{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:13:58Z","timestamp":1771956838534,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T00:00:00Z","timestamp":1590364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,5,25]]},"DOI":"10.1145\/3378678.3391880","type":"proceedings-article","created":{"date-parts":[[2020,5,26]],"date-time":"2020-05-26T00:21:35Z","timestamp":1590452495000},"page":"36-41","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Programming tensor cores from an image processing DSL"],"prefix":"10.1145","author":[{"given":"Savvas","family":"Sioutas","sequence":"first","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, Netherlands"}]},{"given":"Sander","family":"Stuijk","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, Netherlands"}]},{"given":"Twan","family":"Basten","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, Netherlands"}]},{"given":"Lou","family":"Somers","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, Netherlands"}]},{"given":"Henk","family":"Corporaal","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2020,5,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI'18)","author":"Chen Tianqi","year":"2018"},{"key":"e_1_3_2_1_2_1","unstructured":"Sharan Chetlur Cliff Woolley Philippe Vandermersch Jonathan Cohen John Tran Bryan Catanzaro and Evan Shelhamer. 2014. cuDNN: Efficient Primitives for Deep Learning. CoRR abs\/1410.0759 (2014). arXiv:1410.0759 http:\/\/arxiv.org\/abs\/1410.0759  Sharan Chetlur Cliff Woolley Philippe Vandermersch Jonathan Cohen John Tran Bryan Catanzaro and Evan Shelhamer. 2014. cuDNN: Efficient Primitives for Deep Learning. CoRR abs\/1410.0759 (2014). arXiv:1410.0759 http:\/\/arxiv.org\/abs\/1410.0759"},{"key":"e_1_3_2_1_3_1","volume-title":"Retrieved","author":"Intel Corporation","year":"2020"},{"key":"e_1_3_2_1_4_1","unstructured":"NVIDIA Corporation. 2008. NVIDIA cuBLAS library. https:\/\/developer.nvidia.com\/cublas version 10.0.  NVIDIA Corporation. 2008. NVIDIA cuBLAS library. https:\/\/developer.nvidia.com\/cublas version 10.0."},{"key":"e_1_3_2_1_5_1","volume-title":"Retrieved","author":"NVIDIA Corporation","year":"2017"},{"key":"e_1_3_2_1_6_1","volume-title":"Retrieved","author":"NVIDIA Corporation","year":"2017"},{"key":"e_1_3_2_1_7_1","volume-title":"Retrieved","author":"NVIDIA Corporation","year":"2017"},{"key":"e_1_3_2_1_8_1","unstructured":"Ian J. Goodfellow Yoshua Bengio and Aaron Courville. 2016. Deep Learning. MIT Press Cambridge MA USA. http:\/\/www.deeplearningbook.org.  Ian J. Goodfellow Yoshua Bengio and Aaron Courville. 2016. Deep Learning. MIT Press Cambridge MA USA. http:\/\/www.deeplearningbook.org."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/977395.977673"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2394802"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3107953"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2716282.2716290"},{"key":"e_1_3_2_1_15_1","unstructured":"TVM. 2019. TVM GitHub Repository (Apache-2.0 license). https:\/\/github.com\/apache\/incubator-tvm (commit 9ff44969e3b566a8f1a7a50c327f63a3427984420.  TVM. 2019. TVM GitHub Repository (Apache-2.0 license). https:\/\/github.com\/apache\/incubator-tvm (commit 9ff44969e3b566a8f1a7a50c327f63a3427984420."},{"key":"e_1_3_2_1_16_1","volume-title":"Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions. CoRR abs\/1802.04730","author":"Vasilache Nicolas","year":"2018"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106343"}],"event":{"name":"SCOPES '20: 23rd International Workshop on Software and Compilers for Embedded Systems","location":"St. Goar Germany","acronym":"SCOPES '20","sponsor":["SIGBED ACM Special Interest Group on Embedded Systems","EDAA European Design Automation Association"]},"container-title":["Proceedings of the 23th International Workshop on Software and Compilers for Embedded Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3378678.3391880","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3378678.3391880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:19Z","timestamp":1750200079000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3378678.3391880"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,25]]},"references-count":17,"alternative-id":["10.1145\/3378678.3391880","10.1145\/3378678"],"URL":"https:\/\/doi.org\/10.1145\/3378678.3391880","relation":{},"subject":[],"published":{"date-parts":[[2020,5,25]]},"assertion":[{"value":"2020-05-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}