{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:59:46Z","timestamp":1775667586200,"version":"3.50.1"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s42514-024-00187-x","type":"journal-article","created":{"date-parts":[[2024,5,2]],"date-time":"2024-05-02T07:01:36Z","timestamp":1714633296000},"page":"115-129","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["AIbench: a tool for benchmarking Huawei ascend AI processors"],"prefix":"10.1007","volume":"6","author":[{"given":"Yang","family":"Xiao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8550-9241","authenticated-orcid":false,"given":"Zeke","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,5,2]]},"reference":[{"key":"187_CR1","doi-asserted-by":"crossref","unstructured":"Huang, H., Wang, Z., Zhang, J., He, Z., Wu, C., Xiao, J., Alonso, G.: Shuhai: a tool for benchmarking high bandwidth memory on fpgas. TC (2022)","DOI":"10.1109\/TC.2021.3075765"},{"key":"187_CR2","unstructured":"Jia, Z., Maggioni, M., Staiger, B., Scarpazza, D.P.: Dissecting the nvidia volta gpu architecture via microbenchmarking (2018). arXiv:1804.06826"},{"key":"187_CR3","doi-asserted-by":"crossref","unstructured":"Jouppi, N.P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., : In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, pp. 1\u201312 (2017)","DOI":"10.1145\/3079856.3080246"},{"key":"187_CR4","doi-asserted-by":"crossref","unstructured":"Jouppi, N.P., Kurian, G., Li, S., Ma, P., Nagarajan, R., Nai, L., Patil, N., Subramanian, S., Swing, A., Towles, B., et al.: Tpu v4: an optically reconfigurable supercomputer for machine learning with hardware support for embeddings (2023). arXiv:2304.01433","DOI":"10.1145\/3579371.3589350"},{"key":"187_CR5","unstructured":"Kumar, S., Bitorff, V., Chen, D., Chou, C., Hechtman, B., Lee, H., Kumar, N., Mattson, P., Wang, S., Wang, T., et al.: Scale mlperf-0.6 models on google tpu-v3 pods (2019). arXiv:1909.09756"},{"key":"187_CR6","doi-asserted-by":"crossref","unstructured":"Liao, H., Tu, J., Xia, J., Zhou, X.: Davinci: a scalable architecture for neural network computing. In: Hot Chips Symposium, pp. 1\u201344 (2019)","DOI":"10.1109\/HOTCHIPS.2019.8875654"},{"key":"187_CR7","doi-asserted-by":"crossref","unstructured":"Liao, H., Tu, J., Xia, J., Liu, H., Zhou, X., Yuan, H., Hu, Y.: Ascend: a scalable and unified architecture for ubiquitous deep neural network computing: Industry track paper. In: 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 789\u2013801 (2021). IEEE","DOI":"10.1109\/HPCA51647.2021.00071"},{"issue":"8","key":"187_CR8","first-page":"1618","volume":"45","author":"W Lu","year":"2022","unstructured":"Lu, W., Zhang, F., He, Y., Chen, Y., Zhai, J., Du, X.: Evaluation and optimization for huawei ascend neural network accelerator. Chin. J. Comput. 45(8), 1618\u201337 (2022)","journal-title":"Chin. J. Comput."},{"key":"187_CR9","doi-asserted-by":"crossref","unstructured":"Manev, K., Vaishnav, A., Koch, D.: Unexpected diversity: quantitative memory analysis for zynq ultrascale+ systems. In: FPT (2019)","DOI":"10.1109\/ICFPT47387.2019.00029"},{"issue":"1","key":"187_CR10","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/TPDS.2016.2549523","volume":"28","author":"X Mei","year":"2016","unstructured":"Mei, X., Chu, X.: Dissecting gpu memory hierarchy through microbenchmarking. IEEE Trans. Parallel Distrib. Syst. 28(1), 72\u201386 (2016)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"2","key":"187_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2636342","volume":"47","author":"S Mittal","year":"2014","unstructured":"Mittal, S., Vetter, J.S.: A survey of methods for analyzing and improving gpu energy efficiency. ACM Comput. Surv. (CSUR) 47(2), 1\u201323 (2014)","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"2","key":"187_CR12","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/MM.2021.3058217","volume":"41","author":"T Norrie","year":"2021","unstructured":"Norrie, T., Patil, N., Yoon, D.H., Kurian, G., Li, S., Laudon, J., Young, C., Jouppi, N., Patterson, D.: The design process for google\u2019s training chips: Tpuv2 and tpuv3. IEEE Micro 41(2), 56\u201363 (2021)","journal-title":"IEEE Micro"},{"key":"187_CR13","doi-asserted-by":"publisher","unstructured":"Reuther, A., Michaleas, P., Jones, M., Gadepally, V., Samsi, S., Kepner, J.: Survey and benchmarking of machine learning accelerators. In: 2019 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20139 (2019). https:\/\/doi.org\/10.1109\/HPEC.2019.8916327","DOI":"10.1109\/HPEC.2019.8916327"},{"key":"187_CR14","doi-asserted-by":"publisher","unstructured":"Sengupta, J., Kubendran, R., Neftci, E., Andreou, A.: High-speed, real-time, spike-based object tracking and path prediction on google edge tpu. In: 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), pp. 134\u2013135 (2020). https:\/\/doi.org\/10.1109\/AICAS48895.2020.9073867","DOI":"10.1109\/AICAS48895.2020.9073867"},{"key":"187_CR15","doi-asserted-by":"crossref","unstructured":"Wang, Z., Huang, H., Zhang, J., Alonso, G.: Shuhai: benchmarking high bandwidth memory on fpgas. In: 2020 IEEE 28th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp. 111\u2013119. IEEE (2020a)","DOI":"10.1109\/FCCM48280.2020.00024"},{"key":"187_CR16","doi-asserted-by":"publisher","unstructured":"Wang, Y., Wang, Q., Shi, S., He, X., Tang, Z., Zhao, K., Chu, X.: Benchmarking the performance and energy efficiency of ai accelerators for ai training. In: 2020 20th IEEE\/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID), pp. 744\u2013751 (2020b). https:\/\/doi.org\/10.1109\/CCGrid49817.2020.00-15","DOI":"10.1109\/CCGrid49817.2020.00-15"},{"key":"187_CR17","doi-asserted-by":"crossref","unstructured":"Wong, H., Papadopoulou, M.-M., Sadooghi-Alvandi, M., Moshovos, A.: Demystifying gpu microarchitecture through microbench marking. In: 2010 IEEE International Symposium on Performance Analysis of Systems & Software (ISPASS), pp. 235\u2013246. IEEE (2010)","DOI":"10.1109\/ISPASS.2010.5452013"},{"issue":"7","key":"187_CR18","doi-asserted-by":"publisher","first-page":"1740","DOI":"10.1109\/TPDS.2020.3046870","volume":"32","author":"C Zhang","year":"2020","unstructured":"Zhang, C., Zhang, F., Guo, X., He, B., Zhang, X., Du, X.: imlbench: a machine learning benchmark suite for cpu-gpu integrated architectures. IEEE Trans. Parallel Distrib. Syst. 32(7), 1740\u20131752 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"187_CR19","doi-asserted-by":"crossref","unstructured":"Zohouri, H.R., Matsuoka, S.: The memory controller wall: benchmarking the intel fpga sdk for opencl memory interface. In: H2RC (2019)","DOI":"10.1109\/H2RC49586.2019.00007"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-024-00187-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-024-00187-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-024-00187-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T09:05:15Z","timestamp":1715677515000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-024-00187-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":19,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["187"],"URL":"https:\/\/doi.org\/10.1007\/s42514-024-00187-x","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]},"assertion":[{"value":"27 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 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":"Yang Xiao from Zhejiang University declares that there are no commercial or related interests representing conflicts of interest in the submitted work. Zeke Wang from Zhejiang University declares that there are no commercial or related interests representing conflicts of interest in the submitted work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}