{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T00:52:29Z","timestamp":1781311949631,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"name":"Swedish Foundation for Strategic Research","award":["CHI19-0048"],"award-info":[{"award-number":["CHI19-0048"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,8]]},"DOI":"10.1145\/3721145.3725776","type":"proceedings-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:57:17Z","timestamp":1755867437000},"page":"1219-1233","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["MEMPLEX: A Memory System with Replication and Migration of Data for Multi-Chiplet NUMA Architectures"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6104-3739","authenticated-orcid":false,"given":"Neethu Bal","family":"Mallya","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Gothenburg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9878-4509","authenticated-orcid":false,"given":"Bhavishya","family":"Goel","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Gothenburg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0452-3664","authenticated-orcid":false,"given":"Ioannis","family":"Sourdis","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Gothenburg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Advanced Micro Devices Inc.2023. AMD CDNA\u2122 3 Architecture. Retrieved 7 Feb 2025 from https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-tech-docs\/white-papers\/amd-cdna-3-white-paper.pdf"},{"key":"e_1_3_3_2_3_2","unstructured":"Karl Bridge. 2022. NUMA Support - Win32 Apps. Retrieved 7 Feb 2025 from https:\/\/learn.microsoft.com\/en-us\/windows\/win32\/procthread\/numa-support"},{"key":"e_1_3_3_2_4_2","unstructured":"Adrian Chadd. 2018. FreeBSD Manual Pages. Retrieved 7 Feb 2025 from https:\/\/man.freebsd.org\/cgi\/man.cgi?query=numa&sektion=4&manpath=FreeBSD%2B14.0-RELEASE%2Band%2BPorts"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Jack Choquette Wishwesh Gandhi Olivier Giroux Nick Stam and Ronny Krashinsky. 2021. NVIDIA A100 Tensor Core GPU: Performance and Innovation. IEEE Micro 41 2 (Mar 2021) 29\u201335. 10.1109\/MM.2021.3061394","DOI":"10.1109\/MM.2021.3061394"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750387"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783738"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240768"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Fredrik Dahlgren and Josep Torrellas. 1999. Cache-Only Memory Architectures. Computer 32 6 (Jun 1999) 72\u201379. 10.1109\/2.769448","DOI":"10.1109\/2.769448"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/264107.264205"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530428"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/HICSS.1994.323136"},{"key":"e_1_3_3_2_13_2","unstructured":"Jiri Herrmann. 2019. Automatic NUMA Balancing Red Hat Enterprise Linux 7. Retrieved 7 Feb 2025 from https:\/\/access.redhat.com\/documentation\/en-us\/red_hat_enterprise_linux\/7\/html\/virtualization_tuning_and_optimization_guide\/sect-virtualization_tuning_optimization_guide-numa-auto_numa_balancing"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783739"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628089"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446068"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.51"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485957"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2013.6557149"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830808"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00012"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00050"},{"key":"e_1_3_3_2_23_2","unstructured":"Christoph Lameter and Minchan Kim. 2016. Page Migration. Retrieved 7 Feb 2025 from https:\/\/www.kernel.org\/doc\/Documentation\/vm\/page_migration"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/384286.264206"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750383"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Daniel Lenoski James Laudon Kourosh Gharachorloo W-D Weber Anoop Gupta John Hennessy Mark Horowitz and Monica\u00a0S. Lam. 1992. The Stanford Dash Multiprocessor. Computer 25 3 (Apr 1992) 63\u201379. 10.1109\/2.121510","DOI":"10.1109\/2.121510"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Shang Li Zhiyuan Yang Dhiraj Reddy Ankur Srivastava and Bruce Jacob. 2020. DRAMsim3: A Cycle-Accurate Thermal-Capable DRAM Simulator. IEEE Computer Architecture Letters (CAL) 19 2 (Jul 2020) 106\u2013109. 10.1109\/LCA.2020.2973991","DOI":"10.1109\/LCA.2020.2973991"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079089"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","unstructured":"Gabriel Loh and Mark\u00a0D. Hill. 2012. Supporting Very Large DRAM Caches with Compound-Access Scheduling and MissMap. IEEE Micro 32 3 (May 2012) 70\u201378. 10.1109\/MM.2012.25","DOI":"10.1109\/MM.2012.25"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155673"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/232973.233006"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10992969"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056027"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00014"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807626"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731107"},{"key":"e_1_3_3_2_37_2","unstructured":"NEC CORPORATION. 2018. SX-Aurora TSUBASA Architecture Guide Revision 1.1. Retrieved 7 Feb 2025 from https:\/\/sxauroratsubasa.sakura.ne.jp\/documents\/guide\/pdfs\/Aurora_ISA_guide.pdf"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00032"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2003.1238020"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2006.311859"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.39"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.30"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.20"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485963"},{"key":"e_1_3_3_2_45_2","unstructured":"Kanoj Sarcar. 1999. What is NUMA?Retrieved 7 Feb 2025 from https:\/\/www.kernel.org\/doc\/html\/v5.4\/vm\/numa.html"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.56"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1992.753306"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2017.8203849"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS61541.2024.00025"},{"key":"e_1_3_3_2_50_2","volume-title":"Proceedings of the International Conference on Physics of Reactors (PHYSOR 2014)","author":"Tramm John\u00a0R","year":"2014","unstructured":"John\u00a0R Tramm, Andrew\u00a0R Siegel, Tanzima Islam, and Martin Schulz. 2014. XSBench - The Development and Verification of a Performance Abstraction for Monte Carlo Reactor Analysis. In Proceedings of the International Conference on Physics of Reactors (PHYSOR 2014)."},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","unstructured":"Evangelos Vasilakis Vassilis Papaefstathiou Pedro Trancoso and Ioannis Sourdis. 2019. Decoupled Fused Cache: Fusing a Decoupled LLC with a DRAM Cache. ACM Transactions on Architecture and Code Optimization (TACO) 15 4 Article 65 (Jan 2019) 23\u00a0pages. 10.1145\/3293447","DOI":"10.1145\/3293447"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00101"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00059"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/237090.237205"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","unstructured":"Steven\u00a0J.E. Wilton and Norman\u00a0P. Jouppi. 1996. CACTI: An Enhanced Cache Access and Cycle Time Model. IEEE Journal of Solid-State Circuits (JSSC) 31 5 (1996) 677\u2013688. 10.1109\/4.509850","DOI":"10.1109\/4.509850"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.1997.569686"}],"event":{"name":"ICS '25: 2025 International Conference on Supercomputing","location":"Salt Lake City USA","acronym":"ICS '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 39th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721145.3725776","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:01:57Z","timestamp":1755867717000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721145.3725776"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,8]]},"references-count":55,"alternative-id":["10.1145\/3721145.3725776","10.1145\/3721145"],"URL":"https:\/\/doi.org\/10.1145\/3721145.3725776","relation":{},"subject":[],"published":{"date-parts":[[2025,6,8]]},"assertion":[{"value":"2025-08-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}