{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:32:25Z","timestamp":1750221145305,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":10,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,6,18]],"date-time":"2018-06-18T00:00:00Z","timestamp":1529280000000},"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":[[2018,6,18]]},"DOI":"10.1145\/3211346.3211354","type":"proceedings-article","created":{"date-parts":[[2018,6,7]],"date-time":"2018-06-07T19:49:37Z","timestamp":1528400977000},"page":"42-51","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Diesel: DSL for linear algebra and neural net computations on GPUs"],"prefix":"10.1145","author":[{"given":"Venmugil","family":"Elango","sequence":"first","affiliation":[{"name":"NVIDIA, USA"}]},{"given":"Norm","family":"Rubin","sequence":"additional","affiliation":[{"name":"NVIDIA, USA"}]},{"given":"Mahesh","family":"Ravishankar","sequence":"additional","affiliation":[{"name":"NVIDIA, USA"}]},{"given":"Hariharan","family":"Sandanagobalane","sequence":"additional","affiliation":[{"name":"NVIDIA, USA"}]},{"given":"Vinod","family":"Grover","sequence":"additional","affiliation":[{"name":"NVIDIA, USA"}]}],"member":"320","published-online":{"date-parts":[[2018,6,18]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1145\/1375581.1375595"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.1145\/2743016"},{"unstructured":"NVIDIA. 2018. CuBLAS: Dense Linear Algebra on GPUs. https: \/\/developer.nvidia.com\/cublas  NVIDIA. 2018. CuBLAS: Dense Linear Algebra on GPUs. https: \/\/developer.nvidia.com\/cublas","key":"e_1_3_2_1_3_1"},{"unstructured":"NVIDIA. 2018. CUDA programming guide. http: \/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html# device-memory-accesses  NVIDIA. 2018. CUDA programming guide. http: \/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html# device-memory-accesses","key":"e_1_3_2_1_4_1"},{"unstructured":"NVIDIA. 2018. CuDNN: GPU Accelerated Deep Learning. https: \/\/developer.nvidia.com\/cudnn  NVIDIA. 2018. CuDNN: GPU Accelerated Deep Learning. https: \/\/developer.nvidia.com\/cudnn","key":"e_1_3_2_1_5_1"},{"key":"e_1_3_2_1_6_1","volume-title":"CUTLASS: Fast Linear Algebra in CUDA C++. https: \/\/github.com\/NVIDIA\/cutlass","author":"NVIDIA.","year":"2018","unstructured":"NVIDIA. 2018 . CUTLASS: Fast Linear Algebra in CUDA C++. https: \/\/github.com\/NVIDIA\/cutlass NVIDIA. 2018. CUTLASS: Fast Linear Algebra in CUDA C++. https: \/\/github.com\/NVIDIA\/cutlass"},{"unstructured":"OpenAI. 2018. OpenAI: Open single and half precision GEMM implementations. https:\/\/github.com\/openai\/openai-gemm  OpenAI. 2018. OpenAI: Open single and half precision GEMM implementations. https:\/\/github.com\/openai\/openai-gemm","key":"e_1_3_2_1_7_1"},{"key":"e_1_3_2_1_8_1","volume-title":"Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions. ArXiv e-prints (Feb.","author":"Vasilache N.","year":"2018","unstructured":"N. Vasilache , O. Zinenko , T. Theodoridis , P. Goyal , Z. DeVito , W. S. Moses , S. Verdoolaege , A. Adams , and A. Cohen . 2018 . Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions. ArXiv e-prints (Feb. 2018). arXiv: cs.PL\/1802.04730 N. Vasilache, O. Zinenko, T. Theodoridis, P. Goyal, Z. DeVito, W. S. Moses, S. Verdoolaege, A. Adams, and A. Cohen. 2018. Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions. ArXiv e-prints (Feb. 2018). arXiv: cs.PL\/1802.04730"},{"key":"e_1_3_2_1_9_1","volume-title":"Mathematical Software \u2013 ICMS","author":"Verdoolaege Sven","year":"2010","unstructured":"Sven Verdoolaege . 2010. isl: An Integer Set Library for the Polyhedral Model . In Mathematical Software \u2013 ICMS 2010 , Komei Fukuda, Joris van der Hoeven, Michael Joswig, and Nobuki Takayama (Eds.). Springer Berlin Heidelberg , Berlin, Heidelberg, 299\u2013302. Sven Verdoolaege. 2010. isl: An Integer Set Library for the Polyhedral Model. In Mathematical Software \u2013 ICMS 2010, Komei Fukuda, Joris van der Hoeven, Michael Joswig, and Nobuki Takayama (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 299\u2013302."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_10_1","DOI":"10.1145\/2400682.2400713"}],"event":{"sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"],"acronym":"PLDI '18","name":"PLDI '18: ACM SIGPLAN Conference on Programming Language Design and Implementation","location":"Philadelphia PA USA"},"container-title":["Proceedings of the 2nd ACM SIGPLAN International Workshop on Machine Learning and Programming Languages"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3211346.3211354","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3211346.3211354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:08:14Z","timestamp":1750208894000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3211346.3211354"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,18]]},"references-count":10,"alternative-id":["10.1145\/3211346.3211354","10.1145\/3211346"],"URL":"https:\/\/doi.org\/10.1145\/3211346.3211354","relation":{},"subject":[],"published":{"date-parts":[[2018,6,18]]},"assertion":[{"value":"2018-06-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}