Matches in SemOpenAlex for { <https://semopenalex.org/work/W2156560068> ?p ?o ?g. }
- W2156560068 endingPage "327" @default.
- W2156560068 startingPage "296" @default.
- W2156560068 abstract "Tuning compiler optimizations for rapidly evolving hardware makes porting and extending an optimizing compiler for each new platform extremely challenging. Iterative optimization is a popular approach to adapting programs to a new architecture automatically using feedback-directed compilation. However, the large number of evaluations required for each program has prevented iterative compilation from widespread take-up in production compilers. Machine learning has been proposed to tune optimizations across programs systematically but is currently limited to a few transformations, long training phases and critically lacks publicly released, stable tools. Our approach is to develop a modular, extensible, self-tuning optimization infrastructure to automatically learn the best optimizations across multiple programs and architectures based on the correlation between program features, run-time behavior and optimizations. In this paper we describe Milepost GCC, the first publicly-available open-source machine learning-based compiler. It consists of an Interactive Compilation Interface (ICI) and plugins to extract program features and exchange optimization data with the cTuning.org open public repository. It automatically adapts the internal optimization heuristic at function-level granularity to improve execution time, code size and compilation time of a new program on a given architecture. Part of the MILEPOST technology together with low-level ICI-inspired plugin framework is now included in the mainline GCC. We developed machine learning plugins based on probabilistic and transductive approaches to predict good combinations of optimizations. Our preliminary experimental results show that it is possible to automatically reduce the execution time of individual MiBench programs, some by more than a factor of 2, while also improving compilation time and code size. On average we are able to reduce the execution time of the MiBench benchmark suite by 11% for the ARC reconfigurable processor. We also present a realistic multi-objective optimization scenario for Berkeley DB library using Milepost GCC and improve execution time by approximately 17%, while reducing compilation time and code size by 12% and 7% respectively on Intel Xeon processor." @default.
- W2156560068 created "2016-06-24" @default.
- W2156560068 creator A5000532071 @default.
- W2156560068 creator A5005850474 @default.
- W2156560068 creator A5005906959 @default.
- W2156560068 creator A5011820045 @default.
- W2156560068 creator A5023657363 @default.
- W2156560068 creator A5027001025 @default.
- W2156560068 creator A5027157407 @default.
- W2156560068 creator A5030275930 @default.
- W2156560068 creator A5038498641 @default.
- W2156560068 creator A5039109446 @default.
- W2156560068 creator A5040252809 @default.
- W2156560068 creator A5053657595 @default.
- W2156560068 creator A5060154788 @default.
- W2156560068 creator A5077533727 @default.
- W2156560068 creator A5080713659 @default.
- W2156560068 creator A5080877258 @default.
- W2156560068 creator A5083325184 @default.
- W2156560068 date "2011-01-07" @default.
- W2156560068 modified "2023-09-26" @default.
- W2156560068 title "Milepost GCC: Machine Learning Enabled Self-tuning Compiler" @default.
- W2156560068 cites W1509875415 @default.
- W2156560068 cites W1522561852 @default.
- W2156560068 cites W1708603942 @default.
- W2156560068 cites W1844404537 @default.
- W2156560068 cites W1990832096 @default.
- W2156560068 cites W1991495385 @default.
- W2156560068 cites W2033145463 @default.
- W2156560068 cites W2056579078 @default.
- W2156560068 cites W2060533244 @default.
- W2156560068 cites W2064823029 @default.
- W2156560068 cites W2076290291 @default.
- W2156560068 cites W2081211681 @default.
- W2156560068 cites W2093708648 @default.
- W2156560068 cites W2099625934 @default.
- W2156560068 cites W2100933152 @default.
- W2156560068 cites W2101924328 @default.
- W2156560068 cites W2112502633 @default.
- W2156560068 cites W2116243944 @default.
- W2156560068 cites W2133376191 @default.
- W2156560068 cites W2136386610 @default.
- W2156560068 cites W2137311321 @default.
- W2156560068 cites W2138547938 @default.
- W2156560068 cites W2142079700 @default.
- W2156560068 cites W2143124065 @default.
- W2156560068 cites W2149207009 @default.
- W2156560068 cites W2157070686 @default.
- W2156560068 cites W2158600037 @default.
- W2156560068 cites W2166879008 @default.
- W2156560068 cites W2171539112 @default.
- W2156560068 cites W2534461193 @default.
- W2156560068 cites W2911717821 @default.
- W2156560068 cites W3136479147 @default.
- W2156560068 cites W4205854416 @default.
- W2156560068 cites W4213200025 @default.
- W2156560068 cites W4235343816 @default.
- W2156560068 cites W4238708425 @default.
- W2156560068 cites W4243305730 @default.
- W2156560068 cites W2103074808 @default.
- W2156560068 doi "https://doi.org/10.1007/s10766-010-0161-2" @default.
- W2156560068 hasPublicationYear "2011" @default.
- W2156560068 type Work @default.
- W2156560068 sameAs 2156560068 @default.
- W2156560068 citedByCount "177" @default.
- W2156560068 countsByYear W21565600682012 @default.
- W2156560068 countsByYear W21565600682013 @default.
- W2156560068 countsByYear W21565600682014 @default.
- W2156560068 countsByYear W21565600682015 @default.
- W2156560068 countsByYear W21565600682016 @default.
- W2156560068 countsByYear W21565600682017 @default.
- W2156560068 countsByYear W21565600682018 @default.
- W2156560068 countsByYear W21565600682019 @default.
- W2156560068 countsByYear W21565600682020 @default.
- W2156560068 countsByYear W21565600682021 @default.
- W2156560068 countsByYear W21565600682022 @default.
- W2156560068 countsByYear W21565600682023 @default.
- W2156560068 crossrefType "journal-article" @default.
- W2156560068 hasAuthorship W2156560068A5000532071 @default.
- W2156560068 hasAuthorship W2156560068A5005850474 @default.
- W2156560068 hasAuthorship W2156560068A5005906959 @default.
- W2156560068 hasAuthorship W2156560068A5011820045 @default.
- W2156560068 hasAuthorship W2156560068A5023657363 @default.
- W2156560068 hasAuthorship W2156560068A5027001025 @default.
- W2156560068 hasAuthorship W2156560068A5027157407 @default.
- W2156560068 hasAuthorship W2156560068A5030275930 @default.
- W2156560068 hasAuthorship W2156560068A5038498641 @default.
- W2156560068 hasAuthorship W2156560068A5039109446 @default.
- W2156560068 hasAuthorship W2156560068A5040252809 @default.
- W2156560068 hasAuthorship W2156560068A5053657595 @default.
- W2156560068 hasAuthorship W2156560068A5060154788 @default.
- W2156560068 hasAuthorship W2156560068A5077533727 @default.
- W2156560068 hasAuthorship W2156560068A5080713659 @default.
- W2156560068 hasAuthorship W2156560068A5080877258 @default.
- W2156560068 hasAuthorship W2156560068A5083325184 @default.
- W2156560068 hasBestOaLocation W21565600683 @default.
- W2156560068 hasConcept C101468663 @default.
- W2156560068 hasConcept C106251023 @default.