{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:43:30Z","timestamp":1773193410213,"version":"3.50.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,10,12]],"date-time":"2021-10-12T00:00:00Z","timestamp":1633996800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,12]],"date-time":"2021-10-12T00:00:00Z","timestamp":1633996800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2021R1A2C1003379"],"award-info":[{"award-number":["2021R1A2C1003379"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s10586-021-03429-7","type":"journal-article","created":{"date-parts":[[2021,10,12]],"date-time":"2021-10-12T22:11:29Z","timestamp":1634076689000},"page":"597-617","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["K-Scheduler: dynamic intra-SM multitasking management with execution profiles on GPUs"],"prefix":"10.1007","volume":"25","author":[{"given":"Sejin","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4799-3209","authenticated-orcid":false,"given":"Yoonhee","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,12]]},"reference":[{"key":"3429_CR1","unstructured":"TOP-500. https:\/\/www.top500.org\/"},{"issue":"2","key":"3429_CR2","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1145\/2408776.2408794","volume":"56","author":"J Dean","year":"2013","unstructured":"Dean, J., Barroso, L.A.: The tail at scale. Commun. ACM 56(2), 74\u201380 (2013)","journal-title":"Commun. ACM"},{"key":"3429_CR3","unstructured":"EC2 ELASTIC GPUS, A. (2017). https:\/\/aws.amazon.com\/ec2\/Elastic-GPUs\/"},{"key":"3429_CR4","unstructured":"NIMBIX. https:\/\/www.nimbix.net\/cloud-computing-nvidia\/"},{"key":"3429_CR5","unstructured":"MICROSOFT-AZURE. https:\/\/docs.microsoft.com\/en-au\/azure\/virtual-machines\/windows\/sizes-gpu"},{"issue":"9","key":"3429_CR6","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1002\/cpe.728","volume":"15","author":"JJ Dongarra","year":"2003","unstructured":"Dongarra, J.J., Luszczek, P., Petitet, A.: The linpack benchmark: past, present and future. Concurr. Comput.: Pract. Exp. 15(9), 803\u2013820 (2003)","journal-title":"Concurr. Comput.: Pract. Exp."},{"key":"3429_CR7","doi-asserted-by":"crossref","unstructured":"Dongarra, J., Heroux, M.A.: Toward a new metric for ranking high performance computing systems. Sandia report, SAND2013-4744 312, 150 (2013)","DOI":"10.2172\/1089988"},{"key":"3429_CR8","doi-asserted-by":"crossref","unstructured":"Allen, T., Feng, X., Ge, R.: Slate: enabling workload-aware efficient multiprocessing for modern gpgpus. In: 2019 IEEE international parallel and distributed processing symposium (IPDPS), pp.\u00a0252\u2013261. IEEE","DOI":"10.1109\/IPDPS.2019.00035"},{"key":"3429_CR9","unstructured":"NVIDIA-MULTI-PROCESS-SERVICE.   (2020). https:\/\/docs.nvidia.com\/deploy\/pdf\/CUDA-Multi-Process-Service-Overview.pdf"},{"issue":"4","key":"3429_CR10","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MM.2015.71","volume":"35","author":"MJ Schulte","year":"2015","unstructured":"Schulte, M.J., Ignatowski, M., Loh, G.H., Beckmann, B.M., Brantley, W.C., Gurumurthi, S., Jayasena, N., Paul, I., Reinhardt, S.K., Rodgers, G.: Achieving exascale capabilities through heterogeneous computing. IEEE Micro 35(4), 26\u201336 (2015)","journal-title":"IEEE Micro"},{"key":"3429_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, W., Cui, W., Fu, K., Chen, Q., Mawhirter, D.E., Wu, B., Li, C., Guo, M.: Laius: Towards latency awareness and improved utilization of spatial multitasking accelerators in datacenters. In: Proceedings of the ACM international conference on supercomputing, pp.\u00a058\u201368 (2019)","DOI":"10.1145\/3330345.3330351"},{"key":"3429_CR12","doi-asserted-by":"crossref","unstructured":"Zhao, X., Jahre, M., Eeckhout, L.: Hsm: A hybrid slowdown model for multitasking gpus. In: Proceedings of the twenty-fifth international conference on architectural support for programming languages and operating systems, pp.\u00a01371\u20131385 (2020)","DOI":"10.1145\/3373376.3378457"},{"key":"3429_CR13","doi-asserted-by":"crossref","unstructured":"Zhao, X., Wang, Z., Eeckhout, L.: Classification-driven search for effective sm partitioning in multitasking gpus. In: Proceedings of the 2018 international conference on supercomputing, pp.\u00a065\u201375 (2018)","DOI":"10.1145\/3205289.3205311"},{"key":"3429_CR14","doi-asserted-by":"crossref","unstructured":"Dai, H., Lin, Z., Li, C., Zhao, C., Wang, F., Zheng, N., Zhou, H.: Accelerate gpu concurrent kernel execution by mitigating memory pipeline stalls. In: 2018 IEEE international symposium on high performance computer architecture (HPCA), pp.\u00a0208\u2013220. IEEE (2018)","DOI":"10.1109\/HPCA.2018.00027"},{"key":"3429_CR15","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yang, J., Melhem, R., Childers, B., Zhang, Y., Guo, M.: Simultaneous multikernel gpu: multi-tasking throughput processors via fine-grained sharing. In: 2016 IEEE international symposium on high performance computer architecture (HPCA), pp.\u00a0358\u2013369. IEEE (2016)","DOI":"10.1109\/HPCA.2016.7446078"},{"key":"3429_CR16","doi-asserted-by":"crossref","unstructured":"Xu, Q., Jeon, H., Kim, K., Ro, W.W., Annavaram, M. Warped-slicer.: Efficient intra-sm slicing through dynamic resource partitioning for gpu multiprogramming. In: 2016 ACM\/IEEE 43rd annual international symposium on computer architecture (ISCA) (2016), pp.\u00a0230\u2013242. IEEE (2016)","DOI":"10.1109\/ISCA.2016.29"},{"key":"3429_CR17","doi-asserted-by":"crossref","unstructured":"Che, S., Boyer, M., Meng, J., Tarjan, D., Sheaffer, J.W., Lee, S.-H., Skadron, K. Rodinia.: Rodinia: A benchmark suite for heterogeneous computing. In: 2009 IEEE international symposium on workload characterization (IISWC), pp.\u00a044\u201354. IEEE (2009)","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"3429_CR18","unstructured":"NVIDIA-CUDA-SAMPLE.   https:\/\/docs.nvidia.com\/cuda\/cuda-samples\/index.html"},{"key":"3429_CR19","unstructured":"Stratton, J.A., Rodrigues, C., Sung, I.-J., Obeid, N., Chang, L.-W., Anssari, N., Liu, G.D., Hwu, W.-M.W.: Parboil: a revised benchmark suite for scientific and commercial throughput computing. Center for Reliable and High-Performance Computing 127,(2012)"},{"key":"3429_CR20","doi-asserted-by":"crossref","unstructured":"Danalis, A., Marin, G., McCurdy, C., Meredith, J.S., Roth, P.C., Spafford, K., Tipparaju, V., Vetter, J.S.: The scalable heterogeneous computing (SHOC) benchmark suite. In: Proceedings of the 3rd workshop on general-purpose computation on graphics processing units, pp. 63\u201374 (2010)","DOI":"10.1145\/1735688.1735702"},{"key":"3429_CR21","unstructured":"POLYHEDRAL-BENCHMARK-SUITE. http:\/\/web.cse.ohio-state.edu\/pouchet.2\/software\/polybench\/"},{"key":"3429_CR22","unstructured":"PROGRAMMING GUIDE, C.-C. (2021).    https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html"},{"key":"3429_CR23","unstructured":"TUNING GUIDE, K.   (2021). https:\/\/docs.nvidia.com\/cuda\/kepler-tuning-guide\/index.html"},{"issue":"6","key":"3429_CR24","doi-asserted-by":"publisher","first-page":"604","DOI":"10.5626\/JOK.2021.48.6.604","volume":"48","author":"Sejin Kim","year":"2021","unstructured":"Kim, S., Qichen Chen, H.Y., Kim, Y.: Performance analysis of concurrent multitasking for efficient resource utilization of gpus. J. KIISE 48(6), 604\u2013611 (2021)","journal-title":"J. KIISE"},{"key":"3429_CR25","unstructured":"NVCC.   (2021). https:\/\/docs.nvidia.com\/cuda\/cuda-compiler-driver-nvcc\/index.html"},{"key":"3429_CR26","doi-asserted-by":"crossref","unstructured":"Chen, Q., Chung, H., Son, Y., Kim, Y., and Yeom, H.Y.: Smcompactor: a workload-aware fine-grained resource management framework for gpgpus. In: Proceedings of the 36th annual ACM symposium on applied computing, SAC \u201921, pp.\u00a01147\u20131155 (2021)","DOI":"10.1145\/3412841.3441989"},{"key":"3429_CR27","doi-asserted-by":"crossref","unstructured":"Park, J.J.K., Park, Y., Mahlke, S.: Dynamic resource management for efficient utilization of multitasking gpus. In: Proceedings of the twenty-second international conference on architectural support for programming languages and operating systems, pp.\u00a0527\u2013540 (2017)","DOI":"10.1145\/3037697.3037707"},{"key":"3429_CR28","doi-asserted-by":"crossref","unstructured":"Thomas, W., Toraskar, S., Singh, V.: Dynamic optimizations in gpu using roofline model. In: 2021 IEEE international symposium on circuits and systems (ISCAS), pp.\u00a01\u20135 (2021)","DOI":"10.1109\/ISCAS51556.2021.9401255"},{"key":"3429_CR29","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.jpdc.2020.03.009","volume":"141","author":"M Wei","year":"2020","unstructured":"Wei, M., Zhao, W., Chen, Q., Dai, H., Leng, J., Li, C., Zheng, W., Guo, M.: Predicting and reining in application-level slowdown on spatial multitasking gpus. J. Parallel Distrib. Comput. 141, 99\u2013114 (2020)","journal-title":"J. Parallel Distrib. Comput."},{"key":"3429_CR30","doi-asserted-by":"crossref","unstructured":"Alizadeh, N.S., Momtazpour, M.: Machine learning-based interference detection in gpgpu concurrent kernel execution. In: 2020 25th international computer conference, computer society of Iran (CSICC), pp.\u00a01\u20134. IEEE (2020)","DOI":"10.1109\/CSICC49403.2020.9050074"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-021-03429-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-021-03429-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-021-03429-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T22:11:50Z","timestamp":1642630310000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-021-03429-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,12]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["3429"],"URL":"https:\/\/doi.org\/10.1007\/s10586-021-03429-7","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,12]]},"assertion":[{"value":"12 April 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 October 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Written informed consent for publication of this paper was obtained\nfrom Sookmyung Women\u2019s University and all authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}