{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T15:35:12Z","timestamp":1787758512490,"version":"build-2784847793"},"reference-count":44,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2018,12,31]],"date-time":"2018-12-31T00:00:00Z","timestamp":1546214400000},"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":["ACM Trans. Archit. Code Optim."],"published-print":{"date-parts":[[2018,12,31]]},"abstract":"<jats:p>Graphics Processing Units (GPUs) are vastly used for running massively parallel programs. GPU kernels exhibit different behavior at runtime and can usually be classified in a simple form as either \u201ccompute-bound\u201d or \u201cmemory-bound.\u201d Recent GPUs are capable of concurrently running multiple kernels, which raises the question of how to most appropriately schedule kernels to achieve higher performance. In particular, co-scheduling of compute-bound and memory-bound kernels seems promising. However, its benefits as well as drawbacks must be determined along with which kernels should be selected for a concurrent execution. Classifying kernels can be performed online by instrumentation based on performance counters. This work conducts a thorough analysis of the metrics collected from various benchmarks from Rodinia and CUDA SDK. The goal is to find the minimum number of effective metrics that enables online classification of kernels with a low overhead. This study employs a wrapper-based feature selection method based on the Fisher feature selection criterion. The results of experiments show that to classify kernels with a high accuracy, only three and five metrics are sufficient on a Kepler and a Pascal GPU, respectively. The proposed method is then utilized for a runtime scheduler. The results show an average speedup of 1.18\u00d7 and 1.1\u00d7 compared with a serial and a random scheduler, respectively.<\/jats:p>","DOI":"10.1145\/3295690","type":"journal-article","created":{"date-parts":[[2019,1,8]],"date-time":"2019-01-08T15:53:12Z","timestamp":1546962792000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Metric Selection for GPU Kernel Classification"],"prefix":"10.1145","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8783-6243","authenticated-orcid":false,"given":"S.-Kazem","family":"Shekofteh","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid","family":"Noori","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahmoud","family":"Naghibzadeh","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hadi Sadoghi","family":"Yazdi","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Holger","family":"Fr\u00f6ning","sequence":"additional","affiliation":[{"name":"Institute of Computer Engineering, Ruprecht-Karls University of Heidelberg, Heidelberg, Baden-Wurttemberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,1,8]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.02.005"},{"key":"e_1_2_1_2_1","unstructured":"D. B. Kirk and W. W. Hwu. 2012. Programming Massively Parallel Processors. Morgan Kaufmann.   D. B. Kirk and W. W. Hwu. 2012. Programming Massively Parallel Processors. Morgan Kaufmann."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2597917.2597925"},{"key":"e_1_2_1_4_1","unstructured":"NVIDIA. 2018. Streams. In CUDA C Programming Guide PG-02829-001_v9.2.  NVIDIA. 2018. Streams. In CUDA C Programming Guide PG-02829-001_v9.2."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2586074"},{"key":"e_1_2_1_6_1","unstructured":"NVIDIA. 2017. CUDA Runtime API v9.2.148.  NVIDIA. 2017. CUDA Runtime API v9.2.148."},{"key":"e_1_2_1_7_1","unstructured":"NVIDIA. 2017. CUPTI User's Guide DA-05679-001 _v6.0.  NVIDIA. 2017. CUPTI User's Guide DA-05679-001 _v6.0."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2632216"},{"key":"e_1_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Y. Zhang Z. Xing C. Liu C. Tang and Q. Wang. 2018. Locality based warp scheduling in GPGPUs. Futur. Gener. Comput. Syst. 82 (May 2018) 520--527.  Y. Zhang Z. Xing C. Liu C. Tang and Q. Wang. 2018. Locality based warp scheduling in GPGPUs. Futur. Gener. Comput. Syst. 82 (May 2018) 520--527.","DOI":"10.1016\/j.future.2017.02.036"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.29"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2630697"},{"key":"e_1_2_1_12_1","volume-title":"Proceedings of the 2009 IEEE International Symposium on Performance Analysis of Systems and Software. 163--174","author":"Bakhoda A.","unstructured":"A. Bakhoda , G. L. Yuan , W. W. L. Fung , H. Wong , and T. M. Aamodt . 2009. Analyzing CUDA workloads using a detailed GPU simulator . In Proceedings of the 2009 IEEE International Symposium on Performance Analysis of Systems and Software. 163--174 . A. Bakhoda, G. L. Yuan, W. W. L. Fung, H. Wong, and T. M. Aamodt. 2009. Analyzing CUDA workloads using a detailed GPU simulator. In Proceedings of the 2009 IEEE International Symposium on Performance Analysis of Systems and Software. 163--174."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.257"},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of the 2016 6th International Conference on Computer and Knowledge Engineering (ICCKE\u201916)","author":"Mohammadi R.","unstructured":"R. Mohammadi , S.-K. Shekofteh , M. Naghibzadeh , and H. Noori . 2016. A dynamic special-purpose scheduler for concurrent kernels on GPU . In Proceedings of the 2016 6th International Conference on Computer and Knowledge Engineering (ICCKE\u201916) . 218--222. R. Mohammadi, S.-K. Shekofteh, M. Naghibzadeh, and H. Noori. 2016. A dynamic special-purpose scheduler for concurrent kernels on GPU. In Proceedings of the 2016 6th International Conference on Computer and Knowledge Engineering (ICCKE\u201916). 218--222."},{"key":"e_1_2_1_15_1","volume-title":"Proceedings of the 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA\u201914)","author":"Lee M.","unstructured":"M. Lee , S. Song , J. Moon , J. Kim , W. Seo , Y. Cho , and S. Ryu . 2014. Improving GPGPU resource utilization through alternative thread block scheduling . In Proceedings of the 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA\u201914) . 260--271. M. Lee, S. Song, J. Moon, J. Kim, W. Seo, Y. Cho, and S. Ryu. 2014. Improving GPGPU resource utilization through alternative thread block scheduling. In Proceedings of the 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA\u201914). 260--271."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400716"},{"key":"e_1_2_1_17_1","volume-title":"Proceedings of the 32nd ISC (the International Supercomputing Conference) on High Performance.","author":"Shekofteh S.-K.","unstructured":"S.-K. Shekofteh , H. Noori , M. Naghibzadeh , H. S. Yazdi , and H. Froning . 2017. Enhancing performance of graphics processing units through better scheduling of concurrent kernels . In Proceedings of the 32nd ISC (the International Supercomputing Conference) on High Performance. S.-K. Shekofteh, H. Noori, M. Naghibzadeh, H. S. Yazdi, and H. Froning. 2017. Enhancing performance of graphics processing units through better scheduling of concurrent kernels. In Proceedings of the 32nd ISC (the International Supercomputing Conference) on High Performance."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2549523"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818950.2818979"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2012.6189201"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306801"},{"key":"e_1_2_1_22_1","volume-title":"The OpenCL Specification","author":"Munshi A.","unstructured":"A. Munshi . 2014. The OpenCL Specification ( 22 nd ed.). Khronos OpenCL Working Group . A. Munshi. 2014. The OpenCL Specification (22nd ed.). Khronos OpenCL Working Group.","edition":"22"},{"key":"e_1_2_1_23_1","unstructured":"K. Asanovic R. Bodik B. C. Catanzaro J. J. Gebis P. Husbands K. Keutzer D. A. Patterson W. L. Plishker J. Shalf S. W. Williams and K. A. Yelick. 2006. The Landscape of Parallel Computing Research: A View from Berkeley. Technical Report UCB\/EECS-2006-183.  K. Asanovic R. Bodik B. C. Catanzaro J. J. Gebis P. Husbands K. Keutzer D. A. Patterson W. L. Plishker J. Shalf S. W. Williams and K. A. Yelick. 2006. The Landscape of Parallel Computing Research: A View from Berkeley. Technical Report UCB\/EECS-2006-183."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2015.51"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2017.04.002"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2636342"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751213"},{"key":"e_1_2_1_29_1","volume-title":"Introduction to Statistical Pattern Recognition","author":"Fukunaga K.","unstructured":"K. Fukunaga . 1990. Parametric classifiers . In Introduction to Statistical Pattern Recognition ( 2 nd ed). Academic Press , 124--180. K. Fukunaga. 1990. Parametric classifiers. In Introduction to Statistical Pattern Recognition (2nd ed). Academic Press, 124--180.","edition":"2"},{"key":"e_1_2_1_30_1","unstructured":"NVIDIA. 2018. CUDA Samples SDK Reference Manual v 9.0.106.  NVIDIA. 2018. CUDA Samples SDK Reference Manual v 9.0.106."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_2_1_32_1","unstructured":"W. W. Daniel and others. 1978. Applied Nonparametric Statistics. Houghton Mifflin.  W. W. Daniel and others. 1978. Applied Nonparametric Statistics. Houghton Mifflin."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-014-1338-z"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967940"},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of the 13th Annual IEEE\/ACM International Symposium on Code Generation and Optimization. 1--11","author":"Jiao Q.","unstructured":"Q. Jiao , M. Lu , H. P. Huynh , and T. Mitra . 2015. Improving GPGPU energy-efficiency through concurrent kernel execution and DVFS . In Proceedings of the 13th Annual IEEE\/ACM International Symposium on Code Generation and Optimization. 1--11 . Q. Jiao, M. Lu, H. P. Huynh, and T. Mitra. 2015. Improving GPGPU energy-efficiency through concurrent kernel execution and DVFS. In Proceedings of the 13th Annual IEEE\/ACM International Symposium on Code Generation and Optimization. 1--11."},{"key":"e_1_2_1_36_1","volume-title":"Proceedings of the 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA\u201915)","author":"Wu G.","unstructured":"G. Wu , J. L. Greathouse , A. Lyashevsky , N. Jayasena , and D. Chiou . 2015. GPGPU performance and power estimation using machine learning . In Proceedings of the 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA\u201915) . 564--576. G. Wu, J. L. Greathouse, A. Lyashevsky, N. Jayasena, and D. Chiou. 2015. GPGPU performance and power estimation using machine learning. In Proceedings of the 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA\u201915). 564--576."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/11549468_24"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1229428.1229479"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2015.22"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.11.003"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.07.111"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.574797"},{"key":"e_1_2_1_44_1","first-page":"212","article-title":"Variational characterization of eigenvalues of Hermitian matrices","volume":"67","author":"Horn R. A.","year":"1985","unstructured":"R. A. Horn and C. R. Johnson . 1985 . Variational characterization of eigenvalues of Hermitian matrices . Matrix Analysis 67 , 3 (1985), 212 . R. A. Horn and C. R. Johnson. 1985. Variational characterization of eigenvalues of Hermitian matrices. Matrix Analysis 67, 3 (1985), 212.","journal-title":"Matrix Analysis"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.2307\/2528964"}],"container-title":["ACM Transactions on Architecture and Code Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3295690","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3295690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:12:50Z","timestamp":1750201970000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3295690"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,31]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,12,31]]}},"alternative-id":["10.1145\/3295690"],"URL":"https:\/\/doi.org\/10.1145\/3295690","relation":{},"ISSN":["1544-3566","1544-3973"],"issn-type":[{"value":"1544-3566","type":"print"},{"value":"1544-3973","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,31]]},"assertion":[{"value":"2018-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-11-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-01-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}