Paul M. Bennett
ABSTRACT
The U. S. Department of Defense High Performance Computing Modernization Program (HPCMP) has implemented sustained systems performance testing on high performance computing systems in use at DoD Supercomputing Resource Centers. The intent is to monitor performance improvements by updates to the operating system, compiler suites, and numerical and communications libraries, and to monitor penalties arising from security patches. In practice, each system's workload is simulated by appropriate choices of user application codes representative of the HPCMP computational technical areas. Past successes include surfacing an imminent failure of an OST in a Cray XT3, incomplete configuration of a scheduler update on an SGI Altix 4700, performance issues associated with a communications library update for a Linux Networx Advanced Technology Cluster, and intermittent resetting of Intel Nehalem cores to standard mode from turbo mode. This history demonstrates that SSP testing is critical to deliver the highest quality of service to the HPCMP users.
- Bennett, P., Cable, S., Alter, R., Mahmoodi, M., and Oppe, T. 2006. Targeting CCM-, CEA-, and CSM-based computing to specific architectures based upon HPCMP systems assessment. In Proceedings of the HPCMP Users Group Conference 2006 (Denver, CO, June 26-29, 2006). UGC '06. IEEE Computer Society, Los Alamitos, CA, 360--366. Google Scholar
Digital Library
- Blackford, L., Cleary, A., Choi, J., D'Azevedo, E., Demmel, J., Dhillon, I., Dongarra, J., Hammarling, S., Henry, G., Petitet, A., Stanley, K., Walker, D., and Whaley, R. 1997. ScaLAPACK Users' Guide. SIAM, Philadelphia, PA. Google ScholarDigital Library
- Bleck, R. 2002. An oceanic general circulation model framed in hybrid isopycnic-Cartesian coordinates. Ocean Model., 4, 1 (Jan., 2002), 55--88.Google Scholar
- Cable, S., Oppe, T., Ward, W., Jr., Campbell, R., Jr., Gordnier, R., Burnley, V., Grismer, M., and Buning, P. 2005. CFD-based HPCMP systems assessment using AERO, AVUS, and OVERFLOW-2. In Proceedings of the HPCMP Users Group Conference 2005 (Nashville, TN, June 27-30, 2005). UGC '05. IEEE Computer Society, Los Alamitos, CA, 349--355. Google ScholarDigital Library
- Cliburn, J. 2005. ERDC MSRC installs most powerful supercomputer in DoD, ERDC MSRC Major Shared Resource Center RESOURCE (Fall 2005), 10.Google Scholar
- Donagarra, J., and Luszczek, P. 2005. Introduction to the HPCChallenge Benchmark Suite. Technical Report ICL-UT-05-01. University of Tennessee, Knoxville.Google Scholar
- Fatoohi, R. 2008. Performance evaluation of NSF application benchmarks on parallel systems. In Proceedings of the 22nd IEEE International Symposium on Parallel and Distributed Processing (Miami, FL, Apr. 14--18, 2008), IPDPS '08. IEEE Computer Society, Los Alamitos, CA, 1--8.Google ScholarCross Ref
- Gordon, M. and Schmidt, M. 2005. Advances in electronic structure theory: GAMESS a decade later. In Theory and Applications of Computational Chemistry, the first forty years, eds. Dykstra, C., Frenking, G., Kim, K., and Scuseria, G. Elsevier, Amsterdam, The Netherlands.Google Scholar
- Hertel E., Jr., Bell, R., Elrick, M., Farnsworth, A., Kerley, G., McGiaun, J., Pemey, S., Silling, S., Taylor, P., and Yarrington, L. 1992. CTH: A software family for multi-dimensional shock physics analysis. Technical Report SAND-92-2089C. Sandia National Laboratories, Albuquerque, New Mexico.Google Scholar
- Hertel, E., Jr., et al. 1993. CTH: A Software Family for Multi-Dimensional Shock Physics Analysis. In Proceedings of the 19
th
International Symposium on Shock Waves (Marseilles, France, July 26-30, 1993). Springer-Verlag, Berlin, Germany. Volume 1, 377--382.Google Scholar
- Karypis, G. and Kumar, V. 1998. Multilevel k-way partitioning scheme for irregular graphs. J. Parallel Distrib. Comput. 48, 1 (Jan. 10, 1998), 96--129. Google ScholarDigital Library
- Karypis, G. and Kumar, V. 1999. Parallel multilevel k-way partitioning scheme for irregular graphs. SIAM Rev. 41, 2 (1999), 278--300. Google ScholarDigital Library
- Karypis, G., Schloegel, K., and Kumar, V. 1997. PARMETIS: Parallel graph partitioning scheme and matrix ordering library. Technical report, University of Minnesota, Department of Computer Science and Engineering.Google Scholar
- Kramer, W., Shalf, J., and Strohmaier, E. 2005. The NERSC Sustained System Performance (SSP) Metric. Paper LBNL-58868. Lawrence Berkeley National Laboratory.Google Scholar
- Leach, C., Oppe, T., Ward, W., Jr., and Campbell, R., Jr. 2005. CWO-based HPCMP systems assessment using HYCOM and WRF. In Proceedings of the HPCMP Users Group Conference 2005 (Nashville, TN, June 27-30, 2005), UGC '05. IEEE Computer Society, Los Alamitos, CA, 356--359. Google ScholarDigital Library
- Schloegel, K., Karypis, G., and Kumar, V. 2000. A unified algorithm for load-balancing adaptive scientific simulations. In Proceedings of the 2000 ACM/IEEE conference on Supercomputing (CDROM) (Dallas, TX, Nov. 4-10, 2000), Supercomputing '00. IEEE Computer Society, Washington, D. C., Article 59. Google ScholarDigital Library
- Schmidt, M., Baldridge, K., Boatz, J., Elbert, S., Gordon, M., Jensen, J., Koseki, S., Matsunaga, N., Nguyen, K., Su, S., Windus, T., Dupuis, M., and Montgomery, J. 1993. General Atomic and Molecular Electronic Structure System. J. Comput. Chem., 14, 11 (Nov. 1993), 1347--1363. Google ScholarDigital Library
- Tomaro, R., Strang, W., and Sankar, L. 1997. An implicit algorithm for solving time-dependent flows on unstructured grids. Paper. At 35th Aerospace Sciences Meeting and Exhibit (Reno, NV, Jan. 6-10, 1997), AIAA, Reston, VA, AIAA 97--0333.Google ScholarCross Ref
- Tracy, F., Oppe, T., Ward, W., Jr., and Peterkin, R., Jr. 2003. A survey of the algorithms in the TI-03 application benchmarking suite with emphasis on linear system solvers. In Proceedings of the 2003 Users Group Conference (Bellevue, WA, June 9-13, 2003), UGC '03. IEEE Computer Society, Los Alamitos, CA, 332--336. Google ScholarDigital Library
- Tracy, F. 2005. Role of algorithms in understanding performance of the TI-05 benchmark suite. In Proceedings of the HPCMP Users Group Conference 2005 (Nashville, TN, June 27-30, 2005), UGC '05. IEEE Computer Society, Los Alamitos, CA, 420--426. Google ScholarDigital Library
Index Terms
- Sustained systems performance monitoring at the U. S. Department of Defense high performance computing modernization program
Recommendations
Modeling and predicting performance of high performance computing applications on hardware accelerators
Hybrid-core systems speedup applications by offloading certain compute operations that can run faster on hardware accelerators. However, such systems require significant programming and porting effort to gain a performance benefit from the accelerators. ...
High Performance Computing via a GPU
ICISE '09: Proceedings of the 2009 First IEEE International Conference on Information Science and EngineeringGraphics processor units (GPUs), such as the AMD FireStream series, offer a tremendous computing power that is frequently an order of magnitude larger than even the most modern multi-core CPUs, making them an attractive platform for high performance ...
Performance evaluation of Intel® transactional synchronization extensions for high-performance computing
SC '13: Proceedings of the International Conference on High Performance Computing, Networking, Storage and AnalysisIntel has recently introduced Intel® Transactional Synchronization Extensions (Intel® TSX) in the Intel 4th Generation Core™ Processors. With Intel TSX, a processor can dynamically determine whether threads need to serialize through lock-protected ...
Comments