HC-Midware: A Middleware to Enable High Performance Communication System Simulation in Heterogeneous Cloud

Cloud computing has become a popular high performance computing model where resources are provided as services over the Web. Users are starting to adopt the cloud model in communication applications. However, due to the complexity of parallel/cloud computing, it is difficult for average users to express a parallel computing paradigm for their applications in cloud. In order to isolate users from the complexity of parallel/cloud programming, a middleware to enable high performance communication system simulation, called HC-Midware, is proposed. It hides the details of MapReduce programming from users by automatically launching mappers through a set of user programming APIs. Directive-based parallelization scheme automatically "translates" a serial program into a SMP or Multi-core based parallel program. Heterogeneous computing resources can be invoked to conduct parallel execution by API-based scheme which highlights the adaptability of HC-Midware. A two-step scheduling scheme is proposed to maximize the throughput of the cloud system. We evaluate HC-Midware by executing three representative communication system simulation applications in a private cloud. Good scalability and adaptability were observed in the experimental results.

[1]  M. Viberg,et al.  Two decades of array signal processing research: the parametric approach , 1996, IEEE Signal Process. Mag..

[2]  Emmanuel Agullo,et al.  QR Factorization on a Multicore Node Enhanced with Multiple GPU Accelerators , 2011, 2011 IEEE International Parallel & Distributed Processing Symposium.

[3]  Patrick P. Bergmans,et al.  A simple converse for broadcast channels with additive white Gaussian noise (Corresp.) , 1974, IEEE Trans. Inf. Theory.

[5]  Rajkumar Buyya,et al.  GridSim: a toolkit for the modeling and simulation of distributed resource management and scheduling for Grid computing , 2002, Concurr. Comput. Pract. Exp..

[6]  Bin Zhou,et al.  Multiple-GPU accelerated range-Doppler algorithm for synthetic aperture radar imaging , 2011, 2011 IEEE RadarCon (RADAR).

[7]  L. Timmoneri,et al.  Combined use of graphics processing unit (GPU) and Central Processing Unit (CPU) for passive radar signal & data elaboration , 2011, 2011 12th International Radar Symposium (IRS).

[8]  Henri Casanova,et al.  Scheduling distributed applications: the SimGrid simulation framework , 2003, CCGrid 2003. 3rd IEEE/ACM International Symposium on Cluster Computing and the Grid, 2003. Proceedings..

[9]  Eddy Caron,et al.  Cloud Computing Resource Management through a Grid Middleware: A Case Study with DIET and Eucalyptus , 2009, 2009 IEEE International Conference on Cloud Computing.

[10]  Tetsu Narumi,et al.  DS-CUDA: A Middleware to Use Many GPUs in the Cloud Environment , 2012, 2012 SC Companion: High Performance Computing, Networking Storage and Analysis.

[11]  Marta Mattoso,et al.  SciCumulus: A Lightweight Cloud Middleware to Explore Many Task Computing Paradigm in Scientific Workflows , 2010, 2010 IEEE 3rd International Conference on Cloud Computing.

[12]  Michel C. Jeruchim,et al.  Simulation of Communication Systems: Modeling, Methodology and Techniques , 2000 .

[13]  Shuying Li,et al.  A Novel PCM/FM Multi-symbol Detection Algorithm for FPGA Implementation , 2009 .

[14]  Joseph R. Cavallaro,et al.  A massively parallel implementation of QC-LDPC decoder on GPU , 2011, 2011 IEEE 9th Symposium on Application Specific Processors (SASP).

[15]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[16]  Shiyong Lu,et al.  A MapReduce-Enabled Scientific Workflow Composition Framework , 2009, 2009 IEEE International Conference on Web Services.

[17]  Steven W. McLaughlin,et al.  An efficient Chase decoder for turbo product codes , 2004, IEEE Transactions on Communications.

[18]  Ying Liu,et al.  Design and evaluation of multi-GPU enabled Multiple Symbol Detection algorithm , 2016, The Journal of Supercomputing.