{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T18:06:44Z","timestamp":1730225204521,"version":"3.28.0"},"reference-count":73,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/hpcs48598.2019.9188169","type":"proceedings-article","created":{"date-parts":[[2020,9,9]],"date-time":"2020-09-09T20:58:33Z","timestamp":1599685113000},"page":"880-889","source":"Crossref","is-referenced-by-count":2,"title":["Trillium: The code is the IR"],"prefix":"10.1109","author":[{"given":"Amogh","family":"Akshintala","sequence":"first","affiliation":[]},{"given":"Hangchen","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Arthur","family":"Peters","sequence":"additional","affiliation":[]},{"given":"Christopher J.","family":"Rossbach","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","article-title":"Full virtualization for gpus reconsidered","author":"yu","year":"2017","journal-title":"14th Workshop on Duplicating Deconstructing and Debunking (WDDD) ISCA"},{"key":"ref72","article-title":"An introduction to computational networks and the computational network toolkit","author":"yu","year":"2014","journal-title":"Microsoft Technical Report MSR-TR-2014–112"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/2854038.2854041"},{"key":"ref70","first-page":"15","article-title":"Protection strategies for direct access to virtualized i\/o devices","author":"willmann","year":"2008","journal-title":"2008 USENIX Annual Technical Conference"},{"key":"ref39","first-page":"2","article-title":"Timegraph: Gpu scheduling for real-time multi-tasking environments","author":"kato","year":"2011","journal-title":"Proceedings of the 2011 USENIX Conference on USENIX Annual Technical Conference USENIXATC’11"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC.and.EUC.2013.245"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2367589.2367593"},{"key":"ref31","first-page":"379391","article-title":"A gpgpu transparent virtualization component for high performance computing clouds","author":"giunta","year":"2010","journal-title":"Euro-par 2010-parallel Processing"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2011.6152718"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2892242.2892246"},{"key":"ref36","first-page":"231","article-title":"Efficient and scalable paravirtual i\/o system","author":"har\u2019el","year":"2013","journal-title":"Proceedings of the 2013 USENIX Conference on Annual Technical Conference USENIX ATC'13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1519138.1519141"},{"journal-title":"Kate Gregory and Ade Miller C++ AMP accelerated massive parallelism with Microsoft Visual C++","year":"2014","key":"ref34"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.69"},{"key":"ref62","first-page":"109","article-title":"Gpuvm: Why not virtualizing gpus at the hypervisor?","author":"suzuki","year":"2014","journal-title":"Proceedings of the 2014 USENIX Conference on USENIX Annual Technical Conference USENIX ATC’14"},{"key":"ref61","first-page":"1","article-title":"Virtualizing i\/o devices on vmware workstation’s hosted virtual machine monitor","author":"sugerman","year":"2001","journal-title":"Proc General Track 2001 Usenix Ann Technical Conf"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IPPS.1998.669932"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1618525.1618534"},{"key":"ref64","first-page":"121","article-title":"A full gpu virtualization solution with mediated pass-through","author":"tian","year":"2014","journal-title":"Proceedings of the 2014 USENIX Conference on USENIX Annual Technical Conference USENIX ATC’14"},{"key":"ref27","first-page":"10","article-title":"Sr-iov networking in xen: Architecture, design and implementation","author":"dong","year":"2008","journal-title":"Proceedings of the First Conference on I\/O Virtualization WIOV’08"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/HPCSim.2016.7568395"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2016.7482091"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1007\/978-3-642-14122-5_44","article-title":"An efficient implementation of gpu virtualization in high performance clusters","author":"duato","year":"2010","journal-title":"Proceedings of the 2009 international conference on Parallel processing Euro-Par’09"},{"journal-title":"Tungsten Graphics ShaderInfrastructure","article-title":"VMware, X.org, Nouveau","year":"2012","key":"ref67"},{"key":"ref68","first-page":"2:1","article-title":"Gpu virtualization for high performance general purpose computing on the esx hypervisor","author":"vu","year":"2014","journal-title":"Proceedings of the High Performance Computing Symposium - HPC"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/2892242.2892249"},{"journal-title":"Francisco Jerez’s TGSI back-end","year":"2018","key":"ref2"},{"journal-title":"Cairo-perf-trace","year":"2018","key":"ref1"},{"key":"ref20","first-page":"41","article-title":"Qemu, a fast and portable dynamic translator","author":"bellard","year":"2005","journal-title":"USENIX Annual Technical Conference Freenix track"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141947"},{"journal-title":"Bitfusion FlexDirect Virtualization Technology White Paper","year":"2019","key":"ref21"},{"key":"ref24","first-page":"21","article-title":"Zero-copy tcp in solaris","author":"jerry chu","year":"1996","journal-title":"Proceedings of the 1996 Annual Conference on USENIX Annual Technical Conference"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"ref25","article-title":"Torch7: A matlab-like environment for machine learning","author":"collobert","year":"2011","journal-title":"BigLearn NIPS Workshop number EPFL-CONF-192376"},{"journal-title":"Windows GDI","article-title":"Microsoft Inc","year":"2017","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1272366.1272390"},{"journal-title":"GPUfs Integrating a file system with GPUs","year":"2013","author":"silberstein","key":"ref59"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2011.112"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2011.6114174"},{"journal-title":"The OpenGL Graphics System A Specification","year":"2006","author":"segal","key":"ref56"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522715"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/2043556.2043579"},{"key":"ref53","first-page":"1","article-title":"Cu2rcu: Towards the complete rcuda remote gpu virtualization and sharing solution","volume":"0","author":"reano","year":"2012","journal-title":"20th Annual International Conference on High Performance Computing"},{"key":"ref52","first-page":"1","article-title":"Redesigning xens memory sharing mechanism for safe and efficient i\/o virtualization","author":"ram","year":"2010","journal-title":"Proceedings of the 2nd Conference on I\/O Virtualization"},{"journal-title":"Gallium3D technical overview","year":"2017","key":"ref10"},{"journal-title":"The Mesa 3d Graphics Library","year":"2017","key":"ref11"},{"key":"ref40","first-page":"37","article-title":"Gdev: First-class gpu resource management in the operating system","author":"kato","year":"2012","journal-title":"Proceedings of the 2012 USENIX Conference on Annual Technical Conference USENIX ATC"},{"journal-title":"Top500 Supercomputer Sites","year":"2019","key":"ref12"},{"key":"ref13","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv preprint arXiv 1603 04467"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056046"},{"journal-title":"Amazon Elastic Compute Cloud","article-title":"Amazon","year":"2015","key":"ref15"},{"journal-title":"Amazon EC2 P3 Instances","article-title":"Inc or Its Affiliates Amazon Web Services","year":"2018","key":"ref16"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1145\/2541940.2541943","article-title":"I\/o paravirtualization at the device file boundary","author":"sani","year":"2014","journal-title":"Proceedings of the 19th International Conference onArchitectural Support for Programming Languages and Operating Systems ASPLOS ’14"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTERWKSP.2010.5613086"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1165389.945462"},{"journal-title":"GPU Applications Catalog","year":"2018","key":"ref4"},{"journal-title":"Galliumcompute","year":"2018","key":"ref3"},{"journal-title":"Phoronix test suite","year":"2018","key":"ref6"},{"journal-title":"Hans de Goede’s TGSI back-end","year":"2018","key":"ref5"},{"journal-title":"NVIDIA CUDA 4 0","year":"2011","key":"ref8"},{"journal-title":"Why frame rate and resolution matter","year":"2011","key":"ref7"},{"key":"ref49","first-page":"3","article-title":"High performance vmm-bypass i\/o in virtual machines","author":"liu","year":"2006","journal-title":"Proceedings of the Annual Conference on USENIX ’06 Annual Technical Conference ATEC ’06"},{"journal-title":"Nouveau Open-Source Driver","year":"2017","key":"ref9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1254810.1254816"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WAINA.2011.82"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2011.88"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304623"},{"journal-title":"Vulkan 1 0 64 - A Specification","article-title":"Khronos Group","year":"2017","key":"ref41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1254810.1254816"},{"key":"ref43","first-page":"201","article-title":"GPUnet: Networking abstractions for GPU programs","author":"kim","year":"2014","journal-title":"Proceedings of the 11th USENIX Conference on OperatingSystems Design and Implementation OSDI’14"}],"event":{"name":"2019 International Conference on High Performance Computing & Simulation (HPCS)","start":{"date-parts":[[2019,7,15]]},"location":"Dublin, Ireland","end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Conference on High Performance Computing & Simulation (HPCS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9183768\/9188050\/09188169.pdf?arnumber=9188169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:50:28Z","timestamp":1658094628000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9188169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/hpcs48598.2019.9188169","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}