{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T18:00:13Z","timestamp":1785952813266,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":79,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T00:00:00Z","timestamp":1645488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["1937599"],"award-info":[{"award-number":["1937599"]}],"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":[[2022,2,28]]},"DOI":"10.1145\/3503222.3507706","type":"proceedings-article","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T20:49:01Z","timestamp":1645562941000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["TaskStream: accelerating task-parallel workloads by recovering program structure"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1654-6684","authenticated-orcid":false,"given":"Vidushi","family":"Dadu","sequence":"first","affiliation":[{"name":"University of California at Los Angeles, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8483-3824","authenticated-orcid":false,"given":"Tony","family":"Nowatzki","sequence":"additional","affiliation":[{"name":"University of California at Los Angeles, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,2,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. Apache MADlib: Big Data Machine Learning in SQL. https:\/\/madlib.apache.org\/"},{"key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. Intel Math Kernel library.. http:\/\/software.intel.com\/en-us\/intel-mkl"},{"key":"e_1_3_2_1_3_1","unstructured":"[n. d.]. PyTorch Geometric.. https:\/\/www.pyg.org\/"},{"key":"e_1_3_2_1_4_1","unstructured":"2021. Accelerated Computing with a Reconfigurable Dataflow Architecture. https:\/\/sambanova.ai\/wp-content\/uploads\/2021\/06\/SambaNova_RDA_Whitepaper_English.pdf"},{"key":"e_1_3_2_1_5_1","unstructured":"2021. Cerebras Systems: Achieving Industry Best AI Performance Through A Systems Approach. https:\/\/cerebras.net\/wp-content\/uploads\/2021\/04\/Cerebras-CS-2-Whitepaper.pdf"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378454"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/341800.341801"},{"key":"e_1_3_2_1_8_1","volume-title":"Instruction sets should be free: The case for risc-v. EECS Department","author":"Asanovi\u0107 Krste","year":"2014","unstructured":"Krste Asanovi\u0107 and David A Patterson. 2014. Instruction sets should be free: The case for risc-v. EECS Department, University of California, Berkeley, Tech. Rep. UCB\/EECS-2014-146, https:\/\/riscv.org\/publications\/"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2024716.2024718"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/209936.209958"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3310229"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/155332.155358"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1248377.1248396"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00014"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/jetcas.2019.2910232"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2017.7995277"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Jason Cong Hui Huang Chiyuan Ma Bingjun Xiao and Peipei Zhou. 2014. A fully pipelined and dynamically composable architecture of CGRA. In FCCM. 9\u201316. https:\/\/doi.org\/10.1109\/fccm.2014.12 10.1109\/fccm.2014.12","DOI":"10.1109\/fccm.2014.12"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00053"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358276"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358291"},{"key":"e_1_3_2_1_21_1","volume-title":"T. N. Vijaykumar, and Mithuna Thottethodi.","author":"Gondimalla Ashish","year":"2021","unstructured":"Ashish Gondimalla, Sree Charan Gundabolu, T. N. Vijaykumar, and Mithuna Thottethodi. 2021. Barrier-Free Large-Scale Sparse Tensor Accelerator (BARISTA) For Convolutional Neural Networks. CoRR, abs\/2104.08734 (2021), arxiv:2104.08734. arxiv:2104.08734"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470425"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155628"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2660193.2660194"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2435264.2435296"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/micro.2016.7783708"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178493"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273440.1250683"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173176"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3062341.3062385"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.75"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00028"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45234-8_7"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/fpga.1996.564808"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5220\/0001787803310340"},{"key":"e_1_3_2_1_37_1","unstructured":"Naveen Muralimanohar Rajeev Balasubramonian and Norman P Jouppi. 2009. CACTI 6.0: A tool to model large caches. HP Laboratories 22\u201331. https:\/\/www.hpl.hp.com\/techreports\/2009\/HPL-2009-85.html"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480048"},{"key":"e_1_3_2_1_39_1","unstructured":"Chris Nicol. 2017. A Coarse Grain Reconfigurable Array (CGRA) for Statically Scheduled Data Flow Computing. WaveComputing WhitePaper http:\/\/www.silicon-russia.com\/public_materials\/2017_10_08_msu_rountable\/background\/CGRA+Whitepaper.pdf"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3243176.3243212"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","unstructured":"Tony Nowatzki Vinay Gangadhar Newsha Ardalani and Karthikeyan Sankaralingam. 2017. Stream-Dataflow Acceleration. ISCA \u201917. ACM New York NY USA. 416\u2013429. isbn:978-1-4503-4892-8 https:\/\/doi.org\/10.1145\/3079856.3080255 10.1145\/3079856.3080255","DOI":"10.1145\/3079856.3080255"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/fccm.2017.37"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485935"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080256"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"e_1_3_2_1_47_1","volume-title":"Workshop on Computer Architecture Research with RISC-V (CARRV). https:\/\/carrv.github.io\/2017\/papers\/roelke-risc5-carrv2017","author":"Roelke Alec","unstructured":"Alec Roelke and Mircea R. Stan. 2017. RISC5: Implementing the RISC-V ISA in gem5. In Workshop on Computer Architecture Research with RISC-V (CARRV). https:\/\/carrv.github.io\/2017\/papers\/roelke-risc5-carrv2017.pdf"},{"key":"e_1_3_2_1_48_1","volume-title":"Capstan: A Vector RDA for Sparsity. arxiv:cs.AR\/2104.12760.","author":"Rucker Alexander","year":"2021","unstructured":"Alexander Rucker, Matthew Vilim, Tian Zhao, Yaqi Zhang, Raghu Prabhakar, and Kunle Olukotun. 2021. Capstan: A Vector RDA for Sparsity. arxiv:cs.AR\/2104.12760."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.9"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/pact.2011.9"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1735971.1736055"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2345141.2248428"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018758"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358292"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.9"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2612669.2612678"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.859540"},{"key":"e_1_3_2_1_58_1","unstructured":"Tuan Ta Lin Cheng and Christopher Batten. 2018. Simulating Multi-Core RISC-V Systems in gem5. https:\/\/carrv.github.io\/2018\/papers\/CARRV_2018_paper_3.pdf"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ipdps.2017.48"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00042"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00039"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00035"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853234"},{"key":"e_1_3_2_1_64_1","unstructured":"Zhengrong Wang Jian Weng Sihao Liu and Tony Nowatzki. 2022. Near-Stream Computing: General and Transparent Near-Cache Acceleration. In HPCA. https:\/\/seanzw.github.io\/pub\/hpca2022-near-stream-computing.pdf"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/hpca51647.2021.00060"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00032"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00063"},{"key":"e_1_3_2_1_68_1","unstructured":"Bob Wheeler. 2020. Growing AI Diversity and Complexity Demands Flexible Data-Center Accelerators. https:\/\/www.linleygroup.com\/uploads\/simple-machines-wp.pdf"},{"key":"e_1_3_2_1_69_1","unstructured":"WikiChip. 2019. Configurable Spatial Accelerator. https:\/\/en.wikichip.org\/wiki\/intel\/configurable_spatial_accelerator."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/ccgrid.2013.99"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358259"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358318"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/micro50266.2020.00064"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/isca45697.2020.00024"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/2486159.2486175"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173197"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446702"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2020.3043870"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322249"}],"event":{"name":"ASPLOS '22: 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","location":"Lausanne Switzerland","acronym":"ASPLOS '22","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 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503222.3507706","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503222.3507706","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503222.3507706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:39Z","timestamp":1750191099000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503222.3507706"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,22]]},"references-count":79,"alternative-id":["10.1145\/3503222.3507706","10.1145\/3503222"],"URL":"https:\/\/doi.org\/10.1145\/3503222.3507706","relation":{},"subject":[],"published":{"date-parts":[[2022,2,22]]},"assertion":[{"value":"2022-02-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}