{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:22:26Z","timestamp":1760710946805,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031061554"},{"type":"electronic","value":"9783031061561"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-06156-1_37","type":"book-chapter","created":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T20:29:39Z","timestamp":1654720179000},"page":"468-479","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["An Experimental Study of\u00a0SYCL Task Graph Parallelism for\u00a0Large-Scale Machine Learning Workloads"],"prefix":"10.1007","author":[{"given":"Cheng-Hsiang","family":"Chiu","sequence":"first","affiliation":[]},{"given":"Dian-Lun","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Tsung-Wei","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,6,9]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Bauer, M., Treichler, S., Slaughter, E., Aiken, A.: Legion: expressing locality and independence with logical regions. In: SC 2012: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, pp. 1\u201311. IEEE (2012)","key":"37_CR1","DOI":"10.1109\/SC.2012.71"},{"doi-asserted-by":"crossref","unstructured":"Bosilca, G., Bouteiller, A., Danalis, A., Herault, T., Lemariner, P., Dongarra, J.: DAGuE: a generic distributed DAG engine for high performance computing, pp. 1151\u20131158. IEEE, Anchorage (2011)","key":"37_CR2","DOI":"10.1109\/IPDPS.2011.281"},{"unstructured":"Codeplay Software Ltd. https:\/\/codeplay.com","key":"37_CR3"},{"unstructured":"cuBLAS. https:\/\/docs.nvidia.com\/cuda\/cublas\/index.html","key":"37_CR4"},{"unstructured":"cuSPARSE. https:\/\/docs.nvidia.com\/cuda\/cusparse\/index.html","key":"37_CR5"},{"unstructured":"DPC++ Compiler. https:\/\/intel.github.io\/llvm-docs\/GetStartedGuide.html","key":"37_CR6"},{"unstructured":"DPC++ Reference: Unified Shared Memory. https:\/\/reurl.cc\/5oYVOz","key":"37_CR7"},{"issue":"12","key":"37_CR8","doi-asserted-by":"publisher","first-page":"3202","DOI":"10.1016\/j.jpdc.2014.07.003","volume":"74","author":"HC Edwards","year":"2014","unstructured":"Edwards, H.C., Trott, C.R., Sunderland, D.: Kokkos: enabling manycore performance portability through polymorphic memory access patterns. J. Parallel Distrib. Comput. 74(12), 3202\u20133216 (2014)","journal-title":"J. Parallel Distrib. Comput."},{"doi-asserted-by":"crossref","unstructured":"Guo, G., Huang, T.W., Lin, Y., Wong, M.: GPU-accelerated path-based timing analysis. In: ACM\/IEEE Design Automation Conference (DAC) (2021)","key":"37_CR9","DOI":"10.1109\/DAC18074.2021.9586316"},{"doi-asserted-by":"crossref","unstructured":"Guo, Z., Huang, T.W., Lin, Y.: GPU-accelerated static timing analysis. In: IEEE\/ACM International Conference on Computer-aided Design (ICCAD), pp. 1\u20138 (2020)","key":"37_CR10","DOI":"10.1145\/3400302.3415631"},{"unstructured":"HPEC Sparse Deep Neural Network Inference Challenge. https:\/\/graphchallenge.mit.edu\/challenges","key":"37_CR11"},{"doi-asserted-by":"crossref","unstructured":"Huang, T.W., Lin, C.X., Guo, G., Wong, M.: Cpp-taskflow: fast task-based parallel programming using modern c++. In: 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 974\u2013983. IEEE (2019)","key":"37_CR12","DOI":"10.1109\/IPDPS.2019.00105"},{"issue":"4","key":"37_CR13","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1109\/TCAD.2020.3007319","volume":"40","author":"TW Huang","year":"2021","unstructured":"Huang, T.W., Lin, C.X., Wong, M.D.F.: OpenTimer v2: a parallel incremental timing analysis engine. IEEE Trans. Comput.-Aided Des. Integr. Circ. Syst. (TCAD) 40(4), 776\u2013789 (2021)","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circ. Syst. (TCAD)"},{"doi-asserted-by":"crossref","unstructured":"Huang, T.W., Wong, M.: OpenTimer: a high-performance timing analysis tool. In: IEEE\/ACM International Conference on Computer-aided Design (ICCAD), pp. 895\u2013902 (2015)","key":"37_CR14","DOI":"10.1109\/ICCAD.2015.7372666"},{"unstructured":"Intel oneAPI. https:\/\/reurl.cc\/2bpNzX","key":"37_CR15"},{"unstructured":"Khronos SYCL group. https:\/\/www.khronos.org\/sycl\/","key":"37_CR16"},{"doi-asserted-by":"crossref","unstructured":"Lin, D.L., Huang, T.W.: A novel inference algorithm for large sparse neural network using task graph parallelism. In: 2020 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20137. IEEE (2020)","key":"37_CR17","DOI":"10.1109\/HPEC43674.2020.9286218"},{"doi-asserted-by":"crossref","unstructured":"Lin, D.L., Huang, T.W.: Efficient GPU computation using task graph parallelism. In: 2021 IEEE\/ACM European Conference on Parallel and Distributed Computing. IEEE (2021)","key":"37_CR18","DOI":"10.1007\/978-3-030-85665-6_27"},{"unstructured":"NVIDIA cdDNN. https:\/\/developer.nvidia.com\/cudnn","key":"37_CR19"},{"unstructured":"NVIDIA CUDA Graph. https:\/\/developer.nvidia.com\/blog\/cuda-graphs\/","key":"37_CR20"},{"unstructured":"syclFlow. https:\/\/taskflow.github.io\/taskflow\/GPUTaskingsyclFlow.html","key":"37_CR21"},{"unstructured":"Unified Shared Memory. https:\/\/reurl.cc\/WElyRx","key":"37_CR22"},{"unstructured":"Yao, J., Li, C.: CUDA graph in TensorFlow. In: Nvidia GPU Technology Conference (GTC) (2021)","key":"37_CR23"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2021: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-06156-1_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T20:34:43Z","timestamp":1654720483000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-06156-1_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031061554","9783031061561"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-06156-1_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"9 June 2022","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":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2021.euro-par.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":"136","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":"39","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":"29% - 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":"6","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)"}}]}}