{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T17:58:57Z","timestamp":1781719137679,"version":"3.54.5"},"reference-count":83,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>As high performance computing (HPC) moves towards exascale, storage systems face core challenges such as data flooding, bandwidth bottlenecks, mixed load coordination, and performance cost balancing. This article systematically reviews the cutting-edge technologies of high performance storage systems, covering four aspects: storage architecture, hardware, software, and networking. At the architecture level, storage computing separation, distributed and hierarchical architectures decouple computing and storage resources, and optimize latency and scalability through high-speed networks. Typical cases include supercomputer systems such as Frontier and Fugaku. In terms of hardware, persistent memory, all flash array, and integrated storage and computing chips significantly improve throughput and reduce latency, while ZNS SSD and QLC technology optimize cost and lifespan. At the software level, distributed parallel file systems respond to massive small files and high concurrency access through burst buffering technology. In network communication, low latency protocols such as Slingshot, InfiniBand, and RoCE support TB level bandwidth, while CXL technology promotes storage resource pooling. In the future, photon interconnection, AI native architecture, and green energy-saving technologies will further promote the development of high performance storage towards efficiency and intelligence, to support ZB level storage requirements in scenarios such as Exascale computing and AI training.<\/jats:p>","DOI":"10.1007\/s42514-025-00268-5","type":"journal-article","created":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T09:00:13Z","timestamp":1765962013000},"page":"254-274","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Survey of storage systems in high performance computing"],"prefix":"10.1007","volume":"8","author":[{"given":"Gen","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenlong","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhe","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinhai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,17]]},"reference":[{"issue":"1","key":"268_CR1","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1145\/3606557.3606562","volume":"57","author":"H Al Maruf","year":"2023","unstructured":"Al Maruf, H., Chowdhury, M.: Memory disaggregation: advances and open challenges. ACM SIGOPS Oper. Syst. Rev. 57(1), 28\u201335 (2023)","journal-title":"ACM SIGOPS Oper. Syst. Rev."},{"key":"268_CR2","unstructured":"Argonne Leadership Computing Facility.: Aurora Supercomputer[EB\/OL]. [2025\u201302\u201315]. (2024) https:\/\/www.alcf.anl.gov\/aurora"},{"key":"268_CR3","unstructured":"Arpaci-Dusseau, R.H., Arpaci-Dusseau, A.C.: The Andrew File System (AFS)[EB\/OL]. University of Wisconsin-Madison, [2025\u201302\u201315]. (2023) https:\/\/pages.cs.wisc.edu\/~remzi\/OSTEP\/dist-afs.pdf"},{"key":"268_CR4","first-page":"1","volume-title":"Benchmarking HPC clusters with CFD codes[C]. In: Proc of the Platform for Advanced Scientific Computing Conference","author":"F Banchelli","year":"2020","unstructured":"Banchelli, F., Garcia-Gasulla, M., Houzeaux, G., et al.: Benchmarking HPC clusters with CFD codes[C]. In: Proc of the Platform for Advanced Scientific Computing Conference, pp. 1\u201311. ACM, US (2020)"},{"key":"268_CR5","doi-asserted-by":"crossref","unstructured":"Bergman, S., Mutlu, O., Yong, W., et al.: Composable storage servers: a storage paradigm for disaggregated systems[C]. In: 2024 International Conference on Networking, Architecture and Storage (NAS). IEEE, pp. 1\u20134 (2024)","DOI":"10.1109\/NAS63802.2024.10781363"},{"key":"268_CR6","first-page":"102","volume-title":"Benefits of IME-FUSE for I\/O-intensive HPC applications[C]. In: High Performance Computing","author":"E Betke","year":"2018","unstructured":"Betke, E., Kunkel, J.: Benefits of IME-FUSE for I\/O-intensive HPC applications[C]. In: High Performance Computing, pp. 102\u2013115. Springer, Cham (2018)"},{"issue":"5","key":"268_CR7","first-page":"1","volume":"54","author":"Z Bing","year":"2024","unstructured":"Bing, Z., Qian, Z., Fei, H., et al.: Design of high-speed large-capacity storage system based on NVMe-oF[J]. Aeronaut. Comput. Tech. 54(5), 1\u20135 (2024). (in Chinese)","journal-title":"Aeronaut. Comput. Tech."},{"key":"268_CR8","unstructured":"Broadcom.: NVMe-oF Performance White Paper: Stingray-Based Storage Appliance [EB\/OL]. [2025-02-19]. (2019) https:\/\/docs.broadcom.com\/doc\/broadcom-stingray-100G-NVMe-oF-performance"},{"key":"268_CR10","unstructured":"Ceph Official Website[EB\/OL]. [2025\u201302\u201315]. (2025) https:\/\/ceph.io\/en\/"},{"key":"268_CR11","volume-title":"Technical specification for capacity and performance testing of storage devices: T\/CSMT DZ006-2024[S]","author":"China Metrology Society","year":"2025","unstructured":"China Metrology Society: Technical specification for capacity and performance testing of storage devices: T\/CSMT DZ006-2024[S]. China Metrology Society, Beijing (2025). (in Chinese)"},{"key":"268_CR12","doi-asserted-by":"crossref","unstructured":"Chowdhury, F., Zhu, Y., Heer, T., et al.: I\/o characterization and performance evaluation of beegfs for deep learning[C]. In: Proceedings of the 48th International Conference on Parallel Processing, pp. 1\u201310 (2019)","DOI":"10.1145\/3337821.3337902"},{"key":"268_CR13","volume-title":"Information technology - General specification for disk arrays: GB\/T 35297\u20132017[S]","author":"CNS Committee","year":"2017","unstructured":"Committee, C.N.S.: Information technology - General specification for disk arrays: GB\/T 35297\u20132017[S]. China Standards Press, Beijing (2017). (in Chinese)"},{"key":"268_CR15","unstructured":"DAOS Community.: DAOS: Distributed Asynchronous Object Storage[EB\/OL]. [2025\u201302\u201315]. (2024) https:\/\/daos.io\/"},{"key":"268_CR16","unstructured":"ExtremeTech.: HP terminates \u201cThe Machine\u201d project[EB\/OL]. [2025\u201302\u201315]. (2024) https:\/\/www.extremetech.com\/extreme\/207897-hp-kills-the-machine-repurposes-design-around-conventional-technologies"},{"issue":"2","key":"268_CR17","first-page":"1","volume":"56","author":"D Fujiki","year":"2023","unstructured":"Fujiki, D., Xiaowei, W., Subramaniyan, A., et al.: In-\/near-memory computing: a survey[J]. ACM Comput. Surv. 56(2), 1\u201335 (2023)","journal-title":"ACM Comput. Surv."},{"key":"268_CR18","unstructured":"Fungible FS1600 Pushes Hyperscale Storage to the Data Center [EB\/OL]. [2025-02-19]. (2025) https:\/\/www.storagereview.com\/review\/fungible-fs1600-pushes-hyperscale-storage-to-the-data-center"},{"issue":"7\u20138","key":"268_CR19","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1080\/10618562.2020.1778168","volume":"34","author":"M Garcia-Gasulla","year":"2020","unstructured":"Garcia-Gasulla, M., Houzeaux, G., Eguzkitza, B., et al.: Performance analysis of CFD methods on HPC systems[J]. Int. J. Comput. Fluid Dyn. 34(7\u20138), 508\u2013528 (2020)","journal-title":"Int. J. Comput. Fluid Dyn."},{"key":"268_CR20","unstructured":"GekkoFS Team.: GekkoFS documentation[EB\/OL]. [2025\u201302\u201315]. (2024) https:\/\/storage.bsc.es\/projects\/gekkofs\/documentation\/"},{"issue":"1","key":"268_CR21","first-page":"1","volume":"8","author":"A Gharakhani","year":"2015","unstructured":"Gharakhani, A., Zohoor, H.: Applications of computational fluid dynamics in engineering fields. J. Appl. Fluid Mech. 8(1), 1\u201310 (2015)","journal-title":"J. Appl. Fluid Mech."},{"key":"268_CR22","doi-asserted-by":"crossref","unstructured":"Bang, F.: Gptcache: an open-source semantic cache for llm applications enabling faster answers and cost savings[C]. In: Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023), pp. 212\u2013218 (2023)","DOI":"10.18653\/v1\/2023.nlposs-1.24"},{"key":"268_CR23","doi-asserted-by":"crossref","unstructured":"Guo, C., Wu, H., Deng, Z., et al.: RDMA over converged Ethernet at scale[C]. In: Proc of ACM SIGCOMM 2016. New York: ACM, pp. 26-38. (2016)","DOI":"10.1145\/2934872.2934908"},{"key":"268_CR24","doi-asserted-by":"publisher","DOI":"10.1201\/EBK1439811924","volume-title":"Introduction to high performance computing for scientists and engineers[M]","author":"G Hager","year":"2010","unstructured":"Hager, G., Wellein, G.: Introduction to high performance computing for scientists and engineers[M]. CRC Press, Boca Raton (2010)"},{"key":"268_CR27","unstructured":"HPE.: About HPE DataWarp[EB\/OL]. [2025\u201302\u201315]. (2024) https:\/\/www.hpe.com\/psnow\/resources\/ebooks\/a00113970en_us_v2\/About_DataWarp.html"},{"key":"268_CR28","unstructured":"HPE. Slingshot interconnect for exascale era[EB\/OL]. [2025\u201302\u201319]. (2024) https:\/\/www.hpe.com\/psnow\/doc\/a50002368chp"},{"key":"268_CR29","unstructured":"Huawei.: OceanStor Dorado all-flash storage[EB\/OL]. [2025-02-19]. (2025) https:\/\/e.huawei.com\/cn\/topic\/storage\/all-flash-storage\/new-generation-dorado"},{"key":"268_CR30","unstructured":"Hynix, S.K.: SK Hynix demonstrates industry\u2019s first ZNS SSD solution[EB\/OL]. [2025\u201302\u201315]. (2019) https:\/\/news.skhynix.com.cn\/sk-hynix-demonstrates-industrys-first-zns-based-ssd-solution-for-data-centers"},{"key":"268_CR31","unstructured":"IBM.: IBM Storage Scale System[EB\/OL]. [2025\u201302\u201315]. (2024) https:\/\/www.ibm.com\/cn-zh\/products\/storage-scale-system"},{"key":"268_CR32","unstructured":"IBM. General Parallel File System 4.1.0.4[EB\/OL]. [2025\u201302\u201315]. (2025) https:\/\/www.ibm.com\/docs\/en\/gpfs\/4.1.0.4"},{"key":"268_CR33","unstructured":"Intel.: Intel\u00ae Silicon Photonics Technology[EB\/OL]. [2025\u201302\u201315]. (2024a) https:\/\/www.intel.cn\/content\/www\/cn\/zh\/products\/details\/network-io\/silicon-photonics.html (in Chinese)"},{"key":"268_CR34","unstructured":"Intel.: Intel\u00ae Optane\u2122 Memory[EB\/OL]. [2025\u201302\u201315]. (2024b) https:\/\/www.intel.cn\/content\/www\/cn\/zh\/products\/details\/memory-storage\/optane-memory.html (in Chinese)"},{"key":"268_CR35","unstructured":"It\u2019s time to talk about HPC storage: Perspectives on the past and future[EB\/OL]. IEEE Xplore, [2025\u201302\u201314]. (2021) https:\/\/ieeexplore.ieee.org\/document\/9658238"},{"key":"268_CR36","doi-asserted-by":"crossref","unstructured":"Jeong J, Jung C.: PMEM-spec: persistent memory speculation (strict persistency can trump relaxed persistency) [C]. In: Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems. 517\u2013529 (2021)","DOI":"10.1145\/3445814.3446698"},{"key":"268_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.114806","volume":"265","author":"C Jin","year":"2020","unstructured":"Jin, C., Patki, T., Thiagarajan, J.J., et al.: Power consumption models of servers in data centers[J]. Appl. Energy 265, 114806 (2020)","journal-title":"Appl. Energy"},{"key":"268_CR38","first-page":"179","volume-title":"Immersed boundary methods[M]\/\/Computational Fluid Dynamics","author":"T Kajishima","year":"2017","unstructured":"Kajishima, T., Taira, K.: Immersed boundary methods[M]\/\/Computational Fluid Dynamics, pp. 179\u2013205. Springer, Cham (2017)"},{"key":"268_CR39","unstructured":"Kalia ,A., Kaminsky, M., Andersen, D.: Design guidelines for high-performance RDMA systems[C]. In: Proc of the 12th USENIX Conference on File and Storage Technologies. Santa Clara: USENIX Association (2016)"},{"issue":"1","key":"268_CR40","first-page":"16","volume":"54","author":"W Kang","year":"2024","unstructured":"Kang, W., Kou, J., Zhao, W.: Development status and challenges of compute-in-memory chips. Chin. J. Comput. 54(1), 16\u201324 (2024). (in Chinese)","journal-title":"Chin. J. Comput."},{"issue":"1","key":"268_CR41","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1007\/s11390-023-2907-5","volume":"38","author":"KS Khorassani","year":"2023","unstructured":"Khorassani, K.S., Chen, C.C., Ramesh, B., et al.: High performance mpi over the slingshot interconnect. J. Comput. Sci. Technol. 38(1), 128\u2013145 (2023)","journal-title":"J. Comput. Sci. Technol."},{"key":"268_CR42","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.jpdc.2020.10.007","volume":"148","author":"D Koo","year":"2021","unstructured":"Koo, D., Lee, J., Liu, J., et al.: An empirical study of I\/O separation for burst buffers in HPC systems. J. Parallel Distrib. Comput. 148, 96\u2013108 (2021)","journal-title":"J. Parallel Distrib. Comput."},{"key":"268_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2022.101884","volume":"65","author":"M Kurz","year":"2022","unstructured":"Kurz, M., Offenh\u00e4user, P., Viola, D., et al.: Deep reinforcement learning for CFD on HPC systems[J]. J. Comput. Sci. 65, 101884 (2022)","journal-title":"J. Comput. Sci."},{"issue":"14","key":"268_CR44","doi-asserted-by":"publisher","first-page":"6552","DOI":"10.3390\/app11146552","volume":"11","author":"C Lange","year":"2021","unstructured":"Lange, C., Barthelm\u00e4s, P., Rosnitschek, T., et al.: Impact of HPC and automated CFD on virtual product development[J]. Appl. Sci. 11(14), 6552 (2021)","journal-title":"Appl. Sci."},{"issue":"9","key":"268_CR45","first-page":"1175","volume":"46","author":"X Liao","year":"2016","unstructured":"Liao, X., Xiao, N.: New high performance computing systems and technologies. Chin. J. Comput. 46(9), 1175\u20131210 (2016). (in Chinese)","journal-title":"Chin. J. Comput."},{"issue":"5","key":"268_CR46","first-page":"550","volume":"27","author":"Z Licheng","year":"2016","unstructured":"Licheng, Z., Wenhai, S., Huadong, X., et al.: Application of high performance computing in meteorological field[J]. J. Appl. Meteorol. 27(5), 550\u2013558 (2016). (in Chinese)","journal-title":"J. Appl. Meteorol."},{"key":"268_CR47","unstructured":"LLNL.: Parallel File Systems | HPC @ LLNL[EB\/OL]. [2025-02-15]. (2024) https:\/\/hpc.llnl.gov\/hardware\/file-systems\/parallel-file-systems#Lustre"},{"key":"268_CR48","doi-asserted-by":"publisher","DOI":"10.2172\/1632124","volume-title":"Storage 2020: a vision for future HPC storage[R]","author":"GK Lockwood","year":"2017","unstructured":"Lockwood, G.K., Hazen, D.A., et al.: Storage 2020: a vision for future HPC storage[R]. Lawrence Berkeley National Laboratory, Berkeley (2017)"},{"key":"268_CR49","unstructured":"Lu, W.: I\/O patterns and optimization strategies for deep learning workloads[C]. In: China Lustre User Summit. China: China LUG, (2021)"},{"key":"268_CR50","unstructured":"Lukken C, Trivedi A.: Past, present and future of computational storage: a survey[J]. arXiv preprint arXiv:2112.09691 (2021)"},{"key":"268_CR51","unstructured":"LUMI Consortium.: LUMI Supercomputer[EB\/OL]. [2025-02-15]. (2024) https:\/\/www.lumi-supercomputer.eu\/"},{"key":"268_CR52","unstructured":"Lustre File System[EB\/OL]. [2025\u201302\u201315]. (2024) https:\/\/www.lustre.org\/"},{"key":"268_CR53","unstructured":"Lv, W., Lu, Y., Zhang, Y., et al.: InfiniFS: Efficient metadata service for distributed filesystems[C]. In: Proc of the 20th USENIX Conference on File and Storage Technologies. Santa Clara: USENIX Association (2022)"},{"issue":"2","key":"268_CR55","first-page":"353","volume":"3","author":"K Mizzi","year":"2015","unstructured":"Mizzi, K., Kellett, P., Demirel, Y.K., et al.: HPC and CFD in marine industry: past, present and future[J]. J. Mar. Sci. Eng. 3(2), 353\u2013376 (2015)","journal-title":"J. Mar. Sci. Eng."},{"key":"268_CR56","unstructured":"National Supercomputing Center in Tianjin. Hardware Service Resources[EB\/OL]. [2025-02-15]. (2010) https:\/\/www.nscc-tj.cn\/cjjs_zy_th1 (in Chinese)"},{"key":"268_CR57","unstructured":"NVIDIA.: Accelerated Scientific Innovation with InfiniBand [EB\/OL]. [2025-02-15]. (2024a) https:\/\/www.nvidia.com\/en-us\/networking\/products\/infiniband\/"},{"key":"268_CR58","unstructured":"NVIDIA.: NVIDIA Magnum IO GPUDirect Storage Overview[EB\/OL]. [2025-02-15]. (2024b) https:\/\/docs.nvidia.com\/gpudirect-storage\/overview-guide\/index.html"},{"key":"268_CR59","unstructured":"NVIDIA.: DGX systems for enterprise AI[EB\/OL]. [2025-02-19]. (2025a) https:\/\/www.nvidia.cn\/data-center\/dgx-systems\/"},{"key":"268_CR60","unstructured":"NVIDIA.: GPUDirect Storage[EB\/OL]. [2025\u201302\u201319]. (2025b) https:\/\/docs.nvidia.com\/gpudirect-storage\/"},{"key":"268_CR61","unstructured":"OLCF.: Orion Visualization System[EB\/OL]. [2025-02-15]. (2022) https:\/\/www.olcf.ornl.gov\/olcf-resources\/data-visualization-resources\/orion\/"},{"key":"268_CR62","unstructured":"OLCF.: Frontier Supercomputer[EB\/OL]. [2025-02-15]. (2024) https:\/\/www.olcf.ornl.gov\/frontier\/"},{"key":"268_CR63","unstructured":"ORNL.: Oak Ridge \u2018Jaguar\u2019 Supercomputer[EB\/OL]. [2025-02-15]. (2009) https:\/\/www.ornl.gov\/news\/oak-ridge-jaguar-supercomputer-worlds-fastest"},{"key":"268_CR64","doi-asserted-by":"crossref","unstructured":"Pan, X., Li, E., Li, Q., et al.: InstAttention: in-storage attention offloading for cost-effective long-context LLM inference[C]. In: 2025 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, pp. 1510\u20131525 (2025)","DOI":"10.1109\/HPCA61900.2025.00113"},{"key":"268_CR65","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511840531","volume-title":"Turbulent flows[M]","author":"SB Pope","year":"2000","unstructured":"Pope, S.B.: Turbulent flows[M]. Cambridge University Press, Cambridge (2000)"},{"key":"268_CR66","doi-asserted-by":"crossref","unstructured":"Qian, Y., Li, X., Ihara, S., et al.: LPCC: hierarchical persistent client caching for lustre[C]. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201314 (2019)","DOI":"10.1145\/3295500.3356139"},{"issue":"9","key":"268_CR67","first-page":"1303","volume":"50","author":"D Qian","year":"2020","unstructured":"Qian, D., Wang, R.: Challenges of exascale computing. Chin. J. Comput. 50(9), 1303\u20131326 (2020). (in Chinese)","journal-title":"Chin. J. Comput."},{"issue":"7","key":"268_CR68","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/2699414","volume":"58","author":"DA Reed","year":"2015","unstructured":"Reed, D.A., Dongarra, J.: Exascale computing and big data. Commun. ACM 58(7), 56\u201368 (2015)","journal-title":"Commun. ACM"},{"key":"268_CR69","unstructured":"Reed, D., Gannon, D., Dongarra, J.. Reinventing high performance computing: Challenges and opportunities[J]. arXiv:2203.02544, (2022)"},{"key":"268_CR71","doi-asserted-by":"crossref","unstructured":"Ren Z, Trivedi A.: Performance characterization of modern storage stacks: Posix i\/o, libaio, spdk, and io_uring [C]. In: Proceedings of the 3rd Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems. pp. 35\u201345. (2023)","DOI":"10.1145\/3578353.3589545"},{"key":"268_CR72","unstructured":"RIKEN.: RIKEN Center for Computational Science[EB\/OL]. [2025-02-15]. (2024) https:\/\/www.r-ccs.riken.jp\/en\/"},{"key":"268_CR73","unstructured":"Samsung.: Smart SSD | Samsung Semiconductor[EB\/OL]. [2025\u201302\u201315]. (2025) https:\/\/semiconductor.samsung.cn\/ssd\/smart-ssd\/ (in Chinese)"},{"issue":"2","key":"268_CR74","first-page":"283","volume":"53","author":"W Shi","year":"2016","unstructured":"Shi, W., Wang, D.: Survey of NVM-based transactional storage systems. J. Comput. Res. Dev. 53(2), 283\u2013296 (2016). (in Chinese)","journal-title":"J. Comput. Res. Dev."},{"key":"268_CR75","first-page":"1","volume":"18","author":"J Shu","year":"2023","unstructured":"Shu, J.: Prospects for new storage-compute separation architectures. Commun. CCF 18, 1\u20138 (2023). (in Chinese)","journal-title":"Commun. CCF"},{"key":"268_CR77","volume-title":"High performance computing: Modern systems and practices[M]","author":"T Sterling","year":"2017","unstructured":"Sterling, T., Brodowicz, M., Anderson, M.: High performance computing: Modern systems and practices[M]. Morgan Kaufmann, San Francisco (2017)"},{"key":"268_CR79","unstructured":"Supercomputer[EB\/OL].: Baike, [2025\u201302\u201314]. (2025) https:\/\/www.baike.com\/wikiid\/7254357206303277059 (in Chinese)"},{"key":"268_CR80","unstructured":"Ten application challenges for next-generation E-class supercomputers[EB\/OL]. Xinhuanet, [2025\u201302\u201314]. (2021) https:\/\/www.news.cn\/science\/2021-12\/10\/c_1310362761.htm (in Chinese)"},{"key":"268_CR81","unstructured":"Tencent Cloud. MLPerf: Storage testing standard for AI scenarios[EB\/OL]. [2025\u201302\u201319]. (2024) https:\/\/cloud.tencent.com\/developer\/article\/MLPerf (in Chinese)"},{"key":"268_CR82","unstructured":"TOP500.: Home - TOP500 Supercomputer Sites[EB\/OL]. [2025\u201302\u201315]. (2024) https:\/\/www.top500.org"},{"key":"268_CR83","volume-title":"BurstFS: a distributed burst buffer file system[C]. In: Proc of SC16","author":"T Wang","year":"2016","unstructured":"Wang, T., Mohror, K., Moody, A., et al.: BurstFS: a distributed burst buffer file system[C]. In: Proc of SC16. IEEE, Salt Lake City (2016)"},{"key":"268_CR86","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, H., Li, C., et al.: Boosting data center performance via intelligently managed multi-backend disaggregated memory[C]. In: SC24: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, pp. 1\u201318 (2024)","DOI":"10.1109\/SC41406.2024.00043"},{"key":"268_CR87","unstructured":"He, X., Yang, B., Gao, J., et al.: HadaFS: a file system bridging local and shared burst buffers for exascale supercomputers[C]. In: Proc of the 21st USENIX Conference on File and Storage Technologies. Santa Clara: USENIX Association (2023)"},{"issue":"1","key":"268_CR88","first-page":"1","volume":"59","author":"Ma Xiaoxiao","year":"2022","unstructured":"Xiaoxiao, Ma., Fan, Y., Zhan, W., et al.: Survey of smart NICs[J]. J. Comput. Res. Dev. 59(1), 1\u201321 (2022). (in Chinese)","journal-title":"J. Comput. Res. Dev."},{"key":"268_CR89","unstructured":"Xu J, Swanson S. NOVA: a log-structured file system for hybrid Volatile\/Non-volatile main memories[C]. In: 14th USENIX Conference on File and Storage Technologies (FAST 16). pp. 323\u2013338 (2016)"},{"issue":"6","key":"268_CR91","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3638757","volume":"56","author":"Z Ye","year":"2024","unstructured":"Ye, Z., Gao, W., Hu, Q., et al.: Deep learning workload scheduling in gpu datacenters: a survey. ACM Comput. Surv. 56(6), 1\u201338 (2024)","journal-title":"ACM Comput. Surv."},{"issue":"7","key":"268_CR92","first-page":"1579","volume":"49","author":"Z Yuelong","year":"2012","unstructured":"Yuelong, Z., Xiaoling, X., Yongcai, C., et al.: Performance-optimized small file storage strategy[J]. J. Comput. Res. Dev. 49(7), 1579\u20131586 (2012). (in Chinese)","journal-title":"J. Comput. Res. Dev."},{"issue":"11","key":"268_CR93","first-page":"2609","volume":"11","author":"Du Zeng Lingbo","year":"2021","unstructured":"Zeng Lingbo, Du., Yunfei, W.W., et al.: Optimization practices for Lustre file system on Tianhe-2[J]. Comput. Sci. Appl. 11(11), 2609\u20132618 (2021). (in Chinese)","journal-title":"Comput. Sci. Appl."},{"key":"268_CR94","unstructured":"Zheng, Q., Patil, S., Gibson, G.: DeltaFS: a scalable no-ground-truth filesystem[C]. In: Proc of SC21. St. Louis: IEEE (2021)"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-025-00268-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-025-00268-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-025-00268-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T08:15:41Z","timestamp":1781252141000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-025-00268-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":83,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["268"],"URL":"https:\/\/doi.org\/10.1007\/s42514-025-00268-5","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"22 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 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 certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}