{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T22:50:40Z","timestamp":1725749440409},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642399572"},{"type":"electronic","value":"9783642399589"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-39958-9_16","type":"book-chapter","created":{"date-parts":[[2013,9,23]],"date-time":"2013-09-23T01:23:35Z","timestamp":1379899415000},"page":"182-196","source":"Crossref","is-referenced-by-count":9,"title":["FuPerMod: A Framework for Optimal Data Partitioning for Parallel Scientific Applications on Dedicated Heterogeneous HPC Platforms"],"prefix":"10.1007","author":[{"given":"David","family":"Clarke","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziming","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladimir","family":"Rychkov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey","family":"Lastovetsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Aubanel, E., Wu, X.: Incorporating latency in heterogeneous graph partitioning. In: IPDPS 2007, pp. 1\u20138 (2007)","DOI":"10.1109\/IPDPS.2007.370577"},{"issue":"10","key":"16_CR2","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1109\/71.963416","volume":"12","author":"O. Beaumont","year":"2001","unstructured":"Beaumont, O., Boudet, V., Rastello, F., Robert, Y.: Matrix multiplication on heterogeneous platforms. IEEE Trans. Parallel Distrib. Syst.\u00a012(10), 1033\u20131051 (2001)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Catalyurek, U., Boman, E., Devine, K., et al.: Hypergraph-based dynamic load balancing for adaptive scientific computations. In: IPDPS 2007, pp. 1 \u201311 (2007)","DOI":"10.1109\/IPDPS.2007.370258"},{"issue":"6-8","key":"16_CR4","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1016\/j.parco.2007.12.001","volume":"34","author":"C. Chevalier","year":"2008","unstructured":"Chevalier, C., Pellegrini, F.: PT-Scotch: A tool for efficient parallel graph ordering. Parallel Computing\u00a034(6-8), 318\u2013331 (2008)","journal-title":"Parallel Computing"},{"key":"16_CR5","unstructured":"Choi, J.: A new parallel matrix multiplication algorithm on distributed-memory concurrent computers. In: HPC Asia 1997, pp. 224\u2013229 (1997)"},{"key":"16_CR6","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1142\/S0129626411000163","volume":"21","author":"D. Clarke","year":"2011","unstructured":"Clarke, D., Lastovetsky, A., Rychkov, V.: Dynamic load balancing of parallel computational iterative routines on highly heterogeneous HPC platforms. Parallel Processing Letters\u00a021, 195\u2013217 (2011)","journal-title":"Parallel Processing Letters"},{"key":"16_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1007\/978-3-642-29737-3_50","volume-title":"Euro-Par 2011: Parallel Processing Workshops","author":"D. Clarke","year":"2012","unstructured":"Clarke, D., Lastovetsky, A., Rychkov, V.: Column-based matrix partitioning for parallel matrix multiplication on heterogeneous processors based on functional performance models. In: Alexander, M., et al. (eds.) Euro-Par 2011, Part I. LNCS, vol.\u00a07155, pp. 450\u2013459. Springer, Heidelberg (2012)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Fatica, M.: Accelerating Linpack with CUDA on heterogenous clusters. In: GPGPU-2, pp. 46\u201351. ACM (2009)","DOI":"10.1145\/1513895.1513901"},{"key":"16_CR9","unstructured":"Karypis, G., Schloegel, K.: ParMETIS: Parallel Graph Partitioning and Sparse Matrix Ordering Library. Version 4.0 (2013), \n                    \n                      http:\/\/glaros.dtc.umn.edu\/gkhome\/fetch\/sw\/parmetis\/manual.pdf"},{"key":"16_CR10","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1177\/1094342006074864","volume":"21","author":"A. Lastovetsky","year":"2007","unstructured":"Lastovetsky, A., Reddy, R.: Data partitioning with a functional performance model of heterogeneous processors. Int. J. High Perform. C\u00a021, 76\u201390 (2007)","journal-title":"Int. J. High Perform. C"},{"key":"16_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/978-3-642-14122-5_13","volume-title":"Euro-Par 2009 \u2013 Parallel Processing Workshops","author":"A. Lastovetsky","year":"2010","unstructured":"Lastovetsky, A., Reddy, R.: Distributed data partitioning for heterogeneous processors based on partial estimation of their functional performance models. In: Lin, H.-X., Alexander, M., Forsell, M., Kn\u00fcpfer, A., Prodan, R., Sousa, L., Streit, A. (eds.) Euro-Par 2009. LNCS, vol.\u00a06043, pp. 91\u2013101. Springer, Heidelberg (2010)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Luk, C.K., Hong, S., Kim, H.: Qilin: Exploiting parallelism on heterogeneous multiprocessors with adaptive mapping. In: MICRO-42, pp. 45\u201355 (2009)","DOI":"10.1145\/1669112.1669121"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Malony, A.D., Biersdorff, S., Shende, S., et al.: Parallel performance measurement of heterogeneous parallel systems with GPUs. In: ICPP 2011, pp. 176\u2013185 (2011)","DOI":"10.1109\/ICPP.2011.71"},{"key":"16_CR14","unstructured":"Ogata, Y., Endo, T., Maruyama, N., Matsuoka, S.: An efficient, model-based CPU-GPU heterogeneous FFT library. In: IPDPS 2008, pp. 1 \u201310 (2008)"},{"key":"16_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1007\/978-3-642-23178-0_29","volume-title":"Parallel Computing Technologies","author":"V. Rychkov","year":"2011","unstructured":"Rychkov, V., Clarke, D., Lastovetsky, A.: Using multidimensional solvers for optimal data partitioning on dedicated heterogeneous HPC platforms. In: Malyshkin, V. (ed.) PaCT 2011. LNCS, vol.\u00a06873, pp. 332\u2013346. Springer, Heidelberg (2011)"},{"issue":"5","key":"16_CR16","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1016\/S0167-739X(00)00107-2","volume":"17","author":"C. Walshaw","year":"2001","unstructured":"Walshaw, C., Cross, M.: Multilevel mesh partitioning for heterogeneous communication networks. Future Generation Comput. Syst.\u00a017(5), 601\u2013623 (2001)","journal-title":"Future Generation Comput. Syst."},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Yang, C., Wang, F., Du, Y., et al.: Adaptive optimization for petascale heterogeneous CPU\/GPU computing. In: Cluster 2010, pp. 19\u201328 (2010)","DOI":"10.1109\/CLUSTER.2010.12"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Rychkov, V., Lastovetsky, A.: Data partitioning on heterogeneous multicore platforms. In: Cluster 2011, pp. 580\u2013584 (2011)","DOI":"10.1109\/CLUSTER.2011.64"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Rychkov, V., Lastovetsky, A.: Data partitioning on heterogeneous multicore and multi-GPU systems using functional performance models of data-parallel applications. In: Cluster 2012, pp. 191\u2013199 (2012)","DOI":"10.1109\/CLUSTER.2012.34"}],"container-title":["Lecture Notes in Computer Science","Parallel Computing Technologies"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-39958-9_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,17]],"date-time":"2019-05-17T13:25:33Z","timestamp":1558099533000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-39958-9_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642399572","9783642399589"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-39958-9_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}