{"id":"W4381389666","doi":"10.1145/3589236.3589241","title":"GPU Auto-tuning Framework for Optimal Performance and Power Consumption","year":2023,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Loop unrolling; Computer science; Parallel computing; Code (set theory); Sorting; Energy consumption; Computer engineering; Tuner; Code generation; Power (physics); General-purpose computing on graphics processing units; Algorithm; Compiler; Graphics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002783105,0.00007593088,0.00008179067,0.0001035238,0.000181364,0.0001273992,0.0002319161,0.00006069541,0.000009486131],"category_scores_gemma":[0.0000472834,0.00007043294,0.00002197015,0.0002212481,0.00002619183,0.0002382838,0.0001560333,0.00007291322,0.00003126899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009527157,"about_ca_system_score_gemma":0.00001545798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.156275e-7,"about_ca_topic_score_gemma":7.01273e-8,"domain_scores_codex":[0.9993665,0.00001442858,0.0001165876,0.0002248456,0.00008947495,0.0001881946],"domain_scores_gemma":[0.9995182,0.0001560682,0.0000398714,0.0001943811,0.00004658512,0.00004492186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000419127,0.00005667969,0.01031309,0.0001425525,0.00004168984,0.000006244237,0.002895427,0.05060779,0.0003797735,0.795791,0.03303751,0.1066864],"study_design_scores_gemma":[0.00009730821,0.00006829147,0.004398283,0.00002976529,0.000001212465,0.000004336458,0.000007939996,0.9903546,0.0004507359,0.002451602,0.00202636,0.000109553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04442232,0.00002393284,0.9527392,0.0004169487,0.00012896,0.0001182087,5.12936e-7,0.001490751,0.0006591121],"genre_scores_gemma":[0.37116,0.00005789859,0.6281312,0.0001714593,0.0000141816,0.00001408708,0.000001885664,0.000004775679,0.0004444601],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9397468,"threshold_uncertainty_score":0.2872172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03043240931931272,"score_gpt":0.2950581890938484,"score_spread":0.2646257797745357,"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."}}