{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:10:05Z","timestamp":1750205405440,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T00:00:00Z","timestamp":1554336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100011002","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61722208"],"award-info":[{"award-number":["61722208"]}],"id":[{"id":"10.13039\/501100011002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DOE Early Career Award","award":["DE-SC0013700"],"award-info":[{"award-number":["DE-SC0013700"]}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2018R1D1A1B07050463"],"award-info":[{"award-number":["2018R1D1A1B07050463"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1455404,CCF-1525609,CNS-1717425,CCF-1703487"],"award-info":[{"award-number":["CCF-1455404,CCF-1525609,CNS-1717425,CCF-1703487"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2017YFB1003103"],"award-info":[{"award-number":["2017YFB1003103"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,4,4]]},"DOI":"10.1145\/3297858.3304032","type":"proceedings-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T18:38:43Z","timestamp":1554403123000},"page":"153-166","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["HiWayLib"],"prefix":"10.1145","author":[{"given":"Zhen","family":"Zheng","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Chanyoung","family":"Oh","sequence":"additional","affiliation":[{"name":"University of Seoul, Seoul, Rebublic of Korea"}]},{"given":"Jidong","family":"Zhai","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Xipeng","family":"Shen","sequence":"additional","affiliation":[{"name":"North Carolina State University, Raleigh, UNK, USA"}]},{"given":"Youngmin","family":"Yi","sequence":"additional","affiliation":[{"name":"University of Seoul, Seoul, Rebublic of Korea"}]},{"given":"Wenguang","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2019,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"e_1_3_2_1_2_1","volume-title":"Pyramid methods in image processing. RCA engineer","author":"Adelson Edward H","year":"1984","unstructured":"Edward H Adelson, Charles H Anderson, James R Bergen, Peter J Burt, and Joan M Ogden. 1984. Pyramid methods in image processing. RCA engineer, Vol. 29, 6 (1984), 33--41."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1572769.1572792"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1631"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24322-6_14"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2016.35"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37414"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.573673"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.363415"},{"key":"e_1_3_2_1_10_1","volume-title":"Pascal GPU with NVLink. In Hot Chips 28 Symposium (HCS)","author":"Danskin John","year":"2016","unstructured":"John Danskin and Denis Foley. 2016. Pascal GPU with NVLink. In Hot Chips 28 Symposium (HCS), 2016 IEEE. IEEE, 1--24."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581285"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370036.2145849"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1278177.1278182"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.66"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1345206.1345215"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1168857.1168877"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851275.1851207"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810479.1810540"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2015.15"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2259016.2259038"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1993316.1993516"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967952"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.55"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465007"},{"key":"e_1_3_2_1_25_1","volume-title":"Abstract Representation of Shared Data for Heterogeneous Computing. In The 30th International Workshop on Languages and Compilers for Parallel Computing. Springer","author":"Kumar Tushar","year":"2017","unstructured":"Tushar Kumar, Aravind Natarajan, Wenjia Ruan, Mario Badr, Dario S Gracia, and Calin Cascaval. 2017. Abstract Representation of Shared Data for Heterogeneous Computing. In The 30th International Workshop on Languages and Compilers for Parallel Computing. Springer 2017."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2014.7040988"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807632"},{"key":"e_1_3_2_1_28_1","first-page":"517","article-title":"An OpenMP Programming Toolkit for Hybrid CPU\/GPU Clusters Based on Software Unified Memory","volume":"32","author":"Li Hung-Fu","year":"2016","unstructured":"Hung-Fu Li, Tyng-Yeu Liang, and Yu-Jie Lin. 2016. An OpenMP Programming Toolkit for Hybrid CPU\/GPU Clusters Based on Software Unified Memory. Journal of Information Science and Engineering, Vol. 32, 3 (2016), 517--539.","journal-title":"Journal of Information Science and Engineering"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2012.28"},{"volume-title":"d.} a","author":"NVIDIA Corporation","key":"e_1_3_2_1_30_1","unstructured":"NVIDIA Corporation. {n. d.} a. NVIDIA Collective Communications Library. https:\/\/developer.nvidia.com\/nccl ."},{"key":"e_1_3_2_1_31_1","unstructured":"NVIDIA Corporation. {n. d.} b. NVIDIA Warp Shuffle. https:\/\/devblogs.nvidia.com\/using-cuda-warp-level-primitives ."},{"key":"e_1_3_2_1_32_1","unstructured":"NVIDIA Corporation. {n. d.} c. Unified Memory Programming. http:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html#um-unified-memory-programming-hd ."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2015.7177522"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370824"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983990.2984015"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967964"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766973"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541942"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2544100"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ESTIMedia.2013.6704502"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-011-0157-1"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2597652.2597675"},{"volume-title":"Proxy-Guided Load Balancing of Graph Processing Workloads on Heterogeneous Clusters. In 2016 45th International Conference on Parallel Processing (ICPP). 77--86","author":"Song S.","key":"e_1_3_2_1_44_1","unstructured":"S. Song, M. Li, X. Zheng, M. LeBeane, J. H. Ryoo, R. Panda, A. Gerstlauer, and L. K. John. 2016. Proxy-Guided Load Balancing of Graph Processing Workloads on Heterogeneous Clusters. In 2016 45th International Conference on Parallel Processing (ICPP). 77--86."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661250"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581262"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.7"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2012.255"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2009.20"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2014.16"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2637364.2592002"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018754"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2017.7863726"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123978"}],"event":{"name":"ASPLOS '19: Architectural Support for Programming Languages and Operating Systems","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"],"location":"Providence RI USA","acronym":"ASPLOS '19"},"container-title":["Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304032","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304032","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:14Z","timestamp":1750204394000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304032"}},"subtitle":["A Software Framework for Enabling High Performance Communications for Heterogeneous Pipeline Computations"],"short-title":[],"issued":{"date-parts":[[2019,4,4]]},"references-count":54,"alternative-id":["10.1145\/3297858.3304032","10.1145\/3297858"],"URL":"https:\/\/doi.org\/10.1145\/3297858.3304032","relation":{},"subject":[],"published":{"date-parts":[[2019,4,4]]},"assertion":[{"value":"2019-04-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}