{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T14:32:48Z","timestamp":1770647568884,"version":"3.49.0"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030727888","type":"print"},{"value":"9783030727895","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-72789-5_3","type":"book-chapter","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T22:48:05Z","timestamp":1616712485000},"page":"32-48","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["FLARE: Flexibly Sharing Commodity GPUs to Enforce QoS and Improve Utilization"],"prefix":"10.1007","author":[{"given":"Wei","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Mawhirter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,3,26]]},"reference":[{"key":"3_CR1","unstructured":"Text classification in TensorFlow (2017). https:\/\/github.com\/tensorflow\/tensorflow\/tree\/master\/tensorflow\/examples\/learn#text-classification"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Adriaens, J., Compton, K., Kim, N.S., Schulte, M.J.: The case for GPGPU spatial multitasking. In: HPCA (2012)","DOI":"10.1109\/HPCA.2012.6168946"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Allen, T., Feng, X., Ge, R.: Slate: enabling workload-aware efficient multiprocessing for modern GPGPUs. In: IPDPS (2019)","DOI":"10.1109\/IPDPS.2019.00035"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Barroso, L.A., Clidaras, J., H\u00f6lzle, U.: The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines, 2nd edn. Synthesis Lectures on Computer Architecture. Morgan & Claypool Publishers (2013)","DOI":"10.2200\/S00516ED2V01Y201306CAC024"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Che, S., et al.: Rodinia: a benchmark suite for heterogeneous computing. In: IISWC (2009)","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Chen, G., Zhao, Y., Shen, X., Zhou, H.: EffiSha: a software framework for enabling efficient preemptive scheduling of GPU. In: Sarkar, V., Rauchwerger, L. (eds.) PPoPP, pp. 3\u201316. ACM (2017)","DOI":"10.1145\/3155284.3018748"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Q., Yang, H., Guo, M., Kannan, R.S., Mars, J., Tang, L.: Prophet: precise QoS prediction on non-preemptive accelerators to improve utilization in warehouse-scale computers. In: ASPLOS (2017)","DOI":"10.1145\/3037697.3037700"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Q., Yang, H., Mars, J., Tang, L.: Baymax: QoS awareness and increased utilization of non-preemptive accelerators in warehouse scale computers. In: ASPLOS (2016)","DOI":"10.1145\/2872362.2872368"},{"key":"3_CR9","unstructured":"Chung, J., G\u00fcl\u00e7ehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR, abs\/1412.3555 (2014)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Danalis, A., et al.: The scalable heterogeneous computing (SHOC) benchmark suite. In: GPGPU (2010)","DOI":"10.1145\/1735688.1735702"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Han, W., Mawhirter, D., Buland, M., Wu, B.: Graphie: large-scale asynchronous graph traversals on just a GPU. In: PACT 2017 (2017)","DOI":"10.1109\/PACT.2017.41"},{"issue":"8","key":"3_CR12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"12","key":"3_CR13","doi-asserted-by":"publisher","first-page":"3472","DOI":"10.1109\/TPDS.2017.2717908","volume":"28","author":"C-H Hong","year":"2017","unstructured":"Hong, C.-H., Spence, I.T.A., Nikolopoulos, D.S.: FairGV: fair and fast GPU virtualization. IEEE Trans. Parallel Distrib. Syst. 28(12), 3472\u20133485 (2017)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"3","key":"3_CR14","doi-asserted-by":"publisher","first-page":"35:1","DOI":"10.1145\/3068281","volume":"50","author":"C-H Hong","year":"2017","unstructured":"Hong, C.-H., Spence, I.T.A., Nikolopoulos, D.S.: GPU virtualization and scheduling methods: a comprehensive survey. ACM Comput. Surv. 50(3), 35:1\u201335:37 (2017)","journal-title":"ACM Comput. Surv."},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Kehne, J., Metter, J., Bellosa, F.: GPUswap: enabling oversubscription of GPU memory through transparent swapping. In: VEE (2015)","DOI":"10.1145\/2731186.2731192"},{"issue":"3","key":"3_CR16","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1109\/TPDS.2014.2313342","volume":"26","author":"Y Liang","year":"2015","unstructured":"Liang, Y., Huynh, H.P., Rupnow, K., Goh, R.S.M., Chen, D.: Efficient GPU spatial-temporal multitasking. IEEE Trans. Parallel Distrib. Syst. 26(3), 748\u2013760 (2015)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Liang, Y., Li, X., Xie, X.: Exploring cache bypassing and partitioning for multi-tasking on GPUs. In: ICCAD (2017)","DOI":"10.1109\/ICCAD.2017.8203754"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Lo, D., Cheng, L., Govindaraju, R., Barroso, L.A., Kozyrakis, C.: Towards energy proportionality for large-scale latency-critical workloads. In: ISCA (2014)","DOI":"10.1109\/ISCA.2014.6853237"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Lo, D., Cheng, L., Govindaraju, R., Ranganathan, P., Kozyrakis, C.: Heracles: improving resource efficiency at scale. In: ISCA (2015)","DOI":"10.1145\/2749469.2749475"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Mars, J., Tang, L., Hundt, R., Skadron, K., Soffa, M.L.: Bubble-up: increasing utilization in modern warehouse scale computers via sensible co-locations. In: MICRO (2011)","DOI":"10.1145\/2155620.2155650"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Park, J.J.K., Park, Y., Mahlke, S.: Chimera: collaborative preemption for multitasking on a shared GPU. In: ASPLOS (2015)","DOI":"10.1145\/2694344.2694346"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Park, J.J.K., Park, Y., Mahlke, S.A.: Dynamic resource management for efficient utilization of multitasking GPUs. In: ASPLOS (2017)","DOI":"10.1145\/3037697.3037707"},{"key":"3_CR23","unstructured":"Sutskever, I., Martens, J., Hinton, G.E.: Generating text with recurrent neural networks. In: ICML (2011)"},{"key":"3_CR24","unstructured":"Suzuki, Y., Kato, S., Yamada, H., Kono, K.: GPUvm: why not virtualizing GPUs at the hypervisor? In: USENIX ATC (2014)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Suzuki, Y., Yamada, H., Kato, S., Kono, K.: GLoop: an event-driven runtime for consolidating GPGPU applications. In: SoCC (2017)","DOI":"10.1145\/3127479.3132023"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Tanasic, I., Gelado, I., Cabezas, J., Ramirez, A., Navarro, N., Valero, M.: Enabling preemptive multiprogramming on GPUs. In: ISCA (2014)","DOI":"10.1109\/ISCA.2014.6853208"},{"key":"3_CR27","unstructured":"Tian, K., Dong, Y., Cowperthwaite, D.: A full GPU virtualization solution with mediated pass-through. In: USENIX ATC (2014)"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Y., Davidson, A., Pan, Y., Wu, Y., Riffel, A., Owens, J.D.: Gunrock: a high-performance graph processing library on the GPU. In: PPoPP (2015)","DOI":"10.1145\/2688500.2688538"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yang, J., Melhem, R., Childers, B., Zhang, Y., Guo, M.: Quality of service support for fine-grained sharing on GPUs. In: ISCA (2017)","DOI":"10.1145\/3079856.3080203"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Wu, B., Chen, G., Li, D., Shen, X., Vetter, J.S.: Enabling and exploiting flexible task assignment on GPU through SM-centric program transformations. In: ICS (2015)","DOI":"10.1145\/2751205.2751213"},{"key":"3_CR31","unstructured":"Bo, W., Liu, X., Zhou, X., Jiang, C.: FLEP: enabling flexible and efficient preemption on GPUs. In: ASPLOS (2017)"},{"key":"3_CR32","unstructured":"Zhang, W., et al.: Laius: towards latency awareness and improved utilization of spatial multitasking accelerators in datacenters. In: ICS (2019)"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Laurenzano, M.A., Mars, J., Tang, L.: SMiTe: precise QoS prediction on real-system SMT processors to improve utilization in warehouse scale computers. In: MICRO (2014)","DOI":"10.1109\/MICRO.2014.53"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, H., Erez, M.: Dirigent: enforcing QoS for latency-critical tasks on shared multicore systems. In: ASPLOS (2016)","DOI":"10.1145\/2872362.2872394"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-72789-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T22:52:08Z","timestamp":1616712728000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-72789-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030727888","9783030727895"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-72789-5_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"26 March 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LCPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Languages and Compilers for Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Atlanta, GA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"lcpc2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lcpc19.cc.gatech.edu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Hotcrp","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"17","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"8","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"47% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}