{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T04:17:14Z","timestamp":1774671434842,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":100,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,3,9]],"date-time":"2020-03-09T00:00:00Z","timestamp":1583712000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1845986"],"award-info":[{"award-number":["1845986"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,3,9]]},"DOI":"10.1145\/3373376.3378497","type":"proceedings-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T22:37:01Z","timestamp":1584139021000},"page":"417-433","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":48,"title":["Livia"],"prefix":"10.1145","author":[{"given":"Elliot","family":"Lockerman","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Axel","family":"Feldmann","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}]},{"given":"Mohammad","family":"Bakhshalipour","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Alexandru","family":"Stanescu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Shashwat","family":"Gupta","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Daniel","family":"Sanchez","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Pittsburgh, PA, USA"}]},{"given":"Nathan","family":"Beckmann","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]}],"member":"320","published-online":{"date-parts":[[2020,3,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.21"},{"key":"e_1_3_2_1_2_1","volume-title":"Proc. ISCA-27","author":"Agarwal V."},{"key":"e_1_3_2_1_3_1","unstructured":"Agner Fog. 2020. The microarchitecture of Intel AMD and VIA CPUs. https:\/\/www.agner.org\/optimize\/microarchitecture.pdf.  Agner Fog. 2020. The microarchitecture of Intel AMD and VIA CPUs. https:\/\/www.agner.org\/optimize\/microarchitecture.pdf."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2004.824300"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173189"},{"key":"e_1_3_2_1_7_1","unstructured":"ARM. 2019. Cortex M0+. http:\/\/www.arm.com\/products\/processors\/ cortex-m\/cortex-m0plus.php.  ARM. 2019. Cortex M0+. http:\/\/www.arm.com\/products\/processors\/ cortex-m\/cortex-m0plus.php."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2015.12"},{"key":"e_1_3_2_1_9_1","volume-title":"Proc. PACT-22","author":"Beckmann Nathan","year":"2013"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056061"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1640089.1640096"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/74851.74861"},{"key":"e_1_3_2_1_13_1","unstructured":"Bryan Black. 2013. Die Stacking is Happening!. In MICRO-46 Keynote.  Bryan Black. 2013. Die Stacking is Happening!. In MICRO-46 Keynote."},{"key":"e_1_3_2_1_14_1","volume-title":"Proc. ASPLOS-XXIII.","author":"Boroumand Amirali","year":"2018"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2000.854380"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972740.43"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00014"},{"key":"e_1_3_2_1_19_1","unstructured":"CORGi Research Group. 2020. CORGi Research Group Web Page. https:\/\/cmu-corgi.github.io\/.  CORGi Research Group. 2020. CORGi Research Group Web Page. https:\/\/cmu-corgi.github.io\/."},{"key":"e_1_3_2_1_20_1","volume-title":"Introduction to algorithms","author":"Cormen Thomas H"},{"key":"e_1_3_2_1_21_1","volume-title":"GPU Computing: To Exascale and Beyond. In Supercomputing '10","author":"Dally William J.","year":"2010"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2013.6670342"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555269"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00040"},{"key":"e_1_3_2_1_25_1","volume-title":"Proc. ISCA-38","author":"Esmaeilzadeh H."},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. of the 2006 ACM\/IEEE conf. on Supercomputing.","author":"Fatahalian K."},{"key":"e_1_3_2_1_27_1","unstructured":"Michael Feldman. 2018. Intel Ships Xeon Skylake Processor with Integrated FPGA. https:\/\/www.top500.org\/news\/ intel-ships-xeon-skylake-processor-with-integrated-fpga\/.  Michael Feldman. 2018. Intel Ships Xeon Skylake Processor with Integrated FPGA. https:\/\/www.top500.org\/news\/ intel-ships-xeon-skylake-processor-with-integrated-fpga\/."},{"key":"e_1_3_2_1_28_1","volume-title":"Proc. ISCA-45","author":"Fuchs Adi","year":"2018"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.22"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446059"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749755"},{"key":"e_1_3_2_1_32_1","volume-title":"Dally","author":"Han Song","year":"2016"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.46"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2003.821545"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPGA.1997.624600"},{"key":"e_1_3_2_1_36_1","unstructured":"John Hennessy and David Patterson. 2018. A New Golden Age for Computer Architecture: Domain-Specific Hardware\/Software Co- Design Enhanced Security Open Instruction Sets and Agile Chip Development. In Turing Award Lecture.  John Hennessy and David Patterson. 2018. A New Golden Age for Computer Architecture: Domain-Specific Hardware\/Software Co- Design Enhanced Security Open Instruction Sets and Agile Chip Development. In Turing Award Lecture."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11515-8_3"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967958"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001159"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2016.7753257"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00018"},{"key":"e_1_3_2_1_43_1","unstructured":"Intel. 2018. Intel Arria 10 Device Datasheet. https: \/\/www.intel.com\/content\/dam\/www\/programmable\/us\/en\/pdfs\/ literature\/hb\/arria-10\/a10_datasheet.pdf.  Intel. 2018. Intel Arria 10 Device Datasheet. https: \/\/www.intel.com\/content\/dam\/www\/programmable\/us\/en\/pdfs\/ literature\/hb\/arria-10\/a10_datasheet.pdf."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540730"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815971"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783708"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/264107.264207"},{"key":"e_1_3_2_1_48_1","unstructured":"Norman P Jouppi Cliff Young Nishant Patil David Patterson Gaurav Agrawal Raminder Bajwa Sarah Bates Suresh Bhatia Nan Boden Al Borchers etal 2017. In-datacenter performance analysis of a tensor processing unit. arXiv preprint arXiv:1704.04760 (2017).  Norman P Jouppi Cliff Young Nishant Patil David Patterson Gaurav Agrawal Raminder Bajwa Sarah Bates Suresh Bhatia Nan Boden Al Borchers et al. 2017. In-datacenter performance analysis of a tensor processing unit. arXiv preprint arXiv:1704.04760 (2017)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749471"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.89"},{"key":"e_1_3_2_1_51_1","unstructured":"Richard E Kessler and James L Schwarzmeier. 1993. CRAY T3D: A new dimension for Cray Research. In Compcon Spring'93 Digest of Papers.  Richard E Kessler and James L Schwarzmeier. 1993. CRAY T3D: A new dimension for Cray Research. In Compcon Spring'93 Digest of Papers."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2017.05.020"},{"key":"e_1_3_2_1_53_1","unstructured":"Omer Khan Mieszko Lis and Srini Devadas. 2010. Em2: A scalable shared-memory multicore architecture. (2010).  Omer Khan Mieszko Lis and Srini Devadas. 2010. Em2: A scalable shared-memory multicore architecture. (2010)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967948"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1994.288140"},{"key":"e_1_3_2_1_56_1","volume-title":"Proc. OSDI-12","author":"Kwon Youngjin","year":"2016"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/264107.264206"},{"key":"e_1_3_2_1_58_1","volume-title":"Image annotation via graph learning. Pattern recognition","author":"Liu Jing","year":"2009"},{"key":"e_1_3_2_1_59_1","volume-title":"Challenges in parallel graph processing. PPL 17, 01","author":"Lumsdaine Andrew","year":"2007"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00022"},{"key":"e_1_3_2_1_61_1","volume-title":"Why on-chip cache coherence is here to stay. Commun. ACM","author":"Martin Milo","year":"2012"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00010"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872362.2872363"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358254"},{"key":"e_1_3_2_1_65_1","volume-title":"Stream-Dataflow Acceleration. In Proc. ISCA- 44","author":"Nowatzki Tony","year":"2017"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/325164.325117"},{"key":"e_1_3_2_1_68_1","volume-title":"Rangharajan Venkatesan, Brucek Khailany, Joel Emer, Stephen W. Keckler, and William J. Dally.","author":"Parashar Angshuman","year":"2017"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080217"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322212"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080256"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844483"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/1250662.1250709"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/192007.192062"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/2145694.2145708"},{"key":"e_1_3_2_1_76_1","volume-title":"Proc. ISCA-16","author":"Sakai Shuichi","year":"1989"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.20"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.9"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/237090.237144"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/165123.165152"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/192007.192072"},{"key":"e_1_3_2_1_82_1","volume-title":"Proc. DAC-46","author":"Shacham Ofer","year":"2009"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19328-6_1"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442530"},{"key":"e_1_3_2_1_85_1","unstructured":"Etienne Sicard. 2017. Introducing 7-nm FinFET technology in Microwind. (2017).  Etienne Sicard. 2017. Introducing 7-nm FinFET technology in Microwind. (2017)."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124540"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123986"},{"key":"e_1_3_2_1_88_1","volume-title":"WaveScalar. In Proc. MICRO-36","author":"Swanson Steven","year":"2003"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080214"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/139669.140382"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196895"},{"key":"e_1_3_2_1_92_1","volume-title":"John F Brown III, and Anant Agarwal","author":"Wentzlaff David","year":"2007"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.24"},{"key":"e_1_3_2_1_94_1","unstructured":"Xilinx. 2017. ZC706 evaluation board for the Zynq- 7000 XC7Z045 all programmable SoC user guide. https: \/\/www.xilinx.com\/support\/documentation\/boards_and_kits\/ zc706\/ug954-zc706-eval-board-xc7z045-ap-soc.pdf.  Xilinx. 2017. ZC706 evaluation board for the Zynq- 7000 XC7Z045 all programmable SoC user guide. https: \/\/www.xilinx.com\/support\/documentation\/boards_and_kits\/ zc706\/ug954-zc706-eval-board-xc7z045-ap-soc.pdf."},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830807"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600213"},{"key":"e_1_3_2_1_97_1","volume-title":"IEEE Computer Architecture Letters","author":"Zhang Dan","year":"2016"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173197"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783737"},{"key":"e_1_3_2_1_100_1","volume-title":"Proc. MICRO-48","author":"Zhang Guowei","year":"2015"},{"key":"e_1_3_2_1_101_1","article-title":"Leveraging Hardware Caches for Memoization","volume":"17","author":"Zhang Guowei","year":"2018","journal-title":"Computer Architecture Letters (CAL)"}],"event":{"name":"ASPLOS '20: Architectural Support for Programming Languages and Operating Systems","location":"Lausanne Switzerland","acronym":"ASPLOS '20","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3373376.3378497","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3373376.3378497","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3373376.3378497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:32:59Z","timestamp":1750199579000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3373376.3378497"}},"subtitle":["Data-Centric Computing Throughout the Memory Hierarchy"],"short-title":[],"issued":{"date-parts":[[2020,3,9]]},"references-count":100,"alternative-id":["10.1145\/3373376.3378497","10.1145\/3373376"],"URL":"https:\/\/doi.org\/10.1145\/3373376.3378497","relation":{},"subject":[],"published":{"date-parts":[[2020,3,9]]},"assertion":[{"value":"2020-03-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}