{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:42:30Z","timestamp":1768030950973,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Department of Energy","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2003709,2104023,2303064,2247080,2312673"],"award-info":[{"award-number":["2003709,2104023,2303064,2247080,2312673"]}],"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":[[2023,8,7]]},"DOI":"10.1145\/3588195.3592994","type":"proceedings-article","created":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T20:47:00Z","timestamp":1691441220000},"page":"129-142","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["FZ-GPU: A Fast and High-Ratio Lossy Compressor for Scientific Computing Applications on GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8937-4067","authenticated-orcid":false,"given":"Boyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Indiana University, Bloomington, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1101-9148","authenticated-orcid":false,"given":"Jiannan","family":"Tian","sequence":"additional","affiliation":[{"name":"Indiana University, Bloomington, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9935-5674","authenticated-orcid":false,"given":"Sheng","family":"Di","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6244-1264","authenticated-orcid":false,"given":"Xiaodong","family":"Yu","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6577-227X","authenticated-orcid":false,"given":"Yunhe","family":"Feng","sequence":"additional","affiliation":[{"name":"University of North Texas, Denton, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0630-1600","authenticated-orcid":false,"given":"Xin","family":"Liang","sequence":"additional","affiliation":[{"name":"University of Kentucky, Lexington, KY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5422-4497","authenticated-orcid":false,"given":"Dingwen","family":"Tao","sequence":"additional","affiliation":[{"name":"Indiana University, Bloomington, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7890-3934","authenticated-orcid":false,"given":"Franck","family":"Cappello","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,8,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3015569"},{"key":"e_1_3_2_1_2_1","volume-title":"Online","author":"Vishwanath S. C. V.","year":"2019","unstructured":"S. C. V. Vishwanath and K. Harms, Parallel i\/o on mira, https:\/\/www.alcf.anl.gov\/files\/Parallel_IO_on_Mira_0.pdf, Online, 2019."},{"key":"e_1_3_2_1_3_1","first-page":"438","volume-title":"IEEE","author":"Liang X.","year":"2018","unstructured":"X. Liang, S. Di, D. Tao, S. Li, S. Li, H. Guo, Z. Chen, and F. Cappello, \"Error-controlled lossy compression optimized for high compression ratios of scientific datasets,\" in 2018 IEEE International Conference on Big Data, IEEE, 2018, pp. 438--447."},{"key":"e_1_3_2_1_4_1","first-page":"179","volume-title":"An efficient transformation scheme for lossy data compression with point-wise relative error bound,\" in IEEE International Conference on Cluster Computing","author":"Liang X.","year":"2018","unstructured":"X. Liang, S. Di, D. Tao, Z. Chen, and F. Cappello, \"An efficient transformation scheme for lossy data compression with point-wise relative error bound,\" in IEEE International Conference on Cluster Computing, Belfast, UK: IEEE, 2018, pp. 179--189."},{"key":"e_1_3_2_1_5_1","volume-title":"Networking, Storage and Analysis","author":"Meister D.","year":"2012","unstructured":"D. Meister, J. Kaiser, A. Brinkmann, T. Cortes, M. Kuhn, and J. Kunkel, \"A study on data deduplication in HPC storage systems,\" in SC '12: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, Salt Lake City, UT, USA: IEEE, 2012, p. 7."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.14529\/jsfi140205"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342019853336"},{"key":"e_1_3_2_1_8_1","first-page":"730","volume-title":"Fast error-bounded lossy HPC data compression with SZ,\" in 2016 IEEE International Parallel and Distributed Processing Symposium","author":"Di S.","year":"2016","unstructured":"S. Di and F. Cappello, \"Fast error-bounded lossy HPC data compression with SZ,\" in 2016 IEEE International Parallel and Distributed Processing Symposium, Chicago, IL, USA: IEEE, 2016, pp. 730--739."},{"key":"e_1_3_2_1_9_1","first-page":"1129","article-title":"Significantly improving lossy compression for scientific data sets based on multidimensional prediction and error-controlled quantization,\" in 2017 IEEE International Parallel and Distributed Processing Symposium, Orlando, FL","author":"Tao D.","year":"2017","unstructured":"D. Tao, S. Di, Z. Chen, and F. Cappello, \"Significantly improving lossy compression for scientific data sets based on multidimensional prediction and error-controlled quantization,\" in 2017 IEEE International Parallel and Distributed Processing Symposium, Orlando, FL, USA: IEEE, 2017, pp. 1129--1139.","journal-title":"USA: IEEE"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2014.2346458"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3201176"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2006.143"},{"key":"e_1_3_2_1_13_1","unstructured":"https:\/\/lcls.slac.stanford.edu\/lasers\/lcls-ii Online."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414624"},{"key":"e_1_3_2_1_15_1","volume-title":"Online","year":"2019","unstructured":"cuZFP, https:\/\/github.com\/LLNL\/zfp\/tree\/develop\/src\/cuda_zfp, Online, 2019."},{"key":"e_1_3_2_1_16_1","first-page":"859","volume-title":"IEEE","author":"Chen J.","year":"2021","unstructured":"J. Chen, L. Wan, X. Liang, B. Whitney, Q. Liu, D. Pugmire, N. Thompson, J. Y. Choi, M. Wolf, T. Munson, I. Foster, and S. Klasky, \"Accelerating multigrid-based hierarchical scientific data refactoring on gpus,\" in 2021 IEEE International Parallel and Distributed Processing Symposium, IEEE, 2021, pp. 859--868."},{"key":"e_1_3_2_1_17_1","unstructured":"Compression Modes https:\/\/zfp.readthedocs.io\/en\/release0.5.4\/modes.html."},{"key":"e_1_3_2_1_18_1","first-page":"105","volume-title":"IEEE","author":"Jin S.","year":"2020","unstructured":"S. Jin, P. Grosset, C. M. Biwer, J. Pulido, J. Tian, D. Tao, and J. Ahrens, \"Understanding GPU-based lossy compression for extreme-scale cosmological simulations,\" in 2020 IEEE International Parallel and Distributed Processing Symposium, IEEE, 2020, pp. 105--115."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.17487\/RFC1951"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1952.273898"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1977.1055714"},{"key":"e_1_3_2_1_22_1","volume-title":"Filter for improving compression of typed binary data,\" Astrophysics Source Code Library, ascl--1712","author":"Masui K.","year":"2017","unstructured":"K. Masui, \"Bitshuffle: Filter for improving compression of typed binary data,\" Astrophysics Source Code Library, ascl--1712, 2017."},{"key":"e_1_3_2_1_23_1","first-page":"2716","volume-title":"IEEE","author":"Zhao K.","year":"2020","unstructured":"K. Zhao, S. Di, X. Lian, S. Li, D. Tao, J. Bessac, Z. Chen, and F. Cappello, \"Sdrbench: Scientific data reduction benchmark for lossy compressors,\" in 2020 IEEE International Conference on Big Data, IEEE, 2020, pp. 2716--2724."},{"issue":"1","key":"e_1_3_2_1_24_1","first-page":"1992","article-title":"The JPEG still picture compression standard","volume":"38","author":"Wallace G. K.","unstructured":"G. K. Wallace, \"The JPEG still picture compression standard,\" IEEE Transactions on Consumer Electronics, vol. 38, no. 1, pp. xviii--xxxiv, 1992.","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103090"},{"key":"e_1_3_2_1_26_1","volume-title":"A multilevel technique for compression of floating-point data,\" in DRBSD-2 Workshop at Supercomputing","author":"Ainsworth M","year":"2017","unstructured":"M Ainsworth, O Tugluk, B Whitney, and S Klasky, \"Mgard: A multilevel technique for compression of floating-point data,\" in DRBSD-2 Workshop at Supercomputing, 2017."},{"key":"e_1_3_2_1_27_1","volume-title":"Tthresh: Tensor compression for multidimensional visual data,\" IEEE transactions on visualization and computer graphics","author":"Ballester-Ripoll R.","unstructured":"R. Ballester-Ripoll, P. Lindstrom, and R. Pajarola, \"Tthresh: Tensor compression for multidimensional visual data,\" IEEE transactions on visualization and computer graphics, vol. 26, no. 9, pp. 2891--2903, 2019."},{"key":"e_1_3_2_1_28_1","volume-title":"CUDA by example: an introduction to general-purpose GPU programming","author":"Sanders J.","year":"2010","unstructured":"J. Sanders and E. Kandrot, CUDA by example: an introduction to general-purpose GPU programming. Addison-Wesley Professional, 2010."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8659.00681"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.17487\/rfc1952"},{"key":"e_1_3_2_1_31_1","volume-title":"Online","author":"Zstd","year":"2019","unstructured":"Zstd, https:\/\/github.com\/facebook\/zstd\/releases, Online, 2019."},{"key":"e_1_3_2_1_32_1","first-page":"283","volume-title":"IEEE","author":"Tian J.","year":"2021","unstructured":"J. Tian, S. Di, X. Yu, C. Rivera, K. Zhao, S. Jin, Y. Feng, X. Liang, D. Tao, and F. Cappello, \"Optimizing error-bounded lossy compression for scientific data on gpus,\" in 2021 IEEE International Conference on Cluster Computing, IEEE, 2021, pp. 283--293."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/3503585.3503597"},{"key":"e_1_3_2_1_34_1","first-page":"444","volume-title":"IEEE","author":"Zhou Q","year":"2021","unstructured":"Q Zhou, C Chu, N. Kumar, P. Kousha, S. M. Ghazimirsaeed, H. Subramoni, and D. K. Panda, \"Designing high-performance mpi libraries with on-the-fly compression for modern gpu clusters,\" in 2021 IEEE International Parallel and Distributed Processing Symposium, IEEE, 2021, pp. 444--453."},{"key":"e_1_3_2_1_35_1","first-page":"319","volume-title":"Increasing efficiency of data transfer between main memory and intel xeon phi coprocessor or nvidia gpus with data compression,\" in International Conference on Parallel Computing Technologies","author":"Besedin K. Y.","year":"2015","unstructured":"K. Y. Besedin, P. S. Kostenetskiy, and S. O. Prikazchikov, \"Increasing efficiency of data transfer between main memory and intel xeon phi coprocessor or nvidia gpus with data compression,\" in International Conference on Parallel Computing Technologies, Springer, 2015, pp. 319--323."},{"key":"e_1_3_2_1_36_1","volume-title":"Online","author":"Wright Jon","year":"2022","unstructured":"Jon Wright, Bslz4 decoding, https:\/\/github.com\/jonwright\/bslz4decoders, Online, 2022."},{"key":"e_1_3_2_1_37_1","unstructured":"Nvcomp https:\/\/github.com\/NVIDIA\/nvcomp."},{"key":"e_1_3_2_1_38_1","volume-title":"Oct.","author":"Harris M","year":"2017","unstructured":"M Harris and K Perelygin, Cooperative groups: Flexible cuda thread programming, https:\/\/developer.nvidia.com\/blog\/cooperative-groups\/, Oct. 2017."},{"key":"e_1_3_2_1_39_1","unstructured":"Nvidia\/cub: Cooperative primitives for cuda c. https:\/\/github.com\/NVIDIA\/cub."},{"key":"e_1_3_2_1_40_1","volume-title":"Online","author":"System Community Earth","year":"2019","unstructured":"Community Earth System Model (CESM) Atmosphere Model, http:\/\/www.cesm.ucar.edu\/models\/, Online, 2019."},{"key":"e_1_3_2_1_41_1","volume-title":"Online","author":"Simulation Data Hurricane ISABEL","year":"2019","unstructured":"Hurricane ISABEL Simulation Data, http:\/\/vis.computer.org\/vis2004contest\/data.html, Online, 2019."},{"key":"e_1_3_2_1_42_1","unstructured":"NYX simulation https:\/\/amrex-astro.github.io\/Nyx\/ Online."},{"key":"e_1_3_2_1_43_1","volume-title":"Online","author":"QMCPACK","year":"2019","unstructured":"QMCPACK: many-body ab initio Quantum Monte Carlo code, http:\/\/vis.computer.org\/vis2004contest\/data.html, Online, 2019."},{"key":"e_1_3_2_1_44_1","first-page":"2494","volume-title":"IEEE","author":"Jin S.","year":"2022","unstructured":"S. Jin, S. Di, J. Tian, S. Byna, D. Tao, and F. Cappello, \"Improving prediction-based lossy compression dramatically via ratio-quality modeling,\" in 2022 IEEE 38th International Conference on Data Engineering (ICDE), IEEE, 2022, pp. 2494--2507."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2938503"},{"key":"e_1_3_2_1_46_1","first-page":"348","volume-title":"IEEE","author":"Lu T.","year":"2018","unstructured":"T. Lu, Q. Liu, X. He, H. Luo, E. Suchyta, J. Choi, N. Podhorszki, S. Klasky, M. Wolf, T. Liu, et al., \"Understanding and modeling lossy compression schemes on hpc scientific data,\" in 2018 IEEE International Parallel and Distributed Processing Symposium, IEEE, 2018, pp. 348--357."},{"key":"e_1_3_2_1_47_1","first-page":"881","volume-title":"IEEE","author":"Tian J.","year":"2021","unstructured":"J. Tian, C. Rivera, S. Di, J. Chen, X. Liang, D. Tao, and F. Cappello, \"Revisiting huffman coding: Toward extreme performance on modern gpu architectures,\" in 2021 IEEE International Parallel and Distributed Processing Symposium, IEEE, 2021, pp. 881--891."},{"key":"e_1_3_2_1_48_1","first-page":"717","volume-title":"IEEE","author":"Rivera C.","year":"2022","unstructured":"C. Rivera, S. Di, J. Tian, X. Yu, D. Tao, and F. Cappello, \"Optimizing huffman decoding for error-bounded lossy compression on gpus,\" in 2022 IEEE International Parallel and Distributed Processing Symposium, IEEE, 2022, pp. 717--727."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2021.3066151"},{"key":"e_1_3_2_1_50_1","first-page":"567","volume-title":"IEEE","author":"Underwood R.","year":"2020","unstructured":"R. Underwood, S. Di, J. C. Calhoun, and F. Cappello, \"Fraz: A generic high-fidelity fixed-ratio lossy compression framework for scientific floating-point data,\" in 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS), IEEE, 2020, pp. 567--577."},{"key":"e_1_3_2_1_51_1","first-page":"1","volume-title":"IEEE","author":"Barrow M.","year":"2022","unstructured":"M. Barrow, Z. Wu, S. Lloyd, M. Gokhale, H. Patel, and P. Lindstrom, \"Zhw: A numerical codec for big data scientific computation,\" in 2022 International Conference on Field-Programmable Technology (ICFPT), IEEE, 2022, pp. 1--9."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3154096"},{"key":"e_1_3_2_1_53_1","first-page":"892","volume-title":"IEEE Computer Society","author":"Liu J.","year":"2022","unstructured":"J. Liu, S. Di, K. Zhao, X. Liang, Z. Chen, and F. Cappello, \"Dynamic quality metric oriented error bounded lossy compression for scientific datasets,\" in 2022 SC22: International Conference for High Performance Computing, Networking, Storage and Analysis (SC), IEEE Computer Society, 2022, pp. 892--906."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2859932"},{"key":"e_1_3_2_1_55_1","first-page":"171","article-title":"Ultrafast error-bounded lossy compression for scientific datasets,\" in Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing, ser. HPDC '22","volume":"159","author":"Yu X.","year":"2022","unstructured":"X. Yu, S. Di, K. Zhao, J. Tian, D. Tao, X. Liang, and F. Cappello, \"Ultrafast error-bounded lossy compression for scientific datasets,\" in Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing, ser. HPDC '22, Association for Computing Machinery, 2022, 159--171.","journal-title":"Association for Computing Machinery"},{"key":"e_1_3_2_1_56_1","volume-title":"https:\/\/github.com\/NVIDIA\/nvcomp","author":"Nvcomp","year":"2022","unstructured":"Nvcomp, https:\/\/github.com\/NVIDIA\/nvcomp, 2022."},{"key":"e_1_3_2_1_57_1","volume-title":"Understanding ssim,\" arXiv preprint arXiv:2006.13846","author":"Nilsson J.","year":"2020","unstructured":"J. Nilsson and T. Akenine-M\u00f6ller, \"Understanding ssim,\" arXiv preprint arXiv:2006.13846, 2020."},{"key":"e_1_3_2_1_58_1","unstructured":"Sz parallel mode with openmp https:\/\/github.com\/szcompressor\/SZ\/blob\/master\/sz\/src\/sz_omp.c."},{"key":"e_1_3_2_1_59_1","unstructured":"Benchmark of measuring bandwidth of multiple gpu https:\/\/github.com\/enfiskutensykkel\/multi-gpu-bwtest."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10035-z"},{"key":"e_1_3_2_1_61_1","first-page":"1","volume-title":"Storage and Analysis","author":"Knorr F.","year":"2021","unstructured":"F. Knorr, P. Thoman, and T. Fahringer, \"Ndzip-gpu: Efficient lossless compression of scientific floating-point data on gpus,\" in Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2021, pp. 1--14."},{"key":"e_1_3_2_1_62_1","unstructured":"Hipify https:\/\/github.com\/ROCm-Developer-Tools\/HIPIFY."},{"key":"e_1_3_2_1_63_1","unstructured":"Syclomatic https:\/\/github.com\/oneapi-src\/SYCLomatic."}],"event":{"name":"HPDC '23: The 32nd International Symposium on High-Performance Parallel and Distributed Computing","location":"Orlando FL USA","acronym":"HPDC '23","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588195.3592994","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3588195.3592994","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3588195.3592994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:25Z","timestamp":1750178845000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588195.3592994"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":63,"alternative-id":["10.1145\/3588195.3592994","10.1145\/3588195"],"URL":"https:\/\/doi.org\/10.1145\/3588195.3592994","relation":{},"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"2023-08-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}