{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003106974,0.0001273323,0.0001747025,0.0001625385,0.0001349164,0.0001918091,0.0005009827,0.00005604202,0.0000832046],"category_scores_gemma":[0.00003669954,0.00011376,0.00006975901,0.00053593,0.00001042292,0.0003125455,0.0002766996,0.0001792261,0.00008706224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003869943,"about_ca_system_score_gemma":0.00003577297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002819115,"about_ca_topic_score_gemma":0.000001788806,"domain_scores_codex":[0.9989712,0.00008403812,0.0002080191,0.0003325217,0.0001557368,0.0002485301],"domain_scores_gemma":[0.999314,0.00008727914,0.00009681913,0.0003644155,0.00006945435,0.00006807863],"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":[0.000003418276,0.00002032624,0.07762082,0.000007278281,0.00001688536,0.000003449456,0.0001153737,0.9120245,0.0009602506,0.003629837,0.00003981235,0.005558074],"study_design_scores_gemma":[0.0001715875,0.00003116782,0.0003098874,0.00002488341,0.000003059423,0.000004711875,0.000003878821,0.9973428,0.001101131,0.0001964071,0.0006457099,0.0001647292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09488644,0.0001423517,0.9009407,0.00006154789,0.00009732285,0.00009573904,7.638225e-8,0.0009224144,0.002853425],"genre_scores_gemma":[0.6903403,0.000006406319,0.3084079,0.00009765408,0.00001847194,7.306716e-7,8.074613e-7,0.000007813893,0.001119865],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5954539,"threshold_uncertainty_score":0.4638998,"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."}}