{"id":"W2901073342","doi":"10.1109/ispass.2019.00028","title":"Analyzing Machine Learning Workloads Using a Detailed GPU Simulator","year":2019,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; General-purpose computing on graphics processing units; Architecture; Code (set theory); Deep learning; FLOPS; Computer architecture; CUDA; Source code; Artificial intelligence; Parallel computing; Operating system; Programming language; Graphics","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":[0.0007249145,0.0008805337,0.0004530686,0.000529969,0.0004134046,0.0007002098,0.001378217,0.0007090289,0.002953797],"category_scores_gemma":[0.003654495,0.0004193244,0.0004409455,0.001030533,0.0004203173,0.001114771,0.0004447037,0.001069809,0.0005883976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001301305,"about_ca_system_score_gemma":0.00155662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01424001,"about_ca_topic_score_gemma":0.0135641,"domain_scores_codex":[0.9994112,0.0001382386,0.00004024169,0.00008903292,0.0002233275,0.00009791576],"domain_scores_gemma":[0.9982725,0.0007795821,0.00008441547,0.0003340261,0.0004271826,0.0001023028],"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":[0.0003370952,0.0002847862,0.01329548,0.0001831958,0.00009886792,0.0001800659,0.000166198,0.9289671,0.01178135,0.005013762,0.01196053,0.02773167],"study_design_scores_gemma":[0.00002143722,0.00005238971,0.0008829195,0.000004187762,0.00000753476,0.00001093442,0.00002172364,0.9931976,0.003459012,0.000707315,0.00162814,0.000006793106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8806682,0.0004998468,0.08270165,0.0006639708,0.0002537845,0.0002451885,0.004754012,0.01262081,0.01759264],"genre_scores_gemma":[0.9461882,0.000231734,0.04586038,0.0001909235,0.0000200551,0.0001500913,0.004528576,0.0007498416,0.002080205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01424001,"threshold_uncertainty_score":0.02831423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01685559285352249,"score_gpt":0.2641711338523954,"score_spread":0.2473155409988729,"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."}}