An Efficient Run Time Interface for Heterogeneous Architecture of Large Scale Supercomputing System
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32807
An Efficient Run Time Interface for Heterogeneous Architecture of Large Scale Supercomputing System

Authors: Prabu D., Andrew Aaron James, Vanamala V., Vineeth Simon, Sanjeeb Kumar Deka, Sridharan R., Prahlada Rao B.B., Mohanram N.

Abstract:

In this paper we propose a novel Run Time Interface (RTI) technique to provide an efficient environment for MPI jobs on the heterogeneous architecture of PARAM Padma. It suggests an innovative, unified framework for the job management interface system in parallel and distributed computing. This approach employs proxy scheme. The implementation shows that the proposed RTI is highly scalable and stable. Moreover RTI provides the storage access for the MPI jobs in various operating system platforms and improve the data access performance through high performance C-DAC Parallel File System (C-PFS). The performance of the RTI is evaluated by using the standard HPC benchmark suites and the simulation results show that the proposed RTI gives good performance on large scale supercomputing system.

Keywords: RTI, C-MPI, C-PFS, Scheduler Interface.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1083593

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1397

References:


[1] PARAM10000 Supercomputer ,Centre for Development of Advanced Computing(C-DAC) http://www.cdac.in/HTmL/param.asp
[2] CDAC Terascale supercomputing facility CTSF, www.cdac.in/html/ctsf/resource.asp
[3] PARAM Padma Supercomputing Cluster, C-DAC, http://www.cdac.in/html/parampma.asp
[4] PARAMNet, CDAC, www.cdac.in/HTmL/pdf/PARAMNet.pdf
[5] IBM-s Load Leveler. http://csit1cwe.fsu.edu/extra_link/LoadL/lllv2mst10.html.
[6] William Gropps, Ewing Lusk, Nathan Doss and Anthony Skjellum. "A High-Performance, Portable Implementation of MPI Message Passing Interface Standard". Available at http://www.mcs.anl.gov/mpi/
[7] IBM-s Parallel Operating System (poe). http://www- 03.ibm.com/systems/p/software/pe.html
[8] Resource Management System, Centre for Development of Advanced Computing (C-DAC), India. at www.cdac.in/html/ssdgblr/rms.asp
[9] Chansup Byun, Christopher Duncan and Stephanie Burk: "A Comparison of Job Managements Systems in Supporting HPC Cluster Tools" SUPerG, Vancouver, Fall 2000.
[10] CDAC Cluster Runtime Environment. C-HPC Cluster Tools. Available at http://www.cdac.in/html/hpcc.asp
[11] Portable Batch System. Available at http://www.openpbs.com
[12] C-DAC Parallel File Systems. Available at www.cdac.in/html/ssdgblr/cpfs.asp
[13] Sun Community Source Licensing. http://wwws.sun.com/software/communitysource
[14] CDAC Message Passing Interface, http://www.cdac.in/html/ssdgblr/cmpi.asp
[15] HPL - A Portable Implementation of the High-Performance Linpack Available at www.netlib.org/benchmark/hpl/
[16] PALLAS Benchmark Available at http://www.pallas.com/e/products/index.htm
[17] C-DAC, Garuda India, The National Grid Computing Initiative http://www.garudaindia.in/tech_research.asp