{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:26:13Z","timestamp":1750220773228,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T00:00:00Z","timestamp":1590364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,5,25]]},"DOI":"10.1145\/3378678.3391885","type":"proceedings-article","created":{"date-parts":[[2020,5,26]],"date-time":"2020-05-26T00:21:35Z","timestamp":1590452495000},"page":"58-61","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Efficient parallel reduction on GPUs with Hipacc"],"prefix":"10.1145","author":[{"given":"Bo","family":"Qiao","sequence":"first","affiliation":[{"name":"Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany"}]},{"given":"Oliver","family":"Reiche","sequence":"additional","affiliation":[{"name":"Siemens Healthineers AG, Erlangen, Germany"}]},{"given":"M. Akif","family":"\u00d6zkan","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany"}]},{"given":"J\u00fcrgen","family":"Teich","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany"}]},{"given":"Frank","family":"Hannig","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany"}]}],"member":"320","published-online":{"date-parts":[[2020,5,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2786763.2694364"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2394802"},{"key":"e_1_3_2_1_4_1","volume-title":"Handbook of Medical Image Processing and Analysis","author":"Bankman I. N.","year":"2008","unstructured":"I. N. Bankman . Handbook of Medical Image Processing and Analysis . Vol. 2 . Academic Press , Dec. 2008 . isbn: 978-0-123-73904-9. I. N. Bankman. Handbook of Medical Image Processing and Analysis. Vol. 2. Academic Press, Dec. 2008. isbn: 978-0-123-73904-9."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCSim.2012.6266966"},{"key":"e_1_3_2_1_6_1","volume-title":"Efficient parallel scan algorithms for GPUs. Tech. rep","author":"Sengupta S.","year":"2008","unstructured":"S. Sengupta , M. Harris , and M. Garland . Efficient parallel scan algorithms for GPUs. Tech. rep . 2008 . S. Sengupta, M. Harris, and M. Garland. Efficient parallel scan algorithms for GPUs. Tech. rep. 2008."},{"key":"e_1_3_2_1_7_1","volume-title":"Shuffle: Tips and Tricks","author":"Demouth J.","year":"2013","unstructured":"J. Demouth . Shuffle: Tips and Tricks . 2013 . url: http:\/\/on-demand.gputechconf.com\/gtc\/2013\/presentations\/S3174-Kepler-Shuffle-Tips-Tricks.pdf. J. Demouth. Shuffle: Tips and Tricks. 2013. url: http:\/\/on-demand.gputechconf.com\/gtc\/2013\/presentations\/S3174-Kepler-Shuffle-Tips-Tricks.pdf."},{"key":"e_1_3_2_1_8_1","volume-title":"Understanding and Using Atomic Memory Operations","author":"Lars Nyland S. J.","year":"2013","unstructured":"S. J. Lars Nyland . Understanding and Using Atomic Memory Operations . 2013 . url: http:\/\/on-demand.gputechconf.com\/gtc\/2013\/presentations\/S3101-Atomic-Memory-Operations.pdf. S. J. Lars Nyland. Understanding and Using Atomic Memory Operations. 2013. url: http:\/\/on-demand.gputechconf.com\/gtc\/2013\/presentations\/S3101-Atomic-Memory-Operations.pdf."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3331057"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661187"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3207719.3207723"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661176"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366428.3380773"},{"key":"e_1_3_2_1_14_1","volume-title":"Optimizing Parallel Reduction in CUDA","author":"Harris M.","year":"2007","unstructured":"M. Harris . Optimizing Parallel Reduction in CUDA . 2007 . url: https:\/\/developer.download.nvidia.com\/assets\/cuda\/files\/reduction.pdf. M. Harris. Optimizing Parallel Reduction in CUDA. 2007. url: https:\/\/developer.download.nvidia.com\/assets\/cuda\/files\/reduction.pdf."},{"key":"e_1_3_2_1_15_1","volume-title":"Write Flexible Kernels with Grid-Stride Loops","author":"Harris M.","year":"2013","unstructured":"M. Harris . Write Flexible Kernels with Grid-Stride Loops . 2013 . url: https:\/\/devblogs.nvidia.com\/cuda-pro-tip-write-flexible-kernels-grid-stride-loops\/. M. Harris. Write Flexible Kernels with Grid-Stride Loops. 2013. url: https:\/\/devblogs.nvidia.com\/cuda-pro-tip-write-flexible-kernels-grid-stride-loops\/."},{"key":"e_1_3_2_1_16_1","volume-title":"Increase Performance with Vectorized Memory Access","author":"Luitjens J.","year":"2013","unstructured":"J. Luitjens . Increase Performance with Vectorized Memory Access . 2013 . url: https:\/\/devblogs.nvidia.com\/cuda-pro-tip-increase-performance-with-vectorized-memory-access\/. J. Luitjens. Increase Performance with Vectorized Memory Access. 2013. url: https:\/\/devblogs.nvidia.com\/cuda-pro-tip-increase-performance-with-vectorized-memory-access\/."},{"key":"e_1_3_2_1_17_1","volume-title":"Faster Parallel Reductions on Kepler","author":"Luitjens J.","year":"2014","unstructured":"J. Luitjens . Faster Parallel Reductions on Kepler . 2014 . url: https:\/\/devblogs.nvidia.com\/faster-parallel-reductions-kepler\/. J. Luitjens. Faster Parallel Reductions on Kepler. 2014. url: https:\/\/devblogs.nvidia.com\/faster-parallel-reductions-kepler\/."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-385963-1.00026-5"}],"event":{"name":"SCOPES '20: 23rd International Workshop on Software and Compilers for Embedded Systems","sponsor":["SIGBED ACM Special Interest Group on Embedded Systems","EDAA European Design Automation Association"],"location":"St. Goar Germany","acronym":"SCOPES '20"},"container-title":["Proceedings of the 23th International Workshop on Software and Compilers for Embedded Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3378678.3391885","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3378678.3391885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:19Z","timestamp":1750200079000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3378678.3391885"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,25]]},"references-count":18,"alternative-id":["10.1145\/3378678.3391885","10.1145\/3378678"],"URL":"https:\/\/doi.org\/10.1145\/3378678.3391885","relation":{},"subject":[],"published":{"date-parts":[[2020,5,25]]},"assertion":[{"value":"2020-05-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}