{"id":"W2883965613","doi":"10.1145/3203217.3203243","title":"Taming irregular applications via advanced dynamic parallelism on GPUs","year":2018,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Computer science; Kernel (algebra); Bottleneck; Overhead (engineering); Parallelism (grammar); Parallel computing; Workload; CUDA; Data parallelism; Computer architecture; Embedded system; Operating system","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":[0.0001415703,0.0001274584,0.0001120429,0.0001148481,0.0002498503,0.00008597001,0.000764426,0.00005535267,0.00001928419],"category_scores_gemma":[0.000009443635,0.0001171742,0.00004396807,0.000374073,0.00006000768,0.0001916838,0.0001577966,0.00008355178,0.0002417486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004196571,"about_ca_system_score_gemma":0.00002242052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005949519,"about_ca_topic_score_gemma":0.000002393831,"domain_scores_codex":[0.9989666,0.0000334765,0.0001852823,0.0004043391,0.0001795484,0.0002306977],"domain_scores_gemma":[0.998973,0.00004697626,0.00007567695,0.0007162881,0.000116389,0.00007174104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008627951,0.0001521308,0.00001988882,0.00000932789,0.00001797606,0.000002587737,0.0004478231,0.007431892,0.001704796,0.2155429,0.002899573,0.7717625],"study_design_scores_gemma":[0.0002168712,0.000155611,0.0001916143,0.00001629707,0.000002319021,0.000007386896,0.000007639197,0.9452623,0.005533488,0.01733078,0.03101566,0.0002600916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006276367,0.00004048527,0.9770942,0.0006130004,0.0001173245,0.0002292485,3.684557e-7,0.001261475,0.02001628],"genre_scores_gemma":[0.459852,0.00001290995,0.5377734,0.0007314544,0.00004824119,0.00005448458,0.000003203851,0.000008323314,0.001515971],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9378303,"threshold_uncertainty_score":0.4778224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007174581648149097,"score_gpt":0.2629762581007464,"score_spread":0.2558016764525973,"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."}}