{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T20:48:25Z","timestamp":1648586905322},"reference-count":26,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Performance and power consumption analysis and characterization for computational benchmarks is important for processor designers and benchmark developers. In this paper, we characterize and analyze different High Performance Computing workloads. We analyze benchmarks characteristics and behavior on various processors and propose a performance estimation analytical model to predict performance for different processor microarchitecture parameters. Performance model is verified to predict performance within &lt;5% error margin between estimated and measured data for different processors. We also propose a power estimation analytical model to estimate power consumption with low error deviation.<\/jats:p>","DOI":"10.2478\/s13537-013-0101-5","type":"journal-article","created":{"date-parts":[[2013,4,1]],"date-time":"2013-04-01T03:16:43Z","timestamp":1364786203000},"page":"1-16","source":"Crossref","is-referenced-by-count":0,"title":["Performance and power analysis for high performance computation benchmarks"],"prefix":"10.2478","volume":"3","author":[{"given":"Joseph","family":"Issa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"374","reference":[{"key":"101_CR1","unstructured":"AMD K10- http:\/\/www.xbitlabs.com\/articles\/cpu\/display\/amd-k10.html"},{"key":"101_CR2","unstructured":"AMD Opteron-K8: http:\/\/www.cpu-world.com\/CPUs\/K8\/index.html"},{"key":"101_CR3","doi-asserted-by":"crossref","unstructured":"Baghsorkhi S., Delahaye M., Patel S., Gropp W., Hwu W., An adaptive performance modeling tool for GPU architectures, In: Proceedings of ACM PPOPP, 105\u2013114, 2010","DOI":"10.1145\/1837853.1693470"},{"key":"101_CR4","doi-asserted-by":"crossref","unstructured":"Bhatai N., Alam S., Performance modeling of emerging HPC architectures, HPCMP Users Group Conference, June 2006","DOI":"10.1109\/HPCMP-UGC.2006.58"},{"key":"101_CR5","unstructured":"BLAS: http:\/\/www.netlib.org\/blas\/"},{"key":"101_CR6","doi-asserted-by":"crossref","unstructured":"Chau-Yi Chou, A semi-empirical model for maximal LINPACK performance predictions\u201d, 6th IEEE International Symposium on Cluster Computing and the Grid, 30 May 2006","DOI":"10.1109\/CCGRID.2006.10"},{"key":"101_CR7","doi-asserted-by":"crossref","unstructured":"Goel et al., Portable, scalable, per-core power estimation for intelligent resource management, Int. Green Computing Conference, 2010","DOI":"10.1109\/GREENCOMP.2010.5598313"},{"key":"101_CR8","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1023\/A:1008013204871","volume":"13","author":"J. Gustafon","year":"1999","unstructured":"Gustafon J., Todi R., Conventional Benchmarks as a sample of the Performance Spectrum, J. Super Comput., 13, 321\u2013342, 1999","journal-title":"J. Super Comput."},{"key":"101_CR9","unstructured":"Hennessy J.L., Patterson D.A, Computer Architecture: A Quantitative Approach (4th Ed., Morgan Kaufmann, 2007)"},{"key":"101_CR10","unstructured":"http:\/\/www.nvidia.com\/content\/GTC\/documents\/SC09_Dongarra.pdf"},{"key":"101_CR11","doi-asserted-by":"crossref","unstructured":"Isci et al., Live, runtime phase monitoring and prediction on real systems with application to dynamic power management, Int. Symposium on Microarchitecture, 2006","DOI":"10.1109\/MICRO.2006.30"},{"key":"101_CR12","unstructured":"Jens S., Performance Prediction on Benchmak Programs for Massively parallel Architectures, 10th Internaltion conference of High-Performance Computer (HPCS), June 1996"},{"key":"101_CR13","doi-asserted-by":"crossref","unstructured":"Kamil S., Power efficiency for high performance computing, IEEE International Symposium on Parallel and Distributed processing, June 2008","DOI":"10.1109\/IPDPS.2008.4536223"},{"key":"101_CR14","unstructured":"LINPACK: http:\/\/www.top500.org\/project\/linpack\/"},{"key":"101_CR15","unstructured":"Livny M., Basney J., Raman R., Tannenbaum T., Mechanisms for High Throughput Computing, SPEEDUP J., 1997"},{"key":"101_CR16","unstructured":"Nvidia GTX460 http:\/\/www.nvidia.com\/object\/product-geforce-gtx-460-us.html"},{"key":"101_CR17","unstructured":"Nvidia GTX570 http:\/\/www.nvidia.com\/object\/product-geforce-gtx-570-us.html"},{"key":"101_CR18","unstructured":"Nvidia GTX580 http:\/\/www.nvidia.com\/object\/product-geforce-gtx-580-us.html"},{"key":"101_CR19","unstructured":"Nvidia nTune utility http:\/\/www.nvidia.com\/object\/ntune_2.00.23.html"},{"key":"101_CR20","unstructured":"Nvidia Tesla C2070 http:\/\/www.nvidia.com\/object\/personal-supercomputing.html"},{"key":"101_CR21","doi-asserted-by":"crossref","unstructured":"Rafael Saavedra H., Smith A.J., Analysis of benchmark characteristics and benchmark performance prediction, ACM Transactions on Comput. Syst., 14, 1996","DOI":"10.1145\/235543.235545"},{"key":"101_CR22","doi-asserted-by":"crossref","unstructured":"Rohr D. et al., Multi-GPU DGEMM and High Performance LINPACK on Highly Energy-Efficient Clusters, IEEE Micro, September 2011","DOI":"10.1109\/MM.2011.66"},{"key":"101_CR23","doi-asserted-by":"crossref","unstructured":"Ryoo S., Rodrigues C.I, Baghsorkhi S.S., Stone S.S., Kirk D.B., Hwu W.W., Optimization Principles and Application Performance Evaluation of a Multithreaded GPU using CUDA, In: Proceedings of the 13th ACM SIGPLAN, 73C82, ACM Press, 2008","DOI":"10.1145\/1345206.1345220"},{"key":"101_CR24","unstructured":"SGEMM: http:\/\/keeneland.gatech.edu\/software\/sgemm_tutorial"},{"key":"101_CR25","doi-asserted-by":"crossref","unstructured":"Snavely A. et al., A Framework for Application Performance Modeling and Prediction, ACM\/IEEE Supercomputing Conference, 2002","DOI":"10.1109\/SC.2002.10004"},{"key":"101_CR26","doi-asserted-by":"crossref","unstructured":"Volkov V., Demmel J.W., Benchmarking GPUs to Tune Dense Linear Algebra SC08, November 2008","DOI":"10.1109\/SC.2008.5214359"}],"container-title":["Open Computer Science"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.2478\/s13537-013-0101-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.2478\/s13537-013-0101-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.2478\/s13537-013-0101-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,28]],"date-time":"2021-02-28T16:19:23Z","timestamp":1614529163000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.2478\/s13537-013-0101-5\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,1,1]]},"references-count":26,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.2478\/s13537-013-0101-5","relation":{},"ISSN":["2299-1093"],"issn-type":[{"value":"2299-1093","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,1,1]]}}}