{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T13:47:57Z","timestamp":1769348877388,"version":"3.49.0"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T00:00:00Z","timestamp":1716422400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T00:00:00Z","timestamp":1716422400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100019492","name":"National Natural Science Foundation of China-China Academy of General Technology Joint Fund for Basic Research","doi-asserted-by":"publisher","award":["62272475"],"award-info":[{"award-number":["62272475"]}],"id":[{"id":"10.13039\/501100019492","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s42514-024-00188-w","type":"journal-article","created":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T13:02:05Z","timestamp":1716469325000},"page":"243-262","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A survey of compute nodes with 100 TFLOPS and beyond for supercomputers"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3061-980X","authenticated-orcid":false,"given":"Junsheng","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongwen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libo","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,23]]},"reference":[{"key":"188_CR1","unstructured":"Alcorn, P.: AMD Shares New CPU Core Roadmap, 3\u00a0nm Zen 5 by 2024, 4th-Gen Infinity Architecture. Tom\u2019s Hardware. https:\/\/www.tomshardware.com\/ (2022). Accessed 15 June 2022"},{"key":"188_CR2","unstructured":"AMD.: AMD RDNA Architecture. https:\/\/www.amd.com\/system\/files\/documents\/rdna-whitepaper.pdf (2019). Accessed 8 June 2019"},{"key":"188_CR3","unstructured":"AMD.: AMD CDNA Architecture. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-business-docs\/white-papers\/amd-cdna-white-paper.pdf (2020). Accessed 18 Nov 2020"},{"key":"188_CR4","unstructured":"AMD.: AMD CDNA\u2122 2 Architecture. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-business-docs\/white-papers\/amd-cdna2-white-paper.pdf (2021). Accessed 16 Aug 2021"},{"key":"188_CR5","unstructured":"AMD.: AMD CDNA\u2122 3 Architecture. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-tech-docs\/white-papers\/amd-cdna-3-white-paper.pdf (2023). Accessed 26 Dec 2023"},{"issue":"4","key":"188_CR6","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1177\/1094342018778123","volume":"32","author":"M Asch","year":"2018","unstructured":"Asch, M., Moore, T., Badia, R., Beck, M., Beckman, P., Bidot, T., Bodin, F., Cappello, F., Choudhary, A., Supinski, B., et al.: Big data and extreme-scale computing: pathways to convergence-toward a shaping strategy for a future software and data ecosystem for scientific inquiry. Int. J. High Perform. C 32(4), 435\u2013479 (2018)","journal-title":"Int. J. High Perform. C"},{"key":"188_CR7","unstructured":"Aurora.: https:\/\/www.alcf.anl.gov\/aurora (2023). Accessed 26 Dec 2023"},{"key":"188_CR8","doi-asserted-by":"crossref","unstructured":"Biswas, A.: Sapphire rapids. In: 2021 IEEE Hot Chips 33 Symposium (HCS), pp. 1\u201322. IEEE, (2021)","DOI":"10.1109\/HCS52781.2021.9566865"},{"key":"188_CR9","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1557\/mrc.2019.118","volume":"9","author":"B Blaiszik","year":"2019","unstructured":"Blaiszik, B., Ward, L.T., Schwarting, M., Gaff, J., Chard, R., Pike, D.W., Chard, K., Foster, I.T.: A data ecosystem to support machine learning in materials science. MRS Commun. 9, 1125\u20131133 (2019)","journal-title":"MRS Commun."},{"key":"188_CR10","doi-asserted-by":"crossref","unstructured":"Blythe, D.: XeHPC Ponte Vecchio. In: 2021 IEEE Hot Chips 33 Symposium (HCS), pp. 1\u201334. IEEE (2021)","DOI":"10.1109\/HCS52781.2021.9567038"},{"key":"188_CR11","doi-asserted-by":"crossref","unstructured":"Burd, T., Li, W., Pistole, J., Venkataraman, S., McCabe, M., Johnson, T., Vinh, J., Yiu, T., Wasio, M., Wong, H.-H., et al.: Zen3: the AMD 2nd-generation 7 nm \u00d7 86\u201364 microprocessor core. In: 2022 IEEE International Solid-State Circuits Conference (ISSCC), pp. 1\u20133. IEEE (2022)","DOI":"10.1109\/ISSCC42614.2022.9731678"},{"issue":"3","key":"188_CR12","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1109\/MM.2023.3256796","volume":"43","author":"J Choquette","year":"2023","unstructured":"Choquette, J.: NVIDIA Hopper H100 GPU: scaling performance. IEEE Micro 43(3), 9\u201317 (2023)","journal-title":"IEEE Micro"},{"key":"188_CR13","doi-asserted-by":"crossref","unstructured":"Choquette, J., Gandhi, W.: NVIDIA A100 GPU: performance and innovation for GPU computing. In: 2020 IEEE Hot Chips 32 Symposium (HCS), pp. 1\u201343. IEEE (2020)","DOI":"10.1109\/HCS49909.2020.9220622"},{"key":"188_CR14","unstructured":"CXL.: Compute Express Link\u2122: The Breakthrough CPU-to-Device Interconnect CXL\u2122. https:\/\/www.computeexpresslink.org\/ (2023). Accessed 26 Dec 2023"},{"key":"188_CR15","doi-asserted-by":"crossref","unstructured":"Evers, M., Barnes, L., Clark, M.: Next generation \u201cZen 3\u201d Core. In: 2021 IEEE Hot Chips 33 Symposium (HCS). pp 1\u201332. IEEE (2021)","DOI":"10.1109\/HCS52781.2021.9567108"},{"issue":"1","key":"188_CR16","first-page":"1532","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. JMLR 23(1), 1532\u20134435 (2022)","journal-title":"JMLR"},{"key":"188_CR17","unstructured":"Frontier.: Oak Ridge National Laboratorys Frontier Supercomputer. https:\/\/docs.olcf.ornl.gov\/systems\/frontier_user_guide.html (2024). Accessed 26 Jan 2024"},{"key":"188_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-016-5588-7","volume":"59","author":"H Fu","year":"2016","unstructured":"Fu, H., Liao, J., Yang, J., Wang, L., Song, Z., Huang, X., Yang, C., Xue, W., Liu, F., Qiao, F., et al.: The sunway TaihuLight supercomputer: system and applications. Sci. China Inf. Sci. 59, 072001 (2016)","journal-title":"Sci. China Inf. Sci."},{"key":"188_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3104-7","volume":"64","author":"J Gao","year":"2021","unstructured":"Gao, J., Zheng, F., Qi, F., Ding, Y., Li, H., Lu, H., He, W., Wei, H., Jin, L., Liu, X., et al.: Sunway supercomputer architecture towards exascale computing: analysis and practice. Sci. China Inf. Sci. 64, 141101 (2021)","journal-title":"Sci. China Inf. Sci."},{"issue":"4","key":"188_CR20","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/2.375174","volume":"28","author":"M Gokhale","year":"1995","unstructured":"Gokhale, M., Holmes, B., Iobst, K.: Processing in memory: the Terasys massively parallel PIM array. Computer 28(4), 23\u201331 (1995)","journal-title":"Computer"},{"key":"188_CR21","doi-asserted-by":"crossref","unstructured":"Gomes, W., Koker, A., Stover, P., Ingerly, D., Siers, S., Venkataraman, S., Pelto, C., Shah, T., Rao, A., O\u2019Mahony, F., et al.: Ponte Vecchio: a multi-tile 3D stacked processor for exascale computing. In: 2022 IEEE International Solid-State Circuits Conference (ISSCC), pp. 42\u201344. IEEE (2022)","DOI":"10.1109\/ISSCC42614.2022.9731673"},{"issue":"1","key":"188_CR22","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1109\/JSSC.2017.2748623","volume":"53","author":"C Gonzalez","year":"2018","unstructured":"Gonzalez, C., Floyd, M., Fluhr, E., Restle, P., Dreps, D., Sperling, M., Rao, R., Hogenmiller, D., Vezyrtis, C., Chuang, P., et al.: The 24-core POWER9 processor with adaptive clocking, 25-Gb\/s accelerator links, and 16-Gb\/s PCIe Gen4. IEEE J. Solid State Circuits 53(1), 91\u2013101 (2018)","journal-title":"IEEE J. Solid State Circuits"},{"issue":"2","key":"188_CR23","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1109\/MM.2023.3237491","volume":"43","author":"D Gouk","year":"2023","unstructured":"Gouk, D., Kwon, M., Bae, H., Lee, S., Jung, M.: Memory pooling with CXL. IEEE Micro 43(2), 48\u201357 (2023)","journal-title":"IEEE Micro"},{"key":"188_CR24","unstructured":"Green500 the list.: https:\/\/www.top500.org\/lists\/green500\/2022\/06\/ (2022). Accessed 15 June 2022"},{"issue":"2","key":"188_CR25","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/MCSE.2018.021651341","volume":"20","author":"J Hines","year":"2018","unstructured":"Hines, J.: Stepping up to summit. Comput. Sci. Eng. 20(2), 78\u201382 (2018)","journal-title":"Comput. Sci. Eng."},{"key":"188_CR26","unstructured":"HPL-MxP results.: https:\/\/hpl-mxp.org\/results.md (2023). Accessed 14 Nov 2023"},{"key":"188_CR27","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1186\/s40537-020-00361-2","volume":"7","author":"EA Huerta","year":"2020","unstructured":"Huerta, E.A., Khan, A., Davis, E., Bushell, C., Gropp, W., Katz, D.S., Kindratenko, V., Koric, S., Kramer, W.T.C., McGinty, B., et al.: Convergence of artificial intelligence and high performance computing on NSF-supported cyberinfrastructure. J. Big Data 7, 88 (2020)","journal-title":"J. Big Data"},{"key":"188_CR28","doi-asserted-by":"crossref","unstructured":"IBM POWER9 NPU team.: Functionality and performance of NVLink with IBM POWER9 processors. IBM J. Res. Dev. 64(4\/5), 91\u2013910 (2018)","DOI":"10.1147\/JRD.2018.2846978"},{"key":"188_CR29","doi-asserted-by":"crossref","unstructured":"Ingerly, D. B., Amin, S., Aryasomayajula, L., Balankutty, A., Borst, D., Chandra, A., Cheemalapati, K., Cook, C. S., Criss, R., Enamul, K., et al.: Foveros: 3D integration and the use of face-to-face chip stacking for logic devices. In: 2019 IEEE International Electron Devices Meeting (IEDM), pp. 1961\u20131964. IEEE (2019)","DOI":"10.1109\/IEDM19573.2019.8993637"},{"key":"188_CR30","doi-asserted-by":"crossref","unstructured":"Ishii, A., Wells, R.: The Nvlink-network switch: Nvidia\u2019s switch chip for high communication-bandwidth superpods. In: 2022 IEEE Hot Chips 34 symposium (HCS), pp. 1\u201323. IEEE (2022)","DOI":"10.1109\/HCS55958.2022.9895480"},{"key":"188_CR31","doi-asserted-by":"crossref","unstructured":"Jang, J., Kim, H., Lee, H.: Characterizing memory access patterns of various convolutional neural networks for utilizing processing-in-memory. In: 2023 International Conference on Electronics, Information, and Communication (ICEIC), pp. 1\u20133. IEEE (2023)","DOI":"10.1109\/ICEIC57457.2023.10049894"},{"key":"188_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, H.: Intel\u2019s Ponte Vecchio GPU: architecture, systems & software. In: 2022 IEEE Hot Chips 34 Symposium (HCS), pp. 1\u201329. IEEE (2022)","DOI":"10.1109\/HCS55958.2022.9895631"},{"key":"188_CR33","doi-asserted-by":"crossref","unstructured":"Kahle, J.A., Moreno, J., Dreps, D.: Summit and sierra: designing AI\/HPC supercomputers. In: 2019 IEEE International Solid-State Circuits Conference (ISSCC), pp. 42\u201343. IEEE (2019)","DOI":"10.1109\/ISSCC.2019.8662426"},{"key":"188_CR34","doi-asserted-by":"crossref","unstructured":"Kang, W., Zhang, H., Zhao, W.: Spintronic memories: from memory to computing-in-memory. In: 2019 IEEE\/ACM International Symposium on Nanoscale Architectures (NANOARCH), pp. 1\u20132. IEEE (2019)","DOI":"10.1109\/NANOARCH47378.2019.181298"},{"key":"188_CR35","doi-asserted-by":"crossref","unstructured":"Kim, H., Baek, S., Song, J., Song, T.: A novel processing unit and architecture for process-in memory (PIM) in NAND flash memory. In: 2022 19th International SoC Design Conference (ISOCC), pp. 127\u2013128. IEEE (2022)","DOI":"10.1109\/ISOCC56007.2022.10031375"},{"issue":"1","key":"188_CR36","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1109\/TPDS.2019.2928289","volume":"31","author":"A Li","year":"2020","unstructured":"Li, A., Song, S.L., Chen, J., Li, J., Liu, X., Tallent, N.R., Barker, K.J.: Evaluating modern GPU interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect. IEEE Trans. Parallel Distrib. Syst. 31(1), 94\u2013110 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"188_CR37","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1631\/FITEE.1800494","volume":"19","author":"X Liao","year":"2018","unstructured":"Liao, X., Lu, K., Yang, C., Li, J.-W., Yuan, Y., Lai, M.-C., Huang, L., Lu, P.-J., Fang, J., Ren, J.: Moving from exascale to zettascale computing: challenges and techniques. Front. Inf. Technol. Electron. Eng. 19, 1236\u20131244 (2018)","journal-title":"Front. Inf. Technol. Electron. Eng."},{"key":"188_CR38","doi-asserted-by":"crossref","unstructured":"Liu, M.: Unleashing the future of innovation. In: 2021 IEEE International Solid-State Circuits Conference (ISSCC), pp. 9\u201316. IEEE (2021)","DOI":"10.1109\/ISSCC42613.2021.9366060"},{"key":"188_CR39","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/s42514-019-00010-y","volume":"1","author":"Y Lu","year":"2019","unstructured":"Lu, Y.: Paving the way for China exascale computing. CCF Trans. HPC 1, 63\u201372 (2019)","journal-title":"CCF Trans. HPC"},{"key":"188_CR40","doi-asserted-by":"crossref","unstructured":"Mahajan, R., Sankman, R., Patel, N., Kim, D.-w., Aygun, K., Qian, Z., Mekonnen, Y. S., Salama, I. A., Sharan, S., Iyengar, D., et al.: Embedded multi-die interconnect bridge (EMIB)\u2014a high density, high bandwidth packaging interconnect. In: 2016 IEEE 66th Electronic Components and Technology Conference (ECTC), pp. 557\u2013565. IEEE (2016)","DOI":"10.1109\/ECTC.2016.201"},{"issue":"3\u20134","key":"188_CR41","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1177\/10943420231166608","volume":"37","author":"S Matsuoka","year":"2023","unstructured":"Matsuoka, S., Domke, J., Wahib, M., Drozd, A., Hoefler, T.: Myths and legends in high-performance computing. Int. J. High Perform. C 37(3\u20134), 245\u2013259 (2023)","journal-title":"Int. J. High Perform. C"},{"key":"188_CR42","doi-asserted-by":"crossref","unstructured":"Moreau, M., Muhr, E., Bocquet, M., Aziza, H., Portal, J., Giraud, B., No\u00ebl, J.: Reliable ReRAM-based logic operations for computing in memory. In: 2018 IFIP\/IEEE International Conference on Very Large Scale Integration (VLSI-SoC), pp. 192\u2013195. IEEE (2018)","DOI":"10.1109\/VLSI-SoC.2018.8644780"},{"key":"188_CR43","doi-asserted-by":"crossref","unstructured":"Moreno, J.H., Wen, S.: Co-design in high performance computing systems. In: 2021 IEEE International Electron Devices Meeting (IEDM), pp. 1\u20134. IEEE (2021)","DOI":"10.1109\/IEDM19574.2021.9720499"},{"key":"188_CR44","doi-asserted-by":"publisher","first-page":"13455","DOI":"10.1007\/s11227-022-04399-2","volume":"78","author":"S Moreno-\u00c1lvarez","year":"2022","unstructured":"Moreno-\u00c1lvarez, S., Paoletti, M.E., Rico-Gallego, J.A., Haut, J.M.: Heterogeneous gradient computing optimization for scalable deep neural networks. J. Supercomput. 78, 13455\u201313469 (2022)","journal-title":"J. Supercomput."},{"key":"188_CR45","unstructured":"Morgan, T.P.: Lawrence Livermore\u2019s \u201cEl Capitan\u201d To Take AMD\u2019s Instinct APU Mainstream. The Next Platform. https:\/\/www.nextplatform.com\/ (2022). Accessed 22 June 2022"},{"key":"188_CR46","doi-asserted-by":"crossref","unstructured":"Munger, B., Wilcox, K., Sniderman, J., Tung, C., Johnson, B., Schreiber, R., Henrion, C., Gillespie, K., Burd, T., Fair, H. R., et al.: \u201cZen 4\u201d: the AMD 5\u00a0nm 5.7 GHz \u00d7 86\u201364 microprocessor core. In: 2023 IEEE International Solid-State Circuits Conference (ISSCC), pp. 38\u201339. IEEE (2023)","DOI":"10.1109\/ISSCC42615.2023.10067540"},{"key":"188_CR47","doi-asserted-by":"crossref","unstructured":"Nassif, N., Munch, A. O., Molnar, C. L., Pasdast, G., Iyer, S. V., Yang, Z., Mendoza, O., Huddart, M., Venkataraman, S., Kandula, S., et al.: Sapphire rapids: the next-generation Intel Xeon scalable processor. In: 2022 IEEE International Solid-State Circuits Conference (ISSCC), pp. 44\u201346. IEEE (2022)","DOI":"10.1109\/ISSCC42614.2022.9731107"},{"key":"188_CR48","unstructured":"Nvidia.: OpenCL Programming Guide for the CUDA Architecture. https:\/\/www.nvidia.com\/content\/cudazone\/download\/opencl\/nvidia_opencl_programmingguide.pdf (2009). Accessed 27 Aug 2009"},{"key":"188_CR49","unstructured":"Nvidia.: Nvidia Tesla V100 Architecture. https:\/\/images.nvidia.cn\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper.pdf (2017). Accessed 27 Aug 2017"},{"key":"188_CR50","unstructured":"Nvidia.: Nvidia Turing GPU Architecture. https:\/\/images.nvidia.cn\/aem-dam\/en-zz\/Solutions\/design-visualization\/technologies\/turing-architecture\/NVIDIA-Turing-Architecture-Whitepaper.pdf (2018). Accessed 14 Sept 2018"},{"key":"188_CR51","unstructured":"Nvidia.: Nvidia A100 Tensor Core GPU Architecture. https:\/\/images.nvidia.cn\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf (2020). Accessed 23 Dec 2020"},{"key":"188_CR52","unstructured":"Nvidia.: Nvidia H100 Tensor Core GPU Architecture. https:\/\/www.techpowerup.com\/gpu-specs\/docs\/nvidia-gh100-architecture.pdf (2023a). Accessed 27 Dec 2023"},{"key":"188_CR53","unstructured":"Nvidia.: Nvidia DGX H100 User Guide. https:\/\/docs.nvidia.com\/dgx\/dgxh100-user-guide\/dgxh100-user-guide.pdf (2023b). Accessed 27 Dec 2023"},{"key":"188_CR54","unstructured":"Nvidia.: Nvidia DGX SuperPOD: next Generation Scalable Infrastructure for AI Leadership. https:\/\/docs.nvidia.com\/https:\/docs.nvidia.com\/dgx-superpod-reference-architecture-dgx-h100.pdf (2023c). Accessed 22 Sept 2023"},{"key":"188_CR55","unstructured":"Nvidia.: Nvidia DGX SuperPOD Data Center. https:\/\/docs.nvidia.com\/nvidia-dgx-superpod-data-center-design-dgx-h100.pdf (2023d). Accessed 22 May 2023"},{"key":"188_CR56","unstructured":"Nvidia.: NVLink and NVSwitch. https:\/\/www.nvidia.com\/en-us\/data-center\/nvlink\/ (2023e). Accessed 27 Dec 2023"},{"key":"188_CR57","unstructured":"Nvidia.: Nvidia GH200 Grace Hopper Superchip Architecture. https:\/\/resources.nvidia.com\/en-us-grace-cpu\/nvidia-grace-hopper (2024). Accessed 27 Nov 2024"},{"key":"188_CR58","doi-asserted-by":"crossref","unstructured":"Park, S. J., Kim, H., Kim, K.-S., So, J., Ahn, J., Lee, W.-J., Kim, D., Kim, Y.-J., Seok, J., Lee, J.-G., et al.: Scaling of memory performance and capacity with CXL memory expander. In: 2022 IEEE Hot Chips 34 Symposium (HCS), pp. 1\u201327. IEEE (2022)","DOI":"10.1109\/HCS55958.2022.9895633"},{"key":"188_CR59","unstructured":"Pires, F.: AMD\u2019s Third-Gen Infinity Architecture Enables Coherent CPU-GPU Communication. Tom\u2019s Hardware. https:\/\/www.tomshardware.com\/ (2021). Accessed 9 Nov 2021"},{"key":"188_CR60","doi-asserted-by":"crossref","unstructured":"Preface.: Summit and sierra supercomputers. IBM J. Res. Dev. 64(3\/4), 1\u20134 (2020)","DOI":"10.1147\/JRD.2020.2976169"},{"key":"188_CR61","doi-asserted-by":"crossref","unstructured":"Raihan, M.A., Goli, N., Aamodt, T.M.: Modeling deep learning accelerator enabled GPUs. In: 2019 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 79\u201392. IEEE (2019)","DOI":"10.1109\/ISPASS.2019.00016"},{"key":"188_CR62","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/s12045-023-1583-7","volume":"28","author":"V Rajaraman","year":"2023","unstructured":"Rajaraman, V.: Frontier\u2014world\u2019s first ExaFLOPS supercomputer. Resonance 28, 567\u2013576 (2023)","journal-title":"Resonance"},{"key":"188_CR63","doi-asserted-by":"crossref","unstructured":"Sato, M., Ishikawa, Y., Tomita, H., Kodama, Y., Odajima, T., Tsuji, M., Yashiro, H., Aoki, M., Shida, N., Miyoshi, I., et al.: Co-design for A64FX manycore processor and \u201cFugaku\u201d. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201315. IEEE (2020)","DOI":"10.1109\/SC41405.2020.00051"},{"issue":"2","key":"188_CR64","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MM.2021.3136882","volume":"42","author":"M Sato","year":"2022","unstructured":"Sato, M., Kodama, Y., Tsuji, M.: Co-design and system for the supercomputer \u201cFugaku.\u201d IEEE Micro 42(2), 26\u201334 (2022)","journal-title":"IEEE Micro"},{"key":"188_CR65","doi-asserted-by":"crossref","unstructured":"Shimizu, T.: Supercomputer Fugaku: co-designed with application developers\/researchers. In: 2020 IEEE Asian Solid-State Circuits Conference (A-SSCC), pp. 1\u20134. IEEE (2020)","DOI":"10.1109\/A-SSCC48613.2020.9336127"},{"key":"188_CR66","doi-asserted-by":"crossref","unstructured":"Singh, T., Rangarajan, S., John, D., Henrion, C., Southard, S., McIntyre, H., Novak, A., Kosonocky, S., Jotwani, R., Schaefer, A., et al.: Zen: a next-generation high-performance \u00d786 core. In: 2017 IEEE International Solid-State Circuits Conference (ISSCC), pp. 52\u201353. IEEE (2017)","DOI":"10.1109\/ISSCC.2017.7870256"},{"issue":"1","key":"188_CR67","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1109\/JSSC.2017.2752839","volume":"53","author":"T Singh","year":"2018","unstructured":"Singh, T., Schaefer, A., Rangarajan, S., John, D., Henrion, C., Schreiber, R., Rodriguez, M., Kosonocky, S., Naffziger, S., Novak, A.: Zen: an energy-efficient high-performance \u00d7 86 Core. IEEE J. Solid State Circuits 53(1), 102\u2013114 (2018)","journal-title":"IEEE J. Solid State Circuits"},{"key":"188_CR68","doi-asserted-by":"crossref","unstructured":"Singh, T., Rangarajan, S., John, D., Schreiber, R., Oliver, S., Seahra, R., Schaefer, A.: Zen 2: the AMD 7\u00a0nm energy-efficient high-performance \u00d7 86\u201364 microprocessor core. In: 2020 IEEE International Solid-State Circuits Conference (ISSCC), pp. 42\u201344. IEEE (2020)","DOI":"10.1109\/ISSCC19947.2020.9063113"},{"key":"188_CR69","unstructured":"Smith, R.: El Capitan supercomputer detailed: AMD CPUs & GPUs to Drive 2 Exaflops of Compute. AnandTech. https:\/\/www.anandtech.com\/ (2020). Accessed 4 Mar 2007"},{"key":"188_CR71","doi-asserted-by":"crossref","unstructured":"Su, L., Naffziger, S.: Innovation for the next decade of compute efficiency. In: 2023 IEEE International Solid-State Circuits Conference (ISSCC), pp. 8\u201312. IEEE (2023)","DOI":"10.1109\/ISSCC42615.2023.10067810"},{"key":"188_CR72","doi-asserted-by":"crossref","unstructured":"Suggs, D., Bouvier, D., Clark, M., Lepak, K., Subramony, M.: AMD \u201cZEN 2\u201d. In: 2019 IEEE Hot Chips 31 Symposium (HCS), pp. 1\u201324. IEEE (2019)","DOI":"10.1109\/HOTCHIPS.2019.8875673"},{"issue":"2","key":"188_CR73","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/MM.2020.2974217","volume":"40","author":"D Suggs","year":"2020","unstructured":"Suggs, D., Subramony, M., Bouvier, D.: The AMD \u201cZen 2\u201d processor. IEEE Micro 40(2), 45\u201352 (2020)","journal-title":"IEEE Micro"},{"key":"188_CR74","unstructured":"Top500 the list.: https:\/\/www.top500.org\/lists\/top500\/2022\/06\/ (2022). Accessed 15 June 2022"},{"key":"188_CR75","unstructured":"Top500 the list.: https:\/\/www.top500.org\/lists\/top500\/2023\/11\/ (2023). Accessed 14 Nov 2023"},{"key":"188_CR76","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1557\/mrc.2019.107","volume":"9","author":"L Ward","year":"2019","unstructured":"Ward, L., Blaiszik, B., Foster, I., Assary, R.S., Narayanan, B., Curtiss, L.: Machine learning prediction of accurate atomization energies of organic molecules from low-fidelity quantum chemical calculations. MRS Commun. 9, 891\u2013899 (2019)","journal-title":"MRS Commun."},{"issue":"7","key":"188_CR77","doi-asserted-by":"publisher","first-page":"967","DOI":"10.1109\/5.293155","volume":"82","author":"WH Wolf","year":"1994","unstructured":"Wolf, W.H.: Hardware-software co-design of embedded systems. Proc. IEEE 82(7), 967\u2013989 (1994)","journal-title":"Proc. IEEE"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-024-00188-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-024-00188-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-024-00188-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T21:28:23Z","timestamp":1732051703000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-024-00188-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,23]]},"references-count":76,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["188"],"URL":"https:\/\/doi.org\/10.1007\/s42514-024-00188-w","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,23]]},"assertion":[{"value":"12 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}