{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:12:55Z","timestamp":1750219975354,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T00:00:00Z","timestamp":1681516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,15]]},"DOI":"10.1145\/3578245.3583716","type":"proceedings-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T22:14:44Z","timestamp":1680560084000},"page":"127-131","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Core-Level Performance Engineering with the Open-Source Architecture Code Analyzer (OSACA) and the Compiler Explorer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3776-9353","authenticated-orcid":false,"given":"Jan","family":"Laukemann","sequence":"first","affiliation":[{"name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8723-2781","authenticated-orcid":false,"given":"Georg","family":"Hager","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}]}],"member":"320","published-online":{"date-parts":[[2023,4,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304062"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532396"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Christie Alappat Jan Laukemann Thomas Gruber Georg Hager Gerhard Wellein Nils Meyer and Tilo Wettig. 2020. Performance Modeling of Streaming Kernels and Sparse Matrix-Vector Multiplication on A64FX. In 2020 IEEE\/ACM Performance Modeling Benchmarking and Simulation of High Performance Computer Systems (PMBS). 1--7. https:\/\/doi.org\/10.1109\/PMBS51919.2020.00006","DOI":"10.1109\/PMBS51919.2020.00006"},{"key":"e_1_3_2_1_4_1","unstructured":"Andrea Di Biagio. 2023. llvm-mca -- LLVM Machine Code Analyzer. https:\/\/llvm.org\/docs\/CommandGuide\/llvm-mca.html"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2014.7116904"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.2200\/S00273ED1V01Y201006CAC010"},{"key":"e_1_3_2_1_7_1","unstructured":"Matt Godbolt. 2012. Compiler Explorer. https:\/\/godbolt.org\/"},{"key":"e_1_3_2_1_8_1","unstructured":"Julian Hammer Georg Hager and Gerhard Wellein. 2018. OoO Instruction Benchmarking Framework on the Back of Dragons. (2018). https:\/\/sc18.supercomputing.org\/proceedings\/src_poster\/src_poster_pages\/spost115.html SC18 ACM SRC Poster."},{"key":"e_1_3_2_1_9_1","unstructured":"Israel Hirsh and Gideon S. 2012. Intel\u00ae Architecture Code Analyzer. https:\/\/software.intel.com\/en-us\/articles\/intel-architecture-code-analyzer"},{"key":"e_1_3_2_1_10_1","unstructured":"Johannes Hofmann. 2017. ibench - Instruction Benchmarks. https:\/\/github.com\/RRZE-HPC\/ibench"},{"volume-title":"Intel\u00ae 64 and IA-32 Architecture Optimization Reference Manual","author":"Intel Corporation 2023.","key":"e_1_3_2_1_11_1","unstructured":"Intel Corporation 2023. Intel\u00ae 64 and IA-32 Architecture Optimization Reference Manual. Intel Corporation. https:\/\/software.intel.com\/en-us\/download\/intel-64-and-ia-32-architectures-optimization-reference-manual"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1137\/130930352"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"J. Laukemann J. Hammer G. Hager and G. Wellein. 2019. Automatic Throughput and Critical Path Analysis of x86 and ARM Assembly Kernels. In 2019 IEEE\/ACM Performance Modeling Benchmarking and Simulation of High Performance Computer Systems (PMBS). 1--6. https:\/\/doi.org\/10.1109\/PMBS49563.2019.00006","DOI":"10.1109\/PMBS49563.2019.00006"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"J. Laukemann J. Hammer J. Hofmann G. Hager and G. Wellein. 2018. Automated Instruction Stream Throughput Prediction for Intel and AMD Microarchitectures. In 2018 IEEE\/ACM Performance Modeling Benchmarking and Simulation of High Performance Computer Systems (PMBS). 121--131. https:\/\/doi.org\/10.1109\/PMBS.2018.8641578","DOI":"10.1109\/PMBS.2018.8641578"},{"key":"e_1_3_2_1_15_1","volume-title":"Memory Bandwidth and Machine Balance in Current High Performance Computers","author":"McCalpin John D.","year":"1995","unstructured":"John D. McCalpin. 1995. Memory Bandwidth and Machine Balance in Current High Performance Computers. IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter (Dec. 1995), 19--25. http:\/\/cs.virginia.edu\/stream"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on machine learning. PMLR, 4505--4515","author":"Mendis Charith","year":"2019","unstructured":"Charith Mendis, Alex Renda, Saman Amarasinghe, and Michael Carbin. 2019. Ithemal: Accurate, portable and fast basic block throughput estimation using deep neural networks. In International Conference on machine learning. PMLR, 4505--4515."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"}],"event":{"name":"ICPE '23: ACM\/SPEC International Conference on Performance Engineering","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Coimbra Portugal","acronym":"ICPE '23"},"container-title":["Companion of the 2023 ACM\/SPEC International Conference on Performance Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578245.3583716","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3578245.3583716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:20Z","timestamp":1750182560000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578245.3583716"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,15]]},"references-count":17,"alternative-id":["10.1145\/3578245.3583716","10.1145\/3578245"],"URL":"https:\/\/doi.org\/10.1145\/3578245.3583716","relation":{},"subject":[],"published":{"date-parts":[[2023,4,15]]},"assertion":[{"value":"2023-04-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}