{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:37:24Z","timestamp":1743143844861,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030609382"},{"type":"electronic","value":"9783030609399"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-60939-9_16","type":"book-chapter","created":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T17:22:31Z","timestamp":1602696151000},"page":"228-242","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Quantitative Study of Locality in GPU Caches"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2325-1705","authenticated-orcid":false,"given":"Sohan","family":"Lal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ben","family":"Juurlink","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,10,7]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Al-Kiswany, S., Gharaibeh, A., Santos-Neto, E., Yuan, G., Ripeanu, M.: StoreGPU: exploiting graphics processing units to accelerate distributed storage systems. In: Proceedings of the 17th International Symposium on High Performance Distributed Computing, HPDC (2008)","DOI":"10.1145\/1383422.1383443"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Bakhoda, A., Yuan, G.L., Fung, W.W.L., Wong, H., Aamodt, T.M.: Analyzing CUDA workloads using a detailed GPU simulator. In: Proceedings of the IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS (2009)","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"16_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1007\/978-3-642-32820-6_87","volume-title":"Euro-Par 2012 Parallel Processing","author":"D Cederman","year":"2012","unstructured":"Cederman, D., Chatterjee, B., Tsigas, P.: Understanding the performance of concurrent data structures on graphics processors. In: Kaklamanis, C., Papatheodorou, T., Spirakis, P.G. (eds.) Euro-Par 2012. LNCS, vol. 7484, pp. 883\u2013894. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-32820-6_87"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Che, S., et al.: Rodinia: a benchmark suite for heterogeneous computing. In: Proceedings of the IEEE International Symposium on Workload Characterization, IISWC (2009)","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Chang, L.W., Rodrigues, C.I., Lv, J., Wang, Z., Hwu, W.M.: Adaptive cache management for energy-efficient GPU computing. In: Proceedings of the 47th IEEE\/ACM International Symposium on Microarchitecture, MICRO (2014)","DOI":"10.1109\/MICRO.2014.11"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Hong, S., Oguntebi, T., Olukotun, K.: Efficient parallel graph exploration on multi-core CPU and GPU. In: International Conference on Parallel Architectures and Compilation Techniques, PACT (2011)","DOI":"10.1109\/PACT.2011.14"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Jia, W., Shaw, K.A., Martonosi, M.: Characterizing and improving the use of demand-fetched caches in GPUs. In: Proceedings of the 26th ACM International Conference on Supercomputing, ICS (2012)","DOI":"10.1145\/2304576.2304582"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Lal, S., Lucas, J., Andersch, M., Alvarez-Mesa, M., Elhossini, A., Juurlink, B.: GPGPU workload characteristics and performance analysis. In: Proceedings of the 14th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS (2014)","DOI":"10.1109\/SAMOS.2014.6893202"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Li, A., van den Braak, G.J., Kumar, A., Corporaal, H.: Adaptive and transparent cache bypassing for GPUs. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC (2015)","DOI":"10.1145\/2807591.2807606"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Li, A., Song, S.L., Liu, W., Liu, X., Kumar, A., Corporaal, H.: Locality-aware CTA clustering for modern GPUs. In: Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS (2017)","DOI":"10.1145\/3037697.3037709"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Li, C., Song, S.L., Dai, H., Sidelnik, A., Hari, S.K.S., Zhou, H.: Locality-driven dynamic GPU cache bypassing. In: Proceedings of the 29th ACM on International Conference on Supercomputing, ICS (2015)","DOI":"10.1145\/2751205.2751237"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Meng, J., Tarjan, D., Skadron, K.: Dynamic warp subdivision for integrated branch and memory divergence tolerance. In: Proceedings of the 37th Annual International Symposium on Computer Architecture, ISCA (2010)","DOI":"10.1145\/1815961.1815992"},{"key":"16_CR13","unstructured":"NVIDIA: CUDA: Compute Unified Device Architecture (2007). http:\/\/developer.nvidia.com\/object\/gpucomputing.html"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Reguly, I.Z., Giles, M.: Efficient sparse matrix-vector multiplication on cache-based GPUs. In: Proceedings of the Innovative Parallel Computing, InPar (2012)","DOI":"10.1109\/InPar.2012.6339602"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Rogers, T.G., O\u2019Connor, M., Aamodt, T.M.: Cache-conscious wavefront scheduling. In: Proceedings of the 45th Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO (2012)","DOI":"10.1109\/MICRO.2012.16"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Sartori, J., Kumar, R.: Branch and data herding: reducing control and memory divergence for error-tolerant GPU applications. In: Proceedings of the 21st International Conference on Parallel Architectures and Compilation Techniques, PACT (2012)","DOI":"10.1145\/2370816.2370879"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Tarjan, D., Meng, J., Skadron, K.: Increasing memory miss tolerance for SIMD cores. In: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis, SC (2009)","DOI":"10.1145\/1654059.1654082"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Xiao, S., Lin, H., Feng, W.C.: Accelerating protein sequence search in a heterogeneous computing system. In: IEEE International Parallel and Distributed Processing Symposium, IPDPS (2011)","DOI":"10.1109\/IPDPS.2011.115"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Xie, X., Liang, Y., Wang, Y., Sun, G., Wang, T.: Coordinated static and dynamic cache bypassing for GPUs. In: 2015 IEEE 21st International Symposium on High Performance Computer Architecture, HPCA (2015)","DOI":"10.1109\/HPCA.2015.7056023"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, E.Z., Jiang, Y., Guo, Z., Tian, K., Shen, X.: On-the-fly elimination of dynamic irregularities for GPU computing. In: Proceedings of the 16th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS (2011)","DOI":"10.1145\/1950365.1950408"}],"container-title":["Lecture Notes in Computer Science","Embedded Computer Systems: Architectures, Modeling, and Simulation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60939-9_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T22:10:17Z","timestamp":1619302217000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-60939-9_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030609382","9783030609399"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60939-9_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"7 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SAMOS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Embedded Computer Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Samos","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 July 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"samos2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/samos-conference.com","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35","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":"25","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":"0","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":"71% - 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":"2","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}