{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:23:28Z","timestamp":1783103008682,"version":"3.54.6"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032304902","type":"print"},{"value":"9783032304919","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:00:00Z","timestamp":1783123200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:00:00Z","timestamp":1783123200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-30491-9_23","type":"book-chapter","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:08:54Z","timestamp":1783102134000},"page":"357-374","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Characterizing Lossless GPU Data Compression Across AMD CDNA and\u00a0RDNA Architectures"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1080-7230","authenticated-orcid":false,"given":"Cristiano","family":"K\u00fcnas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6081-5904","authenticated-orcid":false,"given":"Gabriel","family":"Freytag","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3915-1135","authenticated-orcid":false,"given":"Jean Luca","family":"Bez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5499-8301","authenticated-orcid":false,"given":"Thiago","family":"Ara\u00fajo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9957-5861","authenticated-orcid":false,"given":"Philippe","family":"Navaux","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,4]]},"reference":[{"issue":"4","key":"23_CR1","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1190\/1.1444815","volume":"65","author":"T Alkhalifah","year":"2000","unstructured":"Alkhalifah, T.: An acoustic wave equation for anisotropic media. Geophysics 65(4), 1239\u20131250 (2000)","journal-title":"Geophysics"},{"key":"23_CR2","unstructured":"AMD: CDNA\u00a02 architecture white paper. Technical report, Advanced Micro Devices (2021). https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-business-docs\/white-papers\/amd-cdna2-white-paper.pdf"},{"key":"23_CR3","unstructured":"AMD: HIP: Heterogeneous-compute interface for portability (2025). https:\/\/github.com\/ROCm\/HIP. Accessed 19 Feb 2026"},{"key":"23_CR4","unstructured":"AMD ROCm: hipCOMP-core: HIP port of compression algorithms (2025). https:\/\/github.com\/ROCm\/hipCOMP-core. Accessed 20 Feb 2026"},{"key":"23_CR5","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-04519-1_1","volume-title":"Cloud Computing and Services Science","author":"D Balouek","year":"2013","unstructured":"Balouek, D., et al.: Adding virtualization capabilities to the Grid\u20195000 testbed. In: Ivanov, I.I., van Sinderen, M., Leymann, F., Shan, T. (eds.) CLOSER 2012. CCIS, vol. 367, pp. 3\u201320. Springer, Cham (2013). https:\/\/doi.org\/10.1007\/978-3-319-04519-1_1"},{"key":"23_CR6","doi-asserted-by":"publisher","unstructured":"Burtchell, B.A., Burtscher, M.: Characterizing the performance of parallel data-compression algorithms across compilers and GPUs. In: Proceedings of the SC \u201925 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 269\u2013278. ACM (2025). https:\/\/doi.org\/10.1145\/3731599.3767369","DOI":"10.1145\/3731599.3767369"},{"key":"23_CR7","doi-asserted-by":"publisher","unstructured":"Che, S., et al.: Rodinia: a benchmark suite for heterogeneous computing. In: IEEE International Symposium on Workload Characterization (IISWC), pp. 44\u201354 (2009). https:\/\/doi.org\/10.1109\/IISWC.2009.5306797","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"23_CR8","doi-asserted-by":"publisher","unstructured":"Chen, J., et al.: HPDR: High-performance portable scientific data reduction framework. In: 2025 IEEE IPDPS, pp. 1104\u20131116. IEEE (2025). https:\/\/doi.org\/10.1109\/IPDPS64566.2025.00101","DOI":"10.1109\/IPDPS64566.2025.00101"},{"key":"23_CR9","doi-asserted-by":"publisher","unstructured":"Chen, X., et al.: Fcbench: cross-domain benchmarking of lossless compression for floating-point data. Proc. VLDB Endowment 17(6), 1418\u20131431 (2024). https:\/\/doi.org\/10.14778\/3648160.3648180","DOI":"10.14778\/3648160.3648180"},{"key":"23_CR10","unstructured":"Collet, Y.: LZ4 - extremely fast compression (2025). https:\/\/lz4.github.io\/lz4\/. Accessed 20 Feb 2026"},{"key":"23_CR11","unstructured":"CSC \u2013 IT Center for Science: LUMI supercomputer (2025). https:\/\/www.lumi-supercomputer.eu\/. Accessed 25 Feb 2025"},{"key":"23_CR12","doi-asserted-by":"publisher","unstructured":"Danalis, A., et al.: The scalable heterogeneous computing (SHOC) benchmark suite. In: Workshop on General-Purpose Computation on Graphics Processing Units (GPGPU), pp. 63\u201374 (2010). https:\/\/doi.org\/10.1145\/1735688.1735702","DOI":"10.1145\/1735688.1735702"},{"key":"23_CR13","doi-asserted-by":"publisher","unstructured":"Di, S., Cappello, F.: Fast error-bounded lossy HPC data compression with SZ. In: IEEE IPDPS, pp. 730\u2013739 (2016). https:\/\/doi.org\/10.1109\/IPDPS.2016.11","DOI":"10.1109\/IPDPS.2016.11"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Fletcher, R.P., Du, X., Fowler, P.J.: Reverse time migration in tilted transversely isotropic (TTI) media. Geophysics 74(6), WCA179\u2013WCA187 (2009)","DOI":"10.1190\/1.3269902"},{"key":"23_CR15","unstructured":"Fomel, S., Sava, P., Vlad, I., Liu, Y., Bashkardin, V.: Madagascar: open-source software project for multidimensional data analysis and reproducible computational experiments (2013)"},{"key":"23_CR16","unstructured":"Google: Snappy: a fast compressor\/decompressor (2025). https:\/\/github.com\/google\/snappy. Accessed 20 Feb 2026"},{"key":"23_CR17","doi-asserted-by":"publisher","unstructured":"Huang, Y., Di, S., Li, G., Cappello, F.: cuSZp2: a GPU lossy compressor with extreme throughput and optimized compression ratio. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE (2024). https:\/\/doi.org\/10.1109\/SC41406.2024.00021","DOI":"10.1109\/SC41406.2024.00021"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Huang, Y., Di, S., Yu, X., Li, G., Cappello, F.: cuSZp: an ultra-fast GPU error-bounded lossy compression framework with optimized end-to-end performance. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201313 (2023)","DOI":"10.1145\/3581784.3607048"},{"key":"23_CR19","doi-asserted-by":"publisher","unstructured":"Knorr, F., Thoman, P., Fahringer, T.: 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, pp. 1\u201314. ACM (2021). https:\/\/doi.org\/10.1145\/3458817.3476224","DOI":"10.1145\/3458817.3476224"},{"issue":"5","key":"23_CR20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0177459","volume":"12","author":"GM Kurtzer","year":"2017","unstructured":"Kurtzer, G.M., Sochat, V., Bauer, M.W.: Singularity: scientific containers for mobility of compute. PLoS ONE 12(5), e0177459 (2017). https:\/\/doi.org\/10.1371\/journal.pone.0177459","journal-title":"PLoS ONE"},{"issue":"12","key":"23_CR21","doi-asserted-by":"publisher","first-page":"2674","DOI":"10.1109\/TVCG.2014.2346458","volume":"20","author":"P Lindstrom","year":"2014","unstructured":"Lindstrom, P.: Fixed-rate compressed floating-point arrays. IEEE TVCG 20(12), 2674\u20132683 (2014). https:\/\/doi.org\/10.1109\/TVCG.2014.2346458","journal-title":"IEEE TVCG"},{"issue":"7","key":"23_CR22","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.1002\/cpe.3125","volume":"26","author":"Q Liu","year":"2014","unstructured":"Liu, Q., et al.: Hello ADIOS: the challenges and lessons of developing leadership class I\/O frameworks. Concurrency Comput. Pract. Experience 26(7), 1453\u20131473 (2014). https:\/\/doi.org\/10.1002\/cpe.3125","journal-title":"Concurrency Comput. Pract. Experience"},{"key":"23_CR23","doi-asserted-by":"publisher","unstructured":"Nicolae, B., Moody, A., Gonsiorowski, E., Mohror, K., Cappello, F.: VeloC: towards high performance adaptive asynchronous checkpointing at large scale. In: IEEE IPDPS, pp. 911\u2013920 (2019). https:\/\/doi.org\/10.1109\/IPDPS.2019.00099","DOI":"10.1109\/IPDPS.2019.00099"},{"key":"23_CR24","unstructured":"NVIDIA: Cascaded compression \u2014 nvCOMP documentation (2024). https:\/\/docs.nvidia.com\/cuda\/nvcomp\/cascaded.html. Accessed 19 Mar 2025"},{"key":"23_CR25","unstructured":"NVIDIA Corporation: CUB: Cooperative primitives for CUDA C++ (2025). https:\/\/nvidia.github.io\/cccl\/cub\/. Accessed 22 Feb 2026"},{"key":"23_CR26","unstructured":"NVIDIA Corporation: nvcomp: High-speed data compression library for nvidia GPUs (2025). https:\/\/developer.nvidia.com\/nvcomp. Accessed 20 Feb 2026"},{"key":"23_CR27","doi-asserted-by":"publisher","unstructured":"Tian, J., et al.: cuSZ: an efficient GPU-based error-bounded lossy compression framework for scientific data. In: ACM PACT, pp. 3\u201315 (2020). https:\/\/doi.org\/10.1145\/3410463.3414624","DOI":"10.1145\/3410463.3414624"},{"key":"23_CR28","unstructured":"TOP500: TOP500 list \u2013 November 2025. https:\/\/top500.org\/lists\/top500\/2025\/11\/ (2025), 66th edn, published November, 2025. Accessed 20 Mar 2026"},{"key":"23_CR29","doi-asserted-by":"publisher","unstructured":"Zhang, B., et al.: FZ-GPU: a fast and high-ratio lossy compressor for scientific computing applications on GPUs. In: Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing, pp. 129\u2013142. ACM (2023). https:\/\/doi.org\/10.1145\/3588195.3592994","DOI":"10.1145\/3588195.3592994"},{"key":"23_CR30","doi-asserted-by":"publisher","unstructured":"Zhang, B., et al.: GPULZ: Optimizing LZSS lossless compression for multi-byte data on modern GPUs. In: Proceedings of the 37th ACM International Conference on Supercomputing, pp. 348\u2013359. ACM (2023). https:\/\/doi.org\/10.1145\/3577193.3593706","DOI":"10.1145\/3577193.3593706"}],"container-title":["Lecture Notes in Computer Science","Computational Science and Its Applications \u2013 ICCSA 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-30491-9_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:09:06Z","timestamp":1783102146000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-30491-9_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,4]]},"ISBN":["9783032304902","9783032304919"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-30491-9_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,4]]},"assertion":[{"value":"4 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCSA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science and Its Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Braga","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccsa2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccsa.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}