{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T18:32:07Z","timestamp":1743013927547,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":25,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642387494"},{"type":"electronic","value":"9783642387500"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-38750-0_27","type":"book-chapter","created":{"date-parts":[[2013,6,10]],"date-time":"2013-06-10T01:26:27Z","timestamp":1370827587000},"page":"357-371","source":"Crossref","is-referenced-by-count":5,"title":["The Effect of Topology-Aware Process and Thread Placement on Performance and Energy"],"prefix":"10.1007","author":[{"given":"Albert","family":"Solernou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeyarajan","family":"Thiyagalingam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mihai C.","family":"Duta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anne E.","family":"Trefethen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"27_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/978-3-642-15291-7_20","volume-title":"Euro-Par 2010 - Parallel Processing","author":"E. Jeannot","year":"2010","unstructured":"Jeannot, E., Mercier, G.: Near-Optimal Placement of MPI Processes on Hierarchical NUMA Architectures. In: D\u2019Ambra, P., Guarracino, M., Talia, D. (eds.) Euro-Par 2010, Part II. LNCS, vol.\u00a06272, pp. 199\u2013210. Springer, Heidelberg (2010)"},{"issue":"4","key":"27_CR2","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1002\/cpe.1643","volume":"23","author":"T. Hoefler","year":"2010","unstructured":"Hoefler, T., Rabenseifner, R., Ritzdorf, H., de Supinski, B.R., Thakur, R., Traeff, J.L.: The Scalable Process Topology Interface of MPI 2.2. Concurrency and Computation: Practice and Experience\u00a023(4), 293\u2013310 (2010)","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Appelbe, B., Hardnett, C., Doddapaneni, S.: Program Transformation for Locality Using Affinity Regions. In: Proceedings of the Sixth Workshop on Languages and Compilers for Parallel Computing (1993)","DOI":"10.1007\/3-540-57659-2_17"},{"key":"27_CR4","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1145\/1366219.1366222","volume-title":"Proceedings of the 2008 Workshop on Memory Access on Future Processors: a Solved Problem? MAW 2008","author":"C. Terboven","year":"2008","unstructured":"Terboven, C., Mey, D.a., Schmidl, D., Jin, H., Reichstein, T.: Data and Thread Affinity in OpenMP Programs. In: Proceedings of the 2008 Workshop on Memory Access on Future Processors: a Solved Problem? MAW 2008, pp. 377\u2013384. ACM, New York (2008)"},{"key":"27_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/978-3-642-16233-6_6","volume-title":"Facing the Multicore-Challenge","author":"S. Mallach","year":"2010","unstructured":"Mallach, S., Gutwenger, C.: Improved scalability by using hardware-aware thread affinities. In: Keller, R., Kramer, D., Weiss, J.-P. (eds.) Facing the Multicore-Challenge. LNCS, vol.\u00a06310, pp. 29\u201341. Springer, Heidelberg (2010)"},{"key":"27_CR6","unstructured":"HWLOC: Portable hardware locality, \n                    http:\/\/www.open-mpi.org\/projects\/hwloc"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Broquedis, F., Clet-Ortega, J., Moreaud, S., Furmento, N., Goglin, B., Mercier, G., Thibault, S., Namyst, R.: hwloc: A generic framework for managing hardware affinities in HPC applications. In: 2010 18th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), pp. 180\u2013186 (February 2010)","DOI":"10.1109\/PDP.2010.67"},{"key":"27_CR8","unstructured":"EMPPACK: Energy\u00a0Measurement and Profiling Package, \n                    http:\/\/www.oerc.ox.ac.uk\/research\/energy-efficient-computing"},{"issue":"3","key":"27_CR9","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1177\/109434209100500306","volume":"5","author":"D. Bailey","year":"1991","unstructured":"Bailey, D., Barszcz, E., Barton, J., Browning, D., al, e.: The NAS parallel benchmarks. The International Journal of Supercomputer Applications\u00a05(3), 63\u201373 (1991)","journal-title":"The International Journal of Supercomputer Applications"},{"key":"27_CR10","unstructured":"Giles, M., Mudalige, G., Spencer, B., Bertolli, C., Reguly, I.: Designing OP2 for GPU architectures. Journal of Parallel and Distributed Computing"},{"issue":"3","key":"27_CR11","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1021\/ct700301q","volume":"4","author":"B. Hess","year":"2008","unstructured":"Hess, B., Kutzner, C., van der Spoel, D., Lindahl, E.: Gromacs 4: Algorithms for highly efficient, load-balanced, and scalable molecular simulation. Journal of Chemical Theory and Computation\u00a04(3), 435\u2013447 (2008)","journal-title":"Journal of Chemical Theory and Computation"},{"key":"27_CR12","unstructured":"Scalalife: Scalable software services for life sciences, \n                    http:\/\/www.scalalife.eu"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Hgberg, C., Nikitin, A.M., Lyubartsev, A.P.: Modification of the CHARMM Force Field for DMPC Lipid Bilayer. Journal of Computational Chemistry (2008)","DOI":"10.1002\/jcc.20974"},{"key":"27_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1007\/BFb0024763","volume-title":"Euro-Par\u201996 - Parallel Processing","author":"J. Labarta","year":"1996","unstructured":"Labarta, J., Girona, S., Pillet, V., Cortes, T., Gregoris, L.: DiP: a parallel program development environment. In: Fraigniaud, P., Mignotte, A., Robert, Y., Boug\u00e9, L. (eds.) Euro-Par 1996. LNCS, vol.\u00a01124, pp. 665\u2013674. Springer, Heidelberg (1996)"},{"key":"27_CR15","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0166-218X(92)90146-2","volume":"37-38","author":"C.P. Kruskal","year":"1992","unstructured":"Kruskal, C.P., Snir, M.: Cost-Performance Tradeoffs for Interconnection Networks. Journal of Discrete Applied Mathematics\u00a037-38, 359\u2013385 (1992)","journal-title":"Journal of Discrete Applied Mathematics"},{"key":"27_CR16","first-page":"353","volume-title":"Proceedings of the 20th Annual International Conference on SuperComputing, ICS 2006","author":"H. Chen","year":"2006","unstructured":"Chen, H., Chen, W., Huang, J., Robert, B., Kuhn, H.: MPIPP: An Automatic Profile-Guided Parallel Process Placement Toolset for SMP Clusters and Multiclusters. In: Proceedings of the 20th Annual International Conference on SuperComputing, ICS 2006, pp. 353\u2013360. ACM, New York (2006)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Pellegrini, F.: Static Mapping by Dual Recursive Bipartitioning of Process Architecture Graphs. In: Proceedings of the Scalable High-Performance Computing Conference, pp. 486\u2013493 (May 1994)","DOI":"10.1007\/3-540-61142-8_588"},{"key":"27_CR18","first-page":"19","volume-title":"Proceedings of the Second International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems, PMBS 2011","author":"C. Su","year":"2011","unstructured":"Su, C., Li, D., Nikolopoulos, D., Grove, M., Cameron, K.W., de Supinski, B.R.: Critical Path-Based Thread Placement for NUMA Systems. In: Proceedings of the Second International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems, PMBS 2011, pp. 19\u201320. ACM, New York (2011)"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Su, C.Y., Li, D., Nikolopoulos, D.S., Cameron, K.W., de Supinski, B.R., Leon, E.A.: Model-Based, Memory-Centric Performance and Power Optimization on NUMA Multiprocessors. In: Proceedings of the 2012 IEEE International Symposium on Workload Characterization, San Diego, CA, pp. 163\u2013174 (November 2012)","DOI":"10.1109\/IISWC.2012.6402921"},{"issue":"5","key":"27_CR20","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1109\/TPDS.2009.76","volume":"21","author":"R. Ge","year":"2010","unstructured":"Ge, R., Feng, X., Song, S., Chang, H.-C., Li, D., Cameron, K.W.: Powerpack: Energy profiling and analysis of high-performance systems and applications. IEEE Transactions on Parallel and Distributed Systems\u00a021(5), 658\u2013671 (2010)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Brooks, D., Tiwari, V., Martonosi, M.: Wattch: a framework for architectural-level power analysis and optimizations. In: ACM SIGARCH Computer Architecture News, vol.\u00a028, pp. 83\u201394. ACM (2000)","DOI":"10.1145\/342001.339657"},{"key":"27_CR22","unstructured":"Wang, S.H.-S., Zhu, X., Peh, L.-S., Malik: Orion: a power-performance simulator for interconnection networks. In: Proceedings of the 35th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO-35), pp. 294\u2013305 (2002)"},{"key":"27_CR23","first-page":"217","volume-title":"Proceedings of the 2nd USENIX Conference on File and Storage Technologies, FAST 2003","author":"J. Zedlewski","year":"2003","unstructured":"Zedlewski, J., Sobti, S., Garg, N., Zheng, F., Krishnamurthy, A., Wang, R.: Modeling hard-disk power consumption. In: Proceedings of the 2nd USENIX Conference on File and Storage Technologies, FAST 2003, pp. 217\u2013230. USENIX Association, Berkeley (2003)"},{"key":"27_CR24","unstructured":"Isci, C., Martonosi, M.: Runtime power monitoring in high-end processors: Methodology and empirical data. In: Proceedings of the 36th Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO 36, pp. 93\u2013104. IEEE Computer Society (2003)"},{"key":"27_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/978-3-540-69338-3_13","volume-title":"High Performance Embedded Architectures and Compilers","author":"C. Hu","year":"2007","unstructured":"Hu, C., Jim\u00e9nez, D.A., Kremer, U.: Efficient program power behavior characterization. In: De Bosschere, K., Kaeli, D., Stenstr\u00f6m, P., Whalley, D., Ungerer, T. (eds.) HiPEAC 2007. LNCS, vol.\u00a04367, pp. 183\u2013197. Springer, Heidelberg (2007)"}],"container-title":["Lecture Notes in Computer Science","Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-38750-0_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T09:13:05Z","timestamp":1639732385000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-642-38750-0_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642387494","9783642387500"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-38750-0_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}