{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T10:04:03Z","timestamp":1781258643123,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Research Foundation","award":["414984028"],"award-info":[{"award-number":["414984028"]}]},{"name":"European Union\u2019s Horizon 2020 research and innovation programme","award":["957407"],"award-info":[{"award-number":["957407"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,30]]},"DOI":"10.1145\/3723851.3723853","type":"proceedings-article","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T03:42:19Z","timestamp":1745379739000},"page":"8-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Towards Memory Disaggregation via NVLink C2C: Benchmarking CPU-Requested GPU Memory Access"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2727-5441","authenticated-orcid":false,"given":"Felix","family":"Werner","sequence":"first","affiliation":[{"name":"HPI, University of Potsdam, Potsdam, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8973-6403","authenticated-orcid":false,"given":"Marcel","family":"Weisgut","sequence":"additional","affiliation":[{"name":"HPI, University of Potsdam, Potsdam, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3335-8045","authenticated-orcid":false,"given":"Tilmann","family":"Rabl","sequence":"additional","affiliation":[{"name":"HPI, University of Potsdam, Potsdam, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,19]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","unstructured":"2018. Functionality and performance of NVLink with IBM POWER9 processors. IBM J. Res. Dev. 62 4\/5 (2018) 9:1\u20139:10. 10.1147\/JRD.2018.2846978","DOI":"10.1147\/JRD.2018.2846978"},{"key":"e_1_3_3_2_3_2","unstructured":"Inc. Advanced Micro\u00a0Devices. 2023. AMD CDNA 3 Architecture. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-tech-docs\/white-papers\/amd-cdna-3-white-paper.pdf Whitepaper."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Marcos\u00a0K. Aguilera Emmanuel Amaro Nadav Amit Erika Hunhoff Anil Yelam and Gerd Zellweger. 2023. Memory disaggregation: why now and what are the challenges. ACM SIGOPS Oper. Syst. Rev. 57 1 (2023) 38\u201346. 10.1145\/3606557.3606563","DOI":"10.1145\/3606557.3606563"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357526.3357574"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593856.3595889"},{"key":"e_1_3_3_2_7_2","series-title":"CEUR Workshop Proceedings","volume-title":"Joint Proceedings of Workshops at the 49th International Conference on Very Large Data Bases (VLDB 2023), Vancouver, Canada, August 28 - September 1, 2023","volume":"3462","author":"Benson Lawrence","year":"2023","unstructured":"Lawrence Benson, Richard Ebeling, and Tilmann Rabl. 2023. Evaluating SIMD Compiler-Intrinsics for Database Systems. In Joint Proceedings of Workshops at the 49th International Conference on Very Large Data Bases (VLDB 2023), Vancouver, Canada, August 28 - September 1, 2023(CEUR Workshop Proceedings, Vol.\u00a03462), Rajesh Bordawekar, Cinzia Cappiello, Vasilis Efthymiou, Lisa Ehrlinger, Vijay Gadepally, Sainyam Galhotra, Sandra Geisler, Sven Groppe, Le\u00a0Gruenwald, Alon\u00a0Y. Halevy, Hazar Harmouch, Oktie Hassanzadeh, Ihab\u00a0F. Ilyas, Ernesto Jim\u00e9nez-Ruiz, Sanjay Krishnan, Tirthankar Lahiri, Guoliang Li, Jiaheng Lu, Wolfgang Mauerer, Umar\u00a0Farooq Minhas, Felix Naumann, M.\u00a0Tamer \u00d6zsu, El\u00a0Kindi Rezig, Kavitha Srinivas, Michael Stonebraker, Satyanarayana\u00a0R. Valluri, Maria-Esther Vidal, Haixun Wang, Jiannan Wang, Yingjun Wu, Xun Xue, Mohamed Za\u00eft, and Kai Zeng (Eds.). CEUR-WS.org. https:\/\/ceur-ws.org\/Vol-3462\/ADMS5.pdf"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Lawrence Benson Leon Papke and Tilmann Rabl. 2022. PerMA-Bench: Benchmarking Persistent Memory Access. Proc. VLDB Endow. 15 11 (2022) 2463\u20132476. 10.14778\/3551793.3551807","DOI":"10.14778\/3551793.3551807"},{"key":"e_1_3_3_2_9_2","unstructured":"Abhishek Bhattacharjee. 2017. Appendix L: Advanced Concepts on Address Translation. (2017). In Computer architecture \u2014 A quantitative approach (6th ed.) John L. Hennessy and David A. Patterson (Eds.). Morgan Kaufmann Cambridge MA USA Appendix L 1\u201369.."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS59251.2023.10254718"},{"key":"e_1_3_3_2_11_2","unstructured":"CXL Consortium. [n. d.]. Compute Express Link specification Revision 3.0. CXL. https:\/\/www.computeexpresslink.org\/ Accessed: 2025-02-07."},{"key":"e_1_3_3_2_12_2","unstructured":"NVIDIA Corporation. 2016. NVIDIA Tesla P100 - The Most Advanced Datacenter Accelerator Ever Built. https:\/\/images.nvidia.com\/content\/pdf\/tesla\/whitepaper\/pascal-architecture-whitepaper.pdf Whitepaper V1.1."},{"key":"e_1_3_3_2_13_2","unstructured":"NVIDIA Corporation. 2017. NVIDIA TESLA V100 GPU ARCHITECTURE - THE WORLD\u2019S MOST ADVANCED DATA CENTER GPU. https:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper.pdf Whitepaper. V1.1."},{"key":"e_1_3_3_2_14_2","unstructured":"NVIDIA Corporation. 2020. NVIDIA A100 Tensor Core GPU Architecture - UNPRECEDENTED ACCELERATION AT EVERY SCALE. https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf Whitepaper. V1.0."},{"key":"e_1_3_3_2_15_2","unstructured":"NVIDIA Corporation. 2023. NVIDIA GH200 Grace Hopper Superchip Architecture - Performance and Productivity for Strong-Scaling HPC and Giant AI Workloads. https:\/\/resources.nvidia.com\/en-us-grace-cpu\/nvidia-grace-hopper Whitepaper. V1.12."},{"key":"e_1_3_3_2_16_2","unstructured":"NVIDIA Corporation. 2023. NVIDIA GH200 Grace Hopper Superchip Benchmark Step-by-Step Guide. https:\/\/docs.nvidia.com\/gh200-superchip-benchmark-guide.pdf"},{"key":"e_1_3_3_2_17_2","unstructured":"NVIDIA Corporation. 2023. NVIDIA Grace CPU Superchip Whitepaper - Performance and Efficiency for the Modern Data Center. https:\/\/resources.nvidia.com\/en-us-grace-cpu\/nvidia-grace-cpu-superchip Whitepaper. V1.0."},{"key":"e_1_3_3_2_18_2","unstructured":"NVIDIA Corporation. 2023. NVIDIA H100 Tensor Core GPU Architecture - EXCEPTIONAL PERFORMANCE SCALABILITY AND SECURITY FOR THE DATA CENTER. https:\/\/resources.nvidia.com\/en-us-tensor-core\/gtc22-whitepaper-hopper Whitepaper. V1.04.."},{"key":"e_1_3_3_2_19_2","unstructured":"NVIDIA Corporation. 2025. Grace Performance Tuning Guide. https:\/\/docs.nvidia.com\/grace-perf-tuning-guide\/index.html Accessed: 2025-03-30."},{"key":"e_1_3_3_2_20_2","unstructured":"Ulrich Drepper. 2007. What Every Programmer Should Know About Memory. (01 2007). https:\/\/people.freebsd.org\/\u00a0lstewart\/articles\/cpumemory.pdf"},{"key":"e_1_3_3_2_21_2","volume-title":"NVIDIA Opens NVLink for Custom Silicon Integration","author":"Edwards Cliff","year":"2022","unstructured":"Cliff Edwards. 2022. NVIDIA Opens NVLink for Custom Silicon Integration. https:\/\/nvidianews.nvidia.com\/news\/nvidia-opens-nvlink-for-custom-silicon-integration"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Mohammad Ewais and Paul Chow. 2023. Disaggregated Memory in the Datacenter: A Survey. IEEE Access 11 (2023) 20688\u201320712. 10.1109\/ACCESS.2023.3250407","DOI":"10.1109\/ACCESS.2023.3250407"},{"key":"e_1_3_3_2_23_2","unstructured":"Luigi Fusco Mikhail Khalilov Marcin Chrapek Giridhar Chukkapalli Thomas Schulthess and Torsten Hoefler. 2024. Understanding data movement in tightly coupled heterogeneous systems: A case study with the Grace Hopper superchip. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.11556 (2024)."},{"key":"e_1_3_3_2_24_2","unstructured":"Geizhals. 2025. NVIDIA A100 40 GB price as of 2025-02-06. https:\/\/geizhals.eu\/fujitsu-s26361-f3396-l4-a1774093.html Accessed: 2025-02-07."},{"key":"e_1_3_3_2_25_2","unstructured":"Geizhals. 2025. NVIDIA A100 80 GB price as of 2025-01-27. https:\/\/geizhals.eu\/fujitsu-s26361-f3935-l616-a1762880.html Accessed: 2025-02-07."},{"key":"e_1_3_3_2_26_2","unstructured":"Geizhals. 2025. Samsung DIMM 16GB DDR5-4800 price as of 2025-02-06. https:\/\/geizhals.de\/samsung-dimm-ddr5-v93906.html Accessed: 2025-02-07."},{"key":"e_1_3_3_2_27_2","unstructured":"John\u00a0L. Hennessy and David\u00a0A. Patterson. 2017. Appendix L: Advanced Concepts on Address Translation. (2017). In Computer architecture \u2014 A quantitative approach (6th ed.) John L. Hennessy and David A. Patterson (Eds.). Morgan Kaufmann Cambridge MA USA Appendix B B1\u2013B60.."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","unstructured":"Pieter Hijma Stijn Heldens Alessio Sclocco Ben van Werkhoven and Henri\u00a0E. Bal. 2023. Optimization Techniques for GPU Programming. ACM Comput. Surv. 55 11 (2023) 239:1\u2013239:81. 10.1145\/3570638","DOI":"10.1145\/3570638"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3662010.3663451"},{"key":"e_1_3_3_2_30_2","unstructured":"Chester Lam. 2024. Grace Hopper Nvidia\u2019s Halfway APU. https:\/\/chipsandcheese.com\/2024\/07\/31\/grace-hopper-nvidias-halfway-apu\/ Accessed: 2024-08-28."},{"key":"e_1_3_3_2_31_2","unstructured":"Arm Limited. 2022. AMBA 5 CHI Architecture Specification. https:\/\/developer.arm.com\/documentation\/ihi0050\/latest Version F."},{"key":"e_1_3_3_2_32_2","volume-title":"Arm Neoverse V2 Core Technical Reference Manual","author":"Limited Arm","year":"2022","unstructured":"Arm Limited. 2022. Arm Neoverse V2 Core Technical Reference Manual. https:\/\/developer.arm.com\/documentation\/102375\/0002\/"},{"key":"e_1_3_3_2_33_2","volume-title":"AMBA CHI Architecture Specification","author":"Limited Arm","year":"2024","unstructured":"Arm Limited. 2024. AMBA CHI Architecture Specification. https:\/\/developer.arm.com\/documentation\/ihi0050\/g\/ Version G."},{"key":"e_1_3_3_2_34_2","unstructured":"Arm Limited. 2024. Arm Neoverse V2 - PMU Guide. https:\/\/developer.arm.com\/documentation\/109709\/r0p2 Revision: r0p2."},{"key":"e_1_3_3_2_35_2","unstructured":"Clemens Lutz. 2022. Scalable data management using GPUs with fast interconnects. Ph.\u00a0D. Dissertation. Technical University of Berlin Germany. https:\/\/nbn-resolving.org\/urn:nbn:de:101:1-2022122101021675299107"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389705"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517911"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517842"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915251"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Ismail Oukid and Lucas Lersch. 2018. On the Diversity of Memory and Storage Technologies. Datenbank-Spektrum 18 2 (2018) 121\u2013127. 10.1007\/S13222-018-0287-8","DOI":"10.1007\/S13222-018-0287-8"},{"key":"e_1_3_3_2_41_2","unstructured":"Robert Sohigian. 21. NVSwitch Accelerates NVIDIA DGX-2. https:\/\/developer.nvidia.com\/blog\/nvswitch-accelerates-nvidia-dgx2\/ Accessed: 2025-02-03."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2010.24"}],"event":{"name":"HCDS '25: 4th Workshop on Heterogeneous Composable and Disaggregated Systems","location":"Rotterdam Netherlands","acronym":"HCDS '25"},"container-title":["Proceedings of the 4th Workshop on Heterogeneous Composable and Disaggregated Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3723851.3723853","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3723851.3723853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:19:00Z","timestamp":1750295940000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3723851.3723853"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,30]]},"references-count":41,"alternative-id":["10.1145\/3723851.3723853","10.1145\/3723851"],"URL":"https:\/\/doi.org\/10.1145\/3723851.3723853","relation":{},"subject":[],"published":{"date-parts":[[2025,3,30]]},"assertion":[{"value":"2025-04-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}