters with communication on the fly. In: 4th int symp on parallel and distributed computing, ISPDC 2005, Lille, France. IEEE CS Press, Los Alamitos, pp 155–162
Tudruj M, Masko L (2006) Fast matrix multiplication in dynamic SMP clusters with communication on the fly in systems on chip technology. In: PARELEC 2006, September. IEEE CS Press, Los Alamitos, pp 77–82
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Open Access This is an open access article distributed under the terms of the Creative Commons Attribution Noncommercial License (https://creativecommons.org/licenses/by-nc/2.0), which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.
About this article
Cite this article
Tudruj, M., Masko, L. & Thor, M. Multi-CMP system with data communication on the fly. J Supercomput 57, 51–64 (2011). https://doi.org/10.1007/s11227-011-0561-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-011-0561-0