{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T07:51:21Z","timestamp":1673509881782},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,10,31]],"date-time":"2013-10-31T00:00:00Z","timestamp":1383177600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2014,4]]},"DOI":"10.1007\/s11227-013-1034-4","type":"journal-article","created":{"date-parts":[[2013,10,30]],"date-time":"2013-10-30T10:07:51Z","timestamp":1383127671000},"page":"183-213","source":"Crossref","is-referenced-by-count":13,"title":["Implementation of GPU virtualization using PCI pass-through mechanism"],"prefix":"10.1007","volume":"68","author":[{"given":"Chao-Tung","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jung-Chun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsien-Yi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ching-Hsien","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,10,31]]},"reference":[{"key":"1034_CR1","unstructured":"TOP 500 (2013) http:\/\/www.top500.org . Accessed 17 September 2013"},{"key":"1034_CR2","unstructured":"nVidia (2013) http:\/\/www.nvidia.com . Accessed 17 September 2013"},{"key":"1034_CR3","unstructured":"Cloud computing (2013) http:\/\/en.wikipedia.org\/wiki\/Cloud_computing . Accessed 17 September 2013"},{"key":"1034_CR4","unstructured":"GPGPU (2013) http:\/\/en.wikipedia.org\/wiki\/GPGPU . Accessed 17 September 2013"},{"key":"1034_CR5","unstructured":"PCI-pass-through (2013) http:\/\/www.ibm.com\/developerworks\/linux\/library\/l-pci-passthrough . Accessed 17 September 2013"},{"key":"1034_CR6","unstructured":"CUDA (2013) http:\/\/www.nvidia.com.tw\/object\/cuda_home_new_tw.html . Accessed 17 September 2013"},{"key":"1034_CR7","unstructured":"National Institute of Standards and Technology (2013) http:\/\/www.nist.gov\/index.html . Accessed 17 September"},{"key":"1034_CR8","unstructured":"Virtualization (2013) http:\/\/en.wikipedia.org\/wiki\/Virtualization . Accessed 17 September 2013"},{"key":"1034_CR9","unstructured":"Full virtualization (2013) http:\/\/en.wikipedia.org\/wiki\/Full_virtualization . Accessed 17 September 2013"},{"key":"1034_CR10","unstructured":"Para virtualization (2013) http:\/\/en.wikipedia.org\/wiki\/Paravirtualization . Accessed 17 September 2013"},{"key":"1034_CR11","unstructured":"Xen (2013) http:\/\/www.xen.org . Accessed 17 September 2013"},{"key":"1034_CR12","unstructured":"KVM (2013) http:\/\/www.linux-kvm.org\/page\/Main_Page . Accessed 17 September 2013"},{"key":"1034_CR13","unstructured":"NVIDIA CUDA SDK (2013) http:\/\/developer.nvidia.com\/cuda-cc-sdk-code-samples . Accessed 17 September 2013"},{"key":"1034_CR14","unstructured":"Download CUDA (2013) http:\/\/developer.nvidia.com\/object\/cuda.htm . Accessed 17 September 2013"},{"key":"1034_CR15","unstructured":"NVIDIA CUDA programming guide (2013) http:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html#abstract . Accessed 17 September 2013"},{"key":"1034_CR16","unstructured":"CUDA-wiki (2013) http:\/\/en.wikipedia.org\/wiki\/CUDA . Accessed 17 September 2013"},{"key":"1034_CR17","series-title":"Lecture notes in computer science","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1007\/978-3-642-15277-1_5","volume-title":"Euro-par 2010\u2014parallel processing","author":"FV Lionetti","year":"2010","unstructured":"Lionetti FV, McCulloch AD, Baden SB (2010) Source-to-source optimization of CUDA C for GPU accelerated cardiac cell modeling. In: Euro-par 2010\u2014parallel processing. Lecture notes in computer science, vol 6271, pp 38\u201349"},{"issue":"Suppl\u00a07","key":"1034_CR18","volume":"10","author":"S Jung","year":"2009","unstructured":"Jung S (2009) Parallelized pairwise sequence alignment using CUDA on multiple GPUs. BMC Bioinform 10(Suppl\u00a07):A3","journal-title":"BMC Bioinform"},{"issue":"10","key":"1034_CR19","doi-asserted-by":"crossref","first-page":"1370","DOI":"10.1016\/j.jpdc.2008.05.014","volume":"68","author":"S Che","year":"2008","unstructured":"Che S, Boyer M, Meng J, Tarjan D, Sheaffer JW, Skadron K (2008) A performance study of general-purpose applications on graphics processors using CUDA. J Parallel Distrib Comput 68(10):1370\u20131380","journal-title":"J Parallel Distrib Comput"},{"key":"1034_CR20","unstructured":"OpenCL (2013) http:\/\/www.khronos.org\/opencl . Accessed 17 September 2013"},{"key":"1034_CR21","unstructured":"OpenCL-wiki (2013) http:\/\/en.wikipedia.org\/wiki\/OpenCL . Accessed 17 September 2013"},{"issue":"4","key":"1034_CR22","doi-asserted-by":"crossref","first-page":"1093","DOI":"10.1016\/j.cpc.2010.12.052","volume":"182","author":"MJ Harvey","year":"2011","unstructured":"Harvey MJ, De Fabritiis G (2011) Swan: a tool for porting CUDA programs to OpenCL. Comput Phys Commun 182(4):1093\u20131099","journal-title":"Comput Phys Commun"},{"key":"1034_CR23","unstructured":"QEMU (2013) http:\/\/wiki.qemu.org\/Main_Page . Accessed 17 September 2013"},{"key":"1034_CR24","unstructured":"VirtualBox (2013) https:\/\/www.virtualbox.org . Accessed 17 September 2013"},{"key":"1034_CR25","first-page":"250","volume-title":"Proceedings of IEEE 34th annual computer software and applications conference","author":"C-TD Lo","year":"2010","unstructured":"Lo C-TD, Qian K (2010) Green computing methodology for next generation computing scientists. In: Proceedings of IEEE 34th annual computer software and applications conference, pp 250\u2013251"},{"key":"1034_CR26","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1109\/GreenCom-CPSCom.2010.110","volume-title":"Proceedings of the 2010 IEEE\/ACM int\u2019l conference on green computing and communications & int\u2019l conference on cyber, physical and social computing (GREENCOM-CPSCOM\u201910)","author":"B Zhong","year":"2010","unstructured":"Zhong B, Feng M, Lung C-H (2010) A green computing based architecture comparison and analysis. In: Proceedings of the 2010 IEEE\/ACM int\u2019l conference on green computing and communications & int\u2019l conference on cyber, physical and social computing (GREENCOM-CPSCOM\u201910), pp 386\u2013391"},{"key":"1034_CR27","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1109\/HPCS.2010.5547126","volume-title":"Proceedings of the 2010 international conference on high performance computing & simulation (HPCS\u00a02010)","author":"J Duato","year":"2010","unstructured":"Duato J, Pe\u00f1a AJ, Silla F, Mayo R, Quintana-Ort\u00ed ES (2010) RCUDA: reducing the number of GPUbased accelerators in high performance clusters. In: Proceedings of the 2010 international conference on high performance computing & simulation (HPCS\u00a02010), June 2010, pp 224\u2013231"},{"key":"1034_CR28","first-page":"1","volume-title":"Proceedings of 18th international conference on high performance computing 2010 (HiPC)","author":"J Duato","year":"2011","unstructured":"Duato J, Pena AJ, Silla F, Fernandez JC, Mayo R, Quintana-Orti ES (2011) Enabling CUDA acceleration within virtual machines using rCUDA. In: Proceedings of 18th international conference on high performance computing 2010 (HiPC), pp 1\u201310"},{"key":"1034_CR29","first-page":"365","volume-title":"Proceedings of international conference on parallel processing (ICPP)","author":"J Duato","year":"2011","unstructured":"Duato J, Pe\u00f1a AJ, Silla F, Mayo R, Quintana-Orti ES (2011) Performance of CUDA virtualized remote GPUs in high performance clusters. In: Proceedings of international conference on parallel processing (ICPP), September\u00a02011, pp 365\u2013374"},{"key":"1034_CR30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IPDPS.2009.5161020","volume-title":"Proceedings of IEEE international symposium on parallel and distributed processing (IPDPS\u201909)","author":"L Shi","year":"2009","unstructured":"Shi L, Chen H, Sun J (2009) VCUDA: GPU accelerated high performance computing in virtual machines. In: Proceedings of IEEE international symposium on parallel and distributed processing (IPDPS\u201909), pp 1\u201311"},{"key":"1034_CR31","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1145\/1519138.1519141","volume-title":"3rd workshop on system-level virtualization for high performance computing","author":"V Gupta","year":"2009","unstructured":"Gupta V, Gavrilovska A, Schwan K, Kharche H, Tolia N, Talwar V, Ranganathan P (2009) GViM: GPU-accelerated virtual machines. In: 3rd workshop on system-level virtualization for high performance computing. ACM, NY, USA, pp 17\u201324"},{"key":"1034_CR32","series-title":"Lecture notes in computer science","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1007\/978-3-642-15277-1_37","volume-title":"Euro-Par 2010\u2014parallel processing","author":"G Giunta","year":"2010","unstructured":"Giunta G, Montella R, Agrillo G, Coviello G (2010) A GPGPU transparent virtualization component for high performance computing clouds. In: Ambra PD, Guarracino M, Talia D (eds) Euro-Par 2010\u2014parallel processing. Lecture notes in computer science, vol 6271. Springer, Berlin, pp 379\u2013391"},{"key":"1034_CR33","unstructured":"Front and back ends (2013) http:\/\/en.wikipedia.org\/wiki\/Front_and_back_ends . Accessed 17 September 2013"},{"key":"1034_CR34","unstructured":"VMGL (2013) http:\/\/sysweb.cs.toronto.edu\/vmgl . Accessed 17 September 2013"},{"key":"1034_CR35","series-title":"Lecture notes in computer science","first-page":"256","volume-title":"Computer architecture","author":"N Amit","year":"2012","unstructured":"Amit N, Ben-Yehuda M, Yassour B-A (2012) IOMMU: strategies for mitigating the IOTLB bottleneck. In: Computer architecture. Lecture notes in computer science, vol 6161, pp 256\u2013274"},{"key":"1034_CR36","unstructured":"NVIDIA Telsa C1060 computing processor (2012) http:\/\/www.nvidia.com\/object\/product_tesla_c1060_us.html . Accessed 12 May 2012"},{"key":"1034_CR37","unstructured":"NVIDIA quadro NVS 295 (2012) http:\/\/www.nvidia.com.tw\/object\/product_quadro_nvs_295_tw.html . Accessed 12 May 2012"},{"key":"1034_CR38","unstructured":"NVIDIA Telsa C2050 computing processor (2013) http:\/\/www.nvidia.com.tw\/object\/product_tesla_C2050_C2070_tw.html . Accessed 17 September 2013"},{"key":"1034_CR39","unstructured":"CentOS (2013) http:\/\/www.centos.org . Accessed 17 September 2013"},{"key":"1034_CR40","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1145\/1254810.1254816","volume-title":"Proceedings of the 3rd international conference on virtual execution environments (VEE\u201907)","author":"HA Lagar-Cavilla","year":"2007","unstructured":"Lagar-Cavilla HA, Tolia N, Satyanarayanan M, de Lara E (2007) VMM-independent graphics acceleration. In: Proceedings of the 3rd international conference on virtual execution environments (VEE\u201907). ACM, New York, pp 33\u201343"},{"issue":"1","key":"1034_CR41","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.cpc.2010.06.035","volume":"182","author":"CT Yang","year":"2010","unstructured":"Yang CT, Huang CL, Lin CF (2010) Hybrid CUDA, OpenMP, and MPI parallel programming on multicore GPU clusters. Comput Phys Commun 182(1):266\u2013269","journal-title":"Comput Phys Commun"},{"key":"1034_CR42","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1109\/ISPA.2010.97","volume-title":"Proceedings of international symposium on parallel and distributed processing with applications (ISPA)","author":"CT Yang","year":"2010","unstructured":"Yang CT, Huang CL, Lin CF, Chang TC (2010) Hybrid parallel programming on GPU clusters. In: Proceedings of international symposium on parallel and distributed processing with applications (ISPA), September 2010, pp 142\u2013147"},{"key":"1034_CR43","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1109\/ISPA.2011.60","volume-title":"Proceedings 2011 IEEE 9th international symposium on parallel and distributed processing with applications (ISPA)","author":"CT Yang","year":"2011","unstructured":"Yang CT, Chang TC, Wang HY, Chu WCC, Chang CH (2011) Performance comparison with OpenMP parallelization for multi-core systems. In: Proceedings 2011 IEEE 9th international symposium on parallel and distributed processing with applications (ISPA), pp 232\u2013237"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-013-1034-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-013-1034-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-013-1034-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,11]],"date-time":"2022-03-11T02:01:22Z","timestamp":1646964082000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-013-1034-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,10,31]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,4]]}},"alternative-id":["1034"],"URL":"https:\/\/doi.org\/10.1007\/s11227-013-1034-4","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,10,31]]}}}