ATOP-Grid is an adaptive middleware which supports workload redistribution under varying resource allocation in both the space and time dimensions. In earlier work [13] [14] [15], we have already shown that time-shared execution of jobs, which splits the CPUs or cores per node between two jobs but shares the network, may provide a performance benefit vs. space sharing, which splits the nodes among the jobs. In this paper, we make a step towards providing a sounder foundation for time-sharing performance, investigating the time sharing behavior of jobs in more detail and looking into communication characteristics, memory access, and cache usage.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
 References
P. Behr, S. Pletner and A.C. Sodan. The PowerMANNA Architecture. Proc. IEEE Con-ference on High Performance Computer Architecture (HPCA), Toulouse, France, pages 277-286, Jan. 2000.
F. Berman, R. Wolski, H. Casanova, W. Cirne, et al. Adaptive Computing on the Grid Using AppLeS. IEEE Trans. on Parallel and Distributed Systems, 14(4):369-382, Apr. 2003.
M. Bhandarkar, L.V. Kale, E. de Sturler, and J. Hoeflinger. Object-Based Adaptive Load Balancing for MPI Programs. Proc. Internat. Conf. on Computational Science, San Fran-cisco/CA, USA, pages 108-117, May 2001.
K. Devine, B. Hendrickson, E. Boman, M.St. John, C. Vaughan. Design of Dynamic Load-Balancing Tools for Par. Applications. Proc. ICS, Santa Fe, 2000.
S. Dong, N.T. Karomis, and G.E. Karniadakis. Grid Solutions for Biological and Physical Cross-Site Simulations on the TeraGrid. Proc. IPDPS, Apr. 2006.
K. Hwang and Z. Xu. Scalable Parallel Computing. McGraw-Hill, Boston, 1999.
Multi-coreProcessors—TheNextEvolutioninComputing,AMD, http://multicore.amd.com/GLOBAL/WhitePapers/Multi-Core ProcessorsWhitePa- per.pdf, 2005
D.M. Pase and M.A. Eckl. A Comparison of Single-Core and Dual-Core Opteron Proces- sor Performance. Linux Clusters—The HPC Revolution, May 2006.
Sharcnet project, http://www.sharcnet.ca.
W. Smith, I. Foster, and V. Taylor. Scheduling with Advanced Reservations. Proc. IPDPS, May 2000.
A.C. Sodan and L. Lan. LOMARC-Lookahead Matchmaking for Multi-Resource Coscheduling on Hyperthreaded CPUs. IEEE Transactions on Parallel and Distributed Computing, Vol. 17, No. 11, Nov. 2006.
A.C. Sodan, G. Gupta. Time vs. Space Adaptation with ATOP-Grid. Proc. ACM Adaptive & Reflective Middleware Workshop, Melbourne, Nov. 2006.
A.C. Sodan and G. Gupta. ATOP-Grid for Unified Multidimensional Adaptation of Grid Applications. Proc. PDCS, Dallas, Nov. 2006.
A.C. Sodan and L. Liu. Dynamic Multi-Resource Monitoring for Predictive Job Schedul- ing with ScoPro. Proc. PDCS, Phoenix, Nov. 2005.
A.C. Sodan. Loosely Coordinated Coscheduling in the Context of Other Dynamic Ap- proaches for Job Scheduling-A Survey. Concurrency & Computation: Practice & Experience, 17(15):1725-1781, Dec. 2005.
A.C. Sodan and L. Lan. LOMARC—Lookahead Matchmaking for Multi-Resource Coscheduling. Proc. JSSPP, New York / USA, Lecture Notes in Computer Science 3277, Springer, June 2004.
A.C. Sodan and M. Riyadh. Co-scheduling of MPI and adaptive thread applications under Solaris. Proc. PDCS, Cambridge/USA, Nov. 2002.
T. Stricker and T. Gross. Global Address Space, Non-Uniform Bandwidth: A Memory System Perf. Characterization of Par. Systems. Proc. HPCA, Feb. 1997.
J. Weinberg, A. Snavely. Symbiotic Space Sharing on SDSC’s DataStar System. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP), Saint-Malo, France, Lecture Notes in Computer Science 4376, Springer, June 2006.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
Zeng, X., Shi, J., Cao, X., Sodan, A.C. (2008). Grid Scheduling with ATOP-Grid under Time Sharing. In: Grid Middleware and Services. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-78446-5_1
Download citation
DOI: https://doi.org/10.1007/978-0-387-78446-5_1
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-78445-8
Online ISBN: 978-0-387-78446-5
eBook Packages: Computer ScienceComputer Science (R0)