{"id":"W2800041898","doi":"10.1155/2018/6093054","title":"A Strategy for Automatic Performance Tuning of Stencil Computations on GPUs","year":2018,"lang":"en","type":"article","venue":"Scientific Programming","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Stencil; Computer science; Computation; Parallel computing; Graphics; Heuristic; CUDA; Set (abstract data type); Algorithm; Computational science; Artificial intelligence; Computer graphics (images)","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":[0.0009584835,0.0001090773,0.0001407205,0.0002460091,0.000593439,0.0003964505,0.0006878791,0.0000380934,0.000003173379],"category_scores_gemma":[0.00008371835,0.0001017517,0.00005876461,0.0008873729,0.0002387836,0.0002899002,0.0001079802,0.0000635219,0.00001370068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003296591,"about_ca_system_score_gemma":0.0001469345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003716428,"about_ca_topic_score_gemma":0.000002309171,"domain_scores_codex":[0.998656,0.00003766883,0.0003045744,0.0003902506,0.0003021923,0.0003092618],"domain_scores_gemma":[0.9987519,0.0001026918,0.0001910041,0.0004402875,0.0004511939,0.00006288936],"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":[0.000004141104,0.00011555,0.0001207629,0.00008883411,0.00001203219,5.11409e-7,0.001484457,0.008045792,0.0003526996,0.01286494,0.0007937411,0.9761165],"study_design_scores_gemma":[0.0001678153,0.0004467797,0.0001518418,0.0001139868,0.000003991572,0.000003163484,0.00004182267,0.9896249,0.005775,0.001033032,0.002515605,0.0001221028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07012089,0.0000288754,0.9277008,0.00005038841,0.0004881828,0.0003716527,0.000001682659,0.0005287532,0.000708746],"genre_scores_gemma":[0.594773,3.874929e-7,0.4049633,0.00001584829,0.00002515565,0.00002529278,0.000004134877,0.000004713729,0.0001881457],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9815791,"threshold_uncertainty_score":0.4564313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04995517516243535,"score_gpt":0.3031897655030896,"score_spread":0.2532345903406543,"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."}}