{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:56:45Z","timestamp":1725559005787},"publisher-location":"Berlin, Heidelberg","reference-count":29,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540254249"},{"type":"electronic","value":"9783540318545"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/11403937_31","type":"book-chapter","created":{"date-parts":[[2010,7,5]],"date-time":"2010-07-05T20:46:11Z","timestamp":1278362771000},"page":"396-409","source":"Crossref","is-referenced-by-count":0,"title":["PerWiz: A What-If Prediction Tool for Tuning Message Passing Programs"],"prefix":"10.1007","author":[{"given":"Fumihiko","family":"Ino","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Kanbe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masao","family":"Okita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenichi","family":"Hagihara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"31_CR1","first-page":"159","volume":"8","author":"Message Passing Interface Forum","year":"1994","unstructured":"Message Passing Interface Forum: MPI: A message-passing interface standard. Int\u2019l J. Supercomputer Applications and High Performance Computing\u00a08, 159\u2013416 (1994)","journal-title":"Int\u2019l J. Supercomputer Applications and High Performance Computing"},{"key":"31_CR2","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/52.84214","volume":"8","author":"M.T. Heath","year":"1991","unstructured":"Heath, M.T., Etheridge, J.A.: Visualizing the performance of parallel programs. IEEE Software\u00a08, 29\u201339 (1991)","journal-title":"IEEE Software"},{"key":"31_CR3","first-page":"69","volume":"12","author":"W.E. Nagel","year":"1996","unstructured":"Nagel, W.E., Arnold, A., Weber, M., Hoppe, H.C., Solchenbach, K.: VAMPIR: Visualization and analysis of MPI resources. The J. Supercomputing\u00a012, 69\u201380 (1996)","journal-title":"The J. Supercomputing"},{"key":"31_CR4","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1177\/109434209901300310","volume":"13","author":"O. Zaki","year":"1999","unstructured":"Zaki, O., Lusk, E., Gropp, W., Swider, D.: Toward scalable performance visualization with Jumpshot. Int\u2019l J. High Performance Computing Applications\u00a013, 277\u2013288 (1999)","journal-title":"Int\u2019l J. High Performance Computing Applications"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Rose, L.A.D., Reed, D.A.: SvPablo: A multi-language architecture-independent performance analysis system. In: Proc. 28th Int\u2019l Conf. Parallel Processing (ICPP 1999), pp. 311\u2013318 (1999)","DOI":"10.1109\/ICPP.1999.797417"},{"key":"31_CR6","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1002\/spe.4380250406","volume":"25","author":"J. Yan","year":"1995","unstructured":"Yan, J., Sarukkai, S., Mehra, P.: Performance measurement, visualization and modeling of parallel and distributed programs using the AIMS toolkit. Software: Practice and Experience\u00a025, 429\u2013461 (1995)","journal-title":"Software: Practice and Experience"},{"key":"31_CR7","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/2.471178","volume":"28","author":"B.P. Miller","year":"1995","unstructured":"Miller, B.P., Callaghan, M.D., Cargille, J.M., Hollingsworth, J.K., Irvin, R.B., Karavanic, K.L., Kunchithapadam, K., Newhall, T.: The Paradyn parallel performance measurement tool. IEEE Computer\u00a028, 37\u201346 (1995)","journal-title":"IEEE Computer"},{"key":"31_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/3-540-36265-7_15","volume-title":"High Performance Computing - HiPC 2002","author":"T. Fahringer","year":"2002","unstructured":"Fahringer, T., Seragiotto, C.: Automatic search for performance problems in parallel and distributed programs by using multi-experiment analysis. In: Sahni, S.K., Prasanna, V.K., Shukla, U. (eds.) HiPC 2002. LNCS, vol.\u00a02552, pp. 151\u2013162. Springer, Heidelberg (2002)"},{"key":"31_CR9","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1002\/cpe.602","volume":"14","author":"H.W. Cain","year":"2002","unstructured":"Cain, H.W., Miller, B.P., Wylie, B.J.N.: A callgraph-based search strategy for automated performance diagnosis. Concurrency and Computation: Practice and Experience\u00a014, 203\u2013217 (2002)","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"31_CR10","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1002\/cpe.779","volume":"15","author":"P.C. Roth","year":"2003","unstructured":"Roth, P.C., Miller, B.P.: Deep Start: a hybrid strategy for automated performance problem searches. Concurrency and Computation: Practice and Experience\u00a015, 1027\u20131046 (2003)","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Block, R.J., Sarukkai, S., Mehra, P.: Automated performance prediction of message-passing parallel programs. In: Proc. High Performance Networking and Computing Conf, SC 1995 (1995)","DOI":"10.1145\/224170.224273"},{"key":"31_CR12","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1109\/71.730530","volume":"9","author":"J.K. Hollingsworth","year":"1998","unstructured":"Hollingsworth, J.K.: Critical path profiling of message passing and shared-memory programs. IEEE Trans. Parallel and Distributed Systems\u00a09, 1029\u20131040 (1998)","journal-title":"IEEE Trans. Parallel and Distributed Systems"},{"key":"31_CR13","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1109\/32.935854","volume":"27","author":"H. Eom","year":"2001","unstructured":"Eom, H., Hollingsworth, J.K.: A tool to help tune where computation is performed. IEEE Trans. Software Engineering\u00a027, 618\u2013629 (2001)","journal-title":"IEEE Trans. Software Engineering"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Ino, F., Fujimoto, N., Hagihara, K.: LogGPS: A parallel computational model for synchronization analysis. In: Proc. 8th ACM SIGPLAN Symp. Principles and Practice of Parallel Programming (PPoPP 2001), pp. 133\u2013142 (2001)","DOI":"10.1145\/379539.379592"},{"key":"31_CR15","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1145\/359545.359563","volume":"21","author":"L. Lamport","year":"1978","unstructured":"Lamport, L.: Time, clocks, and the ordering of events in a distributed system. Communications of the ACM\u00a021, 558\u2013565 (1978)","journal-title":"Communications of the ACM"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Culler, D., Karp, R., Patterson, D., Sahay, A., Schauser, K.E., Santos, E., Subramonian, R., von Eicken, T.: LogP: Towards a realistic model of parallel computation. In: Proc. 4th ACM SIGPLAN Symp. Principles and Practice of Parallel Programming (PPoPP 1993), pp. 1\u201312 (1993)","DOI":"10.1145\/155332.155333"},{"key":"31_CR17","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1006\/jpdc.1997.1346","volume":"44","author":"A. Alexandrov","year":"1997","unstructured":"Alexandrov, A., Ionescu, M., Schauser, K., Scheiman, C.: LogGP: Incorporating long messages into the LogP model for parallel computation. J. Parallel and Distributed Computing\u00a044, 71\u201379 (1997)","journal-title":"J. Parallel and Distributed Computing"},{"key":"31_CR18","unstructured":"Herrarte, V., Lusk, E.: Studying parallel program behavior with upshot. Technical Report ANL\u201391\/15, Argonne National Laboratory (1991)"},{"key":"31_CR19","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1016\/0167-8191(96)00024-5","volume":"22","author":"W. Gropp","year":"1996","unstructured":"Gropp, W., Lusk, E., Doss, N., Skjellum, A.: A high-performance, portable implementation of the MPI message passing interface standard. Parallel Computing\u00a022, 789\u2013828 (1996)","journal-title":"Parallel Computing"},{"key":"31_CR20","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/40.342015","volume":"15","author":"N.J. Boden","year":"1995","unstructured":"Boden, N.J., Cohen, D., Felderman, R.E., Kulawik, A.E., Seitz, C.L., Seizovic, J.N., Su, W.K.: Myrinet: A gigabit-per-second local-area network. IEEE Micro\u00a015, 29\u201336 (1995)","journal-title":"IEEE Micro"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"O\u2019Carroll, F., Tezuka, H., Hori, A., Ishikawa, Y.: The design and implementation of zero copy MPI using commodity hardware with a high performance network. In: Proc. 12th ACM Int\u2019l Conf. Supercomputing (ICS 1998), pp. 243\u2013250 (1998)","DOI":"10.1145\/277830.277883"},{"key":"31_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1007\/3-540-45468-3_69","volume-title":"Medical Image Computing and Computer-Assisted Intervention - MICCAI 2001","author":"J.A. Schnabel","year":"2001","unstructured":"Schnabel, J.A., Rueckert, D., Quist, M., Blackall, J.M., Castellano-Smith, A.D., Hartkens, T., Penney, G.P., Hall, W.A., Liu, H., Truwit, C.L., Gerritsen, F.A., Hill, D.L.G., Hawkes, D.J.: A generic framework for non-rigid registration based on non-uniform multi-level free-form deformations. In: Niessen, W.J., Viergever, M.A. (eds.) MICCAI 2001. LNCS, vol.\u00a02208, pp. 573\u2013581. Springer, Heidelberg (2001)"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Graham, S.L., Kessler, P.B., McKusick, M.K.: gprof: a call graph execution profiler. In: Proc. SIGPLAN Symp. Compiler Construction (SCC 1982), pp. 120\u2013126 (1982)","DOI":"10.1145\/800230.806987"},{"key":"31_CR24","doi-asserted-by":"publisher","first-page":"1745","DOI":"10.1016\/j.parco.2003.05.015","volume":"29","author":"A. Takeuchi","year":"2003","unstructured":"Takeuchi, A., Ino, F., Hagihara, K.: An improved binary-swap compositing for sort-last parallel rendering on distributed memory multiprocessors. Parallel Computing\u00a029, 1745\u20131762 (2003)","journal-title":"Parallel Computing"},{"key":"31_CR25","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.1002\/cpe.778","volume":"15","author":"H.L. Truong","year":"2003","unstructured":"Truong, H.L., Fahringer, T.: SCALEA: a performance analysis tool for parallel programs. Concurrency and Computation: Practice and Experience\u00a015, 1001\u20131025 (2003)","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"31_CR26","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1145\/773056.773060","volume":"30","author":"V. Taylor","year":"2003","unstructured":"Taylor, V., Wu, X., Stevens, R.: Prophesy: An infrastructure for performance analysis and modeling of parallel and grid applications. ACM SIGMETRICS Performance Evaluation Review\u00a030, 13\u201318 (2003)","journal-title":"ACM SIGMETRICS Performance Evaluation Review"},{"key":"31_CR27","doi-asserted-by":"publisher","first-page":"1227","DOI":"10.1006\/jpdc.2002.1839","volume":"62","author":"J. Geisler","year":"2002","unstructured":"Geisler, J., Taylor, V.: Performance coupling: Case studies for improving the performance of scientific applications. J. Parallel and Distributed Computing\u00a062, 1227\u20131247 (2002)","journal-title":"J. Parallel and Distributed Computing"},{"key":"31_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1007\/978-3-540-39707-6_39","volume-title":"High Performance Computing","author":"H. Brunst","year":"2003","unstructured":"Brunst, H., Malony, A.D., Shende, S.S., Bell, R.: Online remote trace analysis of parallel applications on high-performance clusters. In: Veidenbaum, A., Joe, K., Amano, H., Aiso, H. (eds.) ISHPC 2003. LNCS, vol.\u00a02858, pp. 440\u2013449. Springer, Heidelberg (2003)"},{"key":"31_CR29","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/S0167-8191(96)00094-4","volume":"23","author":"J. Labarta","year":"1997","unstructured":"Labarta, J., Girona, S., Cortes, T.: Analyzing scheduling policies using Dimemas. Parallel Computing\u00a023, 23\u201334 (1997)","journal-title":"Parallel Computing"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing for Computational Science - VECPAR 2004"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11403937_31.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T19:50:52Z","timestamp":1605642652000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11403937_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540254249","9783540318545"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/11403937_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}