{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T10:12:52Z","timestamp":1753438372133,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031695766"},{"type":"electronic","value":"9783031695773"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-69577-3_6","type":"book-chapter","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T19:02:05Z","timestamp":1724612525000},"page":"77-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Predicting GPU Kernel\u2019s Performance on\u00a0Upcoming Architectures"],"prefix":"10.1007","author":[{"given":"Lucas","family":"Van Lanker","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hugo","family":"Taboada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elisabeth","family":"Brunet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran\u00e7ois","family":"Trahay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,26]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Abdelkhalik, H., Arafa, Y., Santhi, N., Badawy, A.H.: Demystifying the nvidia ampere architecture through microbenchmarking and instruction-level analysis. In: 2022 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20138 (2022)","DOI":"10.1109\/HPEC55821.2022.9926299"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Ardalani, N., Lestourgeon, C., Sankaralingam, K., Zhu, X.: Cross-architecture performance prediction (XAPP) using CPU code to predict GPU performance. In: Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO) (2015)","DOI":"10.1145\/2830772.2830780"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Bakhoda, A., Yuan, G.L., Fung, W.W.L., Wong, H., Aamodt, T.M.: Analyzing CUDA workloads using a detailed GPU simulator. In: IEEE International Symposium on Performance Analysis of Systems and Software (2009)","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Benatia, A., Ji, W., Wang, Y., Shi, F.: Machine learning approach for the predicting performance of SpMV on GPU. In: IEEE 22nd International Conference on Parallel and Distributed Systems (ICPADS) (2016)","DOI":"10.1109\/ICPADS.2016.0120"},{"key":"6_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2024716.2024718","volume":"39","author":"N Binkert","year":"2011","unstructured":"Binkert, N., et al.: The gem5 simulator. ACM SIGARCH Comput. Archit. News 39, 1\u20137 (2011)","journal-title":"ACM SIGARCH Comput. Archit. News"},{"key":"6_CR6","doi-asserted-by":"publisher","first-page":"e6591","DOI":"10.1002\/cpe.6591","volume":"34","author":"N Ding","year":"2022","unstructured":"Ding, N., Awan, M., Williams, S.: Instruction roofline: an insightful visual performance model for GPUs. Concurrency Comput. Pract. Experience 34, e6591 (2022)","journal-title":"Concurrency Comput. Pract. Experience"},{"issue":"4","key":"6_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3629520","volume":"20","author":"J Domke","year":"2023","unstructured":"Domke, J., et al.: At the locus of performance: quantifying the effects of copious 3D-stacked cache on HPC workloads. ACM Trans. Archit. Code Optim. 20(4), 1\u201326 (2023)","journal-title":"ACM Trans. Archit. Code Optim."},{"key":"6_CR8","doi-asserted-by":"publisher","unstructured":"Gavoille, C., Taboada, H., Carribault, P., Dupros, F., Goglin, B., Jeannot, E.: Relative Performance Projection on Arm Architectures. In: Cano, J., Trinder, P. (eds.) Euro-Par 2022: Parallel Processing. Lecture Notes in Computer Science, vol. 13440. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-12597-3_6","DOI":"10.1007\/978-3-031-12597-3_6"},{"key":"6_CR9","unstructured":"Gu, Y., Wu, W., Li, Y., Chen, L.: UVMBench: a comprehensive benchmark suite for researching unified virtual memory in GPUs. arXiv:2007.09822(2020)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Karlin, I., Keasler, J., Neely, R.: Lulesh 2.0 updates and changes. Tech. rep. (2013)","DOI":"10.2172\/1090032"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Khairy, M., Shen, Z., Aamodt, T.M., Rogers, T.G.: Accel-Sim: an extensible simulation framework for validated GPU modeling. In: ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA) (2020)","DOI":"10.1109\/ISCA45697.2020.00047"},{"key":"6_CR12","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.jpdc.2017.04.002","volume":"107","author":"E Konstantinidis","year":"2017","unstructured":"Konstantinidis, E., Cotronis, Y.: A quantitative roofline model for GPU kernel performance estimation using micro-benchmarks and hardware metric profiling. J. Parallel Distrib. Comput. 107, 37\u201356 (2017)","journal-title":"J. Parallel Distrib. Comput."},{"key":"6_CR13","doi-asserted-by":"publisher","first-page":"e4963","DOI":"10.1002\/cpe.4963","volume":"31","author":"J Kwack","year":"2019","unstructured":"Kwack, J., Arnold, G., Mendes, C., Bauer, G.H.: Roofline analysis with cray performance analysis tools (CrayPat) and roofline-based performance projections for a future architecture. Concurrency Comput. Pract. Experience 31, e4963 (2019)","journal-title":"Concurrency Comput. Pract. Experience"},{"key":"6_CR14","unstructured":"McCalpin, J.D.: Memory bandwidth and machine balance in current high performance computers. IEEE Comput. Soc. Tech. Committee Comput. Archit. (TCCA) Newsl. 2(19\u201325) (1995)"},{"key":"6_CR15","unstructured":"NVIDIA: CUDA C++ Programming Guide (2020). https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html"},{"key":"6_CR16","unstructured":"NVIDIA: Nvidia Nsight Compute. https:\/\/docs.nvidia.com\/nsight-compute\/NsightCompute\/index.html"},{"key":"6_CR17","unstructured":"Petitet, A., et\u00a0al.: HPL - a portable implementation of the high-performance linpack benchmark for distributed-memory computers (2008)"},{"key":"6_CR18","unstructured":"Richards, D., Brantley, P., Dawson, S., Mckenley, S., O\u2019Brien, M.: Quicksilver, version 00 (2016). https:\/\/www.osti.gov\/biblio\/1313660"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Thavappiragasam, M., Scheinberg, A., Elwasif, W., Hernandez, O., Sedova, A.: Performance portability of molecular docking miniapp on leadership computing platforms. In: IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC) (2020)","DOI":"10.1109\/P3HPC51967.2020.00009"},{"issue":"12","key":"6_CR20","doi-asserted-by":"publisher","first-page":"2865","DOI":"10.1109\/TPDS.2020.3004623","volume":"31","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Chu, X.: GPGPU performance estimation with core and memory frequency scaling. IEEE Trans. Parallel Distrib. Syst. 31(12), 2865\u20132881 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"4","key":"6_CR21","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009)","journal-title":"Commun. ACM"},{"key":"6_CR22","doi-asserted-by":"publisher","first-page":"e5547","DOI":"10.1002\/cpe.5547","volume":"32","author":"C Yang","year":"2020","unstructured":"Yang, C., Kurth, T., Williams, S.: Hierarchical roofline analysis for GPUs: accelerating performance optimization for the NERSC-9 perlmutter system. Concurrency Comput. Pract. Experience 32, e5547 (2020)","journal-title":"Concurrency Comput. Pract. Experience"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Yang, C., Wang, Y., Kurth, T., Farrell, S., Williams, S.: Hierarchical roofline performance analysis for deep learning applications. In: Intelligent Computing: Proceedings of the 2021 Computing Conference, vol. 2, pp. 473\u2013491 (2021)","DOI":"10.1007\/978-3-030-80126-7_35"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Yang, C., et\u00a0al.: An empirical roofline methodology for quantitatively assessing performance portability. In: IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC) (2018)","DOI":"10.1109\/P3HPC.2018.00005"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2024: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-69577-3_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T19:05:50Z","timestamp":1724612750000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-69577-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031695766","9783031695773"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-69577-3_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"26 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Madrid","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}