{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T09:01:23Z","timestamp":1758704483728,"version":"3.41.0"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["The Computer Journal"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1093\/comjnl\/bxv022","type":"journal-article","created":{"date-parts":[[2015,4,11]],"date-time":"2015-04-11T00:26:40Z","timestamp":1428712000000},"page":"3279-3294","source":"Crossref","is-referenced-by-count":8,"title":["Realistic Performance Characterization of CFD Applications on Intel Many Integrated Core Architecture"],"prefix":"10.1093","volume":"58","author":[{"given":"Yonggang","family":"Che","sequence":"first","affiliation":[]},{"given":"Chuanfu","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Jianbin","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Yongxian","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhenghua","family":"Wang","sequence":"additional","affiliation":[]}],"member":"286","published-online":{"date-parts":[[2015,4,9]]},"reference":[{"key":"2015113003322746000_58.12.3279.1","unstructured":"Intel Corporation. Many Integrated Core (MIC) Architecture. http:\/\/www.intel.com\/content\/www\/us\/en\/architecture-and-technology\/many-integrated-core\/intel-many-integrated-core-architecture.html (accessed December 20, 2012)."},{"key":"2015113003322746000_58.12.3279.2","unstructured":"Reference Number: 328209-001EN (2012) Intel Xeon Phi Coprocessor Datasheet. Intel Corporation, Santa Clara, CA, USA."},{"key":"2015113003322746000_58.12.3279.3","unstructured":"Jim J. James R. (2013) Intel Xeon Phi Coprocessor High Performance Programming. Morgan Kaufmann Press, Waltham, MA, USA."},{"key":"2015113003322746000_58.12.3279.4","unstructured":"Intel Corporation. An overview of programming for Intel Xeon processors and Intel Xeon Phi coprocessors. http:\/\/download.intel.com\/newsroom\/kits\/xeon\/phi\/pdfs\/overview-programming-intel-xeon-intel-xeon-phi-coprocessors.pdf (accessed June 21, 2013)."},{"key":"2015113003322746000_58.12.3279.5","unstructured":"http:\/\/www.top500.org\/ (accessed December 16, 2013)."},{"key":"2015113003322746000_58.12.3279.6","unstructured":"http:\/\/www.intel.com\/software\/products\/vtune\/ (accessed July 29, 2013)."},{"key":"2015113003322746000_58.12.3279.7","doi-asserted-by":"publisher","DOI":"10.1145\/1964218.1964223"},{"key":"2015113003322746000_58.12.3279.8","doi-asserted-by":"crossref","unstructured":"Andres E. Widhalm M. Caloto A. (2009) Achieving High Speed CFD Simulations: Optimization, Parallelization, and FPGA Acceleration for the Unstructured DLR TAU Code. Proc. 47th AIAA Aerospace Sciences Meeting Including The New Horizons Forum and Aerospace Exposition, Orlando, FL, January 5\u20138, pp. 8745\u20138764. AIAA, VA, USA.","DOI":"10.2514\/6.2009-759"},{"key":"2015113003322746000_58.12.3279.9","doi-asserted-by":"crossref","unstructured":"Anderson W.K. Gropp W.D. Kaushik D.K. Keyes D.E. Smith B.F. (1999) Achieving High Sustained Performance in an Unstructured Mesh CFD Application. Proc. 1999 ACM\/IEEE Conf. on Supercomputing, Portland, OR, USA, November 13\u201318, p. 69. ACM, New York, USA.","DOI":"10.1145\/331532.331600"},{"key":"2015113003322746000_58.12.3279.10","unstructured":"Gropp W.D. Kaushik D.K. Keyes D.E. Smith B.F (1999) Towards Realistic Performance Bounds for Implicit CFD Codes. Proc. Parallel CFD\u201999, Williamsburg, VA, USA, May 23\u201326, pp. 233\u2013240. Elsevier, PA, USA."},{"key":"2015113003322746000_58.12.3279.11","unstructured":"Mavriplis D.J. (2002) Parallel performance investigations of an unstructured mesh Navier\u2013Stokes solver. Int. J. High Perform. Comput. Appl., 16, 395\u2013407."},{"key":"2015113003322746000_58.12.3279.12","doi-asserted-by":"crossref","unstructured":"Camelli F.E. Lohner R. Cebral J.C. Mestreau E.L. (2008) Timings of an Unstructured-grid CFD Code on Common Hardware Platforms and Compilers. Proc. 46th AIAA Aerospace Sciences Meeting and Exhibition, Reno, NV, USA, January 7\u201310, pp. CD-ROM 1-16. AIAA, VA, USA.","DOI":"10.2514\/6.2008-477"},{"key":"2015113003322746000_58.12.3279.13","doi-asserted-by":"crossref","unstructured":"Aftosmis M. Berger M. Biswas R. Djomehri M.J. Hood R. Jin H. Kiris C. (2006) A Detailed Performance Characterization of Columbia Using Aeronautics Benchmarks and Applications. Proc. 44th AIAA Aerospace Sciences Meeting, Reno, NV, USA, January 9\u201312, pp. 1084\u20131100. AIAA, VA, USA.","DOI":"10.2514\/6.2006-84"},{"key":"2015113003322746000_58.12.3279.14","unstructured":"Gerhold T. J\u00e4gersk\u00fcpper J. Brandfass B. Lettich P. (2011) Preparing TAU for Many-Cores. Onera Scientific Days, Chatillon, France, October 7."},{"key":"2015113003322746000_58.12.3279.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2012.05.005"},{"key":"2015113003322746000_58.12.3279.16","unstructured":"Schulz K.W. Ulerich R. Malaya N. Bauman P.T. Stogner R. Simmons C. (2012) Early experiences porting scientific applications to the Many Integrated Core (MIC) platform. http:\/\/users.ices.utexas.edu\/rhys\/papers\/Schulz%20PS2c (accessed January 20, 2013)."},{"key":"2015113003322746000_58.12.3279.17","unstructured":"Brook R.G. Hadri B. Betro V.C. Hulguin R.C. Braby R. (2012) Early Application Experiences with the Intel MIC Architecture in a Cray CX1. Proc. Cray User Group Meeting, Stuttgart, Germany, April 29\u2013May 3, p. 194. Cray User Group, TN, USA."},{"key":"2015113003322746000_58.12.3279.18","unstructured":"http:\/\/www.nas.nasa.gov\/Software\/NPB (accessed September 12, 2012)."},{"key":"2015113003322746000_58.12.3279.19","unstructured":"2003) NAS Parallel Benchmarks, Multi-zone Versions. NASA Advanced Supercomputing Division, NASA Ames Research Center, CA, USA."},{"key":"2015113003322746000_58.12.3279.20","doi-asserted-by":"crossref","unstructured":"Beam R.M. Warming R.F. (1976) An implicit factored scheme for the compressible Navier\u2013Stokes equations. AIAA J., 16, 393\u2013401.","DOI":"10.2514\/3.60901"},{"key":"2015113003322746000_58.12.3279.21","doi-asserted-by":"crossref","unstructured":"Deng X. Zhuang F. Mao M. (1999) On Low Mach Number Perfect Gas Flow Calculations. Proc. 14th AIAA Computational Fluid Dynamics Conf., Norfolk, VA, USA, June 28\u2013July 1, pp. 595\u2013604. AIAA, VA, USA.","DOI":"10.2514\/6.1999-3317"},{"key":"2015113003322746000_58.12.3279.22","unstructured":"Xiang D. Deng X. Mao M. (2002) Study on a novel method for low Mach number flows computation. Acta Aerodynamica Sinica, 20, 373\u2013378 (In Chinese with English abstract)."},{"key":"2015113003322746000_58.12.3279.23","unstructured":"Che Y. Zhang L. Xu C. Wang Y. Liu W. Wang Z. (2014) Optimization of a parallel CFD code and its performance evaluation on Tianhe-1A. Comput. Inf. (to appear)."},{"key":"2015113003322746000_58.12.3279.24","doi-asserted-by":"publisher","DOI":"10.1006\/jcph.2000.6594"},{"key":"2015113003322746000_58.12.3279.25","doi-asserted-by":"publisher","DOI":"10.2514\/1.J050285"},{"key":"2015113003322746000_58.12.3279.26","unstructured":"Che Y. Zhang L. Wang Y. Xu C. Liu W. Wang Z. Liu H. (2012) Uniprocessor Performance Tuning of a Structured Grid-based Parallel CFD Application. Proc. Annual Conf. on High Performance Computing of China, Zhangjiajie, China, October 29\u201331, pp. 39\u201346. CCF TCHPC, Beijing, China (in Chinese with English abstract)."},{"key":"2015113003322746000_58.12.3279.27","doi-asserted-by":"crossref","unstructured":"Che Y. Zhang L. Wang Y. Xu C. Liu W. Cheng X. (2014) Performance Optimization of a CFD Application on Intel Multicore and Manycore Architectures. Proc. 2014 Annual Conf. on Advanced Computer Architecture (Springer CCIS 451), Shenyang, China, August 23\u201324, pp. 83\u201397. Springer, Berlin, Germany.","DOI":"10.1007\/978-3-662-44491-7_7"},{"key":"2015113003322746000_58.12.3279.28","unstructured":"Serdjuk N. Enabling huge paging on MIC with libhugetlbfs library. https:\/\/software.intel.com\/sites\/default\/files\/managed\/c9\/01\/1.2.3-large-page-considerations.pdf (accessed March 10, 2013)."},{"key":"2015113003322746000_58.12.3279.29","unstructured":"SKU# 328207-003EN (2012) Intel Xeon Phi Coprocessor System Software Development Guide. Intel Corporation, Santa Clara, CA, USA."},{"key":"2015113003322746000_58.12.3279.30","unstructured":"Cramer T. Schmidl D. Klemmy M. Mey D.A. (2012) OpenMP Programming on Intel Xeon Phi Coprocessors: An Early Performance Comparison. Proc. Many-Core Applications Research Community Symposium, Aachen, Germany, November 29\u201330, pp. 38\u201344. RWTH Aachen University, Aachen, Germany."},{"key":"2015113003322746000_58.12.3279.31","unstructured":"https:\/\/www.khronos.org\/opencl\/ (accessed October 1, 2014)."},{"key":"2015113003322746000_58.12.3279.32","doi-asserted-by":"crossref","unstructured":"Seo S. Jo G. Lee J. (2012) Performance Characterization of the NAS Parallel Benchmarks in OpenCL. 2011 IEEE Int. Symposium on Workload Characterization, Austin, TX, USA, November 6\u20138, pp. 137\u2013148. IEEE Computer Society Washington, DC, USA.","DOI":"10.1109\/IISWC.2011.6114174"},{"key":"2015113003322746000_58.12.3279.33","doi-asserted-by":"crossref","unstructured":"Document Number: 327357-001 (2012) Intel Xeon Phi Coprocessor (Codename: Knights Corner) Performance Monitoring Units (Revision 1.01). Intel Corporation, Santa Clara, CA, USA.","DOI":"10.1109\/HOTCHIPS.2012.7476487"},{"key":"2015113003322746000_58.12.3279.34","unstructured":"Shannon C. (2012) Optimization and performance tuning for Intel Xeon Phi Coprocessors, Part 2: understanding and using hardware events. https: \/\/software.intel.com\/en-us\/articles\/optimization-and-performance-tuning-for-intel-xeon-phi-copro-cessors-part-2-understanding (accessed May 20, 2013)."},{"key":"2015113003322746000_58.12.3279.35","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"2015113003322746000_58.12.3279.36","unstructured":"McCalpin J. (0000) STREAM: sustainable memory bandwidth with high performance computers. http:\/\/www.cs.virginia.edu\/stream\/ (accessed January 20, 2013)."}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/comjnl\/article-pdf\/58\/12\/3279\/1023647\/bxv022.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T07:03:20Z","timestamp":1747897400000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article-lookup\/doi\/10.1093\/comjnl\/bxv022"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4,9]]},"references-count":36,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2015,11,26]]},"published-print":{"date-parts":[[2015,12]]}},"alternative-id":["10.1093\/comjnl\/bxv022"],"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxv022","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"type":"print","value":"0010-4620"},{"type":"electronic","value":"1460-2067"}],"subject":[],"published":{"date-parts":[[2015,4,9]]}}}