{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T14:10:08Z","timestamp":1749910208126,"version":"3.41.0"},"reference-count":19,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Electron. Express"],"published-print":{"date-parts":[[2017]]},"DOI":"10.1587\/elex.14.20161158","type":"journal-article","created":{"date-parts":[[2017,1,15]],"date-time":"2017-01-15T22:10:42Z","timestamp":1484518242000},"page":"20161158-20161158","source":"Crossref","is-referenced-by-count":2,"title":["Efficient GPU multitasking with latency minimization and cache boosting"],"prefix":"10.1587","volume":"14","author":[{"given":"Jiho","family":"Kim","sequence":"first","affiliation":[{"name":"School of Electronic and Electrical Engineering, Hongik University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minsung","family":"Chu","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering, Hongik University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongjun","family":"Park","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering, Hongik University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] J. T. Adriaens, <i>et al.<\/i>: \u201cThe case for GPGPU spatial multitasking,\u201d HPCA (2012) 1 (DOI: 10.1109\/HPCA.2012.6168946).","DOI":"10.1109\/HPCA.2012.6168946"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] P. Aguilera, <i>et al.<\/i>: \u201cQoS-aware dynamic resource allocation for spatial multitasking GPUs,\u201d ASP-DAC (2014) 726 (DOI: 10.1109\/ASPDAC.2014.6742976).","DOI":"10.1109\/ASPDAC.2014.6742976"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] D. H. Albonesi: \u201cSelective cache ways: On demand cache resource allocation,\u201d MICRO (1999) 248.","DOI":"10.1109\/MICRO.1999.809463"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] A. Bakhoda, <i>et al.<\/i>: \u201cAnalyzing CUDA workloads using a detailed GPU simulator,\u201d ISPASS (2009) 163 (DOI: 10.1109\/ISPASS.2009.4919648).","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] S. Che, <i>et al.<\/i>: \u201cRodinia: A benchmark suite for heterogeneous computing,\u201d IISWC (2009) 163 (DOI: 10.1109\/IISWC.2009.5306797).","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"6","unstructured":"[6] P. N. Glaskowsky: \u201cNVIDIA\u2019s Fermi: the first complete GPU computing architecture,\u201d White paper (2009)."},{"key":"7","unstructured":"[7] C. Gregg, <i>et al.<\/i>: \u201cFine-grained resource sharing for concurrent GPGPU kernels,\u201d USENIX (2012) 10."},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] B. He, <i>et al.<\/i>: \u201cMars: A MapReduce framework on graphics processors,\u201d PACT (2008) 260 (DOI: 10.1145\/1454115.1454152).","DOI":"10.1145\/1454115.1454152"},{"key":"9","doi-asserted-by":"publisher","unstructured":"[9] Y. Lianget al.: \u201cEfficient GPU spatial-temporal multitasking,\u201d IEEE Trans. Parallel Distrib. Syst. <b>26<\/b> (2015) 748 (DOI: 10.1109\/TPDS.2014.2313342).","DOI":"10.1109\/TPDS.2014.2313342"},{"key":"10","unstructured":"[10] J. Nickolls, <i>et al.<\/i>: \u201cNVIDIA CUDA software and GPU parallel computing architecture,\u201d Microprocessor Forum (2007)."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] S. Pai, <i>et al.<\/i>: \u201cImproving GPGPU concurrency with elastic kernels,\u201d ASPLOS (2013) 407 (DOI: 10.1145\/2451116.2451160).","DOI":"10.1145\/2451116.2451160"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] J. J. K. Park, <i>et al.<\/i>: \u201cChimera: Collaborative preemption for multitasking on a shared GPU,\u201d ASPLOS (2015) 593 (DOI: 10.1145\/2694344.2694346).","DOI":"10.1145\/2694344.2694346"},{"key":"13","unstructured":"[13] Polybench: \u201cThe Polyhedral benchmark suit\u201d (2011) http:\/\/www.cse.ohio-state.edu\/~pouchet\/software\/polybench\/GPU."},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] I. Tanasic, <i>et al.<\/i>: \u201cEnabling preemptive multiprogramming on GPUs,\u201d ISCA (2014) 193 (DOI: 10.1109\/ISCA.2014.6853208).","DOI":"10.1109\/ISCA.2014.6853208"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] Z. Wang, <i>et al.<\/i>: \u201cSimultaneous Multikernel GPU: Multi-tasking throughput processors via fine-grained sharing,\u201d HPCA (2016) 358 (DOI: 10.1109\/HPCA.2016.7446078).","DOI":"10.1109\/HPCA.2016.7446078"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] Q. Xu, <i>et al.<\/i>: \u201cWarped-slicer: Efficient Intra-SM slicing through dynamic resource partitioning for GPU multiprogramming,\u201d ISCA (2016) 230 (DOI: 10.1109\/ISCA.2016.29).","DOI":"10.1109\/ISCA.2016.29"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] G. Pekhimenko, <i>et al.<\/i>: \u201cA case for toggle-aware compression for GPU systems,\u201d HPCA (2016) 188 (DOI: 10.1109\/HPCA.2016.7446064).","DOI":"10.1109\/HPCA.2016.7446064"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] N. Agarwal, <i>et al.<\/i>: \u201cSelective GPU caches to eliminate CPU-GPU HW cache coherence,\u201d HPCA (2016) 494 (DOI: 10.1109\/HPCA.2016.7446089).","DOI":"10.1109\/HPCA.2016.7446089"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] J. Kloosterman, <i>et al.<\/i>: \u201cWarpPool: Sharing requests with inter-warp coalescing for throughput processors,\u201d MICRO (2015) 433 (DOI: 10.1145\/2830772.2830830).","DOI":"10.1145\/2830772.2830830"}],"container-title":["IEICE Electronics Express"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/14\/7\/14_14.20161158\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T13:37:35Z","timestamp":1749908255000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/14\/7\/14_14.20161158\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"references-count":19,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2017]]}},"URL":"https:\/\/doi.org\/10.1587\/elex.14.20161158","relation":{},"ISSN":["1349-2543"],"issn-type":[{"type":"electronic","value":"1349-2543"}],"subject":[],"published":{"date-parts":[[2017]]}}}