{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:09:42Z","timestamp":1778170182654,"version":"3.51.4"},"reference-count":129,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2019,6,8]],"date-time":"2019-06-08T00:00:00Z","timestamp":1559952000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,6,8]],"date-time":"2019-06-08T00:00:00Z","timestamp":1559952000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1007\/s11227-019-02911-9","type":"journal-article","created":{"date-parts":[[2019,6,8]],"date-time":"2019-06-08T09:02:22Z","timestamp":1559984542000},"page":"7003-7036","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["The survey on ARM processors for HPC"],"prefix":"10.1007","volume":"75","author":[{"given":"Daniel","family":"Yokoyama","sequence":"first","affiliation":[]},{"given":"Bruno","family":"Schulze","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5159-9517","authenticated-orcid":false,"given":"F\u00e1bio","family":"Borges","sequence":"additional","affiliation":[]},{"given":"Giacomo","family":"Mc Evoy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,8]]},"reference":[{"key":"2911_CR1","unstructured":"HPC Case Study: CFD Applications on ARM. https:\/\/developer.arm.com\/-\/media\/developer\/products\/software-tools\/hpc\/Documentation\/UCAMB_Arm_CFDvFinal.pdf . Accessed 24 Apr 2019"},{"key":"2911_CR2","unstructured":"Linaro releases. https:\/\/releases.linaro.org\/components\/toolchain\/gcc-linaro . Accessed 5 May 2019"},{"key":"2911_CR3","unstructured":"Viso geral sobre intel advanced vector extensions 512. https:\/\/www.intel.com.br\/content\/www\/br\/pt\/architecture-and-technology\/avx-512-overview.html . Accessed 22 Sept 2017"},{"key":"2911_CR4","unstructured":"Linaro. https:\/\/www.linaro.org\/ . Accessed 5 May 2019"},{"key":"2911_CR5","unstructured":"Openhpc releases (2019). https:\/\/github.com\/openhpc\/ohpc\/releases\/ . Accessed 5 May 2019"},{"issue":"1","key":"2911_CR6","doi-asserted-by":"publisher","first-page":"012033","DOI":"10.1088\/1742-6596\/608\/1\/012033","volume":"608","author":"D Abdurachmanov","year":"2015","unstructured":"Abdurachmanov D, Bockelman B, Elmer P, Eulisse G, Knight R, Muzaffar S (2015) Heterogeneous high throughput scientific computing with apm x-gene and intel xeon phi. J Phys Conf Ser 608(1):012033","journal-title":"J Phys Conf Ser"},{"key":"2911_CR7","doi-asserted-by":"publisher","first-page":"012032","DOI":"10.1088\/1742-6596\/608\/1\/012032","volume":"608","author":"D Abdurachmanov","year":"2015","unstructured":"Abdurachmanov D, Elmer P, Eulisse G, Knight R, Niemi T, Nurminen JK, Nyback F, Pestana G, Ou Z, Khan K (2015) Techniques and tools for measuring energy efficiency of scientific software applications. J Phys Conf Ser 608:012032","journal-title":"J Phys Conf Ser"},{"issue":"1","key":"2911_CR8","doi-asserted-by":"publisher","first-page":"012009","DOI":"10.1088\/1742-6596\/523\/1\/012009","volume":"523","author":"D Abdurachmanov","year":"2014","unstructured":"Abdurachmanov D, Elmer P, Eulisse G, Muzaffar S (2014) Initial explorations of arm processors for scientific computing. J Phys Conf Ser 523(1):012009","journal-title":"J Phys Conf Ser"},{"key":"2911_CR9","unstructured":"Addiego N (2017) Evaluation of the efficiency of an ARM-based beowulf cluster versus traditional desktop computing for high performance computing. Master\u2019s thesis, University of San Diego"},{"issue":"6","key":"2911_CR10","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1002\/cpe.1553","volume":"22","author":"L Adhianto","year":"2010","unstructured":"Adhianto L, Banerjee S, Fagan M, Krentel M, Marin G, Mellor-Crummey J, Tallent NR (2010) Hpctoolkit: tools for performance analysis of optimized parallel programs. Concurr Comput Pract Exp 22(6):685\u2013701","journal-title":"Concurr Comput Pract Exp"},{"key":"2911_CR11","unstructured":"Allalen M, Brayford D, Tafani D, Weinberg V, Mohr B, Br\u00f6mmel D, Halver R, Meinke J, Mohanty S (2015) The mont-blanc project: First phase successfully finished. arXiv preprint arXiv:1508.05075"},{"key":"2911_CR12","unstructured":"ARM: ARM Architecture Reference Manual\u2014ARMv7-A and ARMv7-R edition. https:\/\/static.docs.arm.com\/ddi0406\/c\/DDI0406C_C_arm_architecture_reference_manual.pdf (2014). Accessed 24 Apr 2019"},{"key":"2911_CR13","doi-asserted-by":"publisher","unstructured":"Armejach A, Caminal H, Cebrian JM, Langarita R, Gonz\u00e1lez-Alberquilla R, Adeniyi-Jones C, Valero M, Casas M, Moret\u00f3 M (2019) Using arms scalable vector extension on stencil codes. J Supercomput. https:\/\/doi.org\/10.1007\/s11227-019-02842-5","DOI":"10.1007\/s11227-019-02842-5"},{"issue":"4","key":"2911_CR14","first-page":"18","volume":"3","author":"R Azimi","year":"2018","unstructured":"Azimi R, Fox T, Gonzalez W, Reda S (2018) Scale-out vs scale-up: a study of arm-based socs on server-class workloads. ACM Trans Model Perform Eval Comput Syst (TOMPECS) 3(4):18","journal-title":"ACM Trans Model Perform Eval Comput Syst (TOMPECS)"},{"key":"2911_CR15","doi-asserted-by":"crossref","unstructured":"Azimi R, Zhan X, Reda S (2015) How good are low-power 64-bit socs for server-class workloads? In: 2015 IEEE International Symposium on Workload Characterization (IISWC), IEEE, pp 116\u2013117","DOI":"10.1109\/IISWC.2015.21"},{"key":"2911_CR16","unstructured":"Banchelli F, Garcia M, Josep M, Mantovani F, Morillo J, Peiro K, Ramirez G, Teruel X, Mc\u00a0Evoy G, Wanza J, Gracia J, Lumi A, Ganellari D, Schiffmann P (2019) Mb3 d6.9\u2014performance analysis of applications and mini-applications and benchmarking on the project test platforms. Tech. rep. https:\/\/www.montblanc-project.eu\/wp-content\/uploads\/2019\/02\/MB3_D6.9_Performance-analysis-of-applications-and-benchmarking-on-the-project-test-platforms.v1.0.pdf . Accessed 24 Apr 2019"},{"key":"2911_CR17","unstructured":"Barr J (2018) EC2 Instances (A1) Powered by Arm-Based AWS Graviton Processors. https:\/\/aws.amazon.com\/blogs\/aws\/new-ec2-instances-a1-powered-by-arm-based-aws-graviton-processors . Accessed 24 Apr 2019"},{"issue":"4","key":"2911_CR18","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1177\/1094342014552085","volume":"28","author":"BW Barrett","year":"2014","unstructured":"Barrett BW, Brightwell R, Grant R, Hammond SD, Hemmert KS (2014) An evaluation of mpi message rate on hybrid-core processors. Int J High Perform Comput Appl 28(4):415\u2013424. https:\/\/doi.org\/10.1177\/1094342014552085","journal-title":"Int J High Perform Comput Appl"},{"key":"2911_CR19","doi-asserted-by":"crossref","unstructured":"Beserra D, Pinheiro MK, Souveyet C, Steffenel LA, Moreno ED (2017) Performance evaluation of os-level virtualization solutions for hpc purposes on soc-based systems. In: 2017 IEEE 31st International Conference on Advanced Information Networking and Applications (AINA), IEEE, pp 363\u2013370","DOI":"10.1109\/AINA.2017.73"},{"key":"2911_CR20","doi-asserted-by":"publisher","first-page":"e4014","DOI":"10.1002\/cpe.4014","volume":"29","author":"JL Bez","year":"2016","unstructured":"Bez JL, Bernart EE, Santos FF, Schnorr LM, Navaux POA (2016) Performance and energy efficiency analysis of HPC physics simulation applications in a cluster of arm processors. Pract Exp Concurr Comput 29:e4014","journal-title":"Pract Exp Concurr Comput"},{"key":"2911_CR21","unstructured":"Blem E, Menon J, Sankaralingam K (2013) Power struggles: revisiting the risc vs. cisc debate on contemporary arm and x86 architectures. In: 2013 IEEE 19th International Symposium on High Performance Computer Architecture (HPCA2013), IEEE, pp 1\u201312"},{"issue":"2","key":"2911_CR22","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/MM.2015.12","volume":"35","author":"D Boggs","year":"2015","unstructured":"Boggs D, Brown G, Tuck N, Venkatraman K (2015) Denver: Nvidia\u2019s first 64-bit arm processor. IEEE Micro 35(2):46\u201355","journal-title":"IEEE Micro"},{"key":"2911_CR23","doi-asserted-by":"crossref","unstructured":"Brash D (2010) Extensions to the armv7-a architecture. In: 2010 IEEE Hot Chips 22 Symposium (HCS), IEEE, pp 1\u201321","DOI":"10.1109\/HOTCHIPS.2010.7480070"},{"key":"2911_CR24","unstructured":"Bratt I (2018) Arm\u2019s First Generation Machine Learning Processor. https:\/\/www.hotchips.org\/hc30\/2conf\/2.07_ARM_ML_Processor_HC30_ARM_2018_08_17.pdf . Accessed 24 Apr 2019"},{"issue":"1","key":"2911_CR25","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/JSSC.2010.2079410","volume":"46","author":"D Bull","year":"2011","unstructured":"Bull D, Das S, Shivashankar K, Dasika GS, Flautner K, Blaauw D (2011) A power-efficient 32 bit arm processor using timing-error detection and correction for transient-error tolerance and adaptation to pvt variation. IEEE J Solid-State Circ 46(1):18\u201331","journal-title":"IEEE J Solid-State Circ"},{"key":"2911_CR26","doi-asserted-by":"crossref","unstructured":"Calore E, Mantovani F, Ruiz D (2018) Advanced performance analysis of hpc workloads on cavium thunderx. In: 2018 International Conference on High Performance Computing & Simulation (HPCS), IEEE, pp 375\u2013382","DOI":"10.1109\/HPCS.2018.00068"},{"key":"2911_CR27","doi-asserted-by":"crossref","unstructured":"Canuto M, Bosch R, Macias M, Guitart J (2016) A methodology for full-system power modeling in heterogeneous data centers. In: Proceedings of the 9th International Conference on Utility and Cloud Computing, ACM, pp 20\u201329","DOI":"10.1145\/2996890.2996899"},{"key":"2911_CR28","unstructured":"Castell\u00f3 A, Duato J, Mayo R, Pe\u00f1a AJ, Quintana-Ort\u00ed ES, Roca V, Silla F (2014) On the use of remote gpus and low-power processors for the acceleration of scientific applications. In: The Fourth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies (ENERGY), pp 57\u201362"},{"key":"2911_CR29","doi-asserted-by":"crossref","unstructured":"Choi J, Dukhan M, Liu X, Vuduc R (2014) Algorithmic time, energy, and power on candidate hpc compute building blocks. In: 2014 IEEE 28th International Parallel and Distributed Processing Symposium, IEEE, pp 447\u2013457","DOI":"10.1109\/IPDPS.2014.54"},{"key":"2911_CR30","doi-asserted-by":"crossref","unstructured":"Cloutier MF, Paradis C, Weaver VM (2014) Design and analysis of a 32-bit embedded high-performance cluster optimized for energy and performance. In: Proceedings of the 1st International Workshop on Hardware-Software Co-Design for High Performance Computing, IEEE Press, pp 1\u20138","DOI":"10.1109\/Co-HPC.2014.7"},{"key":"2911_CR31","doi-asserted-by":"crossref","unstructured":"Cong J, Huang M, Wu D, Yu CH (2016) Heterogeneous datacenters: options and opportunities. In: Proceedings of the 53rd Annual Design Automation Conference, ACM, p 16","DOI":"10.1145\/2897937.2905012"},{"key":"2911_CR32","doi-asserted-by":"crossref","unstructured":"Corni E, Morganti L, Morigi MP, Brancaccio R, Bettuzzi M, Levi G, Peccenini E, Cesini D, Ferraro A (2016) X-ray computed tomography applied to objects of cultural heritage: Porting and testing the filtered back-projection reconstruction algorithm on low power systems-on-chip. In: 2016 24th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP), IEEE, pp 369\u2013372","DOI":"10.1109\/PDP.2016.60"},{"key":"2911_CR33","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.future.2019.01.024","volume":"96","author":"D D\u2019Agostino","year":"2019","unstructured":"D\u2019Agostino D, Quarati A, Clematis A, Morganti L, Corni E, Giansanti V, Cesini D, Merelli I (2019) Soc-based computing infrastructures for scientific applications and commercial services: performance and economic evaluations. Future Gener Comput Syst 96:11\u201322","journal-title":"Future Gener Comput Syst"},{"key":"2911_CR34","unstructured":"De\u00a0Gelas J (2017) AppliedMicro\u2019s X-Gene 3 SoC Begins Sampling: A Step in ARM\u2019s 2017 Server Ambitions. https:\/\/www.anandtech.com\/show\/11189\/appliedmicro-x-gene-3-soc-starts-sampling . Accessed 24 Apr 2019"},{"issue":"02","key":"2911_CR35","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1142\/S0129626411000151","volume":"21","author":"A Duran","year":"2011","unstructured":"Duran A, Ayguad\u00e9 E, Badia RM, Labarta J, Martinell L, Martorell X, Planas J (2011) Ompss: a proposal for programming heterogeneous multi-core architectures. Parallel Process Lett 21(02):173\u2013193","journal-title":"Parallel Process Lett"},{"key":"2911_CR36","doi-asserted-by":"crossref","unstructured":"Durand Y, Carpenter PM, Adami S, Bilas A, Dutoit D, Farcy A, Gaydadjiev G, Goodacre J, Katevenis M, Marazakis M et\u00a0al (2014) Euroserver: Energy efficient node for european micro-servers. In: 2014 17th Euromicro Conference on Digital System Design (DSD), IEEE, pp 206\u2013213","DOI":"10.1109\/DSD.2014.15"},{"key":"2911_CR37","unstructured":"Elangovan VK, Badia RM, Parra EA (2012) Ompss-opencl programming model for heterogeneous systems. In: International Workshop on Languages and Compilers for Parallel Computing, Springer, pp 96\u2013111"},{"key":"2911_CR38","unstructured":"Feng W, Scogland T. Green500. https:\/\/www.top500.org\/green500\/ . Accessed 5 May 2019"},{"key":"2911_CR39","doi-asserted-by":"crossref","unstructured":"Ferreron A, Jagtap R, Rusitoru R (2016) Identifying representative regions of parallel hpc applications: a cross-architectural evaluation. In: 2016 IEEE International Symposium on Workload Characterization (IISWC), IEEE, pp 1\u20132","DOI":"10.1109\/IISWC.2016.7581284"},{"key":"2911_CR40","unstructured":"Fialho L, Gracia J, Nigay A, Evoy M (2019) Mb3 d7.13\u2014final report on enhancements to message passing. Tech. rep. https:\/\/www.montblanc-project.eu\/wp-content\/uploads\/2019\/02\/MB3_D7.13_Final-report-on-enhancements-to-message-passing-2.pdf . Accessed 24 Apr 2019"},{"issue":"1","key":"2911_CR41","doi-asserted-by":"publisher","first-page":"151","DOI":"10.2298\/CSIS150228063F","volume":"13","author":"S Filiposka","year":"2016","unstructured":"Filiposka S, Mishev A, Juiz C (2016) Current prospects towards energy-efficient top hpc systems. Comput Sci Inf Syst 13(1):151\u2013171","journal-title":"Comput Sci Inf Syst"},{"key":"2911_CR42","unstructured":"Fox T (2017) Revisiting the case of arm socs in high-performance computing clusters. Ph.D. thesis, School of Engineering, Brown University"},{"key":"2911_CR43","doi-asserted-by":"crossref","unstructured":"Frid N, Ivo\u0161evi\u0107 D, Sruk V (2015) Heterogeneity impact on mpsoc platforms performance. In: 2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), IEEE, pp 1071\u20131076","DOI":"10.1109\/MIPRO.2015.7160434"},{"key":"2911_CR44","unstructured":"Geveler M, Ribbrock D, Donner D, Ruelmann H, H\u00f6ppke C, Schneider D, Tomaschewski D, Turek S (2016) The icarus white paper: a scalable, energy-efficient, solar-powered hpc center based on low power gpus. In: European Conference on Parallel Processing, Springer, pp 737\u2013749"},{"key":"2911_CR45","doi-asserted-by":"crossref","unstructured":"G\u00f3mez C, Mart\u00ednez F, Armejach A, Moret\u00f3 M, Mantovani F, Casas M (2019) Design space exploration of next-generation HPC machines. Barcelona Supercomputing Center. http:\/\/hdl.handle.net\/2117\/131511","DOI":"10.1109\/IPDPS.2019.00017"},{"issue":"10","key":"2911_CR46","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/MC.2016.308","volume":"49","author":"RE Grant","year":"2016","unstructured":"Grant RE, Levenhagen M, Olivier SL, DeBonis D, Pedretti KT, Laros JH III (2016) Standardizing power monitoring and control at exascale. Computer 49(10):38\u201346","journal-title":"Computer"},{"key":"2911_CR47","doi-asserted-by":"crossref","unstructured":"Grass T, Allande C, Armejach A, Rico A, Ayguad\u00e9 E, Labarta J, Valero M, Casas M, Moreto M (2016) Musa: a multi-level simulation approach for next-generation hpc machines. In: SC16: International Conference for High Performance Computing, Networking, Storage and Analysis, IEEE, pp 526\u2013537","DOI":"10.1109\/SC.2016.44"},{"key":"2911_CR48","doi-asserted-by":"crossref","unstructured":"Grasso I, Radojkovic P, Rajovic N, Gelado I, Ramirez A (2014) Energy efficient hpc on embedded socs: Optimization techniques for mali gpu. In: 2014 IEEE 28th International on Parallel and Distributed Processing Symposium, IEEE, pp 123\u2013132","DOI":"10.1109\/IPDPS.2014.24"},{"key":"2911_CR49","doi-asserted-by":"crossref","unstructured":"Griessl R, Peykanu M, Hagemeyer J, Porrmann M, Krupop S, vor\u00a0dem Berge M, Kiesel T, Christmann W (2014) A scalable server architecture for next-generation heterogeneous compute clusters. In: 2014 12th IEEE International Conference on Embedded and Ubiquitous Computing (EUC), IEEE, pp 146\u2013153","DOI":"10.1109\/EUC.2014.29"},{"issue":"1","key":"2911_CR50","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1504\/IJAMC.2016.079108","volume":"6","author":"B Gu","year":"2016","unstructured":"Gu B, Kwak Y (2016) Map task allocation strategy in an arm-based hadoop cluster by using local storage as split cache. Int J Adv Media Commun 6(1):65\u201372","journal-title":"Int J Adv Media Commun"},{"key":"2911_CR51","unstructured":"Gwennap L (2017) Performance Arms X-Gene 3 for Cloud. https:\/\/www.linleygroup.com\/uploads\/x-gene-3-for-cloud.pdf . Accessed 24 Apr 2019"},{"key":"2911_CR52","doi-asserted-by":"crossref","unstructured":"Halpern M, Zhu Y, Reddi VJ (2016) Mobile cpu\u2019s rise to power: Quantifying the impact of generational mobile cpu design trends on performance, energy, and user satisfaction. In: 2016 IEEE International Symposium on High Performance Computer Architecture (HPCA), IEEE, pp 64\u201376","DOI":"10.1109\/HPCA.2016.7446054"},{"key":"2911_CR53","unstructured":"Huawei (2019)Huawei Unveils Industry\u2019s Highest-Performance ARM-based CPU. https:\/\/www.huawei.com\/en\/press-events\/news\/2019\/1\/huawei-unveils-highest-performance-arm-based-cpu . Accessed 24 Apr 2019"},{"key":"2911_CR54","unstructured":"Iliescu DA, Petrogalli F. Arm scalable vector extension and application to machine learning. Tech. rep., ARM. https:\/\/developer.arm.com\/solutions\/hpc\/resources\/hpc-white-papers\/arm-scalable-vector-extensions-and-application-to-machine-learning . Whitepaper Accessed 24 Apr 2019"},{"key":"2911_CR55","doi-asserted-by":"crossref","unstructured":"Jackson A, Turner A, Weiland M, Johnson N, Perks O, Parsons M (2019) Evaluating the arm ecosystem for high performance computing. arXiv preprint arXiv:1904.04250","DOI":"10.1145\/3324989.3325722"},{"issue":"4","key":"2911_CR56","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1109\/JSSC.2013.2295977","volume":"49","author":"D Jacquet","year":"2014","unstructured":"Jacquet D, Hasbani F, Flatresse P, Wilson R, Arnaud F, Cesana G, Di Gilio T, Lecocq C, Roy T, Chhabra A et al (2014) A 3 ghz dual core processor arm cortex tm-a9 in 28 nm utbb fd-soi cmos with ultra-wide voltage range and energy efficiency optimization. IEEE J Solid-State Circ 49(4):812\u2013826","journal-title":"IEEE J Solid-State Circ"},{"key":"2911_CR57","doi-asserted-by":"crossref","unstructured":"Jarus M, Varrette S, Oleksiak A, Bouvry P (2013) Performance evaluation and energy efficiency of high-density hpc platforms based on intel, amd and arm processors. In: European Conference on Energy Efficiency in Large Scale Distributed Systems, Springer, pp 182\u2013200","DOI":"10.1007\/978-3-642-40517-4_16"},{"key":"2911_CR58","first-page":"109434201666547","volume":"31","author":"C Jin","year":"2016","unstructured":"Jin C, de Supinski BR, Abramson D, Poxon H, DeRose L, Dinh MN, Endrei M, Jessup ER (2016) A survey on software methods to improve the energy efficiency of parallel computing. Int J High Perform Comput Appl 31:1094342016665471","journal-title":"Int J High Perform Comput Appl"},{"key":"2911_CR59","doi-asserted-by":"crossref","unstructured":"Jundt A, Cauble-Chantrenne A, Tiwari A, Peraza J, Laurenzano MA, Carrington L (2015) Compute bottlenecks on the new 64-bit arm. In: Proceedings of the 3rd International Workshop on Energy Efficient Supercomputing, ACM, p 6","DOI":"10.1145\/2834800.2834806"},{"key":"2911_CR60","unstructured":"Jung YW, Sok SW, Santoso GZ, Shin JS, Kim HY (2015) Prototype of light-weight hypervisor for arm server virtualization. In: Proceedings of the International Conference on Embedded Systems and Applications (ESA). The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp), p 36"},{"key":"2911_CR61","doi-asserted-by":"crossref","unstructured":"Kaewkasi C, Srisuruk W (2014) Optimizing performance and power consumption for an arm-based big data cluster. In: TENCON 2014-2014 IEEE Region 10 Conference, IEEE, pp 1\u20136","DOI":"10.1109\/TENCON.2014.7022399"},{"key":"2911_CR62","doi-asserted-by":"crossref","unstructured":"Kaewkasi C, Srisuruk W (2014) A study of big data processing constraints on a low-power hadoop cluster. In: 2014 International Computer Science and Engineering Conference (ICSEC), IEEE, pp 267\u2013272","DOI":"10.1109\/ICSEC.2014.6978206"},{"key":"2911_CR63","unstructured":"Kalyanasundaram J, Simmhan Y (2017) Arm wrestling with big data: A study of arm64 and x64 servers for data intensive workloads. arXiv preprint arXiv:1701.05996"},{"key":"2911_CR64","doi-asserted-by":"crossref","unstructured":"Kecskemeti G, Hajji W, Tso FP (2017) Modelling low power compute clusters for cloud simulation. In: 2017 25th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP), IEEE, pp 39\u201345","DOI":"10.1109\/PDP.2017.33"},{"key":"2911_CR65","unstructured":"Kennedy P. Intel Atom C2550 Benchmarks - 4 core Avoton tested. https:\/\/www.servethehome.com\/intel-atom-c2550-benchmarks-4-core-avoton-tested . Accessed on 24 Apr 2019"},{"key":"2911_CR66","unstructured":"Kodama Y, Odajima T, Asato A, Sato M (2019) Evaluation of the riken post-k processor simulator. arXiv preprint arXiv:1904.06451"},{"key":"2911_CR67","doi-asserted-by":"crossref","unstructured":"Kumar D, Memon S, Thebo LA (2018) Design, implementation & performance analysis of low cost high performance computing (hpc) clusters. In: 2018 12th International Conference on Signal Processing and Communication Systems (ICSPCS), IEEE, pp 1\u20136","DOI":"10.1109\/ICSPCS.2018.8631769"},{"key":"2911_CR68","doi-asserted-by":"publisher","unstructured":"Laurenzano MA, Tiwari A, Cauble-Chantrenne A, Jundt A, Ward WA, Campbell R, Carrington L (2016) Characterization and bottleneck analysis of a 64-bit armv8 platform. In: 2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp 36\u201345. https:\/\/doi.org\/10.1109\/ISPASS.2016.7482072","DOI":"10.1109\/ISPASS.2016.7482072"},{"key":"2911_CR69","doi-asserted-by":"crossref","unstructured":"Lee Y, Kim S (2015) Empirical characterization of power efficiency for large scale data processing. In: 2015 17th International Conference on Advanced Communication Technology (ICACT), IEEE, pp 787\u2013790","DOI":"10.1109\/ICACT.2015.7224902"},{"issue":"7","key":"2911_CR70","doi-asserted-by":"publisher","first-page":"762","DOI":"10.14778\/2752939.2752945","volume":"8","author":"D Loghin","year":"2015","unstructured":"Loghin D, Tudor BM, Zhang H, Ooi BC, Teo YM (2015) A performance study of big data on small nodes. Proc VLDB Endow 8(7):762\u2013773","journal-title":"Proc VLDB Endow"},{"key":"2911_CR71","doi-asserted-by":"crossref","unstructured":"Lorenzon AF, Cera MC, Beck ACS (2015) On the influence of static power consumption in multicore embedded systems. In: 2015 IEEE International Symposium on Circuits and Systems (ISCAS), IEEE, pp 1374\u20131377","DOI":"10.1109\/ISCAS.2015.7168898"},{"key":"2911_CR72","doi-asserted-by":"crossref","unstructured":"Lorenzon AF, Sartor AL, Cera MC, Beck ACS (2015) Optimized use of parallel programming interfaces in multithreaded embedded architectures. In: 2015 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), IEEE, pp 410\u2013415","DOI":"10.1109\/ISVLSI.2015.85"},{"key":"2911_CR73","unstructured":"Luecke GR, Groth BM, Weeks NT, Kraeva M (2017) Comparing allinea\u2019s and intel\u2019s performance tools for hpc. In: Proceedings of the 25th High Performance Computing Symposium, HPC \u201917, pp. 3:1\u20133:12. Society for Computer Simulation International, San Diego, CA, USA. http:\/\/dl.acm.org\/citation.cfm?id=3108096.3108099"},{"issue":"2","key":"2911_CR74","doi-asserted-by":"publisher","first-page":"13","DOI":"10.3390\/jlpea8020013","volume":"8","author":"F Mantovani","year":"2018","unstructured":"Mantovani F, Calore E (2018) Performance and power analysis of hpc workloads on heterogeneous multi-node clusters. J Low Power Electron Appl 8(2):13","journal-title":"J Low Power Electron Appl"},{"key":"2911_CR75","unstructured":"Mantovani F, Ruiz D, Vilarrubi O, Martorell X, Nieto D, Auweter A, Tafani D, Adeniyi-Jones C, Gloaguen H, Utrera G (2015) D5.11\u2014Final report on porting and tuning of system software to ARM architecture. Tech. rep. https:\/\/www.montblanc-project.eu\/wp-content\/uploads\/2019\/01\/D7.17-Final-report-on-Arm-optimized-Fortran-compiler-and-math-libraries.pdf . Accessed 24 Apr 2019"},{"key":"2911_CR76","doi-asserted-by":"crossref","unstructured":"Mappuji A, Effendy N, Mustaghfirin M, Sondok F, Yuniar RP, Pangesti SP (2016) Study of raspberry pi 2 quad-core cortex-a7 cpu cluster as a mini supercomputer. In: 2016 8th International Conference on Information Technology and Electrical Engineering (ICITEE), IEEE, pp 1\u20134","DOI":"10.1109\/ICITEED.2016.7863250"},{"issue":"17","key":"2911_CR77","doi-asserted-by":"publisher","first-page":"5390","DOI":"10.1002\/cpe.3602","volume":"27","author":"J Maqbool","year":"2015","unstructured":"Maqbool J, Oh S, Fox GC (2015) Evaluating arm hpc clusters for scientific workloads. Concurr Comput Pract Exp 27(17):5390\u20135410","journal-title":"Concurr Comput Pract Exp"},{"key":"2911_CR78","unstructured":"Maynard C, Selwood P (2016) Exascale computing research priorities for the met office forecasting research technical report no: 611"},{"key":"2911_CR79","unstructured":"McCalpin J. STREAM Benchmark results. https:\/\/www.cs.virginia.edu\/stream\/by_date\/Bandwidth.html . Accessed 24 Apr 2019"},{"key":"2911_CR80","unstructured":"McCalpin JD (2016) Memory bandwidth and system balance in HPC systems. SC16 Invited Talk. http:\/\/tiny.cc\/ipvh7y . Accessed 5 May 2019"},{"key":"2911_CR81","first-page":"19","volume":"2","author":"JD McCalpin","year":"1995","unstructured":"McCalpin JD (1995) Memory bandwidth and machine balance in current high performance computers. IEEE Comput Soc Tech Comm Comput Arch (TCCA) Newslett 2:19\u201325","journal-title":"IEEE Comput Soc Tech Comm Comput Arch (TCCA) Newslett"},{"key":"2911_CR82","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5110","author":"S McIntoshSmith","year":"2019","unstructured":"McIntoshSmith S, Price J, Deakin T, Poenaru A (2019) A performance analysis of the first generation of hpc-optimized arm processors. Pract Exp Concurr Comput. https:\/\/doi.org\/10.1002\/cpe.5110","journal-title":"Pract Exp Concurr Comput"},{"key":"2911_CR83","unstructured":"Mellanox: InfiniBand Cards - Overview. http:\/\/www.mellanox.com\/page\/infiniband_cards_overview (2014). Accessed 24 Apr 2019"},{"key":"2911_CR84","doi-asserted-by":"publisher","unstructured":"Milluzzi A, George A, Lam H (2016) Computational and memory analysis of tegra socs. In: 2016 IEEE High Performance Extreme Computing Conference (HPEC), pp 1\u20137. https:\/\/doi.org\/10.1109\/HPEC.2016.7761602","DOI":"10.1109\/HPEC.2016.7761602"},{"key":"2911_CR85","doi-asserted-by":"crossref","unstructured":"Moorthy P, Kapre N (2015) Zedwulf: Power-performance tradeoffs of a 32-node zynq soc cluster. In: 2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), IEEE, pp 68\u201375","DOI":"10.1109\/FCCM.2015.37"},{"key":"2911_CR86","unstructured":"Morales F, Bismarck JL (2016) Evaluating gem5 and qemu virtual platforms for arm multicore architectures. Master\u2019s thesis, KTH, School of Information and Communication Technology (ICT)"},{"key":"2911_CR87","doi-asserted-by":"crossref","unstructured":"Morganti L, Cesini D, Ferraro A (2016) Evaluating systems on chip through hpc bioinformatic and astrophysic applications. In: 2016 24th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP), IEEE, pp 541\u2013544","DOI":"10.1109\/PDP.2016.82"},{"issue":"1","key":"2911_CR88","doi-asserted-by":"publisher","first-page":"012049","DOI":"10.1088\/1742-6596\/681\/1\/012049","volume":"681","author":"V Nikolskiy","year":"2016","unstructured":"Nikolskiy V, Stegailov V (2016) Floating-point performance of arm cores and their efficiency in classical molecular dynamics. J Phys Conf Ser 681(1):012049","journal-title":"J Phys Conf Ser"},{"key":"2911_CR89","unstructured":"NVIDIA: Tegra K1 Technical Reference Manual. http:\/\/loke.as.arizona.edu\/~ckulesa\/binaries\/ONR\/TegraK1_TRM_DP06905001.pdf (2014). Accessed 24 Apr 2019"},{"key":"2911_CR90","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1016\/j.future.2017.09.029","volume":"79","author":"G Oyarzun","year":"2018","unstructured":"Oyarzun G, Borrell R, Gorobets A, Mantovani F, Oliva A (2018) Efficient cfd code implementation for the arm-based mont-blanc architecture. Future Gener Comput Syst 79:786\u2013796","journal-title":"Future Gener Comput Syst"},{"key":"2911_CR91","doi-asserted-by":"crossref","unstructured":"Plugaru V, Varrette S, Bouvry P (2014) Performance analysis of cloud environments on top of energy-efficient platforms featuring low power processors. In: 2014 IEEE 6th International Conference on Cloud Computing Technology and Science (CloudCom), IEEE, pp 416\u2013425","DOI":"10.1109\/CloudCom.2014.94"},{"key":"2911_CR92","unstructured":"Pruitt DD, Freudenthal EA (2016) Preliminary investigation of mobile system features potentially relevant to hpc. In: Proceedings of the 4th International Workshop on Energy Efficient Supercomputing, IEEE Press, pp 54\u201360"},{"key":"2911_CR93","doi-asserted-by":"publisher","unstructured":"Puzovi\u0107 M, Manne S, GalOn S, Ono M (2016) Quantifying energy use in dense shared memory hpc node. In: Proceedings of the 4th International Workshop on Energy Efficient Supercomputing, E2SC \u201916, pp 16\u201323. IEEE Press, Piscataway, NJ, USA. https:\/\/doi.org\/10.1109\/E2SC.2016.7","DOI":"10.1109\/E2SC.2016.7"},{"key":"2911_CR94","doi-asserted-by":"crossref","unstructured":"Raho M, Spyridakis A, Paolino M, Raho D (2015) Kvm, xen and docker: A performance analysis for arm based nfv and cloud computing. In: 2015 IEEE 3rd Workshop on Advances in IEEE Information, Electronic and Electrical Engineering (AIEEE), pp 1\u20138","DOI":"10.1109\/AIEEE.2015.7367280"},{"key":"2911_CR95","doi-asserted-by":"crossref","unstructured":"Rajovic N, Carpenter PM, Gelado I, Puzovic N, Ramirez A, Valero M (2013) Supercomputing with commodity cpus: Are mobile socs ready for hpc? In: 2013 SC-International Conference for High Performance Computing, Networking, Storage and Analysis (SC), IEEE, pp 1\u201312","DOI":"10.1145\/2503210.2503281"},{"key":"2911_CR96","doi-asserted-by":"publisher","unstructured":"Rajovic N, Rico A, Mantovani F, Ruiz D, Vilarrubi JO, Gomez C, Backes L, Nieto D, Servat H, Martorell X, Labarta J, Ayguade E, Adeniyi-Jones C, Derradji S, Gloaguen H, Lanucara P, Sanna N, Mehaut JF, Pouget K, Videau B, Boyer E, Allalen M, Auweter A, Brayford D, Tafani D, Weinberg V, Br\u00f6mmel D, Halver R, Meinke JH, Beivide R, Benito M, Vallejo E, Valero M, Ramirez A (2016) The mont-blanc prototype: An alternative approach for hpc systems. In: SC16: International Conference for High Performance Computing, Networking, Storage and Analysis, pp 444\u2013455. https:\/\/doi.org\/10.1109\/SC.2016.37","DOI":"10.1109\/SC.2016.37"},{"key":"2911_CR97","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1016\/j.future.2013.07.013","volume":"36","author":"N Rajovic","year":"2014","unstructured":"Rajovic N, Rico A, Puzovic N, Adeniyi-Jones C, Ramirez A (2014) Tibidabo: making the case for an arm-based hpc system. Future Gener Comput Syst 36:322\u2013334","journal-title":"Future Gener Comput Syst"},{"issue":"3","key":"2911_CR98","first-page":"581","volume":"7","author":"R Reeda","year":"2015","unstructured":"Reeda R, Cox MA, Wrigley T, Mellado B (2015) A cpu benchmarking characterization of arm based processors. Computer 7(3):581\u2013586","journal-title":"Computer"},{"key":"2911_CR99","doi-asserted-by":"crossref","unstructured":"Rethinagiri SK, Palomar O, Moreno JA, Unsal O, Cristal A (2015) Trigeneous platforms for energy efficient computing of hpc applications. In: 2015 IEEE 22nd International Conference on High Performance Computing (HiPC), IEEE, pp 264\u2013274","DOI":"10.1109\/HiPC.2015.19"},{"key":"2911_CR100","doi-asserted-by":"crossref","unstructured":"Ross JA, Richie DA, Park SJ, Shires DR, Pollock LL (2014) A case study of opencl on an android mobile gpu. In: 2014 IEEE High Performance Extreme Computing Conference (HPEC), pp 1\u20136","DOI":"10.1109\/HPEC.2014.7040987"},{"key":"2911_CR101","doi-asserted-by":"crossref","unstructured":"Rostirolla G, da\u00a0Rosa\u00a0Righi R, Rodrigues VF, Velho P, Padoin EL (2015) Greenhpc: a novel framework to measure energy consumption on hpc applications. In: Sustainable Internet and ICT for Sustainability (SustainIT), 2015, IEEE, pp 1\u20138","DOI":"10.1109\/SustainIT.2015.7101369"},{"key":"2911_CR102","unstructured":"Ruiz D, Mantovani F, Casas M, Labarta J, Spiga F (2018) The HPCG benchmark: analysis, shared memory preliminary improvements and evaluation on an arm-based platform. Polytechnic University of Catalonia. http:\/\/hdl.handle.net\/2117\/116642 . Accessed 5 May 2019"},{"key":"2911_CR103","unstructured":"Rupp K. Knights Landing vs. Knights Corner, Haswell, Ivy Bridge, and Sandy Bridge: STREAM benchmark results. https:\/\/www.karlrupp.net\/2016\/07\/knights-landing-vs-knights-corner-haswell-ivy-bridge-and-sandy-bridge-stream-benchmark-results . Accessed 24 Apr 2019"},{"key":"2911_CR104","unstructured":"Schulz KW, Baird CR, Brayford D, Georgiou Y, Kurtzer GM, Simmel D, Sterling T, Sundararajan N, Van\u00a0Hensbergen E (2016) Cluster computing with openhpc. In: HPCSYSPROS16: Inaugural HPC systems professionals workshop. http:\/\/hdl.handle.net\/2022\/21082"},{"issue":"1","key":"2911_CR105","first-page":"26","volume":"16","author":"S Sch\u00fcrmans","year":"2016","unstructured":"Sch\u00fcrmans S, Onnebrink G, Leupers R, Ascheid G, Chen X (2016) Frequency-aware esl power estimation for arm cortex-a9 using a black box processor model. ACM Trans Embed Comput Syst (TECS) 16(1):26","journal-title":"ACM Trans Embed Comput Syst (TECS)"},{"key":"2911_CR106","unstructured":"Selinger A, Rupp K, Selberherr S (2016) Evaluation of mobile arm-based socs for high performance computing. In: Society for Computer Simulation International Proceedings of the 24th High Performance Computing Symposium, p 21"},{"key":"2911_CR107","doi-asserted-by":"publisher","unstructured":"Sheen SK (2016) Astro-a low-cost, low-power cluster for cpu-gpu hybrid computing using the jetson TK1. Master\u2019s thesis, California Polytechnic State University. https:\/\/doi.org\/10.15368\/theses.2016.45","DOI":"10.15368\/theses.2016.45"},{"key":"2911_CR108","unstructured":"Shore C. Porting to 64-bit arm. Tech. rep., ARM. https:\/\/community.arm.com\/developer\/ip-products\/processors\/b\/processors-ip-blog\/posts\/porting-to-arm-64-bit . Whitepaper Accessed 24 Apr 2019"},{"key":"2911_CR109","doi-asserted-by":"crossref","unstructured":"Silvano C, Agosta G, Bartolini A, Beccari AR, Benini L, Bispo J, Cmar R, Cardoso JM, Cavazzoni C, Martinovi\u010d J et\u00a0al (2016) Autotuning and adaptivity approach for energy efficient exascale hpc systems: the antarex approach. In: Design, Automation & Test in Europe Conference & Exhibition (DATE), pp 708\u2013713. IEEE (2016)","DOI":"10.3850\/9783981537079_1012"},{"key":"2911_CR110","doi-asserted-by":"crossref","unstructured":"Sirin U, Appuswamy R, Ailamaki A (2016) Oltp on a server-grade arm: power, throughput and latency comparison. In: Proceedings of the 12th International Workshop on Data Management on New Hardware, ACM, p 10","DOI":"10.1145\/2933349.2933359"},{"key":"2911_CR111","doi-asserted-by":"publisher","unstructured":"Stegailov V, Vecher V (2018) Efficiency analysis of intel, AMD and Nvidia 64-Bit hardware for memory-bound problems: a case study of Ab initio calculations with VASP, pp 81\u201390. https:\/\/doi.org\/10.1007\/978-3-319-78054-2_8","DOI":"10.1007\/978-3-319-78054-2_8"},{"issue":"2","key":"2911_CR112","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MM.2017.35","volume":"37","author":"N Stephens","year":"2017","unstructured":"Stephens N, Biles S, Boettcher M, Eapen J, Eyole M, Gabrielli G, Horsnell M, Magklis G, Martinez A, Premillieu N et al (2017) The arm scalable vector extension. IEEE Micro 37(2):26\u201339","journal-title":"IEEE Micro"},{"key":"2911_CR113","doi-asserted-by":"publisher","unstructured":"Stokke KR, Stensland HK, Griwodz C, Halvorsen P (2016) A high-precision, hybrid gpu, cpu and ram power model for generic multimedia workloads. In: Proceedings of the 7th International Conference on Multimedia Systems, MMSys \u201916, pp 14:1\u201314:12. ACM, New York, NY, USA. https:\/\/doi.org\/10.1145\/2910017.2910591","DOI":"10.1145\/2910017.2910591"},{"key":"2911_CR114","doi-asserted-by":"publisher","unstructured":"Stokke KR, Stensland HK, Halvorsen P, Griwodz C (2016) High-precision power modelling of the tegra k1 variable smp processor architecture. In: 2016 IEEE 10th International Symposium on Embedded Multicore\/Many-core Systems-on-Chip (MCSOC), pp 193\u2013200. https:\/\/doi.org\/10.1109\/MCSoC.2016.28","DOI":"10.1109\/MCSoC.2016.28"},{"key":"2911_CR115","unstructured":"Strohmaier E, Dongarra J, Horst S, Meuer M, Meuer H (2019) Top 500 The List. https:\/\/www.top500.org\/ . Accessed 5 May 2019"},{"key":"2911_CR116","unstructured":"Sundriyal V, Fought E, Sosonkina M, Windus TL (2016) Power profiling and evaluating the effect of frequency scaling on nwchem. In: Society for Computer Simulation International Proceedings of the 24th High Performance Computing Symposium, p 19"},{"issue":"6","key":"2911_CR117","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/S1369-7021(06)71539-5","volume":"9","author":"SE Thompson","year":"2006","unstructured":"Thompson SE, Parthasarathy S (2006) Moore\u2019s law: the future of si microelectronics. Mater today 9(6):20\u201325","journal-title":"Mater today"},{"key":"2911_CR118","doi-asserted-by":"crossref","unstructured":"Tiwari A, Keipert K, Jundt A, Peraza J, Leang SS, Laurenzano M, Gordon MS, Carrington L (2015) Performance and energy efficiency analysis of 64-bit arm using gamess. In: Proceedings of the 2nd International Workshop on Hardware-Software Co-Design for High Performance Computing, ACM, p 8","DOI":"10.1145\/2834899.2834905"},{"key":"2911_CR119","unstructured":"Trader T (2014) The exascale revolution. https:\/\/www.hpcwire.com\/2014\/10\/23\/exascale-revolution\/ . Accessed 23 July 2016"},{"key":"2911_CR120","doi-asserted-by":"crossref","unstructured":"Villebonnet V, Da\u00a0Costa G, Lefevre L, Pierson JM, Stolf P (2014) Towards generalizing\u201d\u201d big little\u201d\u201d for energy proportional hpc and cloud infrastructures. In: 2014 IEEE Fourth International Conference on Big Data and Cloud Computing (BdCloud), IEEE, pp 703\u2013710","DOI":"10.1109\/BDCloud.2014.99"},{"key":"2911_CR121","doi-asserted-by":"publisher","unstructured":"Weloli JW, Bilavarn S, Derradji S, Belleudy C, Lesmanne S (2016) Efficiency modeling and analysis of 64-bit arm clusters for hpc. In: 2016 Euromicro Conference on Digital System Design (DSD), pp 342\u2013347. https:\/\/doi.org\/10.1109\/DSD.2016.74","DOI":"10.1109\/DSD.2016.74"},{"issue":"1\u20132","key":"2911_CR122","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"RC Whaley","year":"2001","unstructured":"Whaley RC, Petitet A, Dongarra JJ (2001) Automated empirical optimizations of software and the atlas project. Parallel Comput 27(1\u20132):3\u201335","journal-title":"Parallel Comput"},{"issue":"6","key":"2911_CR123","doi-asserted-by":"publisher","first-page":"1643","DOI":"10.1109\/JSSC.2017.2669025","volume":"52","author":"PN Whatmough","year":"2017","unstructured":"Whatmough PN, Das S, Hadjilambrou Z, Bull DM (2017) Power integrity analysis of a 28 nm dual-core arm cortex-a57 cluster using an all-digital power delivery monitor. IEEE J Solid-State Circ 52(6):1643\u20131654","journal-title":"IEEE J Solid-State Circ"},{"issue":"3","key":"2911_CR124","first-page":"607","volume":"7","author":"G Wrigleya","year":"2015","unstructured":"Wrigleya G, Reed R, Mellado B (2015) Memory benchmarking characterisation of arm-based socs. Computer 7(3):607\u2013617","journal-title":"Computer"},{"issue":"1","key":"2911_CR125","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1093\/nsr\/nwv087","volume":"3","author":"X Xie","year":"2016","unstructured":"Xie X (2016) Low-power technologies in high-performance computer: trends and perspectives. Natl Sci Rev 3(1):23\u201325","journal-title":"Natl Sci Rev"},{"key":"2911_CR126","unstructured":"Yoshida T (2018) Fujitsu high performance cpu for the post-k computer. In: Hot Chips 30 Symposium (HCS), Series Hot Chips, vol 18"},{"key":"2911_CR127","doi-asserted-by":"crossref","unstructured":"Zhang J, You S, Gruenwald L (2015) Tiny gpu cluster for big spatial data: A preliminary performance evaluation. In: 2015 IEEE 35th International Conference on Distributed Computing Systems Workshops (ICDCSW), IEEE, pp 142\u2013147","DOI":"10.1109\/ICDCSW.2015.33"},{"issue":"11","key":"2911_CR128","doi-asserted-by":"publisher","first-page":"1934","DOI":"10.1109\/JPROC.2003.818324","volume":"91","author":"VV Zhirnov","year":"2003","unstructured":"Zhirnov VV, Cavin RK, Hutchby JA, Bourianoff GI (2003) Limits to binary logic switch scaling-a gedanken model. Proc IEEE 91(11):1934\u20131939","journal-title":"Proc IEEE"},{"key":"2911_CR129","unstructured":"Zhu Y, Mattina M, Whatmough P (2018) Mobile machine learning hardware at arm: a systems-on-chip (soc) perspective. arXiv preprint arXiv:1801.06274"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-019-02911-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-019-02911-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-019-02911-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T09:06:38Z","timestamp":1694941598000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-019-02911-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,8]]},"references-count":129,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["2911"],"URL":"https:\/\/doi.org\/10.1007\/s11227-019-02911-9","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,8]]},"assertion":[{"value":"8 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}