{"id":"W4308084253","doi":"10.1109/cases55004.2022.00008","title":"Work-in-Progress: MLGOPerf: An ML Guided Inliner to Optimize Performance","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Speedup; Computer science; Spec#; Reinforcement learning; Code (set theory); Parallel computing; Function (biology); Performance improvement; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001473925,0.002069935,0.0009695215,0.0004578208,0.0004056825,0.001311553,0.003291751,0.001663176,0.0109315],"category_scores_gemma":[0.003364592,0.0006291164,0.0007334746,0.0002740162,0.0007071795,0.001980988,0.001582763,0.003395245,0.006008806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007742761,"about_ca_system_score_gemma":0.001204016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00302074,"about_ca_topic_score_gemma":0.003902072,"domain_scores_codex":[0.9990482,0.000262689,0.00003414717,0.000236498,0.0002723992,0.0001460245],"domain_scores_gemma":[0.9989525,0.0003267177,0.00006694238,0.0003297107,0.0002132818,0.0001108641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001038662,0.0008441155,0.00314496,0.0004506407,0.0001982153,0.0002232127,0.0003094821,0.2969946,0.04064983,0.007178581,0.07630973,0.5726579],"study_design_scores_gemma":[0.0001262347,0.0004443744,0.0003960692,0.00003372053,0.00003261718,0.00007453596,0.00001845076,0.950481,0.02739121,0.002805244,0.01815951,0.00003700546],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06004886,0.001942663,0.7633187,0.001229865,0.0006637537,0.0002774944,0.0007849533,0.1599613,0.01177257],"genre_scores_gemma":[0.3984024,0.000604316,0.5531504,0.001304539,0.0002579174,0.0003127957,0.003449772,0.02255188,0.01996602],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0109315,"threshold_uncertainty_score":0.03656948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04182869328765641,"score_gpt":0.3183737498113519,"score_spread":0.2765450565236955,"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."}}