{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T05:10:20Z","timestamp":1767849020741,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,9,7]],"date-time":"2020-09-07T00:00:00Z","timestamp":1599436800000},"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":[[2020,9,7]]},"DOI":"10.1145\/3386263.3406896","type":"proceedings-article","created":{"date-parts":[[2020,9,4]],"date-time":"2020-09-04T21:34:23Z","timestamp":1599255263000},"page":"199-204","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["TUPIM: A Transparent and Universal Processing-in-Memory Architecture for Unmodified Binaries"],"prefix":"10.1145","author":[{"given":"Sheng","family":"Xu","sequence":"first","affiliation":[{"name":"Anhui Normal University & Institute of Computing Technology, Chinese Academy of Sciences, hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuehai","family":"Qian","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinhe","family":"Han","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,9,7]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2015.2409732"},{"issue":"4","key":"e_1_3_2_2_3_1","first-page":"640","article-title":"GraphH: A Processing-in-Memory Architecture for Large-Scale Graph Processing","volume":"38","author":"Dai G.","year":"2019","unstructured":"G. Dai , \" GraphH: A Processing-in-Memory Architecture for Large-Scale Graph Processing ,\" IEEE TCAD , vol. 38 , no. 4 , pp. 640 -- 653 , April 2019 . G. Dai et al., \"GraphH: A Processing-in-Memory Architecture for Large-Scale Graph Processing,\" IEEE TCAD, vol. 38, no. 4, pp. 640--653, April 2019.","journal-title":"IEEE TCAD"},{"key":"e_1_3_2_2_4_1","first-page":"544","article-title":"GraphP: Reducing Communication for PIM-Based Graph Processing with Efficient Data Partition","author":"Zhang M.","year":"2018","unstructured":"M. Zhang , \" GraphP: Reducing Communication for PIM-Based Graph Processing with Efficient Data Partition ,\" in HPCA , Feb 2018 , pp. 544 -- 557 . M. Zhang et al., \"GraphP: Reducing Communication for PIM-Based Graph Processing with Efficient Data Partition,\" in HPCA, Feb 2018, pp. 544--557.","journal-title":"HPCA"},{"key":"e_1_3_2_2_5_1","first-page":"457","article-title":"GraphPIM: Enabling Instruction-Level PIM Offloading in Graph Computing Frameworks","author":"Nai L.","year":"2017","unstructured":"L. Nai , \" GraphPIM: Enabling Instruction-Level PIM Offloading in Graph Computing Frameworks ,\" in HPCA , Feb 2017 , pp. 457 -- 468 . L. Nai et al., \"GraphPIM: Enabling Instruction-Level PIM Offloading in Graph Computing Frameworks,\" in HPCA, Feb 2017, pp. 457--468.","journal-title":"HPCA"},{"issue":"1","key":"e_1_3_2_2_6_1","first-page":"5","article-title":"HMC-MAC: Processing-in Memory Architecture for Multiply-Accumulate Operations with Hybrid Memory Cube","volume":"17","author":"Jeon D.","year":"2018","unstructured":"D. Jeon , \" HMC-MAC: Processing-in Memory Architecture for Multiply-Accumulate Operations with Hybrid Memory Cube ,\" IEEE CAL , vol. 17 , no. 1 , pp. 5 -- 8 , Jan 2018 . D. Jeon et al., \"HMC-MAC: Processing-in Memory Architecture for Multiply-Accumulate Operations with Hybrid Memory Cube,\" IEEE CAL, vol. 17, no. 1, pp. 5--8, Jan 2018.","journal-title":"IEEE CAL"},{"key":"e_1_3_2_2_7_1","first-page":"113","article-title":"Practical Near-Data Processing for In-Memory Analytics Frameworks","author":"Gao M.","year":"2015","unstructured":"M. Gao , \" Practical Near-Data Processing for In-Memory Analytics Frameworks ,\" in PACT , Oct 2015 , pp. 113 -- 124 . M. Gao et al., \"Practical Near-Data Processing for In-Memory Analytics Frameworks,\" in PACT, Oct 2015, pp. 113--124.","journal-title":"PACT"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124544"},{"issue":"1","key":"e_1_3_2_2_9_1","first-page":"46","article-title":"LazyPIM: An Efficient Cache Coherence Mechanism for Processing-in-Memory","volume":"16","author":"Boroumand A.","year":"2017","unstructured":"A. Boroumand , \" LazyPIM: An Efficient Cache Coherence Mechanism for Processing-in-Memory ,\" IEEE CAL , vol. 16 , no. 1 , pp. 46 -- 50 , Jan 2017 . A. Boroumand et al., \"LazyPIM: An Efficient Cache Coherence Mechanism for Processing-in-Memory,\" IEEE CAL, vol. 16, no. 1, pp. 46--50, Jan 2017.","journal-title":"IEEE CAL"},{"key":"e_1_3_2_2_10_1","first-page":"140","article-title":"CuckooPIM: An Efficient and Less-blocking Coherence Mechanism for Processing-in-memory Systems","author":"Xu S.","year":"2019","unstructured":"S. Xu , \" CuckooPIM: An Efficient and Less-blocking Coherence Mechanism for Processing-in-memory Systems ,\" in ASP-DAC , 2019 , pp. 140 -- 145 . S. Xu et al., \"CuckooPIM: An Efficient and Less-blocking Coherence Mechanism for Processing-in-memory Systems,\" in ASP-DAC, 2019, pp. 140--145.","journal-title":"ASP-DAC"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"e_1_3_2_2_12_1","first-page":"680","article-title":"CoolPIM: Thermal-Aware Source Throttling for Efficient PIM Instruction Offloading","author":"Nai L.","year":"2018","unstructured":"L. Nai , \" CoolPIM: Thermal-Aware Source Throttling for Efficient PIM Instruction Offloading ,\" in IPDPS , May 2018 , pp. 680 -- 689 . L. Nai et al., \"CoolPIM: Thermal-Aware Source Throttling for Efficient PIM Instruction Offloading,\" in IPDPS, May 2018, pp. 680--689.","journal-title":"IPDPS"},{"key":"e_1_3_2_2_13_1","first-page":"1387","article-title":"Prometheus: Processing-in-memory heterogeneous architecture design from a multi-layer network theoretic strategy","author":"Xiao Y.","year":"2018","unstructured":"Y. Xiao , \" Prometheus: Processing-in-memory heterogeneous architecture design from a multi-layer network theoretic strategy ,\" in DATE , March 2018 , pp. 1387 -- 1392 . Y. Xiao et al., \"Prometheus: Processing-in-memory heterogeneous architecture design from a multi-layer network theoretic strategy,\" in DATE, March 2018, pp. 1387--1392.","journal-title":"DATE"},{"issue":"1","key":"e_1_3_2_2_14_1","first-page":"6","article-title":"PIMSim: A Flexible and Detailed Processing-in-Memory Simulator","volume":"18","author":"Xu S.","year":"2019","unstructured":"S. Xu , \" PIMSim: A Flexible and Detailed Processing-in-Memory Simulator ,\" IEEE CAL , vol. 18 , no. 1 , pp. 6 -- 9 , Jan 2019 . S. Xu et al., \"PIMSim: A Flexible and Detailed Processing-in-Memory Simulator,\" IEEE CAL, vol. 18, no. 1, pp. 6--9, Jan 2019.","journal-title":"IEEE CAL"},{"key":"e_1_3_2_2_15_1","first-page":"75","article-title":"LLVM: a compilation framework for lifelong program analysis transformation","author":"Lattner C.","year":"2004","unstructured":"C. Lattner and V. Adve , \" LLVM: a compilation framework for lifelong program analysis transformation ,\" in CGO , March 2004 , pp. 75 -- 86 . C. Lattner and V. Adve, \"LLVM: a compilation framework for lifelong program analysis transformation,\" in CGO, March 2004, pp. 75--86.","journal-title":"CGO"},{"key":"e_1_3_2_2_16_1","unstructured":"\"Cache replacement polices. \" [Online]. Available: https:\/\/en.wikipedia.org\/wiki\/Cache_algorithms  \"Cache replacement polices. \" [Online]. Available: https:\/\/en.wikipedia.org\/wiki\/Cache_algorithms"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.111.0025"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/285930.285947"},{"key":"e_1_3_2_2_19_1","unstructured":"Hybrid Memory Cube Consortium \"HMC specification 2.0 \" 2015.  Hybrid Memory Cube Consortium \"HMC specification 2.0 \" 2015."},{"key":"e_1_3_2_2_20_1","unstructured":"\"MESI protocol. \" [Online]. Available: https:\/\/en.wikipedia.org\/wiki\/MESI_protocol  \"MESI protocol. \" [Online]. Available: https:\/\/en.wikipedia.org\/wiki\/MESI_protocol"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2024716.2024718"},{"key":"e_1_3_2_2_22_1","first-page":"1","article-title":"GraphBIG: understanding graph computing in the context of industrial solutions","author":"Nai L.","year":"2015","unstructured":"L. Nai , \" GraphBIG: understanding graph computing in the context of industrial solutions ,\" in SC , Nov 2015 , pp. 1 -- 12 . L. Nai et al., \"GraphBIG: understanding graph computing in the context of industrial solutions,\" in SC, Nov 2015, pp. 1--12.","journal-title":"SC"},{"key":"e_1_3_2_2_23_1","first-page":"243","article-title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","author":"Han S.","year":"2016","unstructured":"S. Han , \" EIE: Efficient Inference Engine on Compressed Deep Neural Network ,\" in ISCA , June 2016 , pp. 243 -- 254 . S. Han et al., \"EIE: Efficient Inference Engine on Compressed Deep Neural Network,\" in ISCA, June 2016, pp. 243--254.","journal-title":"ISCA"},{"key":"e_1_3_2_2_24_1","first-page":"707","volume-title":"March 2015","author":"Schaffner M.","unstructured":"M. Schaffner DRAM or no-DRAM\" Exploring linear solver architectures for image domain warping in 28 nm CMOS,\" in DATE , March 2015 , pp. 707 -- 712 . M. Schaffner et al., \"DRAM or no-DRAM\" Exploring linear solver architectures for image domain warping in 28 nm CMOS,\" in DATE, March 2015, pp. 707--712."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/s121115088"}],"event":{"name":"GLSVLSI '20: Great Lakes Symposium on VLSI 2020","location":"Virtual Event China","acronym":"GLSVLSI '20"},"container-title":["Proceedings of the 2020 on Great Lakes Symposium on VLSI"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3386263.3406896","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3386263.3406896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:13Z","timestamp":1750201993000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3386263.3406896"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,7]]},"references-count":25,"alternative-id":["10.1145\/3386263.3406896","10.1145\/3386263"],"URL":"https:\/\/doi.org\/10.1145\/3386263.3406896","relation":{},"subject":[],"published":{"date-parts":[[2020,9,7]]},"assertion":[{"value":"2020-09-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}