{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T20:22:04Z","timestamp":1751660524078,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,2,23]],"date-time":"2020-02-23T00:00:00Z","timestamp":1582416000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/L01503X\/1"],"award-info":[{"award-number":["EP\/L01503X\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,2,23]]},"DOI":"10.1145\/3366428.3380771","type":"proceedings-article","created":{"date-parts":[[2020,2,19]],"date-time":"2020-02-19T22:50:35Z","timestamp":1582152635000},"page":"41-50","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Automatic generation of specialized direct convolutions for mobile GPUs"],"prefix":"10.1145","author":[{"given":"Naums","family":"Mogers","sequence":"first","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Valentin","family":"Radu","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Li","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack","family":"Turner","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"O'Boyle","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christophe","family":"Dubach","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,2,23]]},"reference":[{"volume-title":"Tensorflow: A system for large-scale machine learning. In 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16). 265--283.","year":"2016","author":"Abadi Mart\u00edn","key":"e_1_3_2_1_1_1"},{"volume-title":"Low-memory gemm-based convolution algorithms for deep neural networks. arXiv preprint arXiv:1709.03395","year":"2017","author":"Anderson Andrew","key":"e_1_3_2_1_2_1"},{"volume-title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274","year":"2015","author":"Chen Tianqi","key":"e_1_3_2_1_3_1"},{"key":"e_1_3_2_1_4_1","unstructured":"Tianqi Chen Thierry Moreau Ziheng Jiang Lianmin Zheng Eddie Yan Haichen Shen Meghan Cowan Leyuan Wang Yuwei Hu Luis Ceze etal 2018. {TVM}: An automated end-to-end optimizing compiler for deep learning. In 13th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 18). 578--594.  Tianqi Chen Thierry Moreau Ziheng Jiang Lianmin Zheng Eddie Yan Haichen Shen Meghan Cowan Leyuan Wang Yuwei Hu Luis Ceze et al. 2018. {TVM}: An automated end-to-end optimizing compiler for deep learning. In 13th { USENIX } Symposium on Operating Systems Design and Implementation ( { OSDI } 18). 578--594."},{"volume-title":"cuDNN: Efficient Primitives for Deep Learning. arXiv arXiv:1410.0759","year":"2014","author":"Chetlur Sharan","key":"e_1_3_2_1_5_1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"volume-title":"Moonshine: Distilling with cheap convolutions. In Advances in Neural Information Processing Systems. 2888--2898.","year":"2018","author":"Crowley Elliot J","key":"e_1_3_2_1_7_1"},{"volume-title":"Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological cybernetics 36, 4","year":"1980","author":"Fukushima Kunihiko","key":"e_1_3_2_1_8_1"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00069"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3168824"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00291"},{"volume-title":"Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv preprint arXiv:1408.5093","year":"2014","author":"Jia Yangqing","key":"e_1_3_2_1_13_1"},{"key":"e_1_3_2_1_14_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.  Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105."},{"volume-title":"Not all ops are created equal! arXiv preprint arXiv:1801.04326","year":"2018","author":"Lai Liangzhen","key":"e_1_3_2_1_15_1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"volume-title":"XLA: TensorFlow, compiled. TensorFlow Dev Summit","year":"2017","author":"Leary Chris","key":"e_1_3_2_1_17_1"},{"key":"e_1_3_2_1_18_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017).  Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017)."},{"key":"e_1_3_2_1_19_1","unstructured":"K. Simonyan and A. Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556 (2014).  K. Simonyan and A. Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556 (2014)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2017.7863730"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980983.2908105"},{"volume-title":"Performance-Portable Autotuning of OpenCL Kernels for Convolutional Layers of Deep Neural Networks. In Workshop on Machine Learning in HPC Environments.","year":"2016","author":"Tsai Yaohung","key":"e_1_3_2_1_22_1"},{"volume-title":"Proceedings of the 35th International Conference on Machine Learning","year":"2017","author":"Tschannen Michael","key":"e_1_3_2_1_23_1"},{"volume-title":"Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions. arXiv preprint arXiv:1802.04730","year":"2018","author":"Vasilache Nicolas","key":"e_1_3_2_1_24_1"},{"volume-title":"Proceedings of the 35th International Conference on Machine Learning","year":"2018","author":"Zhang Jiyuan","key":"e_1_3_2_1_25_1"}],"event":{"name":"PPoPP '20: 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"],"location":"San Diego California","acronym":"PPoPP '20"},"container-title":["Proceedings of the 13th Annual Workshop on General Purpose Processing using Graphics Processing Unit"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3366428.3380771","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3366428.3380771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:32:53Z","timestamp":1750199573000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3366428.3380771"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,23]]},"references-count":25,"alternative-id":["10.1145\/3366428.3380771","10.1145\/3366428"],"URL":"https:\/\/doi.org\/10.1145\/3366428.3380771","relation":{},"subject":[],"published":{"date-parts":[[2020,2,23]]},"assertion":[{"value":"2020-02-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}