{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:37:03Z","timestamp":1772725023993,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T00:00:00Z","timestamp":1593388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,29]]},"DOI":"10.1145\/3392717.3392760","type":"proceedings-article","created":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T18:49:02Z","timestamp":1593456542000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Tuning applications for efficient GPU offloading to in-memory processing"],"prefix":"10.1145","author":[{"given":"Yudong","family":"Wu","sequence":"first","affiliation":[{"name":"University of California"}]},{"given":"Mingyao","family":"Shen","sequence":"additional","affiliation":[{"name":"University of California"}]},{"given":"Yi-Hui","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California"}]},{"given":"Yuanyuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of California"}]}],"member":"320","published-online":{"date-parts":[[2020,6,29]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872887.2750386"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_5_1","volume-title":"Prime: A novel processing-in-memory architecture for neural network computation in reram-based main memory. In ACM SIGARCH Computer Architecture News","author":"Chi Ping","year":"2016"},{"key":"e_1_3_2_1_6_1","unstructured":"NVIDIA Corporation. 2018. NVIDIA TURING GPU ARCHITECTURE. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/design-visualization\/technologies\/turing-architecture\/NVIDIA-Turing-Architecture-Whitepaper.pdf.  NVIDIA Corporation. 2018. NVIDIA TURING GPU ARCHITECTURE. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/design-visualization\/technologies\/turing-architecture\/NVIDIA-Turing-Architecture-Whitepaper.pdf."},{"key":"e_1_3_2_1_7_1","volume-title":"Principles and practices of interconnection networks","author":"Dally William James"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"e_1_3_2_1_9_1","volume-title":"Viram1: A media-oriented vector processor with embedded dram. DAC04","author":"Gebis Joseph","year":"2004"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Scott Grauer-Gray Lifan Xu Robert Searles Sudhee Ayalasomayajula and John Cavazos. 2012. Auto-tuning a high-level language targeted to GPU codes. In 2012 Innovative Parallel Computing (InPar). Ieee.  Scott Grauer-Gray Lifan Xu Robert Searles Sudhee Ayalasomayajula and John Cavazos. 2012. Auto-tuning a high-level language targeted to GPU codes. In 2012 Innovative Parallel Computing (InPar). Ieee.","DOI":"10.1109\/InPar.2012.6339595"},{"key":"e_1_3_2_1_11_1","unstructured":"IMPACT Research Group. 2010. Download Parboil. http:\/\/impact.crhc.illinois.edu\/parboil\/parboil_download_page.aspx  IMPACT Research Group. 2010. Download Parboil. http:\/\/impact.crhc.illinois.edu\/parboil\/parboil_download_page.aspx"},{"key":"e_1_3_2_1_12_1","unstructured":"Mark Harris. 2019. Optimizing Parallel Reduction in CUDA. https:\/\/developer.download.nvidia.com\/assets\/cuda\/files\/reduction.pdf  Mark Harris. 2019. Optimizing Parallel Reduction in CUDA. https:\/\/developer.download.nvidia.com\/assets\/cuda\/files\/reduction.pdf"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001159"},{"key":"e_1_3_2_1_14_1","volume-title":"Asit K Mishra, Mahmut T Kandemir, Onur Mutlu, Ravishankar Iyer, and Chita R Das.","author":"Jog Adwait","year":"2013"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.89"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126965"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898064"},{"key":"e_1_3_2_1_18_1","unstructured":"Vishal Mehta and Maxim Milakov. 2018. OPTIMIZING CUDA APPLICATIONS FOR THE VOLTA\/TURING ARCHITECTURE. http:\/\/on-demand.gputechconf.com\/gtc-il\/2018\/pdf\/sil8140-optimizing-cuda-applications-for-the-volta-turing-gpu-architecture.pdf.  Vishal Mehta and Maxim Milakov. 2018. OPTIMIZING CUDA APPLICATIONS FOR THE VOLTA\/TURING ARCHITECTURE. http:\/\/on-demand.gputechconf.com\/gtc-il\/2018\/pdf\/sil8140-optimizing-cuda-applications-for-the-volta-turing-gpu-architecture.pdf."},{"key":"e_1_3_2_1_19_1","volume-title":"GPU technology conference","author":"Micikevicius Paulius"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155656"},{"key":"e_1_3_2_1_21_1","unstructured":"NVIDIA. 2019. CUDA Toolkit 9.1 Download - Archived. https:\/\/developer.nvidia.com\/cuda-91-download-archive  NVIDIA. 2019. CUDA Toolkit 9.1 Download - Archived. https:\/\/developer.nvidia.com\/cuda-91-download-archive"},{"key":"e_1_3_2_1_22_1","unstructured":"NVIDIA. 2019. CUDA Zone. http:\/\/developer.nvidia.com\/object\/cuda.html  NVIDIA. 2019. CUDA Zone. http:\/\/developer.nvidia.com\/object\/cuda.html"},{"key":"e_1_3_2_1_23_1","unstructured":"NVIDIA. 2019. Optimizing CUDA applications. https:\/\/docs.nvidia.com\/cuda\/cuda-c-best-practices-guide\/index.html#optimizing-cuda-applications.  NVIDIA. 2019. Optimizing CUDA applications. https:\/\/docs.nvidia.com\/cuda\/cuda-c-best-practices-guide\/index.html#optimizing-cuda-applications."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967940"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446064"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/339647.339668"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1345206.1345220"},{"key":"e_1_3_2_1_29_1","unstructured":"Micron Technology. 2011. 4Gb: x4 x8 x16 DDR3 SDRAM. 4Gb:x4 x8 x16DDR3SDRAM  Micron Technology. 2011. 4Gb: x4 x8 x16 DDR3 SDRAM. 4Gb:x4 x8 x16DDR3SDRAM"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2012.6378607"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750399"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.37"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600213"},{"key":"e_1_3_2_1_34_1","first-page":"630","article-title":"Controller for a synchronous DRAM that maximizes throughput by allowing memory requests and commands to be issued out of order","volume":"5","author":"Zuravleff William K","year":"1997","journal-title":"US Patent"}],"event":{"name":"ICS '20: 2020 International Conference on Supercomputing","location":"Barcelona Spain","acronym":"ICS '20","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 34th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3392717.3392760","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3392717.3392760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:15Z","timestamp":1750200075000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3392717.3392760"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,29]]},"references-count":34,"alternative-id":["10.1145\/3392717.3392760","10.1145\/3392717"],"URL":"https:\/\/doi.org\/10.1145\/3392717.3392760","relation":{},"subject":[],"published":{"date-parts":[[2020,6,29]]},"assertion":[{"value":"2020-06-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}