{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:15:51Z","timestamp":1766578551066,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1109\/micro.2016.7783716","type":"proceedings-article","created":{"date-parts":[[2016,12,19]],"date-time":"2016-12-19T22:11:05Z","timestamp":1482185465000},"page":"1-12","source":"Crossref","is-referenced-by-count":19,"title":["KLAP: Kernel launch aggregation and promotion for optimizing dynamic parallelism"],"prefix":"10.1109","author":[{"given":"Izzat","family":"El Hajj","sequence":"first","affiliation":[]},{"given":"Juan","family":"Gomez-Luna","sequence":"additional","affiliation":[]},{"given":"Cheng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Li-Wen","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Dejan","family":"Milojicic","sequence":"additional","affiliation":[]},{"given":"Wen-mei","family":"Hwu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2015.107"},{"key":"ref32","article-title":"Enabling task parallelism in the cuda scheduler","volume":"9","author":"guevara","year":"2009","journal-title":"Workshop on Programming Models for Emerging Architectures"},{"article-title":"private communication","year":"0","author":"chen","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339596"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.19"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2004.1342552"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2737924.2738004"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830818"},{"key":"ref11","first-page":"9","article-title":"Parallel search on video cards","author":"kaldewey","year":"2009","journal-title":"Proceedings of the First USENIX Conference of Hot Topics in Parallelism"},{"key":"ref12","article-title":"CUB:kernel-level software reuse and library design","author":"merrill","year":"2013","journal-title":"GPU Technology Conference Presentation S"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-014-0320-y"},{"key":"ref14","first-page":"1","article-title":"Convergence and scalarization for data-parallel architectures","author":"asanovic","year":"2013","journal-title":"Proceedings of the 2013 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1572769.1572795"},{"key":"ref16","article-title":"The OpenCL specification, version 2.0","author":"howes","year":"0","journal-title":"Khronos Group 2015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442539"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2012.6402918"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1145\/3007787.3001199","article-title":"Laperm: Locality aware scheduler for dynamic parallelism on gpus","author":"wang","year":"2016","journal-title":"International Symposium on Computer Architecture (ISCA)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-014-9883-4"},{"year":"2015","key":"ref27","article-title":"Profiler user's guide v. 7.5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2833179.2833189"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2014.6983039"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853209"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2015.30"},{"year":"0","key":"ref8","article-title":"A CUDA dynamic parallelism case study: PANDA"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1145\/2692916.2555254","article-title":"CUDA-NP: Realizing nested thread-level parallelism in GPGPU applications","volume":"49","author":"yang","year":"2014","journal-title":"ACM SIGPLAN Notices"},{"journal-title":"Heterogeneous System Architecture A new compute platform infrastructure","year":"2015","author":"wen-mei","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750393"},{"key":"ref1","article-title":"Introduction to dynamic parallelism","author":"jones","year":"2012","journal-title":"GPU Technology Conference Presentation S"},{"year":"2015","key":"ref20","article-title":"CUDA samples v. 7.5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1941553.1941597"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2668930.2688046"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-811986-0.00033-9"},{"year":"0","key":"ref23","article-title":"Matrix market"},{"year":"0","key":"ref26","article-title":"CUDA dynamic parallelism API and principles"},{"year":"0","key":"ref25","article-title":"GPU pro tip: CUDA 7 streams simplify concurrency"}],"event":{"name":"2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","start":{"date-parts":[[2016,10,15]]},"location":"Taipei","end":{"date-parts":[[2016,10,19]]}},"container-title":["2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7777315\/7783693\/07783716.pdf?arnumber=7783716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,12]],"date-time":"2020-05-12T00:20:23Z","timestamp":1589242823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7783716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/micro.2016.7783716","relation":{},"subject":[],"published":{"date-parts":[[2016,10]]}}}