{"id":"W2950973902","doi":"10.48550/arxiv.1811.08933","title":"Analyzing Machine Learning Workloads Using a Detailed GPU Simulator","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"MNIST database; General-purpose computing on graphics processing units; Computer science; CUDA; Parallel computing; Partition (number theory); Deep learning; Speedup; Dram; Microarchitecture; Computer architecture; Artificial intelligence; Operating system; Graphics; Computer hardware","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002125271,0.0004097265,0.0004125407,0.0003218361,0.0005081428,0.000160607,0.002048193,0.0002668819,0.00003599361],"category_scores_gemma":[0.00005297094,0.0004901077,0.000243563,0.001450148,0.0001461061,0.0004665802,0.003252999,0.0009970084,0.0001089585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003214542,"about_ca_system_score_gemma":0.0001339442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004128763,"about_ca_topic_score_gemma":0.00003387389,"domain_scores_codex":[0.9974303,0.000187147,0.0002778863,0.001472543,0.0001049772,0.0005271792],"domain_scores_gemma":[0.9974161,0.0002014771,0.0004615116,0.001484275,0.0002028328,0.000233806],"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":[0.00001293688,0.00003105231,0.01212274,0.00001743783,0.00005953747,0.00007318635,0.00005352311,0.9777869,0.0001374339,0.009051815,0.00001683442,0.0006365853],"study_design_scores_gemma":[0.0002619136,0.00002577284,0.000339426,0.00009502607,0.00007419697,0.000005169061,0.000007958432,0.9828295,0.0001299351,0.01508285,0.0006618847,0.0004863866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2965632,0.0001311546,0.7021761,0.00003365033,0.000212922,0.0002332194,0.000003283162,0.0004045644,0.0002419161],"genre_scores_gemma":[0.9762667,0.0001186984,0.02263922,0.00005515357,0.0001945861,0.000001200508,0.00001245261,0.00003661177,0.0006753821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6797035,"threshold_uncertainty_score":0.9997551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07782706764600732,"score_gpt":0.2240376366250882,"score_spread":0.1462105689790809,"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."}}