{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T09:58:02Z","timestamp":1764842282632,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030293994"},{"type":"electronic","value":"9783030294007"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-29400-7_16","type":"book-chapter","created":{"date-parts":[[2019,8,18]],"date-time":"2019-08-18T23:02:41Z","timestamp":1566169361000},"page":"213-226","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Enhancing the Programmability and Performance Portability of GPU Tensor Operations"],"prefix":"10.1007","author":[{"given":"Arya","family":"Mazaheri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes","family":"Schulte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew W.","family":"Moskewicz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Jannesari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,13]]},"reference":[{"key":"16_CR1","unstructured":"Chen, T., et al.: TVM: an automated end-to-end optimizing compiler for deep learning. In: 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2018, pp. 578\u2013594 (2018)"},{"key":"16_CR2","unstructured":"Chetlur, S., et al.: cuDNN: efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Da Silva, H.C., Pisani, F., Borin, E.: A comparative study of SYCL, OpenCL, and OpenMP. In: Proceedings of International Symposium on Computer Architecture and High-Performance Computing Workshops, SBAC-PADW 2016, pp. 61\u201366. IEEE (2016)","DOI":"10.1109\/SBAC-PADW.2016.19"},{"issue":"8","key":"16_CR4","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.parco.2011.10.002","volume":"38","author":"P Du","year":"2012","unstructured":"Du, P., Weber, R., Luszczek, P., Tomov, S., Peterson, G., Dongarra, J.: From CUDA to OpenCL: towards a performance-portable solution for multi-platform GPU programming. Parallel Comput. 38(8), 391\u2013407 (2012)","journal-title":"Parallel Comput."},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Fang, J., Varbanescu, A.L., Sips, H.: A comprehensive performance comparison of CUDA and OpenCL. In: Proceedings of International Conference on Parallel Processing (ICPP), pp. 216\u2013225. IEEE (2011)","DOI":"10.1109\/ICPP.2011.45"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Huynh, L.N., Lee, Y., Balan, R.K.: DeepMon: mobile GPU-based deep learning framework for continuous vision applications. In: Proceedings of 15th Annual International Conference on Mobile Systems, Applications, and Services, MobiSys 2017, pp. 82\u201395. ACM (2017)","DOI":"10.1145\/3081333.3081360"},{"key":"16_CR7","unstructured":"Intel: PlaidML (2019). https:\/\/www.intel.ai\/plaidml"},{"key":"16_CR8","unstructured":"Karimi, K., Dickson, N.G., Hamze, F.: A performance comparison of CUDA and OpenCL. arXiv preprint arXiv:1005.2581 (2010)"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Kim, J., Dao, T.T., Jung, J., Joo, J., Lee, J.: Bridging OpenCL and CUDA: a comparative analysis and translation. In: Proceedings of International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2015, pp. 1\u201312. ACM (2015)","DOI":"10.1145\/2807591.2807621"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Mammeri, N., Juurlink, B.: VComputeBench: a Vulkan benchmark suite for GPGPU on mobile and embedded GPUs. In: Proceedings of International Symposium on Workload Characterization, IISWC 2018, pp. 25\u201335. IEEE (2018)","DOI":"10.1109\/IISWC.2018.8573477"},{"key":"16_CR11","unstructured":"Mazaheri, A., Schulte, J., Moskewicz, M., Wolf, F., Jannesari, A.: Artifact Evaluation (2019). https:\/\/doi.org\/10.6084\/m9.figshare.8490146"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Memeti, S., Li, L., Pllana, S., Ko\u0142odziej, J., Kessler, C.: Benchmarking OpenCL, OpenACC, OpenMP, and CUDA: programming productivity, performance, and energy consumption. In: Proceedings of Workshop on Adaptive Resource Management and Scheduling for Cloud Computing, pp. 1\u20136. ACM (2017)","DOI":"10.1145\/3110355.3110356"},{"key":"16_CR13","unstructured":"Moskewicz, M.W., Jannesari, A., Keutzer, K.: A metaprogramming and autotuning framework for deploying deep learning applications. arXiv preprint arXiv:1611.06945 (2016)"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Moskewicz, M.W., Jannesari, A., Keutzer, K.: Boda: a holistic approach for implementing neural network computations. In: Proceedings of International Conference on Computing Frontier, CF 2017, pp. 53\u201362. ACM (2017)","DOI":"10.1145\/3075564.3077382"},{"key":"16_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/978-3-642-31500-8_12","volume-title":"Parallel Processing and Applied Mathematics","author":"R Sachetto Oliveira","year":"2012","unstructured":"Sachetto Oliveira, R., et al.: Comparing CUDA, OpenCL and OpenGL implementations of the cardiac monodomain equations. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wa\u015bniewski, J. (eds.) PPAM 2011. LNCS, vol. 7204, pp. 111\u2013120. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31500-8_12"},{"key":"16_CR16","unstructured":"Sampson, A.: Let\u2019s fix OpenGL. In: Leibniz International Proceedings in Informatics, LIPIcs 2017, vol. 71. Schloss Dagstuhl, Leibniz-Zentrum f\u00fcer Informatik (2017)"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Su, C.L., Chen, P.Y., Lan, C.C., Huang, L.S., Wu, K.H.: Overview and comparison of OpenCL and CUDA technology for GPGPU. In: Proceedings of Asia Pacific Conference on Circuits and Systems, APCCAS 2012, pp. 448\u2013451. IEEE (2012)","DOI":"10.1109\/APCCAS.2012.6419068"},{"key":"16_CR18","unstructured":"The Khronos Group: Khronos SPIR-V registry (2019). https:\/\/www.khronos.org\/registry\/spir-v"},{"key":"16_CR19","unstructured":"The Khronos Group: Khronos Vulkan registry (2019). https:\/\/www.khronos.org\/registry\/vulkan"},{"key":"16_CR20","unstructured":"Vasilache, N., et al.: Tensor comprehensions: framework-agnostic high-performance machine learning abstractions. arXiv preprint arXiv:1802.04730 (2018)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2019: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-29400-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,13]],"date-time":"2023-08-13T00:03:38Z","timestamp":1691885018000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-29400-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030293994","9783030294007"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-29400-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"13 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"G\u00f6ttingen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"26 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/europar.org\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"142","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":"36","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":"25% - 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":"3,94","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":"4,27","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":"double blind review in two cases","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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}