{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T14:07:30Z","timestamp":1774534050672,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,22]],"date-time":"2019-06-22T00:00:00Z","timestamp":1561161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Agencia Estatal de Investigaci\u00f3n","award":["TIN2016-75344-R"],"award-info":[{"award-number":["TIN2016-75344-R"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,22]]},"DOI":"10.1145\/3307650.3322254","type":"proceedings-article","created":{"date-parts":[[2019,6,14]],"date-time":"2019-06-14T12:42:33Z","timestamp":1560516153000},"page":"424-435","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["SCU"],"prefix":"10.1145","author":[{"given":"Albert","family":"Segura","sequence":"first","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya - BarcelonaTech (UPC)"}]},{"given":"Jose-Maria","family":"Arnau","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya - BarcelonaTech (UPC)"}]},{"given":"Antonio","family":"Gonz\u00e1lez","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya - BarcelonaTech (UPC)"}]}],"member":"320","published-online":{"date-parts":[[2019,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685096"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3023549.3023589"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934664"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2764947.2764954"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742797"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626407002843"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"A. H. Nodehi Sabet J. Qiu and Z. Zhao \"Tigr: Transforming irregular graphs for gpu-friendly graph processing \" in Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems pp. 622--636 ACM 2018.","DOI":"10.1145\/3173162.3173180"},{"key":"e_1_3_2_1_9_1","volume-title":"Understanding and improving graph algorithm performance","author":"S.","year":"2016","unstructured":"S. Beamer III, Understanding and improving graph algorithm performance. University of California, Berkeley, 2016."},{"key":"e_1_3_2_1_10_1","volume-title":"ACM","author":"Billeter M.","year":"2009","unstructured":"M. Billeter, O. Olsson, and U. Assarsson, \"Efficient stream compaction on wide simd many-core architectures,\" in Proceedings of the conference on high performance graphics 2009, pp. 159--166, ACM, 2009."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2717511"},{"key":"e_1_3_2_1_12_1","first-page":"349","volume-title":"2014 IEEE 28th International","author":"Davidson A.","year":"2014","unstructured":"A. Davidson, S. Baxter, M. Garland, and J. D. Owens, \"Work-efficient parallel gpu methods for single-source shortest paths,\" in Parallel and Distributed Processing Symposium, 2014 IEEE 28th International, pp. 349--359, IEEE, 2014."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654078"},{"key":"e_1_3_2_1_14_1","first-page":"359","volume-title":"Thrust: A productivity-oriented library for cuda,\" in GPU computing gems Jade edition","author":"Bell N.","year":"2011","unstructured":"N. Bell and J. Hoberock, \"Thrust: A productivity-oriented library for cuda,\" in GPU computing gems Jade edition, pp. 359--371, Elsevier, 2011."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2660460.2660481"},{"key":"e_1_3_2_1_16_1","volume-title":"Stanford InfoLab","author":"Page L.","year":"1999","unstructured":"L. Page, S. Brin, R. Motwani, and T. Winograd, \"The pagerank citation ranking: Bringing order to the web.,\" tech. rep., Stanford InfoLab, 1999."},{"key":"e_1_3_2_1_17_1","unstructured":"D. Compiler \"Synopsys inc \" 2000."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669172"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2011.4"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508148.2485964"},{"key":"e_1_3_2_1_22_1","first-page":"163","volume-title":"ISPASS 2009. IEEE International Symposium on","author":"Bakhoda A.","year":"2009","unstructured":"A. Bakhoda, G. L. Yuan, W. W. Fung, H. Wong, and T. M. Aamodt, \"Analyzing cuda workloads using a detailed gpu simulator,\" in Performance Analysis of Systems and Software, 2009. ISPASS 2009. IEEE International Symposium on, pp. 163--174, IEEE, 2009."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_24_1","unstructured":"DIMACS \"10th dimacs implementation challenge - graph partitioning and graph clustering \" 2010."},{"key":"e_1_3_2_1_25_1","volume-title":"ACM","author":"Han T. D.","year":"2011","unstructured":"T. D. Han and T. S. Abdelrahman, \"Reducing branch divergence in gpu programs,\" in Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units, p. 3, ACM, 2011."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2038037.1941590"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.15"},{"key":"e_1_3_2_1_28_1","volume-title":"Efficient large-scale graph processing on hybrid cpu and gpu systems,\" arXiv preprint arXiv:1312.3018","author":"Gharaibeh A.","year":"2013","unstructured":"A. Gharaibeh, T. Reza, E. Santos-Neto, L. B. Costa, S. Sallinen, and M. Ripeanu, \"Efficient large-scale graph processing on hybrid cpu and gpu systems,\" arXiv preprint arXiv:1312.3018, 2013."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600227"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851145"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195707"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2017.114"},{"key":"e_1_3_2_1_33_1","article-title":"Graphh: A processing-in-memory architecture for large-scale graph processing","author":"Dai G.","year":"2018","unstructured":"G. Dai, T. Huang, Y. Chi, J. Zhao, G. Sun, Y. Liu, Y. Wang, Y. Xie, and H. Yang, \"Graphh: A processing-in-memory architecture for large-scale graph processing,\" IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2018.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"e_1_3_2_1_34_1","first-page":"531","volume-title":"Graphr: Accelerating graph processing using reram,\" in 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA)","author":"Song L.","year":"2018","unstructured":"L. Song, Y. Zhuo, X. Qian, H. Li, and Y. Chen, \"Graphr: Accelerating graph processing using reram,\" in 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 531--543, Feb 2018."}],"event":{"name":"ISCA '19: The 46th Annual International Symposium on Computer Architecture","location":"Phoenix Arizona","acronym":"ISCA '19","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS\\DATC IEEE Computer Society"]},"container-title":["Proceedings of the 46th International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322254","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3307650.3322254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:54:06Z","timestamp":1750204446000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322254"}},"subtitle":["a GPU stream compaction unit for graph processing"],"short-title":[],"issued":{"date-parts":[[2019,6,22]]},"references-count":33,"alternative-id":["10.1145\/3307650.3322254","10.1145\/3307650"],"URL":"https:\/\/doi.org\/10.1145\/3307650.3322254","relation":{},"subject":[],"published":{"date-parts":[[2019,6,22]]},"assertion":[{"value":"2019-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}