{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T21:03:10Z","timestamp":1767646990753,"version":"3.48.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s44443-025-00347-1","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T17:39:29Z","timestamp":1763141969000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Design of a data prefetcher using hierarchical memory sharing prediction for multi-die architectures"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5507-3269","authenticated-orcid":false,"given":"Jianghua","family":"Gui","sequence":"first","affiliation":[]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[]},{"given":"Anzhou","family":"Lai","sequence":"additional","affiliation":[]},{"given":"Wenzhuo","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"347_CR1","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/2.546611","volume":"29","author":"S Adve","year":"1996","unstructured":"Adve S, Gharachorloo K (1996) Shared memory consistency models: a tutorial. Computer 29:66\u201376","journal-title":"Computer"},{"key":"347_CR2","doi-asserted-by":"crossref","unstructured":"Bakhshalipour M, Shakerinava M, Lotfi-Kamran P, Sarbazi-Azad H (2019) Bingo spatial data prefetcher. In: International symposium on high performance computer architecture, pp 399\u2013411. Washington, DC, USA","DOI":"10.1109\/HPCA.2019.00053"},{"key":"347_CR3","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MM.2024.3375070","volume":"44","author":"R Bhargava","year":"2024","unstructured":"Bhargava R, Troester K (2024) AMD next-generation Zen 4 Core and 4th Gen AMD EPYC server CPUs. IEEE Micro 44:8\u201317","journal-title":"IEEE Micro"},{"key":"347_CR4","doi-asserted-by":"crossref","unstructured":"Byna S, Chen Y, Sun X (2008) A taxonomy of data prefetching mechanisms. In: International symposium on parallel architectures, algorithms, and networks, pp 19\u201324. Sydney, NSW, Australia","DOI":"10.1109\/I-SPAN.2008.24"},{"key":"347_CR5","doi-asserted-by":"crossref","unstructured":"Chan K, Lam K, Wang C (2015) Cache affinity optimization techniques for scaling software transactional memory systems on multi-CMP architectures. In: 14th International symposium on parallel and distributed computing, pp 56\u201365. Limassol, Cyprus","DOI":"10.1109\/ISPDC.2015.14"},{"key":"347_CR6","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1145\/143371.143486","volume":"27","author":"T Chen","year":"1992","unstructured":"Chen T, Baer J (1992) Reducing memory latency via non-blocking and prefetching caches. ACM SIGPLAN Notices 27:51\u201361","journal-title":"ACM SIGPLAN Notices"},{"key":"347_CR7","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1109\/12.381947","volume":"44","author":"T Chen","year":"1995","unstructured":"Chen T, Baer J (1995) Effective hardware-based data prefetching for high-performance processors. IEEE Trans Comput 44:609\u2013623","journal-title":"IEEE Trans Comput"},{"key":"347_CR8","doi-asserted-by":"crossref","unstructured":"Cheng L, Carter J, Dai D (2007) An adaptive cache coherence protocol optimized for producer-consumer sharing. In: 13th International symposium on high performance computer architecture, pp 328\u2013339. Scottsdale, AZ, USA","DOI":"10.1109\/HPCA.2007.346210"},{"key":"347_CR9","volume-title":"Parallel computer architecture: a hardware\/software approach","author":"D Culler","year":"1998","unstructured":"Culler D, Singh J, Gupta A (1998) Parallel computer architecture: a hardware\/software approach. Morgan Kaufmann, San Francisco, California, USA"},{"key":"347_CR10","doi-asserted-by":"crossref","unstructured":"Dagum L, Menon R (1998) OpenMP: an industry standard API for shared-memory programming. IEEE Comput Sci Eng 5:46\u201355","DOI":"10.1109\/99.660313"},{"key":"347_CR11","doi-asserted-by":"crossref","unstructured":"Demetriades S, Cho S (2012) Predicting coherence communication by tracking synchronization points at run time. In: 45th Annual IEEE\/ACM international symposium on microarchitecture, pp 351\u2013362. Vancouver, Canada","DOI":"10.1109\/MICRO.2012.40"},{"key":"347_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3006385","volume":"49","author":"M Diener","year":"2016","unstructured":"Diener M, Cruz E, Alves M, Navaux P, Koren I (2016) Affinity-based thread and data mapping in shared memory systems. ACM Comput Surv 49:1\u201338","journal-title":"ACM Comput Surv"},{"key":"347_CR13","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1145\/144965.145006","volume":"23","author":"J Fu","year":"1992","unstructured":"Fu J, Patel J, Janssens B (1992) Stride directed prefetching in scalar processors. ACM SIGMICRO Newsl 23:102\u2013110","journal-title":"ACM SIGMICRO Newsl"},{"key":"347_CR14","doi-asserted-by":"crossref","unstructured":"Gomes W, Morgan S, Phelps B, Wilson T, Hallnor E (2022) Meteor Lake and Arrow Lake Intel Next-Gen 3D client architecture platform with Foveros. In: IEEE Hot chips 34 symposium, pp 1\u201340. Cupertino, CA, USA","DOI":"10.1109\/HCS55958.2022.9895532"},{"key":"347_CR15","doi-asserted-by":"publisher","first-page":"20250219","DOI":"10.1587\/elex.22.20250219","volume":"22","author":"J Gui","year":"2025","unstructured":"Gui J, Li B, Guo T, Lai A, Zhang S (2025) Design of hierarchical cache coherence protocol based on chiplet architecture. IEICE Electronics Express 22:20250219","journal-title":"IEICE Electronics Express"},{"key":"347_CR16","unstructured":"Hoffmann H, Agarwal A, Devadas S (2009) Partitioning strategies for concurrent programming. https:\/\/dspace.mit.edu\/bitstream\/handle\/1721.1\/59845\/Devadas_Partitioning%20strategies.pdf?sequence=1&isAllowed=y"},{"key":"347_CR17","doi-asserted-by":"crossref","unstructured":"Hu Z, Martonosi M, Kaxiras S (2003) TCP: tag correlating prefetchers. In: 9th International symposium on high-performance computer architecture, pp 317\u2013326. Anaheim, CA, USA","DOI":"10.1109\/HPCA.2003.1183549"},{"key":"347_CR18","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/40.755465","volume":"19","author":"R Kessler","year":"1999","unstructured":"Kessler R (1999) The Alpha 21264 microprocessor. IEEE Micro 19:24\u201336","journal-title":"IEEE Micro"},{"key":"347_CR19","doi-asserted-by":"crossref","unstructured":"Lai A, Falsafi B (1999) Memory sharing predictor: the key to a speculative coherent DSM. In: 26th International symposium on computer architecture, pp 172\u2013183. Atlanta, USA","DOI":"10.1145\/307338.300994"},{"key":"347_CR20","doi-asserted-by":"crossref","unstructured":"Lai A, Falsafi B (2000) Selective, accurate, and timely self-invalidation using Last-Touch Prediction. In: 27th International symposium on computer architecture, pp 139\u2013148. Vancouver, Canada","DOI":"10.1145\/339647.339669"},{"key":"347_CR21","doi-asserted-by":"crossref","unstructured":"Lai A, Fide C, Falsafi B (2001) Dead-Block prediction & Dead-Block correlating prefetchers. In: 28th International symposium on computer architecture, pp 144\u2013154. Gothenburg, Sweden","DOI":"10.1145\/379240.379259"},{"key":"347_CR22","doi-asserted-by":"crossref","unstructured":"Lebeck A, Wood D (1995) Dynamic self-invalidation: reducing coherence overhead in shared-memory multiprocessors. In: 22nd International symposium on computer architecture, pp 48\u201359. Santa Margherita Ligure, Italy","DOI":"10.1145\/223982.223995"},{"key":"347_CR23","doi-asserted-by":"crossref","unstructured":"Michaud P (2016) Best-offset hardware prefetching. In: 22th International symposium on high performance computer architecture, pp 469\u2013480. Barcelona, Spain","DOI":"10.1109\/HPCA.2016.7446087"},{"key":"347_CR24","doi-asserted-by":"crossref","unstructured":"Mukherjee S, Hill M (1998) Using prediction to accelerate coherence protocols. In: 25th Annual international symposium on computer architecture, pp 179\u2013190. Barcelona, Spain","DOI":"10.1109\/ISCA.1998.694773"},{"key":"347_CR25","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/MDAT.2023.3302809","volume":"41","author":"R Munoz","year":"2024","unstructured":"Munoz R (2024) Furthering Moore\u2019s law integration benefits in the chiplet era. IEEE Design Test 41:81\u201390","journal-title":"IEEE Design Test"},{"key":"347_CR26","doi-asserted-by":"crossref","unstructured":"Naffziger S, Beck N, Burd T, Lepak K, Loh G, Subramony M, White S (2021) Pioneering chiplet technology and design for the AMD EPYC and Ryzen processor families: industrial product. In: 48th Annual international symposium on computer architecture, pp 57\u201370. Valencia, Spain","DOI":"10.1109\/ISCA52012.2021.00014"},{"key":"347_CR27","volume-title":"An introduction to parallel programming","author":"P Pacheco","year":"2021","unstructured":"Pacheco P, Malensek M (2021) An introduction to parallel programming. Morgan Kaufmann, San Francisco, California, USA"},{"key":"347_CR28","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10766-025-00796-1","volume":"53","author":"D Pasqualin","year":"2025","unstructured":"Pasqualin D, Diener M, Du Bois AR, Pilla ML (2025) Thread and data mapping in software transactional memory: an overview. Int J Parallel Prog 53:19","journal-title":"Int J Parallel Prog"},{"key":"347_CR29","doi-asserted-by":"crossref","unstructured":"Przybylski S (1990) The performance impact of block sizes and fetch strategies. In: 17th International symposium on computer architecture, pp 160\u2013169. Seattle, WA, USA","DOI":"10.1109\/ISCA.1990.134521"},{"key":"347_CR30","doi-asserted-by":"crossref","unstructured":"Shakerinava M, Golshan F, Ansari A, Lotfi-Kamran P, Sarbazi-Azad H (2022) Evaluation of data prefetchers. Adv Comput 125:69\u201389","DOI":"10.1016\/bs.adcom.2021.11.008"},{"key":"347_CR31","doi-asserted-by":"crossref","unstructured":"Shuaibu M, Musa U, Siddique K, Zhang J, Wang J, Hughes D, Man K (2023) A survey on hardware prefetching in shared-memory multiprocessors. In: IEEE East-West design & test symposium, pp 1\u20138. Batumi, Georgia","DOI":"10.1109\/EWDTS59469.2023.10297025"},{"key":"347_CR32","doi-asserted-by":"crossref","unstructured":"Somogyi S, Wenisch T, Ailamaki A, Falsafi B, Moshovos A (2006) Spatial memory streaming. In: 33rd International symposium on computer architectur, pp 252\u201326. Boston, MA, US","DOI":"10.1109\/ISCA.2006.38"},{"key":"347_CR33","doi-asserted-by":"crossref","unstructured":"Somogyi S, Wenisch T, Hardavellas N, Kim J, Ailamaki A, Falsafi B (2004) Memory coherence activity prediction in commercial workloads. In: 3rd Workshop on memory performance issues: in conjunction with the 31st international symposium on computer architecture, pp 37\u201345. Munich, Germany","DOI":"10.1145\/1054943.1054949"},{"key":"347_CR34","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MM.2024.3450841","volume":"45","author":"W Tang","year":"2025","unstructured":"Tang W, Liu C, Zhang Z (2025) Energy-efficient parallel interconnects for chiplet integration. IEEE Micro 45:41\u201347","journal-title":"IEEE Micro"},{"key":"347_CR35","doi-asserted-by":"publisher","first-page":"1463","DOI":"10.1016\/j.procs.2015.05.336","volume":"51","author":"M Torrents","year":"2015","unstructured":"Torrents M, Martinez R, Molina C (2015) Prefetching challenges in distributed memories for CMPs. Procedia Comput Sci 51:1463\u20131472","journal-title":"Procedia Comput Sci"},{"key":"347_CR36","doi-asserted-by":"crossref","unstructured":"Wenisch T, Somogyi S, Hardavellas N, Kim J, Gniady C, Ailamaki A, Falsafi B (2005) Store-ordered streaming of shared memory. In: 14th International conference on parallel architectures and compilation techniques, pp 75\u201384. St. Louis, USA","DOI":"10.1109\/PACT.2005.37"},{"key":"347_CR37","doi-asserted-by":"crossref","unstructured":"Xia J, Luo L, Pang Z, Zhang J, Chang J (2014) A low overhead Last-Write-Touch prediction scheme. In: IEEE 12th International conference on dependable, autonomic and secure computing, pp 179\u2013183. Dalian, China","DOI":"10.1109\/DASC.2014.40"},{"key":"347_CR38","doi-asserted-by":"publisher","first-page":"21328","DOI":"10.1109\/JIOT.2025.3546874","volume":"12","author":"Z Xing","year":"2025","unstructured":"Xing Z, Ma G, Wang L, Yang L, Guo X, Chen S (2025) Toward visual interaction: hand segmentation by combining 3-d graph deep learning and laser point cloud for intelligent rehabilitation. IEEE Internet Things J 12:21328\u201321338","journal-title":"IEEE Internet Things J"},{"key":"347_CR39","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1145\/146628.139709","volume":"20","author":"T Yeh","year":"1992","unstructured":"Yeh T, Patt Y (1992) Alternative implementations of two-level adaptive branch prediction. ACM SIGARCH Comput Archit News 20:124\u2013134","journal-title":"ACM SIGARCH Comput Archit News"},{"key":"347_CR40","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MM.2020.3045564","volume":"41","author":"F Zaruba","year":"2021","unstructured":"Zaruba F, Schuiki F, Benini L (2021) Manticore: A 4096-core RISC-V chiplet architecture for ultraefficient floating-point computing. IEEE Micro 41:36\u201342","journal-title":"IEEE Micro"},{"key":"347_CR41","doi-asserted-by":"crossref","unstructured":"Zhang W, Zhou Y, Lai A, Yang L, Shao J (2024) ADP: an adaptive downgrade predictor for hybrid multi-die architecture. In: International conference on electronic information engineering & computer communication, pp 1418\u20131423. Wuhan, China","DOI":"10.1109\/EIECC64539.2024.10929263"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-025-00347-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-025-00347-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-025-00347-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:47:38Z","timestamp":1767638858000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-025-00347-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":41,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["347"],"URL":"https:\/\/doi.org\/10.1007\/s44443-025-00347-1","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"type":"print","value":"1319-1578"},{"type":"electronic","value":"2213-1248"}],"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"2 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare they have no financial interests pertaining to this publication.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Financial Interests"}}],"article-number":"314"}}