Pub Date : 2023-05-01DOI: 10.1109/GI59320.2023.00011
W. Langdon, Bradley J. Alexander
Magpie (Machine Automated General Performance Improvement via Evolution of software) has been recently developed by Aymeric Blot from PyGGI 2.0. Like PyGGI, it claims to be able to optimise computer source code written in arbitrary programming languages. So far it has been demonstrated on benchmarks written in Python and C. Recently we have used hill climbing to customise two industrial open source programs: Google's Open Location Code OLC and Uber's Hexagonal Hierarchical Spatial Index H3 [W. B. Langdon et al., “Genetic improvement of LLVM intermediate representation”, in EuroGP 2023]. Magpie found much faster improvements (reducing instruction counts by up to 15% v. 2%) which generalise. Various glitches in Magpie are also reported.
{"title":"Genetic Improvement of OLC and H3 with Magpie","authors":"W. Langdon, Bradley J. Alexander","doi":"10.1109/GI59320.2023.00011","DOIUrl":"https://doi.org/10.1109/GI59320.2023.00011","url":null,"abstract":"Magpie (Machine Automated General Performance Improvement via Evolution of software) has been recently developed by Aymeric Blot from PyGGI 2.0. Like PyGGI, it claims to be able to optimise computer source code written in arbitrary programming languages. So far it has been demonstrated on benchmarks written in Python and C. Recently we have used hill climbing to customise two industrial open source programs: Google's Open Location Code OLC and Uber's Hexagonal Hierarchical Spatial Index H3 [W. B. Langdon et al., “Genetic improvement of LLVM intermediate representation”, in EuroGP 2023]. Magpie found much faster improvements (reducing instruction counts by up to 15% v. 2%) which generalise. Various glitches in Magpie are also reported.","PeriodicalId":414492,"journal":{"name":"2023 IEEE/ACM International Workshop on Genetic Improvement (GI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124183172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/GI59320.2023.00014
Oliver Krauss
We explore the potential of using large-scale Natural Language Processing (NLP) models, such as GPT-3, for enhancing genetic improvement in software development. These models have previously been used to automatically find bugs, or improve software. We propose utilizing these models as a novel mutator, as well as for explaining the patches generated by genetic improvement algorithms. Our initial findings indicate promising results, but further research is needed to determine the scalability and applicability of this approach across different programming languages.
{"title":"Exploring the Use of Natural Language Processing Techniques for Enhancing Genetic Improvement","authors":"Oliver Krauss","doi":"10.1109/GI59320.2023.00014","DOIUrl":"https://doi.org/10.1109/GI59320.2023.00014","url":null,"abstract":"We explore the potential of using large-scale Natural Language Processing (NLP) models, such as GPT-3, for enhancing genetic improvement in software development. These models have previously been used to automatically find bugs, or improve software. We propose utilizing these models as a novel mutator, as well as for explaining the patches generated by genetic improvement algorithms. Our initial findings indicate promising results, but further research is needed to determine the scalability and applicability of this approach across different programming languages.","PeriodicalId":414492,"journal":{"name":"2023 IEEE/ACM International Workshop on Genetic Improvement (GI)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133779268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/GI59320.2023.00012
David Griffin, S. Stepney, Ian T. Vidamour
Novelty search is used to find a range of novel behaviours in a system. Software bugs are behaviours that are a) unexpected and b) incorrect. As the intersection between “novel” and “unexpected” is non-empty, here we overview how novelty search can be employed to find bugs in simulation software. We give an example of this approach applied to the RingSim simulator.
{"title":"DebugNS: Novelty Search for Finding Bugs in Simulators","authors":"David Griffin, S. Stepney, Ian T. Vidamour","doi":"10.1109/GI59320.2023.00012","DOIUrl":"https://doi.org/10.1109/GI59320.2023.00012","url":null,"abstract":"Novelty search is used to find a range of novel behaviours in a system. Software bugs are behaviours that are a) unexpected and b) incorrect. As the intersection between “novel” and “unexpected” is non-empty, here we overview how novelty search can be employed to find bugs in simulation software. We give an example of this approach applied to the RingSim simulator.","PeriodicalId":414492,"journal":{"name":"2023 IEEE/ACM International Workshop on Genetic Improvement (GI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124531906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/GI59320.2023.00015
Myles Watkinson, A. Brownlee
Genetic improvement is a young and growing field. With much research still to be done, a number of tools to support the research community have emerged, with Gin being one such tool targeted at GI for Java. One core component of Gin is the profiler, which is used to identify ‘hot’ methods in target applications: methods where the CPU spends most time and so may offer the most fertile sections of code for improvements to run time. Gin's profiler is HPROF, which was included with JDKs up to version 8. HPROF is no longer supported and so needs replaced if Gin is to support later versions of Java. Furthermore, little investigation has been made within the GI community comparing different profiling approaches. With this paper and its associated accepted pull request, we replace Gin's CPU profiler with Java Flight Recorder (JFR) to allow Gin to be applied to current Java code, allowing researchers working in GI with more recent JVMs to easily integrate profiling in their pipeline. We also contribute an experimental comparison of the HPROF and JFR profilers for the JVM.
{"title":"Updating Gin's profiler for current Java","authors":"Myles Watkinson, A. Brownlee","doi":"10.1109/GI59320.2023.00015","DOIUrl":"https://doi.org/10.1109/GI59320.2023.00015","url":null,"abstract":"Genetic improvement is a young and growing field. With much research still to be done, a number of tools to support the research community have emerged, with Gin being one such tool targeted at GI for Java. One core component of Gin is the profiler, which is used to identify ‘hot’ methods in target applications: methods where the CPU spends most time and so may offer the most fertile sections of code for improvements to run time. Gin's profiler is HPROF, which was included with JDKs up to version 8. HPROF is no longer supported and so needs replaced if Gin is to support later versions of Java. Furthermore, little investigation has been made within the GI community comparing different profiling approaches. With this paper and its associated accepted pull request, we replace Gin's CPU profiler with Java Flight Recorder (JFR) to allow Gin to be applied to current Java code, allowing researchers working in GI with more recent JVMs to easily integrate profiling in their pipeline. We also contribute an experimental comparison of the HPROF and JFR profilers for the JVM.","PeriodicalId":414492,"journal":{"name":"2023 IEEE/ACM International Workshop on Genetic Improvement (GI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127140425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/GI59320.2023.00010
Erik M. Fredericks, Abigail C. Diller, Jared M. Moore
Generative art produces artistic output via algorithmic design. Common examples include flow fields, particle motion, and mathematical formula visualization. Typically an art piece is generated with the artist/programmer acting as a domain expert to create the final output. A large amount of effort is often spent manipulating and/or refining parameters or algorithms and observing the resulting changes in produced images. Small changes to parameters of the various techniques can substantially alter the final product. We present GenerativeGI, a proof of concept evolutionary framework for creating generative art based on an input suite of artistic techniques and desired aesthetic preferences for outputs. GenerativeGI encodes artistic techniques in a grammar, thereby enabling multiple techniques to be combined and optimized via a many-objective evolutionary algorithm. Specific combinations of evolutionary objectives can help refine outputs reflecting the aesthetic preferences of the designer. Experimental results indicate that GenerativeGI can successfully produce more visually complex outputs than those found by random search.
{"title":"Generative Art via Grammatical Evolution","authors":"Erik M. Fredericks, Abigail C. Diller, Jared M. Moore","doi":"10.1109/GI59320.2023.00010","DOIUrl":"https://doi.org/10.1109/GI59320.2023.00010","url":null,"abstract":"Generative art produces artistic output via algorithmic design. Common examples include flow fields, particle motion, and mathematical formula visualization. Typically an art piece is generated with the artist/programmer acting as a domain expert to create the final output. A large amount of effort is often spent manipulating and/or refining parameters or algorithms and observing the resulting changes in produced images. Small changes to parameters of the various techniques can substantially alter the final product. We present GenerativeGI, a proof of concept evolutionary framework for creating generative art based on an input suite of artistic techniques and desired aesthetic preferences for outputs. GenerativeGI encodes artistic techniques in a grammar, thereby enabling multiple techniques to be combined and optimized via a many-objective evolutionary algorithm. Specific combinations of evolutionary objectives can help refine outputs reflecting the aesthetic preferences of the designer. Experimental results indicate that GenerativeGI can successfully produce more visually complex outputs than those found by random search.","PeriodicalId":414492,"journal":{"name":"2023 IEEE/ACM International Workshop on Genetic Improvement (GI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131273499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-19DOI: 10.1109/GI59320.2023.00013
Sungmin Kang, S. Yoo
While Genetic Improvement (GI) is a useful paradigm to improve functional and nonfunctional aspects of software, existing techniques tended to use the same set of mutation operators for differing objectives, due to the difficulty of writing custom mutation operators. In this work, we suggest that Large Language Models (LLMs) can be used to generate objective-tailored mutants, expanding the possibilities of software optimizations that GI can perform. We further argue that LLMs and the GI process can benefit from the strengths of one another, and present a simple example demonstrating that LLMs can both improve the effectiveness of the GI optimization process, while also benefiting from the evaluation steps of GI. As a result, we believe that the combination of LLMs and GI has the capability to significantly aid developers in optimizing their software.
{"title":"Towards Objective-Tailored Genetic Improvement Through Large Language Models","authors":"Sungmin Kang, S. Yoo","doi":"10.1109/GI59320.2023.00013","DOIUrl":"https://doi.org/10.1109/GI59320.2023.00013","url":null,"abstract":"While Genetic Improvement (GI) is a useful paradigm to improve functional and nonfunctional aspects of software, existing techniques tended to use the same set of mutation operators for differing objectives, due to the difficulty of writing custom mutation operators. In this work, we suggest that Large Language Models (LLMs) can be used to generate objective-tailored mutants, expanding the possibilities of software optimizations that GI can perform. We further argue that LLMs and the GI process can benefit from the strengths of one another, and present a simple example demonstrating that LLMs can both improve the effectiveness of the GI optimization process, while also benefiting from the evaluation steps of GI. As a result, we believe that the combination of LLMs and GI has the capability to significantly aid developers in optimizing their software.","PeriodicalId":414492,"journal":{"name":"2023 IEEE/ACM International Workshop on Genetic Improvement (GI)","volume":"35 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131721496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：