{"id":"W1970815868","doi":"10.1109/hpca.2014.6835936","title":"A scalable multi-path microarchitecture for efficient GPU control flow","year":2014,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Advanced Micro Devices","keywords":"Computer science; Parallel computing; Serialization; Microarchitecture; Instruction set; Scalability; Control flow; Speedup; General-purpose computing on graphics processing units; Thread (computing); Graphics; Computer graphics (images); Operating system; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004214484,0.0001276852,0.0001637312,0.00008276328,0.0001589147,0.0001301147,0.0005965712,0.00006100737,0.000005765473],"category_scores_gemma":[0.0000898506,0.0001013261,0.00008501484,0.0001634687,0.000026519,0.00004325532,0.00009202302,0.00007565608,0.00001961566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001778024,"about_ca_system_score_gemma":0.00002719268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001018533,"about_ca_topic_score_gemma":0.000002117611,"domain_scores_codex":[0.9990094,0.00006299336,0.0001738803,0.0003504222,0.0001170447,0.0002862558],"domain_scores_gemma":[0.9991818,0.0001538838,0.00005697829,0.0004137341,0.0001122488,0.00008135918],"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":[0.000021211,0.0002404309,0.0001191468,0.00003335659,0.0000214071,8.812726e-7,0.0004117092,0.8858446,0.001577224,0.02511369,0.01354141,0.07307492],"study_design_scores_gemma":[0.0009151608,0.00008443241,0.00006620766,0.00001148337,0.000002893989,0.000004187971,0.000001328212,0.9878068,0.002881584,0.0005013501,0.007578479,0.0001460721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003702493,0.00003856283,0.9963744,0.0007590815,0.0001479739,0.0003527896,0.000002702057,0.0008314821,0.001122752],"genre_scores_gemma":[0.2580904,7.436032e-7,0.7402951,0.0009554943,0.00004108516,0.00002989878,0.000001886245,0.000007495378,0.000577878],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2577202,"threshold_uncertainty_score":0.4131958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009141866591213008,"score_gpt":0.2375676630856592,"score_spread":0.2284257964944462,"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."}}