{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T04:43:21Z","timestamp":1725857001593},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319395760"},{"type":"electronic","value":"9783319395777"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-39577-7_7","type":"book-chapter","created":{"date-parts":[[2016,5,24]],"date-time":"2016-05-24T09:47:48Z","timestamp":1464083268000},"page":"82-95","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Providing CUDA Acceleration to KVM Virtual Machines in InfiniBand Clusters with rCUDA"],"prefix":"10.1007","author":[{"given":"Ferran","family":"P\u00e9rez","sequence":"first","affiliation":[]},{"given":"Carlos","family":"Rea\u00f1o","sequence":"additional","affiliation":[]},{"given":"Federico","family":"Silla","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,5,24]]},"reference":[{"unstructured":"Kernel-based Virtual Machine. http:\/\/www.linux-kvm.org. Accessed: Jan 2016","key":"7_CR1"},{"unstructured":"NextIO, N2800-ICA \u2014 Flexible and manageable I\/O expansion and virtualization. http:\/\/www.nextio.com\/. Accessed: Mar 2012","key":"7_CR2"},{"unstructured":"Oracle VM VirtualBox. http:\/\/www.virtualbox.org\/. Accessed: Jan 2016","key":"7_CR3"},{"unstructured":"Shadowfax II - scalable implementation of GPGPU assemblies. http:\/\/keeneland.gatech.edu\/software\/keeneland\/kidron. Accessed: Jan 2016","key":"7_CR4"},{"unstructured":"V-GPU: GPU virtualization. http:\/\/www.zillians.com\/products\/vgpu-gpu-virtualization\/. Accessed: Jan 2016","key":"7_CR5"},{"unstructured":"VMware virtualization. http:\/\/www.vmware.com\/. Accessed: Jan 2016","key":"7_CR6"},{"unstructured":"Xen Project. http:\/\/www.xenproject.org\/. Accessed: Jan 2016","key":"7_CR7"},{"unstructured":"Mellanox, Connect-IB Single and Dual QSFP+ Port PCI Express Gen3x16 Adapter Card User Manual (2013). http:\/\/www.mellanox.com\/related-docs\/user_manuals\/Connect-IB_Single_and_Dual_QSFP+_Port_PCI_Express_Gen3_x16_Adapter_Card_User_Manual.pdf","key":"7_CR8"},{"unstructured":"rCUDA: Virtualizing GPUs to reduce cost and improve performance (2014). http:\/\/www.rcuda.net","key":"7_CR9"},{"unstructured":"CUDA API Reference Manual 7.0 (2015). https:\/\/developer.nvidia.com\/cuda-toolkit","key":"7_CR10"},{"unstructured":"NVIDIA Popular GPU-Accelerated Applications Catalog (2015). http:\/\/www.nvidia.es\/content\/tesla\/pdf\/gpu-accelerated-applications-for-hpc.pdf","key":"7_CR11"},{"doi-asserted-by":"crossref","unstructured":"Barak, A., Ben-Nun, T., Levy, E., Shiloh, A.: A package for OpenCL based heterogeneous computing on clusters with many GPU devices. In: 2010 IEEE International Conference on Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS), pp. 1\u20137. IEEE (2010)","key":"7_CR12","DOI":"10.1109\/CLUSTERWKSP.2010.5613086"},{"issue":"18","key":"7_CR13","doi-asserted-by":"publisher","first-page":"2457","DOI":"10.1002\/cpe.1472","volume":"21","author":"S Barrachina","year":"2009","unstructured":"Barrachina, S., Castillo, M., Igual, F.D., Mayo, R., Quintana-Ort\u00ed, E.S., Quintana-Ort\u00ed, G.: Exploiting the capabilities of modern GPUs for dense matrix computations. Concurrency Comput.: Pract. Experience 21(18), 2457\u20132477 (2009)","journal-title":"Concurrency Comput.: Pract. Experience"},{"key":"7_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/978-3-642-14122-5_44","volume-title":"Euro-Par 2009 \u2013 Parallel Processing Workshops","author":"Jos\u00e9 Duato","year":"2010","unstructured":"Duato, Jos\u00e9, Igual, Francisco D., Mayo, Rafael, Pe\u00f1a, Antonio J., Quintana-Ort\u00ed, Enrique S., Silla, Federico: An efficient implementation of GPU virtualization in high performance clusters. In: Lin, Hai-Xiang, Alexander, Michael, Forsell, Martti, Kn\u00fcpfer, Andreas, Prodan, Radu, Sousa, Leonel, Streit, Achim (eds.) Euro-Par 2009. LNCS, vol. 6043, pp. 385\u2013394. Springer, Heidelberg (2010)"},{"doi-asserted-by":"crossref","unstructured":"Felter, W.: An updated performance comparison of virtual machines and linux containers. IBM Research Report (2014)","key":"7_CR15","DOI":"10.1109\/ISPASS.2015.7095802"},{"doi-asserted-by":"crossref","unstructured":"Gaikwad, A., Toke, I.M.: GPU based sparse grid technique for solving multidimensional options pricing PDEs. In: Proceedings of the 2nd Workshop on High Performance Computational Finance, WHPCF 2009, pp. 6: 1\u20136: 9. ACM, New York (2009)","key":"7_CR16","DOI":"10.1145\/1645413.1645419"},{"key":"7_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/978-3-642-15277-1_37","volume-title":"Euro-Par 2010 - Parallel Processing","author":"G Giunta","year":"2010","unstructured":"Giunta, G., Montella, R., Agrillo, G., Coviello, G.: A GPGPU transparent virtualization component for high performance computing clouds. In: D\u2019Ambra, P., Guarracino, M., Talia, D. (eds.) Euro-Par 2010, Part I. LNCS, vol. 6271, pp. 379\u2013391. Springer, Heidelberg (2010)"},{"unstructured":"Group, K.O.W: OpenCL 1.2 Specification (2011)","key":"7_CR18"},{"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 3rd ACM Workshop on System-level Virtualization for High Performance Computing, pp. 17\u201324. ACM (2009)","key":"7_CR19","DOI":"10.1145\/1519138.1519141"},{"doi-asserted-by":"crossref","unstructured":"Iserte, S., Gimeno, A.C., Mayo, R., Quintana-Ort\u00ed, E.S., Silla, F., Duato, J., Rea\u00f1o, C., Prades, J.: SLURM support for remote GPU virtualization: Implementation and performance study. In: 26th IEEE International Symposium on Computer Architecture and High Performance Computing, SBAC-PAD 2014, Paris, France, 22\u201324 October, pp. 318\u2013325 (2014)","key":"7_CR20","DOI":"10.1109\/SBAC-PAD.2014.49"},{"key":"7_CR21","doi-asserted-by":"publisher","first-page":"1","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, 1\u201311 (2013)","journal-title":"BioMed Res. Int."},{"doi-asserted-by":"crossref","unstructured":"Kegel, P., Steuwer, M., Gorlatch, S.: dopencl: Towards a uniform programming approach for distributed heterogeneous multi-many-core systems. In: 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops PhD Forum (IPDPSW), pp. 174\u2013186, May 2012","key":"7_CR22","DOI":"10.1109\/IPDPSW.2012.16"},{"doi-asserted-by":"crossref","unstructured":"Kim, J., Seo, S., Lee, J., Nah, J., Jo, G., Lee, J.: SnuCL: An OpenCL framework for heterogeneous CPU\/GPU clusters. In: Proceedings of the 26th ACM International Conference on Supercomputing, ICS 2012, pp. 341\u2013352. ACM, New York (2012)","key":"7_CR23","DOI":"10.1145\/2304576.2304623"},{"doi-asserted-by":"crossref","unstructured":"Krishnan, V.: Towards an integrated IO and clustering solution using PCI express. In: 2007 IEEE International Conference on Cluster Computing, pp. 259\u2013266. IEEE (2007)","key":"7_CR24","DOI":"10.1109\/CLUSTR.2007.4629239"},{"unstructured":"Laboratories, S.N.: LAMMPS Molecular Dynamics Simulator (2013). http:\/\/lammps.sandia.gov\/","key":"7_CR25"},{"doi-asserted-by":"crossref","unstructured":"Liang, T.Y., Chang, Y.W.: GridCuda: a grid-enabled CUDA programming toolkit. In: 2011 IEEE Workshops of International Conference on Advanced Information Networking and Applications (WAINA), pp. 141\u2013146. IEEE (2011)","key":"7_CR26","DOI":"10.1109\/WAINA.2011.82"},{"issue":"1","key":"7_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-14-117","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 Bioinform. 14(1), 1\u201310 (2013)","journal-title":"BMC Bioinform."},{"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 5th International Workshop on Virtualization Technologies in Distributed Computing, VTDC 2011, pp. 3\u201310. ACM, New York (2011)","key":"7_CR28","DOI":"10.1145\/1996121.1996124"},{"unstructured":"NVIDIA: CUDA C Programming Guide 7.0 (2015)","key":"7_CR29"},{"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 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012, pp. 1207\u20131214. IEEE Computer Society, Washington, DC (2012)","key":"7_CR30","DOI":"10.1109\/SC.Companion.2012.146"},{"issue":"10","key":"7_CR31","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1016\/j.parco.2014.09.011","volume":"40","author":"AJ Pe\u00f1a","year":"2014","unstructured":"Pe\u00f1a, A.J., Rea\u00f1o, C., Silla, F., Mayo, R., Quintana-Ort\u00ed, E.S., Duato, J.: A complete and efficient CUDA-sharing solution for HPC clusters. Parallel Comput. 40(10), 574\u2013588 (2014)","journal-title":"Parallel Comput."},{"unstructured":"Playne, D.P., Hawick, K.A.: Data parallel three-dimensional cahn-hilliard field equation simulation on GPUs with CUDA. In: PDPTA, pp. 104\u2013110 (2009)","key":"7_CR32"},{"unstructured":"Shi, L., Chen, H., Sun, J.: vCUDA: GPU accelerated high performance computing in virtual machines. In: IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2009, pp. 1\u201311. IEEE (2009)","key":"7_CR33"},{"issue":"2","key":"7_CR34","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1093\/bioinformatics\/btq644","volume":"27","author":"PD Vouzis","year":"2010","unstructured":"Vouzis, P.D., Sahinidis, N.V.: Gpu-blast: Using graphics processors to accelerate protein sequence alignment. Bioinformatics 27(2), 182\u2013188 (2010)","journal-title":"Bioinformatics"},{"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: 7th IEEE International Conference on Cloud Computing (CLOUD 2014) (2014)","key":"7_CR35","DOI":"10.1109\/CLOUD.2014.90"},{"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 Annual IEEE\/ACM International Symposium on Code Generation and Optimization, CGO 2014, pp. 44: 44\u201344: 54. ACM, New York (2014)","key":"7_CR36","DOI":"10.1145\/2544137.2544166"},{"doi-asserted-by":"crossref","unstructured":"Xiao, S., Balaji, P., Zhu, Q., Thakur, R., Coghlan, S., Lin, H.,Wen, G., Hong, J., Chun Feng, W.: Vocl: An optimized environment for transparentvirtualization of graphics processing units. In: Proceedings of the 1st Innovative Parallel Computing (InPar) (2012)","key":"7_CR37","DOI":"10.1109\/InPar.2012.6339609"},{"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: 2012 IEEE 4th International Conference on Cloud Computing Technology and Science (CloudCom), pp. 711\u2013716. IEEE (2012)","key":"7_CR38","DOI":"10.1109\/CloudCom.2012.6427531"}],"container-title":["Lecture Notes in Computer Science","Distributed Applications and Interoperable Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-39577-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T02:02:47Z","timestamp":1699840967000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-39577-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319395760","9783319395777"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-39577-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"24 May 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}