{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T14:39:14Z","timestamp":1775054354428,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":32,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540743088","type":"print"},{"value":"9783540743095","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-74309-5_31","type":"book-chapter","created":{"date-parts":[[2007,8,20]],"date-time":"2007-08-20T10:34:15Z","timestamp":1187606055000},"page":"327-338","source":"Crossref","is-referenced-by-count":7,"title":["Open Issues in MPI Implementation"],"prefix":"10.1007","author":[{"given":"Rajeev","family":"Thakur","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Gropp","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"31_CR1","unstructured":"Barnett, M., Gupta, S., Payne, D., Shuler, L., van de Geijn, R., Watts, J.: Interprocessor collective communication library (InterCom). In: Proceedings of Supercomputing 1994 (November 1994)"},{"key":"31_CR2","volume-title":"Proceedings of SC 2002","author":"G. Bosilca","year":"2002","unstructured":"Bosilca, G., Bouteiller, A., Cappello, F., Djilali, S., Fedak, G., Germain, C., Herault, T., Lemarinier, P., Lodygensky, O., Magniette, F., Neri, V., Selikhov, A.: MPICH-V: Toward a scalable fault tolerant MPI for volatile nodes. In: Proceedings of SC 2002, IEEE, Los Alamitos (2002)"},{"issue":"11","key":"31_CR3","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1109\/71.642949","volume":"8","author":"J. Bruck","year":"1997","unstructured":"Bruck, J., Ho, C.-T., Kipnis, S., Upfal, E., Weathersby, D.: Efficient algorithms for all-to-all communications in multiport message-passing systems. IEEE Transactions on Parallel and Distributed Systems\u00a08(11), 1143\u20131156 (1997)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"31_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/11846802_19","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"D. Buntinas","year":"2006","unstructured":"Buntinas, D., Mercier, G., Gropp, W.: Implementation and shared-memory evaluation of MPICH2 over the Nemesis communication subsystem. In: Mohr, B., Tr\u00e4ff, J.L., Worringen, J., Dongarra, J. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface. LNCS, vol.\u00a04192, pp. 86\u201395. Springer, Heidelberg (2006)"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Byna, S., Gropp, W., Sun, X.-H., Thakur, R.: Improving the performance of MPI derived datatypes by optimizing memory-access cost. In: Proceedings of the IEEE International Conference on Cluster Computing (Cluster 2003) (December 2003), pp. 412\u2013419 (2003)","DOI":"10.1109\/CLUSTR.2003.1253341"},{"key":"31_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/3-540-48158-3_7","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"J. Cownie","year":"1999","unstructured":"Cownie, J., Gropp, W.: A standard interface for debugger access to message queue information in MPI. In: Margalef, T., Dongarra, J.J., Luque, E. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface. LNCS, vol.\u00a01697, pp. 51\u201358. Springer, Heidelberg (1999)"},{"key":"31_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/3-540-45255-9_47","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"G.E. Fagg","year":"2000","unstructured":"Fagg, G.E., Dongarra, J.J.: FT-MPI: Fault tolerant MPI, supporting dynamic applications in a dynamic world. In: Dongarra, J.J., Kacsuk, P., Podhorszki, N. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface. LNCS, vol.\u00a01908, pp. 346\u2013353. Springer, Heidelberg (2000)"},{"key":"31_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1007\/11557265_21","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"C. Falzone","year":"2005","unstructured":"Falzone, C., Chan, A., Lusk, E., Gropp, W.: Collective error detection for MPI collective operations. In: Di Martino, B., Kranzlm\u00fcller, D., Dongarra, J.J. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface. LNCS, vol.\u00a03666, pp. 138\u2013147. Springer, Heidelberg (2005)"},{"key":"31_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/11846802_22","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"C. Gottbrath","year":"2006","unstructured":"Gottbrath, C., Barrett, B., Gropp, W.D., Lusk, E., Squyres, J.: An interface to support the identification of dynamic MPI-2 processes for scalable parallel debugging. In: Mohr, B., Tr\u00e4ff, J.L., Worringen, J., Dongarra, J. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface. LNCS, vol.\u00a04192, pp. 115\u2013122. Springer, Heidelberg (2006)"},{"key":"31_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/11846802_11","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"W. Gropp","year":"2006","unstructured":"Gropp, W., Thakur, R.: Issues in developing a thread-safe MPI implementation. In: Mohr, B., Tr\u00e4ff, J.L., Worringen, J., Dongarra, J. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface. LNCS, vol.\u00a04192, pp. 12\u201321. Springer, Heidelberg (2006)"},{"key":"31_CR11","unstructured":"Gropp, W., Thakur, R.: Revealing the performance of MPI RMA implementations. Technical Report ANL\/MCS-P1419-0507, Mathematics and Computer Science Division, Argonne National Laboratory (May 2007)"},{"key":"31_CR12","unstructured":"Intel Trace Analyzer and Collector 7.0 for Linux, http:\/\/www.intel.com"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Jitsumoto, H., Endo, T., Matsuoka, S.: ABARIS: An adaptable fault detection\/recovery component framework for MPIs. In: DPDNS 2007. Proceedings of 12th IEEE Workshop on Dependable Parallel, Distributed and Network-Centric Systems in conjunction with IPDPS 2007 (March 2007)","DOI":"10.1109\/IPDPS.2007.370603"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Karonis, N., de Supinski, B., Foster, I., Gropp, W., Lusk, E., Bresnahan, J.: Exploiting hierarchy in parallel computer networks to optimize collective operation performance. In: IPDPS 2000. Proceedings of the Fourteenth International Parallel and Distributed Processing Symposium, pp. 377\u2013384 (2000)","DOI":"10.1109\/IPDPS.2000.846009"},{"key":"31_CR15","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1145\/301104.301116","volume-title":"PPoPP 1999","author":"T. Kielmann","year":"1999","unstructured":"Kielmann, T., Hofman, R.F.H., Bal, H.E., Plaat, A., Bhoedjang, R.A.F.: MagPIe: MPI\u2019s collective communication operations for clustered wide area systems. In: PPoPP 1999. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 131\u2013140. ACM Press, New York (1999)"},{"key":"31_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1007\/978-3-540-24688-6_61","volume-title":"Computational Science - ICCS 2004","author":"B. Kramme","year":"2004","unstructured":"Kramme, B., M\u00fcller, M.S., Resch, M.M.: MPI application development using the analysis tool MARMOT. In: Bubak, M., van Albada, G.D., Sloot, P.M.A., Dongarra, J.J. (eds.) ICCS 2004. LNCS, vol.\u00a03038, pp. 464\u2013471. Springer, Heidelberg (2004)"},{"issue":"5","key":"31_CR17","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/MC.2006.180","volume":"39","author":"E.A. Lee","year":"2006","unstructured":"Lee, E.A.: The problem with threads. Computer\u00a039(5), 33\u201342 (2006)","journal-title":"Computer"},{"key":"31_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/11846802_13","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"S. Pervez","year":"2006","unstructured":"Pervez, S., Gopalakrishnan, G., Kirby, R.M., Thakur, R., Gropp, W.: Formal verification of programs that use MPI one-sided communication. In: Mohr, B., Tr\u00e4ff, J.L., Worringen, J., Dongarra, J. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface. LNCS, vol.\u00a04192, pp. 30\u201339. Springer, Heidelberg (2006)"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Ritzdorf, H., Tr\u00e4ff, J.L.: Collective operations in NEC\u2019s high-performance MPI libraries. In: IPDPS 2006. Proceedings of the 20th International Parallel and Distributed Processing Symposium (April 2006)","DOI":"10.1109\/IPDPS.2006.1639334"},{"key":"31_CR20","unstructured":"ROMIO: A high-performance, portable MPI-IO implementation. http:\/\/www.mcs.anl.gov\/romio"},{"key":"31_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1007\/978-3-540-39924-7_55","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"R. Ross","year":"2003","unstructured":"Ross, R., Miller, N., Gropp, W.D.: Implementing fast and reusable datatype processing. In: Dongarra, J.J., Laforenza, D., Orlando, S. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface. LNCS, vol.\u00a02840, pp. 404\u2013413. Springer, Heidelberg (2003)"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Sistare, S., vandeVaart, R., Loh, E.: Optimization of MPI collectives on clusters of large-scale SMPs. In: Proceedings of SC 1999: High Performance Networking and Computing (November 1999)","DOI":"10.1145\/331532.331555"},{"key":"31_CR23","unstructured":"Thakur. R., Gropp, W.: Test suite for evaluating performance of MPI implementations that support MPI_THREAD_MULTIPLE. Technical Report ANL\/MCS-P1418-0507, Mathematics and Computer Science Division, Argonne National Laboratory (May 2007)"},{"key":"31_CR24","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1145\/301816.301826","volume-title":"Proceedings of the 6th Workshop on I\/O in Parallel and Distributed Systems","author":"R. Thakur","year":"1999","unstructured":"Thakur, R., Gropp, W., Lusk, E.: On implementing MPI-IO portably and with high performance. In: Proceedings of the 6th Workshop on I\/O in Parallel and Distributed Systems, pp. 23\u201332. ACM Press, New York (1999)"},{"issue":"1","key":"31_CR25","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/S0167-8191(01)00129-6","volume":"28","author":"R. Thakur","year":"2002","unstructured":"Thakur, R., Gropp, W., Lusk, E.: Optimizing noncontiguous accesses in MPI-IO. Parallel Computing\u00a028(1), 83\u2013105 (2002)","journal-title":"Parallel Computing"},{"issue":"1","key":"31_CR26","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1177\/1094342005051521","volume":"19","author":"R. Thakur","year":"2005","unstructured":"Thakur, R., Rabenseifner, R., Gropp, W.: Optimization of collective communication operations in MPICH. International Journal of High-Performance Computing Applications\u00a019(1), 49\u201366 (2005)","journal-title":"International Journal of High-Performance Computing Applications"},{"key":"31_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/11557265_19","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"R. Thakur","year":"2005","unstructured":"Thakur, R., Ross, R., Latham, R.: Implementing byte-range locks using MPI one-sided communication. In: Di Martino, B., Kranzlm\u00fcller, D., Dongarra, J.J. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface. LNCS, vol.\u00a03666, pp. 120\u2013129. Springer, Heidelberg (2005)"},{"key":"31_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/978-3-540-30218-6_28","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"J.L. Tr\u00e4ff","year":"2004","unstructured":"Tr\u00e4ff, J.L.: A simple work-optimal broadcast algorithm for message-passing parallel systems. In: Kranzlm\u00fcller, D., Kacsuk, P., Dongarra, J.J. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface. LNCS, vol.\u00a03241, pp. 173\u2013180. Springer, Heidelberg (2004)"},{"key":"31_CR29","unstructured":"Tr\u00e4ff, J.L., Gropp, W., Thakur, R.: Self-consistent MPI performance requirements. In: Technical report. Euro PVM\/MPI 2007 (submitted, 2007)"},{"key":"31_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/3-540-48158-3_14","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"J.L. Tr\u00e4ff","year":"1999","unstructured":"Tr\u00e4ff, J.L., Hempel, R., Ritzdoff, H., Zimmermann, F.: Flattening on the fly: Efficient handling of MPI derived datatypes. In: Margalef, T., Dongarra, J.J., Luque, E. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface. LNCS, vol.\u00a01697, pp. 109\u2013116. Springer, Heidelberg (1999)"},{"key":"31_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1007\/978-3-540-30218-6_11","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"J.L. Tr\u00e4ff","year":"2004","unstructured":"Tr\u00e4ff, J.L., Worringen, J.: Verifying collective MPI calls. In: Kranzlm\u00fcller, D., Kacsuk, P., Dongarra, J.J. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface. LNCS, vol.\u00a03241, pp. 18\u201327. Springer, Heidelberg (2004)"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Vetter, J.S., de Supinski, B.R.: Dynamic software testing of MPI applications with Umpire. In: Proceedings of SC2000: High Performance Networking and Computing, pp. 70\u201379 (November 2000)","DOI":"10.1109\/SC.2000.10055"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Systems Architecture"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-74309-5_31.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T10:19:47Z","timestamp":1619518787000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-74309-5_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540743088","9783540743095"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-74309-5_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[]}}