{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T14:57:39Z","timestamp":1776956259978,"version":"3.51.4"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001602","name":"Science Foundation Ireland (SFI)","doi-asserted-by":"publisher","award":["14\/IA\/2474"],"award-info":[{"award-number":["14\/IA\/2474"]}],"id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2017,4,1]]},"DOI":"10.1109\/tpds.2016.2608824","type":"journal-article","created":{"date-parts":[[2016,9,13]],"date-time":"2016-09-13T14:12:47Z","timestamp":1473775967000},"page":"1119-1133","source":"Crossref","is-referenced-by-count":48,"title":["New Model-Based Methods and Algorithms for Performance and Energy Optimization of Data Parallel Applications on Homogeneous Multicore Clusters"],"prefix":"10.1109","volume":"28","author":[{"given":"Alexey","family":"Lastovetsky","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ravi","family":"Reddy Manumachu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"3","article-title":"A comparison of high-level full-system power models","author":"rivoire","year":"2008","journal-title":"Proc Conf Power Aware Comput Syst"},{"key":"ref32","article-title":"Model-based optimization of MPDATA on Intel Xeon Phi through load imbalancing","author":"lastovetsky","year":"2015","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.2000.1686"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/71.963416"},{"key":"ref36","article-title":"Parallel FFTW","year":"2016"},{"key":"ref35","article-title":"A survey of power and energy predictive models in HPC systems and applications","author":"o'brien","year":"2016","journal-title":"Submitted to ACM Computing Surveys"},{"key":"ref34","first-page":"12","article-title":"Evaluating the effectiveness of model-based power characterization","author":"mccullough","year":"2011","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref10","first-page":"202","article-title":"High-performance computing on heterogeneous systems: Database queries on CPU and GPU","volume":"20","author":"ili?","year":"2010","journal-title":"High Perform Scientific Comput Special Emphasis Current Capabilities Future Perspectives"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626411000163"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2015.08.002"},{"key":"ref13","first-page":"417","article-title":"Efficient computation of Galois field expressions on hybrid CPU-GPU platforms.","volume":"26","author":"radmanovi?","year":"2016","journal-title":"J Multiple-Valued Logic Soft Comput"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2012.101"},{"key":"ref15","first-page":"693","article-title":"Transparent application acceleration by intelligent scheduling of shared library calls on heterogeneous systems","author":"cola\u00e7o","year":"2013","journal-title":"Parallel Processing and Applied Mathematics"},{"key":"ref16","first-page":"203","article-title":"Heterogeneous sparse matrix computations on hybrid GPU\/CPU platforms","author":"cardellini","year":"2013","journal-title":"Proc Int Conf Parallel Comp"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2014.2375202"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2608824"},{"key":"ref19","first-page":"1","article-title":"An efficient, model-based CPU-GPU heterogeneous FFT library","author":"ogata","year":"2008","journal-title":"Proc IEEE Int Symp Parallel Distrib Process"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-009-0350-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006074864"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-007-0148-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2004.1303051"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2007.06.001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/40.6.356"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-24049-7_3"},{"key":"ref8","article-title":"OpenBLAS: An optimized BLAS library","year":"2016"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1007\/978-3-642-29737-3_50","article-title":"Column-based matrix partitioning for parallel matrix multiplication on heterogeneous processors based on functional performance models","author":"clarke","year":"2012","journal-title":"Proc Euro-Par 2011 Parallel Processing Workshops"},{"key":"ref2","article-title":"Hypertransport","year":"2001"},{"key":"ref9","article-title":"FFTW: A fast, free c FFT library","year":"2016"},{"key":"ref1","article-title":"Intel quickpath interconnect","year":"2008"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2010.12"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1145\/1594835.1504196","article-title":"Solving dense linear systems on platforms with multiple hardware accelerators","volume":"44","author":"quintana-ort\u00ed","year":"2009","journal-title":"SIGPLAN Not"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1145\/1353535.1346318","article-title":"Merge: A programming model for heterogeneous multi-core systems","volume":"42","author":"linderman","year":"2008","journal-title":"ACM SIGOPS Operating Syst Rev"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0743-7315(89)90021-X"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14122-5_9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2004.10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2005.45"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/7875386\/07565748.pdf?arnumber=7565748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:42:53Z","timestamp":1641987773000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7565748\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,1]]},"references-count":36,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2016.2608824","relation":{},"ISSN":["1045-9219"],"issn-type":[{"value":"1045-9219","type":"print"}],"subject":[],"published":{"date-parts":[[2017,4,1]]}}}