{"id":"W2783614532","doi":"10.1145/3197978","title":"A Survey on Compiler Autotuning using Machine Learning","year":2018,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":224,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Compiler; Optimizing compiler; Loop optimization; Leverage (statistics); Interprocedural optimization; Pace; Parallel computing; Artificial intelligence; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01294191,0.001049822,0.002377106,0.000836907,0.0009923284,0.0007495499,0.005059957,0.0005342604,0.00001145251],"category_scores_gemma":[0.002623691,0.0009717431,0.0005484887,0.002110145,0.0001318651,0.0002044495,0.003444215,0.001597795,0.0001750151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000292391,"about_ca_system_score_gemma":0.0003505079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007400461,"about_ca_topic_score_gemma":0.00003209661,"domain_scores_codex":[0.9842545,0.01097922,0.001408015,0.001683337,0.000685667,0.000989252],"domain_scores_gemma":[0.9906126,0.004774376,0.001455816,0.002507939,0.0004169828,0.0002323323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001810547,0.0001052456,0.0006785855,0.001110757,0.000197069,0.00003376366,0.0001472985,0.006959576,1.034923e-7,0.0001584201,0.002343517,0.9882638],"study_design_scores_gemma":[0.0001954602,0.0002095592,0.0004082438,0.009041241,0.00006601941,0.00005700695,7.624415e-7,0.7111483,0.000001614211,0.00006473729,0.2774907,0.001316387],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.00001184289,0.4611945,0.535966,0.000009594472,0.0007712569,0.000324674,0.00001671801,0.001519746,0.0001856652],"genre_scores_gemma":[0.000288128,0.725359,0.2724788,0.0001985573,0.0005762164,0.000007493465,0.0005799245,0.0002274139,0.0002845119],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9869475,"threshold_uncertainty_score":0.9992733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1493865011485346,"score_gpt":0.3737570408707444,"score_spread":0.2243705397222097,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}