{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:46:02Z","timestamp":1772725562886,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T00:00:00Z","timestamp":1648857600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T00:00:00Z","timestamp":1648857600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,2]]},"DOI":"10.1109\/cgo53902.2022.9741289","type":"proceedings-article","created":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T19:51:20Z","timestamp":1648583480000},"page":"106-117","source":"Crossref","is-referenced-by-count":3,"title":["PALMED: Throughput Characterization for Superscalar Architectures"],"prefix":"10.1109","author":[{"given":"Nicolas","family":"Derumigny","sequence":"first","affiliation":[{"name":"Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LIG,Grenoble,France,38000"}]},{"given":"Theophile","family":"Bastian","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LIG,Grenoble,France,38000"}]},{"given":"Fabian","family":"Gruber","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LIG,Grenoble,France,38000"}]},{"given":"Guillaume","family":"Iooss","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LIG,Grenoble,France,38000"}]},{"given":"Christophe","family":"Guillon","sequence":"additional","affiliation":[{"name":"STMicroelectronics,France"}]},{"given":"Louis-Noel","family":"Pouchet","sequence":"additional","affiliation":[{"name":"Colorado State University,Fort Collins,Colorado,USA"}]},{"given":"Fabrice","family":"Rastello","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LIG,Grenoble,France,38000"}]}],"member":"263","reference":[{"key":"ref38","article-title":"BLIS: a framework","author":"zee","year":"0"},{"key":"ref33","year":"0","journal-title":"Sony Corporation and L Project LLVM machine code analyzer"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485963"},{"key":"ref31","first-page":"1","article-title":"CQA: A code quality analyzer tool at binary level","author":"rubial","year":"2014","journal-title":"21st International Conference on High Performance Computing HiPC 2014"},{"key":"ref30","first-page":"1","article-title":"CQA: A code quality analyzer tool at binary level","author":"rubial","year":"2014","journal-title":"21st InternationalConference on High Performance Computing HiPC 2014"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2007.363733"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2010.38"},{"key":"ref34","year":"2018","journal-title":"Update to the llvm scheduling model for intel sandy bridge haswell broadwell and skylake processors"},{"key":"ref10","year":"0","journal-title":"Intel 64 and IA-32 Architectures Optimization Reference Manual"},{"key":"ref11","year":"0","journal-title":"Intel x86 encoder decoder (intel xed)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89894-8_8"},{"key":"ref13","author":"fog","year":"2020","journal-title":"Instruction Tables Lists of Instruction Latencies Throughputs and Micro-operation Breakdowns for Intel AMD and VIA CPUs"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2873289"},{"key":"ref15","author":"granlund","year":"2017","journal-title":"Instruction latencies and throughput for AMD and Intel x86 processors"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56702-0_1"},{"key":"ref17","year":"0","journal-title":"I Hirsh and G S Intel® architecture code analyzer"},{"key":"ref18","year":"0","journal-title":"memory latency and cpuid dumps"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/30.1-2.81"},{"key":"ref28","author":"project","year":"1987","journal-title":"GNU Compiler Collection (GCC)"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1145\/3297858.3304062","article-title":"uops.info: Characterizing latency, throughput, and port usage of instructions on intel microarchitectures","author":"abel","year":"2019","journal-title":"Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems ASPLOS 2019"},{"key":"ref27","article-title":"PolyBench\/C: The polyhedral benchmark suite, version 4.2","author":"pouchet","year":"0"},{"key":"ref3","article-title":"nanoBench: A low-overhead tool for running microbenchmarks on x86 systems","author":"abel","year":"2019","journal-title":"ArXiv e-prints"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2013.6557148"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3385412.3385995"},{"key":"ref5","article-title":"Accurate throughput prediction of basic blocks on recent intel microarchitectures","author":"abel","year":"2021"},{"key":"ref8","author":"chatelet","year":"0","journal-title":"Google exegesis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3185768.3185771"},{"key":"ref2","year":"0","journal-title":"QEMU-the FAST! Processor Emulator"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1109\/ISPASS.2001.990684","article-title":"Automatic memory hierarchy characterization","author":"coleman","year":"2001","journal-title":"2001 IEEE International Symposium on Performance Analysis of Systems and Software ISPASS"},{"key":"ref1","year":"0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919638"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS.2018.8641578"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844480"},{"key":"ref23","article-title":"The gem5 simulator: Version 20.0 +","author":"lowe-power","year":"0"},{"key":"ref26","first-page":"195","volume":"2","author":"nielsen","year":"0","journal-title":"Hierarchical Clustering"},{"key":"ref25","first-page":"4505","article-title":"Ithemal: Accurate, portable and fast basic block throughput estimation using deep neural networks","volume":"97","author":"mendis","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning ICML 2019 ser Proceedings of Machine Learning Research"}],"event":{"name":"2022 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2022,4,2]]},"end":{"date-parts":[[2022,4,6]]}},"container-title":["2022 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9741235\/9741095\/09741289.pdf?arnumber=9741289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,14]],"date-time":"2022-06-14T20:43:02Z","timestamp":1655239382000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9741289\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,2]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/cgo53902.2022.9741289","relation":{},"subject":[],"published":{"date-parts":[[2022,4,2]]}}}