{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T05:51:49Z","timestamp":1733896309493,"version":"3.30.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,22]],"date-time":"2020-06-22T00:00:00Z","timestamp":1592784000000},"content-version":"vor","delay-in-days":366,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1525412, CNS-1525474"],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MINECO","award":["TIN2016-78799-P"]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,22]]},"DOI":"10.1145\/3307650.3322230","type":"proceedings-article","created":{"date-parts":[[2019,6,14]],"date-time":"2019-06-14T12:42:33Z","timestamp":1560516153000},"page":"197-209","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":53,"title":["MGPUSim"],"prefix":"10.1145","author":[{"given":"Yifan","family":"Sun","sequence":"first","affiliation":[{"name":"Northeastern University"}]},{"given":"Trinayan","family":"Baruah","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Saiful A.","family":"Mojumder","sequence":"additional","affiliation":[{"name":"Boston University"}]},{"given":"Shi","family":"Dong","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Xiang","family":"Gong","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Shane","family":"Treadway","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Yuhui","family":"Bao","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Spencer","family":"Hance","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Carter","family":"McCardwell","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Vincent","family":"Zhao","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Harrison","family":"Barclay","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Amir Kavyan","family":"Ziabari","sequence":"additional","affiliation":[{"name":"AMD"}]},{"given":"Zhongliang","family":"Chen","sequence":"additional","affiliation":[{"name":"AMD"}]},{"given":"Rafael","family":"Ubal","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Jos\u00e9 L.","family":"Abell\u00e1n","sequence":"additional","affiliation":[{"name":"Universidad Cat\u00f3lica San Antonio Murcia"}]},{"given":"John","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST"}]},{"given":"Ajay","family":"Joshi","sequence":"additional","affiliation":[{"name":"Boston University"}]},{"given":"David","family":"Kaeli","sequence":"additional","affiliation":[{"name":"Northeastern University"}]}],"member":"320","published-online":{"date-parts":[[2019,6,22]]},"reference":[{"unstructured":"AMD. 2015. AMD Radeon R9 Series Gaming Graphics Cards with High-Bandwidth Memory.","key":"e_1_3_2_1_1_1"},{"volume-title":"Generation 3, Reference Guide.","year":"2016","author":"AMD.","unstructured":"AMD. 2016. Graphics Core Next Architecture, Generation 3, Reference Guide. (2016).","key":"e_1_3_2_1_2_1"},{"unstructured":"AMD. 2017. AMD APP SDK 3.0 Getting Started. (2017).","key":"e_1_3_2_1_3_1"},{"volume-title":"Reference Guide.","year":"2017","author":"AMD.","unstructured":"AMD. 2017. Vega Instruction Set Architecture, Reference Guide. (2017).","key":"e_1_3_2_1_4_1"},{"unstructured":"AMD. 2018. Radeon Compute Profiler. https:\/\/github.com\/GPUOpen-Tools\/RCP","key":"e_1_3_2_1_5_1"},{"unstructured":"AMD. 2018. Radeon Instinct MI60 Accelerator. https:\/\/www.amd.com\/en\/products\/professional-graphics\/instinct-mi60","key":"e_1_3_2_1_6_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1145\/3079856.3080231"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1145\/3123939.3123975"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1145\/3173162.3173169"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_10_1","DOI":"10.1109\/ISPASS.2009.4919648"},{"volume-title":"An analysis of deep neural network models for practical applications. arXiv preprint arXiv:1605.07678","year":"2016","author":"Canziani Alfredo","unstructured":"Alfredo Canziani, Adam Paszke, and Eugenio Culurciello. 2016. An analysis of deep neural network models for practical applications. arXiv preprint arXiv:1605.07678 (2016).","key":"e_1_3_2_1_11_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1109\/TSMC.2017.2690673"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_13_1","DOI":"10.1109\/MICRO.2014.63"},{"doi-asserted-by":"crossref","unstructured":"Sylvain Collange David Defour and David Parello. 2009. Barra a parallel functional GPGPU simulator. (2009).","key":"e_1_3_2_1_14_1","DOI":"10.1109\/MASCOTS.2010.43"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1109\/CVPR.2009.5206848"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1145\/3184407.3184423"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.1145\/84537.84545"},{"volume-title":"Scaling deep learning workloads: NVIDIA DGX-1\/Pascal and intel knights landing. Future Generation Computer Systems","year":"2018","author":"Gawande Nitin A","unstructured":"Nitin A Gawande, Jeff A Daily, Charles Siegel, Nathan R Tallent, and Abhinav Vishnu. 2018. Scaling deep learning workloads: NVIDIA DGX-1\/Pascal and intel knights landing. Future Generation Computer Systems (2018).","key":"e_1_3_2_1_18_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1109\/HPCA.2018.00058"},{"doi-asserted-by":"publisher","unstructured":"Wen-mei Hwu. 2015. Heterogeneous System Architecture: A new compute platform infrastructure. Morgan Kaufmann.","key":"e_1_3_2_1_20_1","DOI":"10.5555\/2935458"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.1016\/j.jmmm.2015.10.054"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.1007\/s10586-014-0400-1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1145\/2818950.2818979"},{"volume-title":"Graphics processing requirements for enabling immersive vr. AMD White Paper","year":"2015","author":"Kanter David","unstructured":"David Kanter. 2015. Graphics processing requirements for enabling immersive vr. AMD White Paper (2015).","key":"e_1_3_2_1_24_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_25_1","DOI":"10.1109\/MICRO.2014.55"},{"doi-asserted-by":"publisher","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.","key":"e_1_3_2_1_26_1","DOI":"10.5555\/2999134.2999257"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.1145\/3126908.3126950"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.5555\/3014904.3015012"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_29_1","DOI":"10.1109\/ISPASS.2013.6557151"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_30_1","DOI":"10.1109\/TC.2015.2444848"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_31_1","DOI":"10.1145\/3297858.3304044"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.1109\/HiPC.2014.7116897"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.1109\/Co-HPC.2014.8"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_34_1","DOI":"10.1145\/3123939.3124534"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_35_1","DOI":"10.1109\/IISWC.2018.8573521"},{"unstructured":"NVIDIA. 2010. CUDA Programming guide.","key":"e_1_3_2_1_36_1"},{"unstructured":"NVIDIA. 2018. Developing a Linux Kernel Module using GPUDirect RDMA. (2018).","key":"e_1_3_2_1_37_1"},{"volume-title":"https:\/\/www.nvidia.com\/en-us\/data-center\/dgx-2\/","year":"2018","author":"NVIDIA.","unstructured":"NVIDIA. 2018. NVIDIA DGX-2. (2018). https:\/\/www.nvidia.com\/en-us\/data-center\/dgx-2\/","key":"e_1_3_2_1_38_1"},{"unstructured":"NVIDIA. 2018. NVIDIA TITAN RTX. https:\/\/www.nvidia.com\/en-us\/titan\/titan-rtx\/","key":"e_1_3_2_1_39_1"},{"unstructured":"Open Source Initiative. {n. d.}. The MIT Licence.","key":"e_1_3_2_1_40_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_41_1","DOI":"10.1145\/1553374.1553486"},{"doi-asserted-by":"crossref","unstructured":"Ahmed Sanaullah Saiful A Mojumder Kathleen M Lewis and Martin C Herbordt. 2016. GPU-accelerated charge mapping.. In HPEC. 1--7.","key":"e_1_3_2_1_42_1","DOI":"10.1109\/HPEC.2016.7761599"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_43_1","DOI":"10.1109\/ICASSP.2016.7472620"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_44_1","DOI":"10.5555\/2028905"},{"volume-title":"OpenCL: A parallel programming standard for heterogeneous computing systems. Computing in science & engineering 12, 3","year":"2010","author":"Stone John E","unstructured":"John E Stone, David Gohara, and Guochun Shi. 2010. OpenCL: A parallel programming standard for heterogeneous computing systems. Computing in science & engineering 12, 3 (2010), 66--73.","key":"e_1_3_2_1_45_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_46_1","DOI":"10.1109\/IISWC.2016.7581262"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_47_1","DOI":"10.1109\/ISPASS.2018.00034"},{"unstructured":"The Go Authors. 2009. Effective Go. (2009).","key":"e_1_3_2_1_48_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_49_1","DOI":"10.1109\/2.769448"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_50_1","DOI":"10.1145\/2370816.2370865"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_51_1","DOI":"10.1109\/ISCA.2018.00075"},{"doi-asserted-by":"publisher","unstructured":"Nandita Vijaykumar Eiman Ebrahimi Kevin Hsieh Phillip B Gibbons and Onur Mutlu. 2018. The Locality Descriptor: A Holistic Cross-Layer Abstraction to Express Data Locality in GPUs. ISCA. 10.1109\/ISCA.2018.00074","key":"e_1_3_2_1_52_1","DOI":"10.1109\/ISCA.2018.00074"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_53_1","DOI":"10.1109\/NYSDS.2017.8085036"},{"volume-title":"Defending DNN Adversarial Attacks with Pruning and Logits Augmentation. In 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP). IEEE, 1144--1148","year":"2018","author":"Wang Siyue","unstructured":"Siyue Wang, Xiao Wang, Shaokai Ye, Pu Zhao, and Xue Lin. 2018. Defending DNN Adversarial Attacks with Pruning and Logits Augmentation. In 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP). IEEE, 1144--1148.","key":"e_1_3_2_1_54_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_55_1","DOI":"10.1007\/s11227-018-2649-2"},{"volume-title":"Deep image: Scaling up image recognition. arXiv preprint arXiv:1501.02876","year":"2015","author":"Wu Ren","unstructured":"Ren Wu, Shengen Yan, Yi Shan, Qingqing Dang, and Gang Sun. 2015. Deep image: Scaling up image recognition. arXiv preprint arXiv:1501.02876 (2015).","key":"e_1_3_2_1_56_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_57_1","DOI":"10.1109\/MICRO.2018.00035"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_58_1","DOI":"10.1145\/2996190"}],"event":{"sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS\\DATC IEEE Computer Society"],"acronym":"ISCA '19","name":"ISCA '19: The 46th Annual International Symposium on Computer Architecture","location":"Phoenix Arizona"},"container-title":["Proceedings of the 46th International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3307650.3322230","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3307650.3322230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T22:53:41Z","timestamp":1733871221000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322230"}},"subtitle":["enabling multi-GPU performance modeling and optimization"],"short-title":[],"issued":{"date-parts":[[2019,6,22]]},"references-count":58,"alternative-id":["10.1145\/3307650.3322230","10.1145\/3307650"],"URL":"https:\/\/doi.org\/10.1145\/3307650.3322230","relation":{},"subject":[],"published":{"date-parts":[[2019,6,22]]},"assertion":[{"value":"2019-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}
