{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:10:28Z","timestamp":1774307428583,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2042155"],"award-info":[{"award-number":["2042155"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3754598.3754636","type":"proceedings-article","created":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:34:32Z","timestamp":1766219672000},"page":"288-298","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Fast and Scalable Mixed Precision Euclidean Distance Calculations Using GPU Tensor Cores"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7935-5538","authenticated-orcid":false,"given":"Brian","family":"Curless","sequence":"first","affiliation":[{"name":"Northern Arizona University, Flagstaff, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0826-6204","authenticated-orcid":false,"given":"Michael","family":"Gowanlock","sequence":"additional","affiliation":[{"name":"Northern Arizona University, Flagstaff, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,12,20]]},"reference":[{"key":"e_1_3_3_2_2_2","first-page":"353","volume-title":"2018 IEEE European Symp. on Security and Privacy","author":"Bos Joppe","year":"2018","unstructured":"Joppe Bos, L\u00e9o Ducas, Eike Kiltz, Tancr\u00e8de Lepoint, Vadim Lyubashevsky, John\u00a0M Schanck, Peter Schwabe, Gregor Seiler, and Damien Stehl\u00e9. 2018. CRYSTALS-Kyber: a CCA-secure module-lattice-based KEM. In 2018 IEEE European Symp. on Security and Privacy. 353\u2013367."},{"key":"e_1_3_3_2_3_2","first-page":"2578","volume-title":"Intl. Conf. on Machine Learning","author":"Bottesch Thomas","year":"2016","unstructured":"Thomas Bottesch, Thomas B\u00fchler, and Markus K\u00e4chele. 2016. Speeding up k-means by approximating Euclidean distances via block vectors. In Intl. Conf. on Machine Learning. PMLR, 2578\u20132586."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/3571885.3571888"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Cu Cui. 2024. Acceleration of tensor-product operations with tensor cores. ACM Transactions on Parallel Computing 11 4 (2024) 1\u201324.","DOI":"10.1145\/3695466"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3331057"},{"key":"e_1_3_3_2_7_2","first-page":"132","volume-title":"2024 IEEE 31st Intl. Conf. on High Performance Computing, Data, and Analytics","author":"Donnelly Brian","year":"2024","unstructured":"Brian Donnelly and Michael Gowanlock. 2024. Multi-Space Tree with Incremental Construction for GPU-Accelerated Range Queries. In 2024 IEEE 31st Intl. Conf. on High Performance Computing, Data, and Analytics. 132\u2013142."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"M. Fasi N.J. Higham M. Mikaitis and S. Pranesh. 2021. Numerical behavior of NVIDIA tensor cores. PeerJ Computer Science 7 (2021) e330.","DOI":"10.7717\/peerj-cs.330"},{"key":"e_1_3_3_2_9_2","first-page":"135","volume-title":"2022 IEEE 29th Intl. Conf. on High Performance Computing, Data, and Analytics","author":"Gallet Benoit","year":"2022","unstructured":"Benoit Gallet and Michael Gowanlock. 2022. Leveraging GPU Tensor Cores for Double Precision Euclidean Distance Calculations. In 2022 IEEE 29th Intl. Conf. on High Performance Computing, Data, and Analytics. 135\u2013144."},{"key":"e_1_3_3_2_10_2","first-page":"357","volume-title":"Intl. Conf. on Computational Science","author":"Gowanlock Michael","year":"2023","unstructured":"Michael Gowanlock, Benoit Gallet, and Brian Donnelly. 2023. Optimization and Comparison of Coordinate-and Metric-Based Indexes on GPUs for Distance Similarity Searches. In Intl. Conf. on Computational Science. Springer, 357\u2013364."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3329785.3329920"},{"key":"e_1_3_3_2_12_2","first-page":"436","volume-title":"IEEE 39th Intl. Conf. on Data Engineering","author":"Huang Qiang","year":"2023","unstructured":"Qiang Huang and Anthony\u00a0KH Tung. 2023. Lightweight-yet-efficient: Revitalizing ball-tree for point-to-hyperplane nearest neighbor search. In IEEE 39th Intl. Conf. on Data Engineering. 436\u2013449."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433824"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3473518"},{"key":"e_1_3_3_2_15_2","first-page":"1","volume-title":"2021 IEEE Intl. Conf. on Cluster Computing","author":"Li Binrui","year":"2021","unstructured":"Binrui Li, Shenggan Cheng, and James Lin. 2021. tcFFT: A Fast Half-Precision FFT Library for NVIDIA Tensor Cores. In 2021 IEEE Intl. Conf. on Cluster Computing. 1\u201311."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00012"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Jiwen Lu Venice\u00a0Erin Liong and Jie Zhou. 2017. Deep hashing for scalable image search. IEEE Transactions on Image Processing 26 5 (2017) 2352\u20132367.","DOI":"10.1109\/TIP.2017.2678163"},{"key":"e_1_3_3_2_18_2","unstructured":"Nvidia. 2025. Double Precision GEMM Using the WMMA API. https:\/\/github.com\/NVIDIA\/cuda-samples Accessed Apr. 1 2025."},{"key":"e_1_3_3_2_19_2","unstructured":"Nvidia. 2025. NVIDIA A100 Tensor Core GPU Architecture. https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf Accessed Apr. 1 2025."},{"key":"e_1_3_3_2_20_2","first-page":"8295","volume-title":"Intl. Conf. on Machine Learning","author":"Ryali Chaitanya","year":"2020","unstructured":"Chaitanya Ryali, John Hopfield, Leopold Grinberg, and Dmitry Krotov. 2020. Bio-inspired hashing for unsupervised similarity search. In Intl. Conf. on Machine Learning. PMLR, 8295\u20138306."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Hanan Samet. 2008. K-Nearest Neighbor Finding Using MaxNearestDist. IEEE Transactions on Pattern Analysis and Machine Intelligence 30 2 (2008) 243\u2013252.","DOI":"10.1109\/TPAMI.2007.1182"},{"key":"e_1_3_3_2_22_2","first-page":"514","volume-title":"European Symp. on Research in Computer Security","author":"Wan Lipeng","year":"2022","unstructured":"Lipeng Wan, Fangyu Zheng, Guang Fan, Rong Wei, Lili Gao, Yuewu Wang, Jingqiang Lin, and Jiankuo Dong. 2022. A novel high-performance implementation of CRYSTALS-Kyber with AI accelerator. In European Symp. on Research in Computer Security. Springer, 514\u2013534."},{"key":"e_1_3_3_2_23_2","unstructured":"Bei Xie Jiaohua Qin Xuyu Xiang Hao Li and Lili Pan. 2018. An Image Retrieval Algorithm Based on Gist and Sift Features. Intl. Journal of Network Security 20 4 (2018) 609\u2013616."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Liang Zheng Yi Yang and Qi Tian. 2017. SIFT meets CNN: A decade survey of instance retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence 40 5 (2017) 1224\u20131244.","DOI":"10.1109\/TPAMI.2017.2709749"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Arthur Zimek Erich Schubert and Hans-Peter Kriegel. 2012. A survey on unsupervised outlier detection in high-dimensional numerical data. Statistical Analysis and Data Mining: The ASA Data Science Journal 5 5 (2012) 363\u2013387.","DOI":"10.1002\/sam.11161"}],"event":{"name":"ICPP '25: 54th International Conference on Parallel Processing","location":"San Diego CA USA","acronym":"ICPP '25"},"container-title":["Proceedings of the 54th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3754598.3754636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:37:22Z","timestamp":1766219842000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3754598.3754636"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":24,"alternative-id":["10.1145\/3754598.3754636","10.1145\/3754598"],"URL":"https:\/\/doi.org\/10.1145\/3754598.3754636","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-12-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}