{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:50:39Z","timestamp":1740099039892,"version":"3.37.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319773971"},{"type":"electronic","value":"9783319773988"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-77398-8_5","type":"book-chapter","created":{"date-parts":[[2018,2,27]],"date-time":"2018-02-27T00:52:54Z","timestamp":1519692774000},"page":"83-102","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Supporting Real-Time Jobs on the IBM Blue Gene\/Q: Simulation-Based Study"],"prefix":"10.1007","author":[{"given":"Daihou","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1288-7521","authenticated-orcid":false,"given":"Eun-Sung","family":"Jung","sequence":"additional","affiliation":[]},{"given":"Rajkumar","family":"Kettimuthu","sequence":"additional","affiliation":[]},{"given":"Ian","family":"Foster","sequence":"additional","affiliation":[]},{"given":"David J.","family":"Foran","sequence":"additional","affiliation":[]},{"given":"Manish","family":"Parashar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,2,28]]},"reference":[{"key":"5_CR1","unstructured":"Cobalt project. http:\/\/trac.mcs.anl.gov\/projects\/cobalt"},{"key":"5_CR2","unstructured":"Frost, NCAR\/CU BG\/L System. https:\/\/wiki.ucar.edu\/display\/BlueGene\/Frost"},{"key":"5_CR3","unstructured":"Mira. https:\/\/www.alcf.anl.gov\/mira"},{"key":"5_CR4","unstructured":"Qsim. http:\/\/trac.mcs.anl.gov\/projects\/cobalt"},{"issue":"4","key":"5_CR5","first-page":"345","volume":"15","author":"G Allen","year":"2001","unstructured":"Allen, G., Angulo, D., Foster, I., Lanfermann, G., Liu, C., Radke, T., Seidel, E., Shalf, J.: The cactus worm: experiments with dynamic resource selection and allocation in a grid environment. IJHPCA 15(4), 345\u2013358 (2001)","journal-title":"IJHPCA"},{"issue":"2","key":"5_CR6","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1006\/jpdc.1997.1335","volume":"43","author":"S Anastasiadis","year":"1997","unstructured":"Anastasiadis, S., Sevcik, K.: Parallel application scheduling on networks of workstations. J. Parallel Distrib. Comput. 43(2), 109\u2013124 (1997)","journal-title":"J. Parallel Distrib. Comput."},{"key":"5_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-56663-5","volume-title":"The MOSIX Distributed Operating System: Load Balancing for UNIX","year":"1993","unstructured":"Barak, A., Guday, S., Wheeler, R.G. (eds.): The MOSIX Distributed Operating System: Load Balancing for UNIX. LNCS, vol. 672. Springer, Heidelberg (1993). https:\/\/doi.org\/10.1007\/3-540-56663-5"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Chiang, S.-H., Vernon, M.K.: Production job scheduling for parallel shared memory systems. In: Proceedings of the 15th International Parallel & Distributed Processing Symposium, Washington, DC, USA, p. 47 (2001)","DOI":"10.1109\/IPDPS.2001.924987"},{"key":"5_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/3-540-39997-6_12","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"W Cirne","year":"2000","unstructured":"Cirne, W., Berman, F.: Adaptive selection of partition size for supercomputer requests. In: Feitelson, D.G., Rudolph, L. (eds.) JSSPP 2000. LNCS, vol. 1911, pp. 187\u2013207. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-39997-6_12"},{"key":"5_CR10","unstructured":"Deng, X., Gu, N., Brecht, T., Lu, K.: Preemptive scheduling of parallel jobs on multiprocessors. In: Proceedings of the Seventh Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 1996, Philadelphia, PA, USA, pp. 159\u2013167 (1996)"},{"key":"5_CR11","unstructured":"Duell, J.: The design and implementation of Berkeley Labs Linux checkpoint\/restart. Technical report (2003). http:\/\/www.nersc.gov\/research\/FTG\/checkpoint\/reports.html"},{"issue":"8","key":"5_CR12","first-page":"885","volume":"65","author":"IP Egwutuoha","year":"2005","unstructured":"Egwutuoha, I.P., Levy, D., Selic, B., Chen, S.: A survey of fault tolerance mechanisms and checkpoint\/restart implementations for high performance computing systems. J. Supercomput. 65(8), 885\u2013900 (2005)","journal-title":"J. Supercomput."},{"key":"5_CR13","unstructured":"Feitelson, D.G.: Job scheduling in multiprogrammed parallel systems. Research Report RC 19790 (87657), IBM T. J. Watson Research Center, October 1994"},{"key":"5_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/3-540-60153-8_20","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"DG Feitelson","year":"1995","unstructured":"Feitelson, D.G., Rudolph, L.: Parallel job scheduling: issues and approaches. In: Feitelson, D.G., Rudolph, L. (eds.) JSSPP 1995. LNCS, vol. 949, pp. 1\u201318. Springer, Heidelberg (1995). https:\/\/doi.org\/10.1007\/3-540-60153-8_20"},{"key":"5_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/11407522_1","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"DG Feitelson","year":"2005","unstructured":"Feitelson, D.G., Rudolph, L., Schwiegelshohn, U.: Parallel job scheduling \u2014 a status report. In: Feitelson, D.G., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2004. LNCS, vol. 3277, pp. 1\u201316. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11407522_1"},{"key":"5_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/3-540-63574-2_14","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"DG Feitelson","year":"1997","unstructured":"Feitelson, D.G., Rudolph, L., Schwiegelshohn, U., Sevcik, K.C., Wong, P.: Theory and practice in parallel job scheduling. In: Feitelson, D.G., Rudolph, L. (eds.) JSSPP 1997. LNCS, vol. 1291, pp. 1\u201334. Springer, Heidelberg (1997). https:\/\/doi.org\/10.1007\/3-540-63574-2_14"},{"key":"5_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/3-540-47954-6_1","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"JP Jones","year":"1999","unstructured":"Jones, J.P., Nitzberg, B.: Scheduling for parallel supercomputing: a historical perspective of achievable utilization. In: Feitelson, D.G., Rudolph, L. (eds.) JSSPP 1999. LNCS, vol. 1659, pp. 1\u201316. Springer, Heidelberg (1999). https:\/\/doi.org\/10.1007\/3-540-47954-6_1"},{"key":"5_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1007\/3-540-36180-4_6","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"WA Ward Jr","year":"2002","unstructured":"Ward Jr., W.A., Mahood, C.L., West, J.E.: Scheduling jobs on parallel systems using a relaxed backfill strategy. In: Feitelson, D.G., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2002. LNCS, vol. 2537, pp. 88\u2013102. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-36180-4_6"},{"issue":"2\/3","key":"5_CR19","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1504\/IJHPCN.2005.008032","volume":"3","author":"R Kettimuthu","year":"2005","unstructured":"Kettimuthu, R., Subramani, V., Srinivasan, S., Gopalsamy, T., Panda, D.K., Sadayappan, P.: Selective preemption strategies for parallel job scheduling. IJHPCN 3(2\/3), 122\u2013152 (2005)","journal-title":"IJHPCN"},{"key":"5_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/3-540-36180-4_5","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"BG Lawson","year":"2002","unstructured":"Lawson, B.G., Smirni, E.: Multiple-queue backfilling scheduling with priorities and reservations for parallel systems. In: Feitelson, D.G., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2002. LNCS, vol. 2537, pp. 72\u201387. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-36180-4_5"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Leung, V.J., Sabin, G., Sadayappan, P.: Parallel job scheduling policies to improve fairness: a case study. In: Lee, W.-C., Yuan, X. (eds.) ICPP Workshops, pp. 346\u2013353. IEEE Computer Society (2010)","DOI":"10.1109\/ICPPW.2010.48"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Leutenneger, L.T., Vernon, M.K.: The performance of multiprogrammed multiprocessor scheduling policies. In: ACM SIGMETRICS Conference on Measurement and Modelling of Computer Systems, pp. 226\u2013236, May 1990","DOI":"10.1145\/98457.98761"},{"key":"5_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/3-540-60153-8_35","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"DA Lifka","year":"1995","unstructured":"Lifka, D.A.: The ANL\/IBM SP scheduling system. In: Feitelson, D.G., Rudolph, L. (eds.) JSSPP 1995. LNCS, vol. 949, pp. 295\u2013303. Springer, Heidelberg (1995). https:\/\/doi.org\/10.1007\/3-540-60153-8_35"},{"key":"5_CR24","unstructured":"Motwani, R., Phillips, S., Torng, E.: Non-clairvoyant scheduling. In: Proceedings of the Fourth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 1993, Philadelphia, PA, USA, pp. 422\u2013431 (1993)"},{"issue":"6","key":"5_CR25","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1109\/71.932708","volume":"12","author":"AW Mu\u2019alem","year":"2001","unstructured":"Mu\u2019alem, A.W., Feitelson, D.G.: Utilization, predictability, workloads, and user runtime estimates in scheduling the IBM SP2 with backfilling. IEEE Trans. Parallel Distrib. Syst. 12(6), 529\u2013543 (2001)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"5_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-642-35867-8_3","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"S Niu","year":"2013","unstructured":"Niu, S., Zhai, J., Ma, X., Liu, M., Zhai, Y., Chen, W., Zheng, W.: Employing checkpoint to improve job scheduling in large-scale systems. In: Cirne, W., Desai, N., Frachtenberg, E., Schwiegelshohn, U. (eds.) JSSPP 2012. LNCS, vol. 7698, pp. 36\u201355. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-35867-8_3"},{"key":"5_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1007\/3-540-63574-2_21","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"EW Parsons","year":"1997","unstructured":"Parsons, E.W., Sevcik, K.C.: Implementing multiprocessor scheduling disciplines. In: Feitelson, D.G., Rudolph, L. (eds.) JSSPP 1997. LNCS, vol. 1291, pp. 166\u2013192. Springer, Heidelberg (1997). https:\/\/doi.org\/10.1007\/3-540-63574-2_21"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Ranganathan, K., Foster, I.: Decoupling computation and data scheduling in distributed data-intensive applications. In: Proceedings of the 11th IEEE International Symposium on High Performance Distributed Computing, HPDC 2002, p. 352. IEEE Computer Society, Washington, DC (2002)","DOI":"10.1109\/HPDC.2002.1029935"},{"key":"5_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/978-3-540-71035-6_5","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"G Sabin","year":"2007","unstructured":"Sabin, G., Lang, M., Sadayappan, P.: Moldable parallel job scheduling using job efficiency: an iterative approach. In: Frachtenberg, E., Schwiegelshohn, U. (eds.) JSSPP 2006. LNCS, vol. 4376, pp. 94\u2013114. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-71035-6_5"},{"key":"5_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1007\/11605300_12","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"G Sabin","year":"2005","unstructured":"Sabin, G., Sadayappan, P.: Unfairness metrics for space-sharing parallel job schedulers. In: Feitelson, D., Frachtenberg, E., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2005. LNCS, vol. 3834, pp. 238\u2013256. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11605300_12"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Schulz, M., Bronevetsky, G., Fernandes, R., Marques, D., Pingali, K., Stodghill, P.: Implementation and evaluation of a scalable application-level checkpoint-recovery scheme for MPI programs. In: Proceedings of the ACM\/IEEE SC 2004 Conference Supercomputing, pp. 38\u201338, November 2004","DOI":"10.1109\/SC.2004.29"},{"issue":"2\u20133","key":"5_CR32","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/0166-5316(94)90036-1","volume":"19","author":"KC Sevcik","year":"1994","unstructured":"Sevcik, K.C.: Application scheduling and processor allocation in multiprogrammed parallel processing systems. Perform. Eval. 19(2\u20133), 107\u2013140 (1994)","journal-title":"Perform. Eval."},{"issue":"9","key":"5_CR33","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.1016\/j.jpdc.2005.05.003","volume":"65","author":"E Shmueli","year":"2005","unstructured":"Shmueli, E., Feitelson, D.G.: Backfilling with lookahead to optimize the packing of parallel jobs. J. Parallel Distrib. Comput. 65(9), 1090\u20131107 (2005)","journal-title":"J. Parallel Distrib. Comput."},{"key":"5_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/3-540-36180-4_2","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"QO Snell","year":"2002","unstructured":"Snell, Q.O., Clement, M.J., Jackson, D.B.: Preemption based backfill. In: Feitelson, D.G., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2002. LNCS, vol. 2537, pp. 24\u201337. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-36180-4_2"},{"key":"5_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/3-540-36180-4_4","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"S Srinivasan","year":"2002","unstructured":"Srinivasan, S., Kettimuthu, R., Subramani, V., Sadayappan, P.: Selective reservation strategies for backfill job scheduling. In: Feitelson, D.G., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2002. LNCS, vol. 2537, pp. 55\u201371. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-36180-4_4"},{"key":"5_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1007\/3-540-36265-7_17","volume-title":"High Performance Computing \u2014 HiPC 2002","author":"S Srinivasan","year":"2002","unstructured":"Srinivasan, S., Subramani, V., Kettimuthu, R., Holenarsipur, P., Sadayappan, P.: Effective selection of partition sizes for moldable scheduling of parallel jobs. In: Sahni, S., Prasanna, V.K., Shukla, U. (eds.) HiPC 2002. LNCS, vol. 2552, pp. 174\u2013183. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-36265-7_17"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Subramani, V., Kettimuthu, R., Srinivasan, S., Sadayappan, P.: Distributed job scheduling on computational grids using multiple simultaneous requests. In: Proceedings of the 11th International Symposium on High Performance Distributed Computing, p. 359. IEEE Computer Society, Washington, DC (2002)","DOI":"10.1109\/HPDC.2002.1029936"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Talby, D., Feitelson, D.G.: Supporting priorities and improving utilization of the IBM SP scheduler using slack-based backfilling. In: Proceedings of the 13th International Parallel Processing Symposium, pp. 513\u2013517 (1999)","DOI":"10.1109\/IPPS.1999.760525"},{"issue":"7","key":"5_CR39","doi-asserted-by":"crossref","first-page":"926","DOI":"10.1016\/j.jpdc.2013.02.006","volume":"73","author":"W Tang","year":"2013","unstructured":"Tang, W., Desai, N., Buettner, D., Lan, Z.: Job scheduling with adjusted runtime estimates on production supercomputers. J. Parallel Distrib. Comput. 73(7), 926\u2013938 (2013)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"12","key":"5_CR40","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1016\/j.parco.2013.08.007","volume":"39","author":"W Tang","year":"2013","unstructured":"Tang, W., Ren, D., Lan, Z., Desai, N.: Toward balanced and sustainable job scheduling for production supercomputers. Parallel Comput. 39(12), 753\u2013768 (2013)","journal-title":"Parallel Comput."},{"issue":"2","key":"5_CR41","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1080\/08940886.2015.1013414","volume":"28","author":"M Thomas","year":"2015","unstructured":"Thomas, M., Dam, K., Marshall, M., Kuprat, A., Carson, J., Lansing, C., Guillen, Z., Miller, E., Lanekoff, I., Laskin, J.: Towards adaptive, streaming analysis of X-ray tomography data. Synchrotron Radiat. News 28(2), 10\u201314 (2015)","journal-title":"Synchrotron Radiat. News"},{"key":"5_CR42","unstructured":"Trebon, N.: Enabling urgent computing within the existing distributed computing infrastructure, Ph.D. thesis. University of Chicago (2011). AAI3472964"},{"key":"5_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/11951957_21","volume-title":"Distributed Computing and Internet Technology","author":"JP Walters","year":"2006","unstructured":"Walters, J.P., Chaudhary, V.: Application-level checkpointing techniques for parallel programs. In: Madria, S.K., Claypool, K.T., Kannan, R., Uppuluri, P., Gore, M.M. (eds.) ICDCIT 2006. LNCS, vol. 4317, pp. 221\u2013234. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11951957_21"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Zahorjan, J., McCann, C.: Processor scheduling in shared memory multiprocessors. In: ACM SIGMETRICS Conference on Measurement and Modelling of Computer Systems, pp. 214\u2013225, May 1990","DOI":"10.1145\/98457.98760"}],"container-title":["Lecture Notes in Computer Science","Job Scheduling Strategies for Parallel Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-77398-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,11]],"date-time":"2019-10-11T18:33:15Z","timestamp":1570818795000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-77398-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319773971","9783319773988"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-77398-8_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}