{"id":"W4238323557","doi":"10.1109/micro.2007.4408272","title":"Dynamic Warp Formation and Scheduling for Efficient GPU Control Flow","year":2007,"lang":"en","type":"article","venue":"Proceedings of the ... annual International Symposium on Microarchitecture/Proceedings of the annual International Symposium on Microarchitecture","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; SIMD; Parallel computing; Control flow; Instruction set; Overhead (engineering); Scheduling (production processes); Graphics; Computer architecture; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001441556,0.0007359427,0.0006361419,0.0005612026,0.0006005449,0.0004484384,0.005158017,0.0003712069,0.000006812856],"category_scores_gemma":[0.0004096148,0.000545858,0.0006946085,0.0007200749,0.0005293719,0.0006205688,0.001277037,0.001016148,0.000003721094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004052439,"about_ca_system_score_gemma":0.00006221248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005651383,"about_ca_topic_score_gemma":0.0000137724,"domain_scores_codex":[0.9951622,0.00002684214,0.001373619,0.001147231,0.001503961,0.0007860959],"domain_scores_gemma":[0.9942098,0.0004238433,0.001660044,0.0003558726,0.003153833,0.0001965869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002432878,0.00102551,0.001350238,0.0004267292,0.0007354734,0.000001466296,0.01143482,0.1154238,0.8168414,0.03262643,0.005479335,0.01222191],"study_design_scores_gemma":[0.006223316,0.001771962,0.004232479,0.002305834,0.0002337629,0.0006435741,0.002000201,0.2126041,0.7366849,0.009353297,0.02195081,0.001995805],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8107293,0.0002472616,0.1139059,0.05563185,0.003904996,0.003507817,0.001528699,0.0005727643,0.009971451],"genre_scores_gemma":[0.9512435,0.00005849002,0.04555377,0.001776964,0.0004007003,0.00007183938,0.00002186244,0.00008462091,0.0007882795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1405142,"threshold_uncertainty_score":0.9996993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005189897355246917,"score_gpt":0.2404863028349994,"score_spread":0.2352964054797525,"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."}}