{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T09:31:03Z","timestamp":1753522263697},"reference-count":18,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2013,8,24]],"date-time":"2013-08-24T00:00:00Z","timestamp":1377302400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2014,8]]},"DOI":"10.1007\/s10766-013-0265-6","type":"journal-article","created":{"date-parts":[[2013,8,23]],"date-time":"2013-08-23T12:38:43Z","timestamp":1377261523000},"page":"601-618","source":"Crossref","is-referenced-by-count":7,"title":["Introducing and Implementing the Allpairs Skeleton for Programming Multi-GPU Systems"],"prefix":"10.1007","volume":"42","author":[{"given":"Michel","family":"Steuwer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Malte","family":"Friese","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastian","family":"Albers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergei","family":"Gorlatch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,8,24]]},"reference":[{"key":"265_CR1","unstructured":"AMD.: Accelerated Parallel Processing Math Libraries (APPML). http:\/\/developer.amd.com\/tools\/heterogeneous-computing\/amd-accelerated-parallel-processing-math-libraries\/ (2013)"},{"key":"265_CR2","doi-asserted-by":"crossref","unstructured":"Arora, N., Shringarpure, A., Vuduc, R.: Direct N-body Kernels for multicore platforms. In: Proceedings of ICPP\u201909, IEEE, pp. 379\u2013387 (2009)","DOI":"10.1109\/ICPP.2009.71"},{"key":"265_CR3","doi-asserted-by":"crossref","unstructured":"Chang, D., Desoky, A., Ouyang, M., Rouchka, E.: Compute pairwise Manhattan distance and Pearson correlation coefficient of data points with GPU. In: Proceedings of SNPD\u201909, IEEE, pp. 501\u2013506 (2009)","DOI":"10.1109\/SNPD.2009.34"},{"issue":"3","key":"265_CR4","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/j.parco.2003.12.002","volume":"30","author":"M Cole","year":"2004","unstructured":"Cole, M.: Bringing skeletons out of the closet: a pragmatic manifesto for skeletal parallel programming. Parallel Comput. 30(3), 389\u2013406 (2004)","journal-title":"Parallel Comput."},{"issue":"1","key":"265_CR5","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1186\/1471-2105-5-118","volume":"5","author":"C Daub","year":"2004","unstructured":"Daub, C., Steuer, R., Selbig, J., Kloska, S.: Estimating mutual information using B-spline functions\u2014an improved similarity measure for analysing gene expression data. BMC Bioinform. 5(1), 118 (2004)","journal-title":"BMC Bioinform."},{"key":"265_CR6","doi-asserted-by":"crossref","unstructured":"Enmyren, J., Kessler, C.: SkePU: a multi-backend skeleton programming library for multi-GPU systems. In: Proceedings 4th international workshop on high-level parallel programming and applications, ACM, pp. 5\u201314 (2010)","DOI":"10.1145\/1863482.1863487"},{"issue":"2","key":"265_CR7","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1504\/IJHPCN.2012.046370","volume":"7","author":"S Ernsting","year":"2012","unstructured":"Ernsting, S., Kuchen, H.: Algorithmic skeletons for multi-core, multi-GPU systems and clusters. Int. J. High Perform. Comput. Netw. 7(2), 129\u2013138 (2012)","journal-title":"Int. J. High Perform. Comput. Netw."},{"issue":"12","key":"265_CR8","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1002\/spe.1026","volume":"40","author":"H Gonz\u00e1lez-V\u00e9lez","year":"2010","unstructured":"Gonz\u00e1lez-V\u00e9lez, H., Leyton, M.: A survey of algorithmic skeleton frameworks: high-level structured parallel programming enablers. Softw. Pract. Exp. 40(12), 1135\u20131160 (2010)","journal-title":"Softw. Pract. Exp."},{"key":"265_CR9","first-page":"1417","volume-title":"Encyclopedia of Parallel Computing","author":"S Gorlatch","year":"2011","unstructured":"Gorlatch, S., Cole, M.: Parallel Skeletons. In: Padua, D. (ed.) Encyclopedia of Parallel Computing, pp. 1417\u20131422. Springer, Berlin (2011)"},{"key":"265_CR10","unstructured":"Hoberock, J., Bell, N.: Thrust: A Parallel Template Library. https:\/\/developer.nvidia.com\/thrust (2009)"},{"key":"265_CR11","volume-title":"Programming Massively Parallel Processors\u2014A Hands-on Approach","author":"DB Kirk","year":"2010","unstructured":"Kirk, D.B., Hwu, W.W.: Programming Massively Parallel Processors\u2014A Hands-on Approach. Morgan Kaufman, Burlington (2010)"},{"issue":"3","key":"265_CR12","first-page":"208","volume":"68","author":"R L\u00e4mmel","year":"2007","unstructured":"L\u00e4mmel, R.: Google\u2019s MapReduce programming model\u2014revisited. Sci. Comput. Program. 68(3), 208\u2013237 (2007)","journal-title":"Sci. Comput. Program."},{"key":"265_CR13","unstructured":"Munshi, A.: The OpenCL Specification. Version 1.2. Khronos OpenCL Working Group, Beaverton, Oregon (2011)"},{"key":"265_CR14","unstructured":"NVIDIA.: NVIDIA CUDA C Programming Guide. http:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide Version 5.0 (2012)"},{"key":"265_CR15","unstructured":"NVIDIA.: CUBLAS. http:\/\/developer.nvidia.com\/cublas (2013)"},{"issue":"2","key":"265_CR16","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.parco.2013.01.002","volume":"39","author":"A Sarje","year":"2013","unstructured":"Sarje, A., Aluru, S.: All-pairs computations on many-core graphics processors. Parallel Comput. 39(2), 79\u201393 (2013)","journal-title":"Parallel Comput."},{"key":"265_CR17","doi-asserted-by":"crossref","unstructured":"Steuwer, M., Kegel, P., Gorlatch, S.: Towards high-level programming of multi-GPU systems using the SkelCL library. In: 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops & PhD Forum (IPDPSW), IEEE, pp. 1858\u20131865 (2012)","DOI":"10.1109\/IPDPSW.2012.229"},{"key":"265_CR18","doi-asserted-by":"crossref","unstructured":"Wirawan, A., Schmidt, B., Kwoh. C.K.: Pairwise distance matrix computation for multiple sequence alignment on the cell broadband engine. In: Proceedings of ICCS\u201909, Springer, pp. 954\u2013963 (2009)","DOI":"10.1007\/978-3-642-01970-8_96"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-013-0265-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-013-0265-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-013-0265-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,21]],"date-time":"2019-07-21T19:54:28Z","timestamp":1563738868000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-013-0265-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8,24]]},"references-count":18,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2014,8]]}},"alternative-id":["265"],"URL":"https:\/\/doi.org\/10.1007\/s10766-013-0265-6","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,8,24]]}}}