{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:39:08Z","timestamp":1776879548382,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,5,8]],"date-time":"2018-05-08T00:00:00Z","timestamp":1525737600000},"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":[[2018,5,8]]},"DOI":"10.1145\/3203217.3203243","type":"proceedings-article","created":{"date-parts":[[2018,7,26]],"date-time":"2018-07-26T07:58:06Z","timestamp":1532591886000},"page":"146-154","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Taming irregular applications via advanced dynamic parallelism on GPUs"],"prefix":"10.1145","author":[{"given":"Jing","family":"Zhang","sequence":"first","affiliation":[{"name":"Virginia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashwin M.","family":"Aji","sequence":"additional","affiliation":[{"name":"AMD Research Advanced Micro Devices, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael L.","family":"Chu","sequence":"additional","affiliation":[{"name":"AMD Research Advanced Micro Devices, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Virginia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu-chun","family":"Feng","sequence":"additional","affiliation":[{"name":"Virginia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,5,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"DIMACS Implementation Challenges. https:\/\/www.cc.gatech.edu\/dimacs10. (2012)."},{"key":"e_1_3_2_1_2_1","unstructured":"The OpenCL Specification v2.0. https:\/\/www.khronos.org\/registry\/OpenCL\/specs\/opencl-2.0.pdf. (2015)."},{"key":"e_1_3_2_1_3_1","unstructured":"NVIDIA Tesla P100 Whitepaper. https:\/\/images.nvidia.com\/content\/pdf\/tesla\/whitepaper\/pascal-architecture-whitepaper.pdf. (2016)."},{"key":"e_1_3_2_1_4_1","unstructured":"Asynchronous Task and Memory Interface (ATMI). https:\/\/github.com\/RadeonOpenCompute\/atmi. (2017)."},{"key":"e_1_3_2_1_5_1","unstructured":"CUDA C Programming Guide. (2017)."},{"key":"e_1_3_2_1_6_1","unstructured":"Radeon's Next-generation Vega architecture. https:\/\/radeon.com\/_downloads\/vega-whitepaper-11.6.17.pdf. (2017)."},{"key":"e_1_3_2_1_7_1","unstructured":"ROCm - Open Source Platform for HPC and Ultrascale GPU Computing. https:\/\/rocm.github.io\/install.html. (2017)."},{"key":"e_1_3_2_1_8_1","unstructured":"Profiler User's Guide. http:\/\/docs.nvidia.com\/cuda\/pdf\/CUDA_Profiler_Users_Guide.pdf. (2018)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2012.6402918"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830818"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195654"},{"key":"e_1_3_2_1_13_1","volume-title":"The elements of statistical learning: data mining, inference and prediction","author":"Hastie T.","unstructured":"T. Hastie, R. Tibshirani, and J. Friedman. The elements of statistical learning: data mining, inference and prediction. Springer."},{"key":"e_1_3_2_1_14_1","volume-title":"Auto-Tuning Strategies for Parallelizing Sparse Matrix-Vector (SpMV) Multiplication on Multi- and Many-Core Processors. In 2017 IEEE Int. Parallel Distrib. Processing Symp. Workshop.","author":"Hou K.","unstructured":"K. Hou, W. c. Feng, and S. Che. Auto-Tuning Strategies for Parallelizing Sparse Matrix-Vector (SpMV) Multiplication on Multi- and Many-Core Processors. In 2017 IEEE Int. Parallel Distrib. Processing Symp. Workshop."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2012.6189201"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2012.6507525"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2015.107"},{"key":"e_1_3_2_1_18_1","volume-title":"Processing Symp. Workshops. 641--652","author":"Madougou S.","unstructured":"S. Madougou, A. L. Varbanescu, C. D. Laat, and R. V. Nieuwpoort. A Tool for Bottleneck Analysis and Performance Prediction for GPU-Accelerated Applications. In 2016 IEEE Int. Parallel Distrib. Processing Symp. Workshops. 641--652."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2665671.2665701"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.17760\/D20249271"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"e_1_3_2_1_22_1","volume-title":"Kaeli. Mystic: Predictive Scheduling for GPU Based Cloud Servers Using Machine Learning. In 2016 IEEE Int. Parallel Distrib. Processing Symp. 353--362","author":"Ukidave Y.","unstructured":"Y. Ukidave, X. Li, andD. Kaeli. Mystic: Predictive Scheduling for GPU Based Cloud Servers Using Machine Learning. In 2016 IEEE Int. Parallel Distrib. Processing Symp. 353--362."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/GreenCom-CPSCom.2010.102"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926291"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750393"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.57"},{"key":"e_1_3_2_1_27_1","volume-title":"Characterization and Analysis of Dynamic Parallelism in Unstructured GPU Applications. In 2014 IEEE Int. Symp. on Workload Characterization. 51--60","author":"Wang J.","unstructured":"J. Wang and S. Yalamanchili. Characterization and Analysis of Dynamic Parallelism in Unstructured GPU Applications. In 2014 IEEE Int. Symp. on Workload Characterization. 51--60."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056063"},{"key":"e_1_3_2_1_29_1","volume-title":"Processing Symp. 534--543","author":"Wu H.","unstructured":"H. Wu, D. Li, and M. Becchi. Compiler-Assisted Workload Consolidation for Efficient Dynamic Parallelism on GPU. In 2016 IEEE Int. Parallel Distrib. Processing Symp. 534--543."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-015-1499-0"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600709"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2014.08.001"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3075564.3078889"},{"key":"e_1_3_2_1_34_1","author":"Yu X.","year":"2018","unstructured":"X. Yu, H. Wang, W. c. Feng, H. Gong, and G. Cao. GPU-Based Iterative Medical CT Image Reconstructions. Journal of Signal Processing Systems (2018).","journal-title":"Journal of Signal Processing Systems ("},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCABS.2015.7344721"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2015.2489662"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/NAS.2011.51"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/2014698.2014875"}],"event":{"name":"CF '18: Computing Frontiers Conference","location":"Ischia Italy","acronym":"CF '18","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 15th ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3203217.3203243","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3203217.3203243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T16:42:12Z","timestamp":1776876132000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3203217.3203243"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,8]]},"references-count":38,"alternative-id":["10.1145\/3203217.3203243","10.1145\/3203217"],"URL":"https:\/\/doi.org\/10.1145\/3203217.3203243","relation":{},"subject":[],"published":{"date-parts":[[2018,5,8]]},"assertion":[{"value":"2018-05-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}