{"id":"W2293015622","doi":"10.1109/icpp.2015.39","title":"Automatic Performance Tuning of Stencil Computations on GPUs","year":2015,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Stencil; Computer science; Heuristics; Computation; Parallel computing; CUDA; Graphics; Titan (rocket family); Heuristic; Computational science; Algorithm; Artificial intelligence; Computer graphics (images)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001221054,0.001242354,0.001069355,0.001078865,0.0007020737,0.001185494,0.00185142,0.0007700216,0.001945213],"category_scores_gemma":[0.006239293,0.0004808732,0.0004783264,0.0009179289,0.0008328481,0.001247886,0.001023902,0.0009714576,0.0005136668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008675783,"about_ca_system_score_gemma":0.001205151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002356934,"about_ca_topic_score_gemma":0.003147204,"domain_scores_codex":[0.9989022,0.0003206715,0.00006163349,0.0002181609,0.0002830259,0.0002142163],"domain_scores_gemma":[0.9977207,0.001120573,0.0001791121,0.0005287367,0.0003262398,0.0001246323],"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":[0.0007093992,0.0004415504,0.009909684,0.0002904392,0.0001455065,0.0002165004,0.0004232432,0.7237512,0.05546451,0.003773279,0.003095898,0.2017788],"study_design_scores_gemma":[0.00007364789,0.0001621067,0.001390766,0.00002144024,0.00002526504,0.00004361642,0.0001215924,0.9683549,0.02509368,0.002952438,0.00172665,0.00003385834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8320493,0.0007057537,0.1479253,0.0003090774,0.00007057645,0.0001616317,0.0002478216,0.007475908,0.0110546],"genre_scores_gemma":[0.9329692,0.0001062332,0.06533337,0.00008899219,0.00001168989,0.00009208869,0.0002344399,0.0006684526,0.0004954477],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002356934,"threshold_uncertainty_score":0.006507456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04905661481208288,"score_gpt":0.2735200655808355,"score_spread":0.2244634507687526,"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."}}