{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T01:10:02Z","timestamp":1751850602745,"version":"3.41.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,9,8]],"date-time":"2018-09-08T00:00:00Z","timestamp":1536364800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s10586-018-2845-0","type":"journal-article","created":{"date-parts":[[2018,9,8]],"date-time":"2018-09-08T05:48:03Z","timestamp":1536385683000},"page":"185-204","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["On the effect of using rCUDA to provide CUDA acceleration to Xen virtual machines"],"prefix":"10.1007","volume":"22","author":[{"given":"Javier","family":"Prades","sequence":"first","affiliation":[]},{"given":"Carlos","family":"Rea\u00f1o","sequence":"additional","affiliation":[]},{"given":"Federico","family":"Silla","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,9,8]]},"reference":[{"key":"2845_CR1","unstructured":"Kernel-Based Virtual Machine, KVM. http:\/\/www.linux-kvm.org (2015). Accessed 19 Oct 2015"},{"key":"2845_CR2","unstructured":"Xen Project. http:\/\/www.xenproject.org\/ (2015). Accessed 19 Oct 2015"},{"key":"2845_CR3","unstructured":"VMware Virtualization. http:\/\/www.vmware.com\/ (2015). Accessed 19 Oct 2015"},{"key":"2845_CR4","unstructured":"Oracle VM VirtualBox. http:\/\/www.virtualbox.org\/ (2015). Accessed 19 Oct 2015"},{"key":"2845_CR5","doi-asserted-by":"crossref","unstructured":"Semnanian, A., Pham, J., Englert, B., Wu, X.: Virtualization technology and its impact on computer hardware architecture. In: Proceedings of the Information Technology: New Generations, ITNG, pp. 719\u2013724 (2011)","DOI":"10.1109\/ITNG.2011.127"},{"key":"2845_CR6","doi-asserted-by":"crossref","unstructured":"Felter, W., Ferreira, A., Rajamony, R., Rubio, J.: An updated performance comparison of virtual machines and linux containers. In: IBM Research Report (2014)","DOI":"10.1109\/ISPASS.2015.7095802"},{"key":"2845_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lu, X., Arnold, M., Panda, D.: MVAPICH2 over OpenStack with SR-IOV: an efficient approach to build HPC Clouds. In: Proceedings of the IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGrid, pp. 71\u201380 (2015)","DOI":"10.1109\/CCGrid.2015.166"},{"key":"2845_CR8","doi-asserted-by":"crossref","unstructured":"Wu, H., Diamos, G., Sheard, T., Aref, M., Baxter, S., Garland, M., Yalamanchili, S.: Red Fox: an execution environment for relational query processing on GPUs. In: Proceedings of the International Symposium on Code Generation and Optimization, CGO (2014)","DOI":"10.1145\/2581122.2544166"},{"key":"2845_CR9","unstructured":"Playne, D.P., Hawick, K.A.: Data parallel three-dimensional Cahn-Hilliard field equation simulation on GPUs with CUDA. In: Proceedings of the Parallel and Distributed Processing Techniques and Applications, PDPTA, pp. 104\u2013110 (2009)"},{"issue":"16","key":"2845_CR10","doi-asserted-by":"publisher","first-page":"2652","DOI":"10.1002\/cpe.3152","volume":"26","author":"I Yamazaki","year":"2014","unstructured":"Yamazaki, I., Dong, T., Solc\u00e0, R., Tomov, S., Dongarra, J., Schulthess, T.: Tridiagonalization of a dense symmetric matrix on multiple GPUs and its application to symmetric eigenvalue problems. Concurr. Comput.: Pract. Exp. 26(16), 2652\u20132666 (2014)","journal-title":"Concurr. Comput.: Pract. Exp."},{"key":"2845_CR11","doi-asserted-by":"crossref","unstructured":"Luo, D.Y.: Canny edge detection on NVIDIA CUDA. In: Proceedings of the Computer Vision and Pattern Recognition Workshops, CVPR Workshops, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPRW.2008.4563088"},{"issue":"7","key":"2845_CR12","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1016\/j.parco.2010.02.006","volume":"36","author":"V Surkov","year":"2010","unstructured":"Surkov, V.: Parallel option pricing with Fourier space time-stepping method on graphics processing units. Parallel Comput. 36(7), 372\u2013380 (2010)","journal-title":"Parallel Comput."},{"issue":"10","key":"2845_CR13","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.1002\/cpe.2943","volume":"25","author":"PK Agarwal","year":"2013","unstructured":"Agarwal, P.K., Hampton, S., Poznanovic, J., Ramanthan, A., Alam, S.R., Crozier, P.S.: Performance modeling of microsecond scale biological molecular dynamics simulations on heterogeneous architectures. Concurr. Comput.: Pract. Exp. 25(10), 1356\u20131375 (2013)","journal-title":"Concurr. Comput.: Pract. Exp."},{"issue":"3","key":"2845_CR14","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.sysarc.2013.09.007","volume":"60","author":"GH Luo","year":"2014","unstructured":"Luo, G.H., Huang, S.K., Chang, Y.S., Yuan, S.M.: A parallel bees algorithm implementation on GPU. J. Syst. Arch. 60(3), 271\u2013279 (2014)","journal-title":"J. Syst. Arch."},{"key":"2845_CR15","unstructured":"NVIDIA GRID Technology. http:\/\/www.nvidia.com\/object\/grid-technology.html (2015). Accessed 19 Oct 2015"},{"key":"2845_CR16","unstructured":"Song, J., et al: KVMGT: a full GPU virtualization solution. In: KVM Forum (2014)"},{"key":"2845_CR17","unstructured":"AMD Multiuser GPU, Hardware-Based Virtualized Solution. http:\/\/www.amd.com\/Documents\/Multiuser-GPU-Datasheet.pdf (2015). Accessed 19 Oct 2015"},{"key":"2845_CR18","unstructured":"V-GPU: GPU Virtualization. https:\/\/github.com\/zillians\/platform_manifest_vgpu (2015). Accessed 19 Oct 2015"},{"key":"2845_CR19","doi-asserted-by":"crossref","unstructured":"Oikawa, M., Kawai, A., Nomura, K., Yasuoka, K., Yoshikawa, K., Narumi, T.: DS-CUDA: a middleware to use many GPUs in the cloud environment. In: Proceedings of the SC Companion: High Performance Computing, Networking Storage and Analysis, SCC, pp. 1207\u20131214 (2012)","DOI":"10.1109\/SC.Companion.2012.146"},{"key":"2845_CR20","doi-asserted-by":"crossref","unstructured":"Rea\u00f1o, C., Silla, F., Shainer, G., Schultz, S.: Local and remote GPUs perform similar with EDR 100G InfiniBand. In: Proceedings of the Industrial Track of the 16th International Middleware Conference, ACM, Middleware Industry \u201915, pp. 4:1\u20134:7 (2015)","DOI":"10.1145\/2830013.2830015"},{"key":"2845_CR21","doi-asserted-by":"crossref","unstructured":"Rea\u00f1o, C., Silla, F., Duato, J.: Enhancing the rCUDA remote GPU virtualization framework: from a prototype to a production solution. In: Proceedings of the 17th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, IEEE Press, CCGrid \u201917, pp. 695\u2013698 (2017)","DOI":"10.1109\/CCGRID.2017.42"},{"key":"2845_CR22","doi-asserted-by":"crossref","unstructured":"Shi, L., Chen, H., Sun, J.: vCUDA: GPU accelerated high performance computing in virtual machines. In: Proceedings of the IEEE Parallel and Distributed Processing Symposium, IPDPS, pp. 1\u201311 (2009)","DOI":"10.1109\/IPDPS.2009.5161020"},{"key":"2845_CR23","doi-asserted-by":"crossref","unstructured":"Liang, T.Y., Chang, Y.W.: GridCuda: A grid-enabled CUDA programming toolkit. In: Proceedings of the IEEE Advanced Information Networking and Applications Workshops, WAINA, pp. 141\u2013146 (2011)","DOI":"10.1109\/WAINA.2011.82"},{"key":"2845_CR24","doi-asserted-by":"crossref","unstructured":"Giunta, G., Montella, R., Agrillo, G., Coviello, G.: A GPGPU transparent virtualization component for high performance computing clouds. In: Proceedings of the Euro-Par Parallel Processing, Euro-Par, pp. 379\u2013391 (2010)","DOI":"10.1007\/978-3-642-15277-1_37"},{"key":"2845_CR25","doi-asserted-by":"crossref","unstructured":"Gupta, V., Gavrilovska, A., Schwan, K., Kharche, H., Tolia, N., Talwar, V., Ranganathan, P. GViM: GPU-accelerated virtual machines. In: Proceedings of the ACM Workshop on System-level Virtualization for High Performance Computing, HPCVirt, pp. 17\u201324 (2009)","DOI":"10.1145\/1519138.1519141"},{"key":"2845_CR26","doi-asserted-by":"crossref","unstructured":"Merritt, A.M., Gupta, V., Verma, A., Gavrilovska, A., Schwan, K.: Shadowfax: scaling in heterogeneous cluster systems via GPGPU assemblies. In: Proceedings of the International Workshop on Virtualization Technologies in Distributed Computing, VTDC, pp. 3\u201310 (2011)","DOI":"10.1145\/1996121.1996124"},{"key":"2845_CR27","unstructured":"Shadowfax II\u2014Scalable Implementation of GPGPU Assemblies. http:\/\/keeneland.gatech.edu\/software\/keeneland\/kidron (2015). Accessed 19 Oct 2015"},{"key":"2845_CR28","doi-asserted-by":"crossref","unstructured":"Walters, J.P., Younge, A.J., Kang, D.I., Yao, K.T., Kang, M., Crago, S.P., Fox, G.C.: GPU-passthrough performance: a comparison of KVM, Xen, VMWare ESXi, and LXC for CUDA and OpenCL applications. In: Proceedings of the IEEE International Conference on Cloud Computing, CLOUD (2014)","DOI":"10.1109\/CLOUD.2014.90"},{"key":"2845_CR29","doi-asserted-by":"crossref","unstructured":"Yang, C.T., Wang, H.Y., Ou, W.S., Liu, Y.T., Hsu, C.H.: On implementation of GPU virtualization using PCI pass-through. In: Proceedings of the IEEE Cloud Computing Technology and Science, CloudCom, pp. 711\u2013716 (2012)","DOI":"10.1109\/CloudCom.2012.6427531"},{"key":"2845_CR30","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1155\/2013\/939460","volume":"2013","author":"H Jo","year":"2013","unstructured":"Jo, H., Jeong, J., Lee, M., Choi, D.H.: Exploiting GPUs in virtual machine for BioCloud. BioMed Res. Int. 2013, 11 (2013). https:\/\/doi.org\/10.1155\/2013\/939460","journal-title":"BioMed Res. Int."},{"key":"2845_CR31","unstructured":"NVIDIA: CUDA C Programming Guide 7.5. http:\/\/docs.nvidia.com\/cuda\/pdf\/CUDA_C_Programming_Guide.pdf (2015a). Accessed 19 Oct 2015"},{"key":"2845_CR32","unstructured":"NVIDIA: CUDA Runtime API Reference Manual 7.5. http:\/\/docs.nvidia.com\/cuda\/pdf\/CUDA_Runtime_API.pdf (2015b). Accessed 19 Oct 2015"},{"key":"2845_CR33","unstructured":"NVIDIA: The NVIDIA GPU Computing SDK Version 5.5 (2013)"},{"key":"2845_CR34","unstructured":"iperf3: A TCP, UDP, and SCTP Network Bandwidth Measurement Tool. https:\/\/github.com\/esnet\/iperf (2015). Accessed 19 Oct 2015"},{"key":"2845_CR35","doi-asserted-by":"crossref","unstructured":"Rea\u00f1o, C., Silla, F.: Reducing the performance gap of remote GPU virtualization with InfiniBand Connect-IB. In: 2016 IEEE Symposium on Computers and Communication (ISCC), pp. 920\u2013925 (2016)","DOI":"10.1109\/ISCC.2016.7543854"},{"key":"2845_CR36","unstructured":"Mellanox: Connect-IB Single and Dual QSFP+ Port PCI Express Gen3 x16 Adapter Card User Manual. http:\/\/www.mellanox.com\/related-docs\/user_manuals\/Connect-IB_Single_and_Dual_QSFP+_Port_PCI_Express_Gen3_%20x16_Adapter_Card_User_Manual.pdf (2014a). Accessed 19 Oct 2015"},{"key":"2845_CR37","unstructured":"Mellanox: ConnectX-3 VPI Single and Dual QSFP+ Port Adapter Card User Manual 1.7. http:\/\/www.mellanox.com\/related-docs\/user_manuals\/ConnectX-3_VPI_Single_and_Dual_QSFP_Port_Adapter_Card_User_Manual.pdf (2013). Accessed 19 Oct 2015"},{"key":"2845_CR38","doi-asserted-by":"crossref","unstructured":"P\u00e9rez, F., Rea\u00f1o, C., Silla, F.: Providing CUDA acceleration to KVM virtual machines in InfiniBand clusters with rCUDA. In: 16th International Conference Distributed Applications and Interoperable Systems (DAIS), pp. 82\u201395. Springer International Publishing (2016)","DOI":"10.1007\/978-3-319-39577-7_7"},{"key":"2845_CR39","unstructured":"Mellanox: Mellanox OFED for Linux User Manual. http:\/\/www.mellanox.com\/related-docs\/prod_software\/Mellanox_OFED_Linux_User_Manual_v2.3-1.0.1.pdf (2014b). Accessed 19 Oct 2015"},{"key":"2845_CR40","doi-asserted-by":"crossref","unstructured":"Rea\u00f1o, C., Mayo, R., Quintana-Ort\u00ed, E., Silla, F., Duato, J., Pe\u00f1a, A.: Influence of InfiniBand FDR on the performance of remote GPU virtualization. In: Proceedings of the IEEE International Conference on Cluster Computing, CLUSTER, pp. 1\u20138 (2013)","DOI":"10.1109\/CLUSTER.2013.6702662"},{"key":"2845_CR41","unstructured":"Laboratories, S.N.: LAMMPS Molecular Dynamics Simulator. http:\/\/lammps.sandia.gov\/ (2013). Accessed 19 Oct 2015"},{"issue":"14","key":"2845_CR42","doi-asserted-by":"publisher","first-page":"2170","DOI":"10.1016\/j.patrec.2009.10.009","volume":"31","author":"Y Liu","year":"2010","unstructured":"Liu, Y., Schmidt, B., Liu, W., Maskell, D.L.: CUDA-MEME: accelerating motif discovery in biological sequences using CUDA-enabled graphics processing units. Pattern Recognit. Lett. 31(14), 2170\u20132177 (2010)","journal-title":"Pattern Recognit. Lett."},{"issue":"1","key":"2845_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-14-1","volume":"14","author":"Y Liu","year":"2013","unstructured":"Liu, Y., Wirawan, A., Schmidt, B.: CUDASW++ 3.0: accelerating Smith-Waterman protein database search by coupling CPU and GPU SIMD instructions. BMC Bioinformat. 14(1), 1\u201310 (2013)","journal-title":"BMC Bioinformat."},{"issue":"2","key":"2845_CR44","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1093\/bioinformatics\/btq644","volume":"27","author":"PD Vouzis","year":"2011","unstructured":"Vouzis, P.D., Sahinidis, N.V.: GPU-BLAST: using graphics processors to accelerate protein sequence alignment. Bioinformatics 27(2), 182\u2013188 (2011)","journal-title":"Bioinformatics"},{"key":"2845_CR45","unstructured":"NVIDIA: NVIDIA Popular GPU-Accelerated Applications Catalog. http:\/\/www.nvidia.com\/content\/gpu-applications\/PDF\/GPU-apps-catalog-mar2015.pdf (2015c). Accessed 19 Oct 2015"},{"key":"2845_CR46","unstructured":"Liu, Y. CUDA-MEME. https:\/\/sites.google.com\/site\/yongchaosoftware\/mcuda-meme (2014). Accessed 19 Oct 2015"},{"key":"2845_CR47","doi-asserted-by":"crossref","unstructured":"Polak, A.: Counting triangles in large graphs on GPU. In: IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 740\u2013746 (2016)","DOI":"10.1109\/IPDPSW.2016.108"},{"key":"2845_CR48","doi-asserted-by":"crossref","unstructured":"Prades, J., Silla, F.: Turning GPUs into floating devices over the cluster: the Beauty of GPU Migration. In: Proceedings of the 6th Workshop on Heterogeneous and Unconventional Cluster Architectures and Applications (HUCAA) (2017)","DOI":"10.1109\/ICPPW.2017.30"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-018-2845-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-018-2845-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-018-2845-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T00:39:19Z","timestamp":1751848759000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-018-2845-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,8]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["2845"],"URL":"https:\/\/doi.org\/10.1007\/s10586-018-2845-0","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"type":"print","value":"1386-7857"},{"type":"electronic","value":"1573-7543"}],"subject":[],"published":{"date-parts":[[2018,9,8]]},"assertion":[{"value":"20 October 2015","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}