{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T14:25:20Z","timestamp":1780410320883,"version":"3.54.1"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T00:00:00Z","timestamp":1776297600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["101144014"],"award-info":[{"award-number":["101144014"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009133","name":"Karlsruhe Institute of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009133","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100024370","name":"Ministero dell'Istruzione dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100024370","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100031478","name":"NextGenerationEU","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100031478","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Future Generation Computer Systems"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.future.2026.108519","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T07:01:49Z","timestamp":1776322909000},"page":"108519","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["On the energy efficiency of sparse matrix computations on multi-GPU clusters"],"prefix":"10.1016","volume":"183","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3661-9836","authenticated-orcid":false,"given":"Massimo","family":"Bernaschi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8493-4550","authenticated-orcid":false,"given":"Alessandro","family":"Celestini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giorgio","family":"Richelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2047-4986","authenticated-orcid":false,"given":"Pasqua","family":"D\u2019Ambra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.future.2026.108519_b1","unstructured":"Electricity 2025. Analysis and forecast to 2027, https:\/\/www.iea.org\/reports\/electricity-2025."},{"key":"10.1016\/j.future.2026.108519_b2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fhpcp.2025.1520207","article-title":"Energy-aware operation of HPC systems in Germany","volume":"3","author":"Suarez","year":"2025","journal-title":"Front. High Perform. Comput."},{"key":"10.1016\/j.future.2026.108519_b3","series-title":"Green500","year":"2025"},{"issue":"3","key":"10.1016\/j.future.2026.108519_b4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2962131","article-title":"Understanding GPU power: A survey of profiling, modeling, and simulation methods","volume":"49","author":"Bridges","year":"2016","journal-title":"ACM Comput. Surv."},{"issue":"5","key":"10.1016\/j.future.2026.108519_b5","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1177\/1094342016672081","article-title":"On the performance and energy efficiency of sparse linear algebra on GPUs","volume":"31","author":"Anzt","year":"2017","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"10.1016\/j.future.2026.108519_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.jnca.2025.104326","article-title":"Next-generation AI for advanced threat detection and security enhancement in DNS over HTTPS","volume":"244","author":"Ali","year":"2025","journal-title":"J. Netw. Comput. Appl."},{"key":"10.1016\/j.future.2026.108519_b7","series-title":"Top500","year":"2025"},{"key":"10.1016\/j.future.2026.108519_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.micpro.2022.104679","article-title":"Towards EXtreme scale technologies and accelerators for euROhpc hw\/sw supercomputing applications for exascale: The TEXTAROSSA approach","volume":"95","author":"Agosta","year":"2022","journal-title":"Microprocess. Microsyst."},{"key":"10.1016\/j.future.2026.108519_b9","series-title":"2024 27th Euromicro Conference on Digital System Design","first-page":"526","article-title":"The TEXTAROSSA project: Cool all the way down to the hardware","author":"Filgueras","year":"2024"},{"key":"10.1016\/j.future.2026.108519_b10","doi-asserted-by":"crossref","first-page":"13533","DOI":"10.1007\/s11227-024-05989-y","article-title":"Alya toward exascale: algorithmic scalability using PSCToolkit","volume":"80","author":"Owen","year":"2024","journal-title":"J. Supercomput."},{"key":"10.1016\/j.future.2026.108519_b11","series-title":"Proceedings of the Platform for Advanced Scientific Computing Conference","article-title":"PETScML: Second-order solvers for training regression problems in scientific machine learning","author":"Zampini","year":"2024"},{"key":"10.1016\/j.future.2026.108519_b12","article-title":"Proactive and privacy-preserving defense for DNS over HTTPS via federated AI attestation (PAFA-doh)","volume":"196","author":"Ali","year":"2026","journal-title":"Neural Netw."},{"key":"10.1016\/j.future.2026.108519_b13","series-title":"2013 IEEE International Symposium on Workload Characterization","first-page":"56","article-title":"Quantifying the energy cost of data movement in scientific applications","author":"Kestor","year":"2013"},{"issue":"12","key":"10.1016\/j.future.2026.108519_b14","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1145\/3554977","article-title":"The evolution of mathematical software","volume":"65","author":"Dongarra","year":"2022","journal-title":"Commun. ACM"},{"key":"10.1016\/j.future.2026.108519_b15","series-title":"2024 IEEE 35th International Conference on Application-Specific Systems, Architectures and Processors","first-page":"143","article-title":"Analyzing GPU energy consumption in data movement and storage","author":"Delestrac","year":"2024"},{"issue":"3","key":"10.1016\/j.future.2026.108519_b16","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1177\/1094342021990738","article-title":"Selecting optimal SpMV realizations for GPUs via machine learning","volume":"35","author":"Dufrechou","year":"2021","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"4","key":"10.1016\/j.future.2026.108519_b17","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1007\/s00450-011-0195-8","article-title":"Optimization of power consumption in the iterative solution of sparse linear systems on graphics processors","volume":"27","author":"Anzt","year":"2012","journal-title":"Comput. Sci. Res. Dev."},{"key":"10.1016\/j.future.2026.108519_b18","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/j.future.2024.06.004","article-title":"Batched sparse and mixed-precision linear algebra interface for efficient use of GPU hardware accelerators in scientific applications","volume":"160","author":"Luszczek","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.future.2026.108519_b19","series-title":"2024 IEEE 36th International Symposium on Computer Architecture and High Performance Computing","first-page":"70","article-title":"A performance and energy study of GPU-resident preconditioners for conjugate gradient solvers: In the context of existing and novel approaches","author":"\u015awirydowicz","year":"2024"},{"issue":"4","key":"10.1016\/j.future.2026.108519_b20","doi-asserted-by":"crossref","DOI":"10.1145\/3190647","article-title":"BootCMatch: a software package for bootstrap AMG based on graph weighted matching","volume":"44","author":"D\u2019Ambra","year":"2018","journal-title":"ACM Trans. Math. Softw."},{"key":"10.1016\/j.future.2026.108519_b21","doi-asserted-by":"crossref","first-page":"102599","DOI":"10.1016\/j.parco.2019.102599","article-title":"AMG based on compatible weighted matching for GPUs","volume":"92","author":"Bernaschi","year":"2020","journal-title":"Parallel Comput."},{"key":"10.1016\/j.future.2026.108519_b22","doi-asserted-by":"crossref","first-page":"100041","DOI":"10.1016\/j.simpa.2020.100041","article-title":"BootCMatchG: an adaptive algebraic multigrid linear solver for GPUs","volume":"6","author":"Bernaschi","year":"2020","journal-title":"Software Impacts"},{"issue":"08","key":"10.1016\/j.future.2026.108519_b23","doi-asserted-by":"crossref","first-page":"2365","DOI":"10.1109\/TPDS.2023.3287238","article-title":"A multi-GPU aggregation-based AMG preconditioner for iterative linear solvers","volume":"34","author":"Bernaschi","year":"2023","journal-title":"IEEE Trans. Parallel & Distrib. Syst."},{"key":"10.1016\/j.future.2026.108519_b24","doi-asserted-by":"crossref","unstructured":"M. Bernaschi, M.G. Carrozzo, A. Celestini, G. Piperno, P. D\u2019Ambra, Communication-reduced Conjugate Gradient Variants for GPU-accelerated Clusters, in: 2025 33rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP), 2025, pp. 178\u2013186, http:\/\/dx.doi.org\/10.1109\/PDP66500.2025.00032.","DOI":"10.1109\/PDP66500.2025.00032"},{"key":"10.1016\/j.future.2026.108519_b25","doi-asserted-by":"crossref","first-page":"409","DOI":"10.6028\/jres.049.044","article-title":"Methods of conjugate gradients for solving linear systems","volume":"49","author":"Hestenes","year":"1952","journal-title":"J. Res. Natl. Bur. Stand."},{"key":"10.1016\/j.future.2026.108519_b26","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.jcp.2014.10.043","article-title":"A massively parallel solver for discrete Poisson-like problems","volume":"281","author":"Notay","year":"2015","journal-title":"J. Comput. Phys."},{"issue":"1","key":"10.1016\/j.future.2026.108519_b27","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/0167-8191(89)90062-8","article-title":"On the efficient implementation of preconditioned s-step conjugate gradient methods on multiprocessors with memory hierarchy","volume":"11","author":"Chronopoulos","year":"1989","journal-title":"Parallel Comput."},{"issue":"5","key":"10.1016\/j.future.2026.108519_b28","doi-asserted-by":"crossref","first-page":"S602","DOI":"10.1137\/140980260","article-title":"AmgX: A library for GPU accelerated algebraic multigrid and preconditioned iterative methods","volume":"37","author":"Naumov","year":"2015","journal-title":"SIAM J. Sci. Comput."},{"issue":"2","key":"10.1016\/j.future.2026.108519_b29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3177754","article-title":"RAPL in action: Experiences in using RAPL for power measurements","volume":"3","author":"Khan","year":"2018","journal-title":"ACM Trans. Model. Perform. Eval. Comput. Syst. (TOMPECS)"},{"key":"10.1016\/j.future.2026.108519_b30","series-title":"2010 39th International Conference on Parallel Processing Workshops","first-page":"207","article-title":"Likwid: A lightweight performance-oriented tool suite for x86 multicore environments","author":"Treibig","year":"2010"},{"key":"10.1016\/j.future.2026.108519_b31","series-title":"Likwid","year":"2025"},{"key":"10.1016\/j.future.2026.108519_b32","series-title":"NVIDIA management library: NVML API reference guide","year":"2025"},{"key":"10.1016\/j.future.2026.108519_b33","unstructured":"powerMonitor, https:\/\/github.com\/alecel\/powerMonitor."},{"key":"10.1016\/j.future.2026.108519_b34","unstructured":"GPowerU, https:\/\/github.com\/crrossi\/GPowerU."},{"issue":"4","key":"10.1016\/j.future.2026.108519_b35","doi-asserted-by":"crossref","first-page":"248","DOI":"10.3390\/info14040248","article-title":"Energy-efficient parallel computing: Challenges to scaling","volume":"14","author":"Lastovetsky","year":"2023","journal-title":"Information"},{"issue":"10","key":"10.1016\/j.future.2026.108519_b36","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1016\/j.parco.2014.09.001","article-title":"A survey of power and energy efficient techniques for high performance numerical linear algebra operations","volume":"40","author":"Tan","year":"2014","journal-title":"Parallel Comput."},{"key":"10.1016\/j.future.2026.108519_b37","unstructured":"Ginkgo, https:\/\/ginkgo-project.github.io."},{"issue":"1","key":"10.1016\/j.future.2026.108519_b38","doi-asserted-by":"crossref","first-page":"2:1","DOI":"10.1145\/3480935","article-title":"Ginkgo: A modern linear operator algebra framework for high performance computing","volume":"48","author":"Anzt","year":"2022","journal-title":"ACM Trans. Math. Software"},{"issue":"5","key":"10.1016\/j.future.2026.108519_b39","doi-asserted-by":"crossref","first-page":"S602","DOI":"10.1137\/140980260","article-title":"AmgX: A library for GPU accelerated algebraic multigrid and preconditioned iterative methods","volume":"37","author":"Naumov","year":"2015","journal-title":"SIAM J. Sci. Comput."},{"key":"10.1016\/j.future.2026.108519_b40","series-title":"NVIDIA, Algebraic multigrid solver (AmgX) library version 2.5.0","year":"2025"},{"issue":"1","key":"10.1016\/j.future.2026.108519_b41","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/1094342015593158","article-title":"High-performance Conjugate-Gradient benchmark: A new metric for ranking high-performance computing systems","volume":"30","author":"Dongarra","year":"2016","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"10.1016\/j.future.2026.108519_b42","series-title":"SuiteSparse Matrix Collection","year":"2026"}],"container-title":["Future Generation Computer Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X26001536?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X26001536?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T13:48:36Z","timestamp":1780408116000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167739X26001536"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":42,"alternative-id":["S0167739X26001536"],"URL":"https:\/\/doi.org\/10.1016\/j.future.2026.108519","relation":{},"ISSN":["0167-739X"],"issn-type":[{"value":"0167-739X","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"On the energy efficiency of sparse matrix computations on multi-GPU clusters","name":"articletitle","label":"Article Title"},{"value":"Future Generation Computer Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.future.2026.108519","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"108519"}}