{"id":"W2110195531","doi":"10.1109/ispass.2010.5452013","title":"Demystifying GPU microarchitecture through microbenchmarking","year":2010,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":447,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"CUDA; Computer science; Speedup; Parallel computing; Suite; Graphics; Microarchitecture; General-purpose computing on graphics processing units; Architecture; Abstraction; Correctness; Computer architecture; Coprocessor; Computation; Computer graphics (images); Programming language","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":[0.000197972,0.0001278789,0.000109885,0.00007234953,0.0002084974,0.0002120491,0.0009147834,0.00009066064,0.0000479472],"category_scores_gemma":[0.00003737633,0.0001097891,0.00005672671,0.0002948178,0.00004001965,0.0002493704,0.0002983424,0.000338622,0.00003161083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000861892,"about_ca_system_score_gemma":0.00003615651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003558906,"about_ca_topic_score_gemma":0.00001459066,"domain_scores_codex":[0.9990802,0.00003051492,0.000171376,0.0003391765,0.0001192624,0.0002594901],"domain_scores_gemma":[0.9992719,0.00006891047,0.0000617001,0.0004897394,0.00005676521,0.0000510186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005743967,0.0001290908,0.001752144,0.0000376095,0.00003591879,0.00002842077,0.003186767,0.002998668,0.3835478,0.4355811,0.02649738,0.1461994],"study_design_scores_gemma":[0.0006213055,0.0000825271,0.001420946,0.00006718053,0.000009441254,0.0004409812,0.00002595071,0.2886967,0.4116576,0.08778209,0.2079394,0.001255871],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006944655,0.00004568155,0.9613798,0.001398964,0.0003858091,0.00008189215,2.674538e-7,0.001069855,0.02869308],"genre_scores_gemma":[0.3359655,0.000004635727,0.6628664,0.0008065273,0.0000608575,0.00000296823,0.000001138657,0.000006046568,0.0002859462],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3477989,"threshold_uncertainty_score":0.447707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01231577622013279,"score_gpt":0.2568736384592354,"score_spread":0.2445578622391027,"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."}}