{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:30:20Z","timestamp":1769747420423,"version":"3.49.0"},"reference-count":25,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2014,2,1]],"date-time":"2014-02-01T00:00:00Z","timestamp":1391212800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004965","name":"Sixth Framework Programme","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004965","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Archit. Code Optim."],"published-print":{"date-parts":[[2014,2]]},"abstract":"<jats:p>Recent work has shown that machine learning can automate and in some cases outperform handcrafted compiler optimisations. Central to such an approach is that machine learning techniques typically rely upon summaries or features of the program. The quality of these features is critical to the accuracy of the resulting machine learned algorithm; no machine learning method will work well with poorly chosen features. However, due to the size and complexity of programs, theoretically there are an infinite number of potential features to choose from. The compiler writer now has to expend effort in choosing the best features from this space. This article develops a novel mechanism to automatically find those features that most improve the quality of the machine learned heuristic. The feature space is described by a grammar and is then searched with genetic programming and predictive modelling. We apply this technique to loop unrolling in GCC 4.3.1 and evaluate our approach on a Pentium 6. On a benchmark suite of 57 programs, GCCs hard-coded heuristic achieves only 3% of the maximum performance available, whereas a state-of-the-art machine learning approach with hand-coded features obtains 59%. Our feature generation technique is able to achieve 76% of the maximum available speedup, outperforming existing approaches.<\/jats:p>","DOI":"10.1145\/2536688","type":"journal-article","created":{"date-parts":[[2014,3,18]],"date-time":"2014-03-18T12:09:07Z","timestamp":1395144547000},"page":"1-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Automatic feature generation for machine learning--based optimising compilation"],"prefix":"10.1145","volume":"11","author":[{"given":"Hugh","family":"Leather","sequence":"first","affiliation":[{"name":"University of Edinburgh, St, Edinburgh, Midlothian"}]},{"given":"Edwin","family":"Bonilla","sequence":"additional","affiliation":[{"name":"NICTA and Australian National University, Australia"}]},{"given":"Michael","family":"O'boyle","sequence":"additional","affiliation":[{"name":"University of Edinburgh, St, Edinburgh, Midlothian"}]}],"member":"320","published-online":{"date-parts":[[2014,2]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2006.37"},{"key":"e_1_2_1_2_1","volume-title":"Ullman","author":"Aho Alfred V.","year":"1986"},{"key":"e_1_2_1_3_1","volume-title":"Evolutionary Programming, Genetic Algorithms","author":"Back Thomas"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/123465.123507"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/996841.996864"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1167473.1167492"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1065910.1065921"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/314403.314414"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015729001611"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669124"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(97)00043-X"},{"key":"e_1_2_1_12_1","first-page":"24","volume-title":"From Animals to Animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior","author":"Koza John R.","year":"1990"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/996841.996863"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2009.21"},{"key":"e_1_2_1_15_1","volume-title":"Proceedings of the 1998 Conference on Advances in Neural Information Processing Systems II. MIT Press","author":"McGovern Amy","year":"1999"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/646053.677574"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2006.38"},{"key":"e_1_2_1_18_1","volume-title":"Programs for Machine Learning. Morgan Kaufmann","author":"Quinlan J. Ross"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/646806.706289"},{"key":"e_1_2_1_20_1","volume-title":"Smola","author":"Sch\u00f6lkopf Bernhard","year":"2001"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.29"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781141"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1504176.1504189"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1504176.1504189"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781140"}],"container-title":["ACM Transactions on Architecture and Code Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2536688","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2536688","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:14:41Z","timestamp":1750277681000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2536688"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,2]]},"references-count":25,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,2]]}},"alternative-id":["10.1145\/2536688"],"URL":"https:\/\/doi.org\/10.1145\/2536688","relation":{},"ISSN":["1544-3566","1544-3973"],"issn-type":[{"value":"1544-3566","type":"print"},{"value":"1544-3973","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,2]]},"assertion":[{"value":"2007-02-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2009-06-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2014-02-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}