Interconnection network performance of multi-core cluster architectures

This paper considers the performance of interconnection networks in single-core and multi-core cluster architectures. Several parameters and system configurations are considered to optimise the performance of single-core cluster as a baseline experiment. These results have been extended to multi-core cluster architectures. The performance measurement involved communication within and between clusters with varying numbers of processor cores to provide a comparative analysis of single-core and multi-core cluster architectures. Analytical analysis provides validation of the simulation results.

[1]  Douglas M. Pase,et al.  A Comparison of Single-Core and Dual-Core Opteron Processor Performance for HPC , 2004 .

[2]  Victor Chang,et al.  Delivery and Adoption of Cloud Computing Services in Contemporary Organizations , 2015 .

[3]  Morteza Analoui,et al.  Improving inter-node communications in multi-core clusters using a contention-free process mapping algorithm , 2013, The Journal of Supercomputing.

[4]  Rajkumar Buyya,et al.  Shared memory multistage clustering structure, an efficient structure for massively parallel processing systems , 2000, Proceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region.

[5]  Gary B. Wills,et al.  An Analytical Model of Multi-Core Multi-Cluster Architecture (MCMCA) , 2015, Open J. Cloud Comput..

[6]  Gary B. Wills,et al.  Performance Evaluation of Multi-Core Multi-Cluster Architecture (MCMCA) , 2014, ESaaSA@CLOSER.

[7]  D. Geer,et al.  Chip makers turn to multicore processors , 2005, Computer.

[8]  Shuichi Ichikawa,et al.  Estimating the Optimal Configuration of a Multi-Core Cluster: A Preliminary Study , 2009, 2009 International Conference on Complex, Intelligent and Software Intensive Systems.

[9]  Robert John Walters,et al.  An architecture for measuring network performance in multi-core multi-cluster architecture (MCMCA) , 2014 .

[10]  Jemal H. Abawajy,et al.  An efficient adaptive scheduling policy for high-performance computing , 2009, Future Gener. Comput. Syst..

[11]  N. Alzeidi,et al.  A new general method to compute virtual channels occupancy probabilities in wormhole networks , 2008, J. Comput. Syst. Sci..

[12]  Dhabaleswar K. Panda,et al.  Designing High Performance and Scalable MPI Intra-node Communication Support for Clusters , 2006, 2006 IEEE International Conference on Cluster Computing.

[13]  Gilad Shainer,et al.  Maximizing Application Performance in a Multi-core, NUMA-Aware Compute Cluster by Multi-level Tuning , 2013, ISC.

[14]  Jules-Raymond Tapamo,et al.  An Analytic Model for Predicting the Performance of Distributed Applications on Multicore Clusters , 2012 .

[15]  Antonio Robles-Gómez,et al.  A Deadlock-Free Dynamic Reconfiguration Scheme for Source Routing Networks Using Close Up*/Down* Graphs , 2011, IEEE Transactions on Parallel and Distributed Systems.

[16]  Bashayer M. Al-Babtain,et al.  A SURVEY ON AMDAHL'S LAW EXTENSION IN MULTICORE ARCHITECTURES , 2013 .

[17]  András Varga,et al.  An overview of the OMNeT++ simulation environment , 2008, SimuTools.

[18]  Mohammad Kazem Akbari,et al.  A performance model for analysis of heterogeneous multi-cluster systems , 2006, Parallel Comput..

[19]  Dhabaleswar K. Panda,et al.  Understanding the Impact of Multi-Core Architecture in Cluster Computing: A Case Study with Intel Dual-Core System , 2007, Seventh IEEE International Symposium on Cluster Computing and the Grid (CCGrid '07).

[20]  Bryan Schauer.  Multicore Processors - A Necessity , 2008 .

[21]  Nael B. Abu-Ghazaleh,et al.  Performance Analysis of a Multithreaded PDES Simulator on Multicore Clusters , 2012, 2012 ACM/IEEE/SCS 26th Workshop on Principles of Advanced and Distributed Simulation.

[22]  Keqiu Li,et al.  Modeling and Analysis of Communication Networks in Multicluster Systems under Spatio-Temporal Bursty Traffic , 2012, IEEE Transactions on Parallel and Distributed Systems.

[23]  Xingfu Wu,et al.  Performance modeling of hybrid MPI/OpenMP scientific applications on large-scale multicore supercomputers , 2011, J. Comput. Syst. Sci..

[24]  Jong-Myon Kim,et al.  An Analysis of Reducing Communication Delay in Network-on-Chip Interconnect Architecture , 2013, Wirel. Pers. Commun..

[25]  Adit Ranadive,et al.  Performance implications of virtualizing multicore cluster machines , 2008, HPCVirt '08.