{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003281785,0.000690248,0.0004382837,0.0005263173,0.0003534246,0.0006137915,0.00123214,0.0004187831,0.003353941],"category_scores_gemma":[0.0008083782,0.0002293418,0.0004288944,0.0004021682,0.0002787415,0.0004306099,0.0005841865,0.0006695731,0.0006729907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006492634,"about_ca_system_score_gemma":0.0009516762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003511847,"about_ca_topic_score_gemma":0.004286402,"domain_scores_codex":[0.9996854,0.00003946491,0.00001029421,0.00005046041,0.0001637459,0.00005066385],"domain_scores_gemma":[0.99979,0.00005072074,0.00002167871,0.00003960048,0.00008095356,0.00001705638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002397784,0.0002055912,0.002701334,0.0002272872,0.00007370271,0.0002344198,0.0001788524,0.5966706,0.1140841,0.0132487,0.009340758,0.262795],"study_design_scores_gemma":[0.00001625825,0.00005096206,0.0003925289,0.000008428174,0.000009083501,0.00004360833,0.0000135649,0.977948,0.01562368,0.00142559,0.004455801,0.00001247823],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04894391,0.0002982052,0.9276707,0.000106586,0.00004775958,0.0001005313,0.0001462351,0.01271387,0.009972177],"genre_scores_gemma":[0.6116909,0.0001420863,0.380072,0.0001171095,0.00002201957,0.0002352448,0.0003614158,0.001759881,0.005599333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003511847,"threshold_uncertainty_score":0.0112201,"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."}}