{"id":"W2160428323","doi":"10.1109/micro.2007.30","title":"Dynamic Warp Formation and Scheduling for Efficient GPU Control Flow","year":2007,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":727,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; SIMD; Parallel computing; Control flow; Instruction set; Overhead (engineering); Scheduling (production processes); Graphics; Computer architecture; Embedded system; Operating system; 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":[],"consensus_categories":[],"category_scores_codex":[0.0006039584,0.0000681443,0.00008009531,0.00009254932,0.0001308629,0.0000877322,0.000169864,0.00003818264,9.275765e-7],"category_scores_gemma":[0.00003652702,0.00005939133,0.00002686509,0.0001126492,0.0000126922,0.0001485156,0.00004324449,0.00003833267,0.000002609793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002582123,"about_ca_system_score_gemma":0.00001093121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001915435,"about_ca_topic_score_gemma":0.000002387539,"domain_scores_codex":[0.9993921,0.00001112725,0.0001717301,0.0001577594,0.00008985672,0.000177428],"domain_scores_gemma":[0.9995568,0.0001164032,0.00005252056,0.0001422191,0.00008433688,0.00004771815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003025462,0.00006973612,0.00007140617,0.00004520603,0.00001347401,0.00000172975,0.0007528592,0.7082294,0.0009105456,0.05713686,0.0003600056,0.2323785],"study_design_scores_gemma":[0.0004025054,0.00004222662,0.0001277276,0.000009093666,0.000001942074,0.000006108875,0.00001025525,0.9968829,0.001347546,0.0008169822,0.0002704783,0.00008225004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0053651,0.00007227235,0.9928263,0.0003426,0.00008551082,0.0002390562,6.312409e-7,0.0004391553,0.0006293186],"genre_scores_gemma":[0.4840815,0.000002758675,0.515694,0.0001739053,0.000006739163,0.000003797046,0.000001273119,0.00000216449,0.00003385348],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4787164,"threshold_uncertainty_score":0.2421908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00861684684107671,"score_gpt":0.2552551377058643,"score_spread":0.2466382908647876,"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."}}