{"id":"W2175055016","doi":"10.1016/j.cpc.2015.10.027","title":"GPU-accelerated adjoint algorithmic differentiation","year":2015,"lang":"en","type":"article","venue":"Computer Physics Communications","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Queen's University; Bundesministerium für Bildung und Forschung","keywords":"Computer science; Parallel computing; Speedup; SIMD; Automatic differentiation; CUDA; Thread (computing); Vectorization (mathematics); Memory bandwidth; Computation; Graphics; Software; Computational science; Algorithm; Computer graphics (images)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004280298,0.0001226482,0.0001302736,0.00004055074,0.00008176953,0.00007229982,0.0004793115,0.00004122176,0.000002373717],"category_scores_gemma":[0.000002452176,0.0001334681,0.00004356108,0.0001898796,0.00004503607,0.0001434129,0.0002502896,0.0001747527,0.00005439861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005789259,"about_ca_system_score_gemma":0.00001692176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001336323,"about_ca_topic_score_gemma":0.000003248503,"domain_scores_codex":[0.9994657,0.00004971554,0.0001603303,0.00009953364,0.00009509355,0.0001296395],"domain_scores_gemma":[0.9985626,0.00003369103,0.00003417409,0.001151479,0.0001499457,0.00006805593],"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":[0.00001026363,0.0008053777,0.0006926152,0.00003777982,0.0004832309,0.000005632272,0.004560631,0.1284521,0.02214015,0.06483398,0.1441345,0.6338438],"study_design_scores_gemma":[0.0001521772,0.00001696324,0.0005517382,0.00002632176,0.0000114871,0.00000236517,0.00001042693,0.9842231,0.002302024,0.007862026,0.004686467,0.0001549397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01004191,0.0003178773,0.9835736,0.0001459258,0.0002909354,0.0001585936,0.000005913633,0.00145612,0.004009105],"genre_scores_gemma":[0.8572986,0.00008369674,0.142188,0.00006433364,0.0001786104,0.0000234755,0.0001231674,0.00002768592,0.00001249489],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.855771,"threshold_uncertainty_score":0.544267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1016604335182507,"score_gpt":0.2736752447108633,"score_spread":0.1720148111926126,"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."}}