{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:39:17Z","timestamp":1768030757558,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T00:00:00Z","timestamp":1628467200000},"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":[[2021,8,9]]},"DOI":"10.1145\/3472456.3472521","type":"proceedings-article","created":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T18:39:57Z","timestamp":1633459197000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Tool-Supported Mini-App Extraction to Facilitate Program Analysis and Parallelization"],"prefix":"10.1145","author":[{"given":"Jan-Patrick","family":"Lehr","sequence":"first","affiliation":[{"name":"Technical University of Darmstadt, Germany"}]},{"given":"Christian","family":"Bischof","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Germany"}]},{"given":"Florian","family":"Dewald","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Germany"}]},{"given":"Heiko","family":"Mantel","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Germany"}]},{"given":"Mohammad","family":"Norouzi","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Germany"}]},{"given":"Felix","family":"Wolf","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Germany"}]}],"member":"320","published-online":{"date-parts":[[2021,10,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00037"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1985793.1985898"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063427"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628100"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.46"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1177\/109434200001400303"},{"key":"e_1_3_2_1_7_1","article-title":"CERE: LLVM-Based Codelet Extractor and REplayer for Piecewise Benchmarking and Optimization","volume":"12","author":"De\u00a0Oliveira Castro Pablo","year":"2015","unstructured":"Pablo De\u00a0Oliveira Castro , Chadi Akel , Eric Petit , Mihail Popov , and William Jalby . 2015 . CERE: LLVM-Based Codelet Extractor and REplayer for Piecewise Benchmarking and Optimization . ACM Trans. Archit. Code Optim. 12 , 1, Article 6(2015), 24\u00a0pages. https:\/\/doi.org\/10.1145\/2724717 Pablo De\u00a0Oliveira Castro, Chadi Akel, Eric Petit, Mihail Popov, and William Jalby. 2015. CERE: LLVM-Based Codelet Extractor and REplayer for Piecewise Benchmarking and Optimization. ACM Trans. Archit. Code Optim. 12, 1, Article 6(2015), 24\u00a0pages. https:\/\/doi.org\/10.1145\/2724717","journal-title":"ACM Trans. Archit. Code Optim."},{"key":"e_1_3_2_1_8_1","volume-title":"Chiral Interactions up to Next-to-Next-to-Next-to-Leading Order and Nuclear Saturation. Physical Review Letters 122 (Jan","author":"Drischler Christian","year":"2019","unstructured":"Christian Drischler , Kai Hebeler , and Achim Schwenk . 2019. Chiral Interactions up to Next-to-Next-to-Next-to-Leading Order and Nuclear Saturation. Physical Review Letters 122 (Jan 2019 ), 042501. Issue 4. https:\/\/doi.org\/10.1103\/PhysRevLett.122.042501 Christian Drischler, Kai Hebeler, and Achim Schwenk. 2019. Chiral Interactions up to Next-to-Next-to-Next-to-Leading Order and Nuclear Saturation. Physical Review Letters 122 (Jan 2019), 042501. Issue 4. https:\/\/doi.org\/10.1103\/PhysRevLett.122.042501"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3276496"},{"key":"e_1_3_2_1_10_1","volume-title":"GNU Scientific Library Reference Manual -","author":"Gough Brian","unstructured":"Brian Gough . 2009. GNU Scientific Library Reference Manual - Third Edition (3 rd ed.). Network Theory Ltd . Brian Gough. 2009. GNU Scientific Library Reference Manual - Third Edition (3rd ed.). Network Theory Ltd.","edition":"3"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2005.01.010"},{"key":"e_1_3_2_1_12_1","volume-title":"6th Intl. Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computing Systems. ACM, Article 4, 11\u00a0pages. https:\/\/doi.org\/10.1145\/2832087.2832092","author":"Hammer Julian","unstructured":"Julian Hammer , Georg Hager , Jan Eitzinger , and Gerhard Wellein . 2015. Automatic Loop Kernel Analysis and Performance Modeling with Kerncraft . In 6th Intl. Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computing Systems. ACM, Article 4, 11\u00a0pages. https:\/\/doi.org\/10.1145\/2832087.2832092 Julian Hammer, Georg Hager, Jan Eitzinger, and Gerhard Wellein. 2015. Automatic Loop Kernel Analysis and Performance Modeling with Kerncraft. In 6th Intl. Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computing Systems. ACM, Article 4, 11\u00a0pages. https:\/\/doi.org\/10.1145\/2832087.2832092"},{"key":"e_1_3_2_1_13_1","volume-title":"Call Tree Controlled Instrumentation for Low-Overhead Survey Measurements. In 2016 IEEE Intl. Parallel and Distributed Processing Symposium Workshops (IPDPSW 2016","author":"Iwainsky Christian","year":"2016","unstructured":"Christian Iwainsky and Christian Bischof . 2016 . Call Tree Controlled Instrumentation for Low-Overhead Survey Measurements. In 2016 IEEE Intl. Parallel and Distributed Processing Symposium Workshops (IPDPSW 2016 ). https:\/\/doi.org\/10.1109\/IPDPSW.2016.5 Christian Iwainsky and Christian Bischof. 2016. Call Tree Controlled Instrumentation for Low-Overhead Survey Measurements. In 2016 IEEE Intl. Parallel and Distributed Processing Symposium Workshops (IPDPSW 2016). https:\/\/doi.org\/10.1109\/IPDPSW.2016.5"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500845"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.05.466"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.117"},{"key":"e_1_3_2_1_17_1","volume-title":"TAU, and Vampir. In Tools for High Performance Computing","author":"Kn\u00fcpfer Andreas","year":"2011","unstructured":"Andreas Kn\u00fcpfer , Christian R\u00f6ssel , Dieter\u00a0an Mey , Scott Biersdorff , Kai Diethelm , Dominic Eschweiler , Markus Geimer , Michael Gerndt , Daniel Lorenz , Allen Malony , Wolfgang\u00a0 E. Nagel , Yury Oleynik , Peter Philippen , Pavel Saviankou , Dirk Schmidl , Sameer Shende , Ronny Tsch\u00fcter , Michael Wagner , Bert Wesarg , and Felix Wolf . 2012. Score-P: A Joint Performance Measurement Run-Time Infrastructure for Periscope,Scalasca , TAU, and Vampir. In Tools for High Performance Computing 2011 . Springer , 79\u201391. https:\/\/doi.org\/10.1007\/978-3-642-31476-6_7 Andreas Kn\u00fcpfer, Christian R\u00f6ssel, Dieter\u00a0an Mey, Scott Biersdorff, Kai Diethelm, Dominic Eschweiler, Markus Geimer, Michael Gerndt, Daniel Lorenz, Allen Malony, Wolfgang\u00a0E. Nagel, Yury Oleynik, Peter Philippen, Pavel Saviankou, Dirk Schmidl, Sameer Shende, Ronny Tsch\u00fcter, Michael Wagner, Bert Wesarg, and Felix Wolf. 2012. Score-P: A Joint Performance Measurement Run-Time Infrastructure for Periscope,Scalasca, TAU, and Vampir. In Tools for High Performance Computing 2011. Springer, 79\u201391. https:\/\/doi.org\/10.1007\/978-3-642-31476-6_7"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2020.01.133"},{"key":"e_1_3_2_1_19_1","volume-title":"Automatic Instrumentation Refinement for Empirical Performance Modeling. In 2019 IEEE\/ACM International Workshop on Programming and Performance Visualization Tools (ProTools). IEEE, 40\u201347","author":"Lehr Jan-Patrick","year":"2019","unstructured":"Jan-Patrick Lehr , Alexandru Calotoiu , Christian Bischof , and Felix Wolf . 2019 . Automatic Instrumentation Refinement for Empirical Performance Modeling. In 2019 IEEE\/ACM International Workshop on Programming and Performance Visualization Tools (ProTools). IEEE, 40\u201347 . https:\/\/doi.org\/10.1109\/ProTools49597.2019.00011 Jan-Patrick Lehr, Alexandru Calotoiu, Christian Bischof, and Felix Wolf. 2019. Automatic Instrumentation Refinement for Empirical Performance Modeling. In 2019 IEEE\/ACM International Workshop on Programming and Performance Visualization Tools (ProTools). IEEE, 40\u201347. https:\/\/doi.org\/10.1109\/ProTools49597.2019.00011"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Jan-Patrick Lehr Alexander H\u00fcck and Christian Bischof. 2018. PIRA: Performance Instrumentation Refinement Automation. In 5th ACM SIGPLAN Intl. Workshop on Artificial Intelligence and Empirical Methods for Software Engineering and Parallel Computing Systems (AI-SEPS\u201918). ACM 1\u201310. https:\/\/doi.org\/10.1145\/3281070.3281071  Jan-Patrick Lehr Alexander H\u00fcck and Christian Bischof. 2018. PIRA: Performance Instrumentation Refinement Automation. In 5th ACM SIGPLAN Intl. Workshop on Artificial Intelligence and Empirical Methods for Software Engineering and Parallel Computing Systems (AI-SEPS\u201918). ACM 1\u201310. https:\/\/doi.org\/10.1145\/3281070.3281071","DOI":"10.1145\/3281070.3281071"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59851-8_1"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3427764.3428320"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2016.03.045"},{"key":"e_1_3_2_1_24_1","volume-title":"Languages and Compilers for Parallel Computing","author":"Liao Chunhua","unstructured":"Chunhua Liao , Daniel\u00a0 J. Quinlan , Richard Vuduc , and Thomas Panas . 2010. Effective Source-to-Source Outlining to Support Whole Program Empirical Optimization . In Languages and Compilers for Parallel Computing . Springer , 308\u2013322. https:\/\/doi.org\/10.1007\/978-3-642-13374-9_21 Chunhua Liao, Daniel\u00a0J. Quinlan, Richard Vuduc, and Thomas Panas. 2010. Effective Source-to-Source Outlining to Support Whole Program Empirical Optimization. In Languages and Compilers for Parallel Computing. Springer, 308\u2013322. https:\/\/doi.org\/10.1007\/978-3-642-13374-9_21"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3587"},{"key":"e_1_3_2_1_26_1","first-page":"190","article-title":"Pin","volume":"40","author":"Luk Chi-Keung","year":"2005","unstructured":"Chi-Keung Luk , Robert Cohn , Robert Muth , Harish Patil , Artur Klauser , Geoff Lowney , Steven Wallace , Vijay\u00a0Janapa Reddi , and Kim Hazelwood . 2005 . Pin : Building Customized Program Analysis Tools with Dynamic Instrumentation. SIGPLAN Not. 40 , 6 (2005), 190 \u2013 200 . https:\/\/doi.org\/10.1145\/1064978.1065034 Chi-Keung Luk, Robert Cohn, Robert Muth, Harish Patil, Artur Klauser, Geoff Lowney, Steven Wallace, Vijay\u00a0Janapa Reddi, and Kim Hazelwood. 2005. Pin: Building Customized Program Analysis Tools with Dynamic Instrumentation. SIGPLAN Not. 40, 6 (2005), 190\u2013200. https:\/\/doi.org\/10.1145\/1064978.1065034","journal-title":"Building Customized Program Analysis Tools with Dynamic Instrumentation. SIGPLAN Not."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.105"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.471178"},{"key":"e_1_3_2_1_29_1","volume-title":"Euro-Par 2020: Parallel Processing(Lecture Notes in Computer Science, Vol.\u00a012247)","author":"Morew Nicolas","unstructured":"Nicolas Morew , Mohammad Norouzi , Ali Jannesari , and Felix Wolf . 2020. Skipping Non-essential Instructions Makes Data-dependence Profiling Faster . In Euro-Par 2020: Parallel Processing(Lecture Notes in Computer Science, Vol.\u00a012247) . Springer . https:\/\/doi.org\/10.1007\/978-3-030-57675-2_1 Nicolas Morew, Mohammad Norouzi, Ali Jannesari, and Felix Wolf. 2020. Skipping Non-essential Instructions Makes Data-dependence Profiling Faster. In Euro-Par 2020: Parallel Processing(Lecture Notes in Computer Science, Vol.\u00a012247). Springer. https:\/\/doi.org\/10.1007\/978-3-030-57675-2_1"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00099"},{"key":"e_1_3_2_1_31_1","volume-title":"A Proof Assistant for Higher-Order Logic","author":"Nipkow Tobias","unstructured":"Tobias Nipkow , Markus Wenzel , and Lawrence\u00a0 C. Paulson . 2002. Isabelle\/HOL : A Proof Assistant for Higher-Order Logic . Springer . https:\/\/doi.org\/10.1007\/3-540-45949-9 Tobias Nipkow, Markus Wenzel, and Lawrence\u00a0C. Paulson. 2002. Isabelle\/HOL: A Proof Assistant for Higher-Order Logic. Springer. https:\/\/doi.org\/10.1007\/3-540-45949-9"},{"key":"e_1_3_2_1_32_1","volume-title":"Euro-Par 2019: Parallel Processing(Lecture Notes in Computer Science, Vol.\u00a011725)","author":"Norouzi Mohammad","unstructured":"Mohammad Norouzi , Qamar Ilias , Ali Jannesari , and Felix Wolf . 2019. Accelerating Data-Dependence Profiling with Static Hints . In Euro-Par 2019: Parallel Processing(Lecture Notes in Computer Science, Vol.\u00a011725) . Springer , 17\u201328. https:\/\/doi.org\/10.1007\/978-3-030-29400-7_2 Mohammad Norouzi, Qamar Ilias, Ali Jannesari, and Felix Wolf. 2019. Accelerating Data-Dependence Profiling with Static Hints. In Euro-Par 2019: Parallel Processing(Lecture Notes in Computer Science, Vol.\u00a011725). Springer, 17\u201328. https:\/\/doi.org\/10.1007\/978-3-030-29400-7_2"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330375"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2011.300"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006064482"},{"key":"e_1_3_2_1_36_1","volume-title":"Formal Methods for Industrial Critical Systems","author":"Slab\u00fd Ji\u0159\u00ed","unstructured":"Ji\u0159\u00ed Slab\u00fd , Jan Strej\u010dek , and Marek Trt\u00edk . 2012. Checking Properties Described by State Machines: On Synergy of Instrumentation, Slicing, and Symbolic Execution . In Formal Methods for Industrial Critical Systems . Springer , 207\u2013221. https:\/\/doi.org\/10.1007\/978-3-642-32469-7_14 Ji\u0159\u00ed Slab\u00fd, Jan Strej\u010dek, and Marek Trt\u00edk. 2012. Checking Properties Described by State Machines: On Synergy of Instrumentation, Slicing, and Symbolic Execution. In Formal Methods for Industrial Critical Systems. Springer, 207\u2013221. https:\/\/doi.org\/10.1007\/978-3-642-32469-7_14"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2005.117"},{"key":"e_1_3_2_1_38_1","volume-title":"Binary Analysis for Measurement and Attribution of Program Performance. In 30th ACM SIGPLAN Conference on Programming Language Design and Implementation(PLDI \u201909)","author":"Tallent R.","year":"2009","unstructured":"Nathan\u00a0 R. Tallent , John\u00a0 M. Mellor-Crummey , and Michael\u00a0 W. Fagan . 2009 . Binary Analysis for Measurement and Attribution of Program Performance. In 30th ACM SIGPLAN Conference on Programming Language Design and Implementation(PLDI \u201909) . ACM, 441\u2013452. https:\/\/doi.org\/10.1145\/1542476.1542526 Nathan\u00a0R. Tallent, John\u00a0M. Mellor-Crummey, and Michael\u00a0W. Fagan. 2009. Binary Analysis for Measurement and Attribution of Program Performance. In 30th ACM SIGPLAN Conference on Programming Language Design and Implementation(PLDI \u201909). ACM, 441\u2013452. https:\/\/doi.org\/10.1145\/1542476.1542526"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503219"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.1984.5010248"},{"key":"e_1_3_2_1_41_1","volume-title":"High Performance Computing","author":"Wilke J.","year":"2040","unstructured":"Jeremiah\u00a0 J. Wilke , Joseph\u00a0 P. Kenny , Samuel Knight , and Sebastien Rumley . 2018. Compiler-Assisted Source-to-Source Skeletonization of Application Models for System Simulation . In High Performance Computing . Springer , 123\u2013143. https:\/\/doi.org\/10.1007\/978-3-319-9 2040 -5_7 Jeremiah\u00a0J. Wilke, Joseph\u00a0P. Kenny, Samuel Knight, and Sebastien Rumley. 2018. Compiler-Assisted Source-to-Source Skeletonization of Application Models for System Simulation. In High Performance Computing. Springer, 123\u2013143. https:\/\/doi.org\/10.1007\/978-3-319-92040-5_7"}],"event":{"name":"ICPP 2021: 50th International Conference on Parallel Processing","location":"Lemont IL USA","acronym":"ICPP 2021"},"container-title":["50th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3472456.3472521","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3472456.3472521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:17:23Z","timestamp":1750191443000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3472456.3472521"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,9]]},"references-count":41,"alternative-id":["10.1145\/3472456.3472521","10.1145\/3472456"],"URL":"https:\/\/doi.org\/10.1145\/3472456.3472521","relation":{},"subject":[],"published":{"date-parts":[[2021,8,9]]},"assertion":[{"value":"2021-10-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}