{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:41:08Z","timestamp":1773193268242,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,12]],"date-time":"2019-10-12T00:00:00Z","timestamp":1570838400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR0011- 18-3-0007"],"award-info":[{"award-number":["HR0011- 18-3-0007"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CAREER-1452994"],"award-info":[{"award-number":["CAREER-1452994"]}],"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":[[2019,10,12]]},"DOI":"10.1145\/3352460.3358254","type":"proceedings-article","created":{"date-parts":[[2019,10,11]],"date-time":"2019-10-11T11:16:45Z","timestamp":1570792605000},"page":"1009-1022","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":49,"title":["PHI"],"prefix":"10.1145","author":[{"given":"Anurag","family":"Mukkara","sequence":"first","affiliation":[{"name":"MIT CSAIL"}]},{"given":"Nathan","family":"Beckmann","sequence":"additional","affiliation":[{"name":"CMU SCS"}]},{"given":"Daniel","family":"Sanchez","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}]}],"member":"320","published-online":{"date-parts":[[2019,10,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573480"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926254"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173189"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573478"},{"key":"e_1_3_2_1_6_1","volume-title":"Flexible Support for Fast Parallel Commutative Updates. arXiv preprint arXiv:1709.09491","author":"Balaji Vignesh","year":"2017","unstructured":"Vignesh Balaji, Dhruva Tirumala, and Brandon Lucia. 2017. Flexible Support for Fast Parallel Commutative Updates. arXiv preprint arXiv:1709.09491 (2017)."},{"key":"e_1_3_2_1_7_1","first-page":"7","volume":"27","author":"Balkesen \u00c7a\u011fr\u0131","year":"2014","unstructured":"\u00c7a\u011fr\u0131 Balkesen, Jens Teubner, Gustavo Alonso, and M Tamer \u00d6zsu. 2014. Mainmemory hash joins on modern processor architectures. IEEE Transactions on Knowledge and Data Engineering 27, 7 (2014).","journal-title":"Data Engineering"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.50"},{"key":"e_1_3_2_1_9_1","volume-title":"The GAP benchmark suite. arXiv:1508.03619 [cs.DC]","author":"Beamer Scott","year":"2015","unstructured":"Scott Beamer, Krste Asanovi\u0107, and David Patterson. 2015. The GAP benchmark suite. arXiv:1508.03619 [cs.DC] (2015)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.112"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078597.3078616"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972740.43"},{"key":"e_1_3_2_1_13_1","volume-title":"Introduction to algorithms","author":"Cormen Thomas H","unstructured":"Thomas H Cormen, Charles E Leiserson, Ronald L Rivest, and Clifford Stein. 2009. Introduction to algorithms (3rd ed.). MIT press.","edition":"3"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847339"},{"key":"e_1_3_2_1_15_1","volume-title":"The University of Florida sparse matrix collection. ACM TOMS 38, 1","author":"Davis Timothy A","year":"2011","unstructured":"Timothy A Davis and Yifan Hu. 2011. The University of Florida sparse matrix collection. ACM TOMS 38, 1 (2011)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3087556.3087580"},{"key":"e_1_3_2_1_17_1","volume-title":"The NYU Ultracomputer? Designing an MIMD Shared Memory Parallel Computer","author":"Gottlieb Allan","year":"1983","unstructured":"Allan Gottlieb, Ralph Grishman, Clyde P. Kruskal, Kevin P. McAuliffe, Larry Rudolph, and Marc Snir. 1983. The NYU Ultracomputer? Designing an MIMD Shared Memory Parallel Computer. IEEE Transactions on computers 2 (1983)."},{"key":"e_1_3_2_1_18_1","volume-title":"A New Frontier for Pull-Based Graph Processing. arXiv preprint arXiv:1903.07754","author":"Grossman Samuel","year":"2019","unstructured":"Samuel Grossman and Christos Kozyrakis. 2019. A New Frontier for Pull-Based Graph Processing. arXiv preprint arXiv:1903.07754 (2019)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178506"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783759"},{"key":"e_1_3_2_1_21_1","volume-title":"Haswell: The fourth-generation intel core processor","author":"Hammarlund Per","year":"2014","unstructured":"Per Hammarlund, Alberto J. Martinez, Atiq A. Bajwa, David L. Hill, Erik Hallnor, Hong Jiang, Martin Dixon, Michael Derr, Mikal Hunsaker, Rajesh Kumar, Randy B. Osborne, Ravi Rajwar, Ronak Singhal, Reynold D'Sa, Robert Chappell, Shiv Kaushik, Srinivas Chennupaty, Stephan Jourdan, Steve Gunther, Tom Piazza, and Ted Burton. 2014. Haswell: The fourth-generation intel core processor. IEEE Micro 34, 2 (2014)."},{"key":"e_1_3_2_1_22_1","volume-title":"Trained Quantization and Huffman Coding. In 4th International Conference on Learning Representations (ICLR-4).","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and William J Dally. 2016. Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. In 4th International Conference on Learning Representations (ICLR-4)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11515-8_3"},{"key":"e_1_3_2_1_24_1","unstructured":"Nangate Inc. 2008. The NanGate 45nm Open Cell Library. http:\/\/www.nangate.com\/?page_id=2325."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815971"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/165123.165154"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 45th annual International Symposium on Computer Architecture (ISCA-45)","author":"Jun Sang-Woo","year":"2018","unstructured":"Sang-Woo Jun, Andy Wright, Sizhuo Zhang, Shuotao Xu, and Arvind. 2018. GraF-Boost: Using accelerated flash storage for external graph analytics. In Proceedings of the 45th annual International Symposium on Computer Architecture (ISCA-45)."},{"key":"e_1_3_2_1_28_1","unstructured":"Richard E Kessler and James L Schwarzmeier. 1993. CRAY T3D: A new dimension for Cray Research. In Digest of Papers. COMPCON Spring."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967948"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133901"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772751"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/264107.264206"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669172"},{"key":"e_1_3_2_1_34_1","volume-title":"Fast computation of empirically tight bounds for the diameter of massive graphs. JEA 13","author":"Magnien Cl\u00e9mence","year":"2009","unstructured":"Cl\u00e9mence Magnien, Matthieu Latapy, and Michel Habib. 2009. Fast computation of empirically tight bounds for the diameter of massive graphs. JEA 13 (2009)."},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the USENIX Annual Technical Conference (USENIX ATC).","author":"Malicevic Jasmina","year":"2017","unstructured":"Jasmina Malicevic, Baptiste Joseph Eustache Lepers, and Willy Zwaenepoel. 2017. Everything you always wanted to know about multicore graph processing but were afraid to ask. In Proceedings of the USENIX Annual Technical Conference (USENIX ATC)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060829"},{"key":"e_1_3_2_1_37_1","unstructured":"Micron. 2013. 1.35V DDR3L power calculator (4Gb x16 chips)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00010"},{"key":"e_1_3_2_1_39_1","volume-title":"AGP'17","author":"Mukkara Anurag","year":"2017","unstructured":"Anurag Mukkara, Nathan Beckmann, and Daniel Sanchez. 2017. Cache-Guided Scheduling: Exploiting caches to maximize locality in graph processing. In AGP'17."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.54"},{"key":"e_1_3_2_1_41_1","unstructured":"Michal Nazarewicz. 2012. A deep dive into CMA. LWN https:\/\/lwn.net\/Articles\/486301\/."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2014.15"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847337"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.24"},{"key":"e_1_3_2_1_45_1","unstructured":"Lawrence Page Sergey Brin Rajeev Motwani and Terry Winograd. 1999. The PageRank citation ranking: Bringing order to the web. Technical Report. Stanford InfoLab."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00067"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485963"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610518"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/237090.237144"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442530"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080206"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00052"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.14778\/2809974.2809983"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915220"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362674"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.24"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the 21st Austrian Workshop on Microelectronics (Austrochip).","author":"Wolf Clifford","year":"2013","unstructured":"Clifford Wolf, Johann Glaser, and Johannes Kepler. 2013. Yosys-a free Verilog synthesis suite. In Proceedings of the 21st Austrian Workshop on Microelectronics (Austrochip)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830807"},{"key":"e_1_3_2_1_59_1","volume-title":"PathGraph: A path centric graph processing system","author":"Yuan Pingpeng","year":"2016","unstructured":"Pingpeng Yuan, Changfeng Xie, Ling Liu, and Hai Jin. 2016. PathGraph: A path centric graph processing system. IEEE TPDS (2016)."},{"key":"e_1_3_2_1_60_1","volume-title":"High-level strategies for parallel shared-memory sparse matrix-vector multiplication","author":"Nicholas Yzelman Albert-Jan","year":"2014","unstructured":"Albert-Jan Nicholas Yzelman and Dirk Roose. 2014. High-level strategies for parallel shared-memory sparse matrix-vector multiplication. IEEE TPDS (2014)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195679"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830774"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00053"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2017.8257937"},{"key":"e_1_3_2_1_65_1","volume-title":"FBSGraph: Accelerating asynchronous graph processing via forward and backward sweeping","author":"Zhang Yu","year":"2018","unstructured":"Yu Zhang, Xiaofei Liao, Hai Jin, Lin Gu, and Bing Bing Zhou. 2018. FBSGraph: Accelerating asynchronous graph processing via forward and backward sweeping. IEEE TKDE (2018)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3276491"},{"key":"e_1_3_2_1_67_1","volume-title":"Proceedings of the USENIX Annual Technical Conference (USENIX ATC).","author":"Zhu Xiaowei","year":"2015","unstructured":"Xiaowei Zhu, Wentao Han, and Wenguang Chen. 2015. GridGraph: Large-scale graph processing on a single machine using 2-level hierarchical partitioning. In Proceedings of the USENIX Annual Technical Conference (USENIX ATC)."}],"event":{"name":"MICRO '52: The 52nd Annual IEEE\/ACM International Symposium on Microarchitecture","location":"Columbus OH USA","acronym":"MICRO '52","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","IEEE CS"]},"container-title":["Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3352460.3358254","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3352460.3358254","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3352460.3358254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T22:27:57Z","timestamp":1753828077000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3352460.3358254"}},"subtitle":["Architectural Support for Synchronization- and Bandwidth-Efficient Commutative Scatter Updates"],"short-title":[],"issued":{"date-parts":[[2019,10,12]]},"references-count":67,"alternative-id":["10.1145\/3352460.3358254","10.1145\/3352460"],"URL":"https:\/\/doi.org\/10.1145\/3352460.3358254","relation":{},"subject":[],"published":{"date-parts":[[2019,10,12]]},"assertion":[{"value":"2019-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}