{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T07:11:52Z","timestamp":1794381112278,"version":"4.9.0"},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540229247","type":"print"},{"value":"9783540278665","type":"electronic"}],"license":[{"start":{"date-parts":[[2004,1,1]],"date-time":"2004-01-01T00:00:00Z","timestamp":1072915200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2004]]},"DOI":"10.1007\/978-3-540-27866-5_16","type":"book-chapter","created":{"date-parts":[[2010,9,16]],"date-time":"2010-09-16T16:20:42Z","timestamp":1284654042000},"page":"119-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Overhead Compensation in Performance Profiling"],"prefix":"10.1007","author":[{"given":"Allen D.","family":"Malony","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sameer S.","family":"Shende","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"16_CR1","unstructured":"Bailey, D., Harris, T., Saphir, W., van der Wijngaart, R., Woo, A., Yarrow, M.: The NAS Parallel Benchmarks 2.0. Technical Report NAS-95-020, NASA Ames Research Center (1995)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Bronevetsky, G., Marques, D., Pingali, K., Stodghill, P.: Collective Operations in an Application-level Fault Tolerant MPI System. In: International Conference on Supercomputing, ICS (2003)","DOI":"10.1145\/782814.782847"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Bronevetsky, G., Marques, D., Pingali, K., Stodghill, P.: Automated Application-level Checkpointing of MPI Programs. In: Principles and Practice of Parallel Programming, PPoPP (2003)","DOI":"10.1145\/781498.781513"},{"issue":"3","key":"16_CR4","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1177\/109434200001400303","volume":"14","author":"S. Browne","year":"2000","unstructured":"Browne, S., Dongarra, J., Garner, N., Ho, G., Mucci, P.: A Portable Programming Interface for Performance Evaluation on Modern Processors. International Journal of High Performance Computing Applications\u00a014(3), 189\u2013204 (2000)","journal-title":"International Journal of High Performance Computing Applications"},{"key":"16_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1007\/3-540-45718-6_80","volume-title":"Computational Science - ICCS 2001","author":"H. Brunst","year":"2001","unstructured":"Brunst, H., Winkler, M., Nagel, W., Hoppe, H.-C.: Performance Optimization for Large Scale Computing: The Scalable VAMPIR Approach. In: Alexandrov, V.N., Dongarra, J., Juliano, B.A., Renner, R.S., Tan, C.J.K. (eds.) ICCS-ComputSci 2001. LNCS, vol.\u00a02074, pp. 751\u2013760. Springer, Heidelberg (2001)"},{"key":"16_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/3-540-44681-8_19","volume-title":"Euro-Par 2001 Parallel Processing","author":"L. Rose De","year":"2001","unstructured":"De Rose, L.: The Hardware Performance Monitor Toolkit. In: Sakellariou, R., Keane, J.A., Gurd, J.R., Freeman, L. (eds.) Euro-Par 2001. LNCS, vol.\u00a02150, p. 122. Springer, Heidelberg (2001)"},{"key":"16_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/3-540-45706-2_21","volume-title":"Euro-Par 2002. Parallel Processing","author":"L. Rose De","year":"2002","unstructured":"De Rose, L., Wolf, F.: CATCH - A Call-Graph Based Automatic Tool for Capture of Hardware Performance Metrics for MPI and OpenMP Applications. In: Monien, B., Feldmann, R.L. (eds.) Euro-Par 2002. LNCS, vol.\u00a02400, pp. 167\u2013176. Springer, Heidelberg (2002)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Fagot, A., de Kergommeaux, J.C.: Systems Assessment of the Overhead of Tracing Parallel Programs. In: Euromicro Workshop on Parallel and Distributed Processing, pp. 179\u2013186 (1996)","DOI":"10.1109\/EMPDP.1996.500585"},{"key":"16_CR9","unstructured":"Fahringer, T., Seragiotto, C.: Experience with Aksum: A Semi-Automatic Multi-Experiment Performance Analysis Tool for Parallel and Distributed Applications. In: Workshop on Performance Analysis and Distributed Computing (2002)"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Graham, S., Kessler, P., McKusick, M.: gprof: A Call Graph Execution Profiler. In: SIGPLAN Symposium on Compiler Construction, June 1982, pp. 120\u2013126 (1982)","DOI":"10.1145\/872726.806987"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Hall, R.: Call Path Profiling. In: International Conference on Software Engineering, pp. 296\u2013306 (1992)","DOI":"10.1145\/143062.143147"},{"key":"16_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1007\/3-540-61626-8_11","volume-title":"Euro-Par \u201996 - Parallel Processing","author":"J. Hollingsworth","year":"1996","unstructured":"Hollingsworth, J., Miller, B.: An Adaptive Cost System for Parallel Program Instrumentation. In: Fraigniaud, P., Mignotte, A., Boug\u00e9, L., Robert, Y. (eds.) Euro-Par 1996. LNCS, vol.\u00a01123, pp. 88\u201397. Springer, Heidelberg (1996)"},{"key":"16_CR13","unstructured":"IBM, Profiling Parallel Programs with Xprofiler, IBM Parallel Environment for AIX: Operation and Use, vol. 2"},{"key":"16_CR14","unstructured":"Janssen, C.: The Visual Profiler, http:\/\/aros.ca.sandia.gov\/~cljanss\/perf\/vprof\/"},{"key":"16_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/3-540-48158-3_6","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"D. Kranzlm\u00fcller","year":"1999","unstructured":"Kranzlm\u00fcller, D., Reussner, R., Schaubschl\u00e4ger, C.: Monitor Overhead Measurement with SKaMPI. In: Margalef, T., Dongarra, J., Luque, E. (eds.) PVM\/MPI 1999. LNCS, vol.\u00a01697, pp. 43\u201350. Springer, Heidelberg (1999)"},{"key":"16_CR16","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1002\/spe.4380010203","volume":"1","author":"D. Knuth","year":"1971","unstructured":"Knuth, D.: An Empirical Study of FORTRAN Programs. Software Practice and Experience\u00a01, 105\u2013133 (1971)","journal-title":"Software Practice and Experience"},{"key":"16_CR17","unstructured":"Malony, A.: Performance Observability. Ph.D. thesis, University of Illinois, Urbana-Champaign (1991)"},{"issue":"4","key":"16_CR18","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1109\/71.149962","volume":"3","author":"A. Malony","year":"1992","unstructured":"Malony, A., Reed, D., Wijshoff, H.: Performance Measurement Intrusion and Perturbation Analysis. IEEE Transactions on Parallel and Distributed Systems\u00a03(4), 433\u2013450 (1992)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Malony, A., Reed, D.: Models for Performance Perturbation Analysis. In: ACM\/ONR Workshop on Parallel and Distributed Debugging, May 1991, pp. 1\u201312 (1991)","DOI":"10.1145\/122759.122760"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Malony, A.: Event Based Performance Perturbation: A Case Study. In: Principles and Practices of Parallel Programming (PPoPP), April 1991, pp. 201\u2013212 (1991)","DOI":"10.1145\/109626.109646"},{"key":"16_CR21","first-page":"37","volume-title":"Distributed and Parallel Systems, From Instruction Parallelism to Cluster Computing, Third Workshop on Distributed and Parallel Systems (DAPSYS 2000)","author":"A. Malony","year":"2000","unstructured":"Malony, A., Shende, S.: Performance Technology for Complex Parallel and Distributed Systems. In: Kotsis, G., Kacsuk, P. (eds.) Distributed and Parallel Systems, From Instruction Parallelism to Cluster Computing, Third Workshop on Distributed and Parallel Systems (DAPSYS 2000), pp. 37\u201346. Kluwer, Dordrecht (2000)"},{"key":"16_CR22","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1023\/A:1015789220266","volume":"23","author":"J. Mellor-Crummey","year":"2002","unstructured":"Mellor-Crummey, J., Fowler, R., Marin, G.: HPCView: A Tool for Top-down Analysis of Node Performance. Journal of Supercomputing\u00a023, 81\u2013104 (2002)","journal-title":"Journal of Supercomputing"},{"key":"16_CR23","unstructured":"Mucci, P.: Dynaprof, http:\/\/www.cs.utk.edu\/~mucci\/dynaprof"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Reed, D., DeRose, L., Zhang, Y.: SvPablo: A Multi-Language Performance Analysis System. In: International Conference on Performance Tools, September 1998, pp. 352\u2013355 (1998)","DOI":"10.1007\/3-540-68061-6_31"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Sarukkai, S., Malony, A.: Perturbation Analysis of High-Level Instrumentation for SPMD Programs. In: Principles and Practices of Parallel Programming (PPoPP), May 1993, pp. 44\u201353 (1993)","DOI":"10.1145\/173284.155337"},{"key":"16_CR26","unstructured":"Unix Programmer\u2019s Manual, prof command, Section 1, Bell Laboratories, Murray Hill, NJ (January 1979)"},{"key":"16_CR27","volume-title":"ACM SIGMETRICS Joint International Conference on Measurement and Modeling of Computer Systems","author":"J. Vetter","year":"2002","unstructured":"Vetter, J.: Dynamic Statistical Profiling of Communication Activity in Distributed Applications. In: ACM SIGMETRICS Joint International Conference on Measurement and Modeling of Computer Systems, ACM, New York (2002)"},{"key":"16_CR28","unstructured":"Wolf, F., Mohr, B.: Automatic Performance Analysis of SMP Cluster Applications. Technical Report IB 2001-05, Research Centre Juelich (2001)"},{"key":"16_CR29","volume-title":"Programming Environments for Massively Parallel Distributed Systems","author":"W. Williams","year":"1994","unstructured":"Williams, W., Hoel, T., Pase, D.: The MPP Apprentice Performance Tool: Delivering the Performance of the Cray T3D. In: Programming Environments for Massively Parallel Distributed Systems, North-Holland, Amsterdam (1994)"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Zagha, M., Larson, B., Turner, S., Itzkowitz, M.: Performance Analysis Using the MIPS R10000 Performance Counters. In: Supercomputing Conference (November 1996)","DOI":"10.1145\/369028.369059"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2004 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-27866-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T16:55:21Z","timestamp":1740502521000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-27866-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004]]},"ISBN":["9783540229247","9783540278665"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-27866-5_16","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/b99409","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2004]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}