{"id":"W4402387922","doi":"10.1109/sbac-pad63648.2024.00012","title":"Exploiting Processor Heterogeneity to Improve Throughput and Reduce Latency for Deep Neural Network Inference","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Latency (audio); Inference; Throughput; Artificial neural network; Deep neural networks; Artificial intelligence; Computer architecture; Computer network; Operating system; Wireless; Telecommunications","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001329157,0.0001725907,0.0001474714,0.00003720842,0.0002236241,0.0003069873,0.0004921964,0.00004457173,0.000002195834],"category_scores_gemma":[0.00005929864,0.0001484793,0.00004454218,0.0006045627,0.0000302275,0.0007569355,0.0003942141,0.000120895,0.00001591815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002569773,"about_ca_system_score_gemma":0.00002947648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004760427,"about_ca_topic_score_gemma":0.00002873987,"domain_scores_codex":[0.9984233,0.00001631236,0.0002413397,0.0007540077,0.0001203655,0.0004446564],"domain_scores_gemma":[0.9990111,0.0003244017,0.00004197167,0.0003929511,0.00008309337,0.0001464838],"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":[0.0000150295,0.00003482111,0.0003092472,0.0001734212,0.00002741491,0.000007576746,0.0007479889,0.02406575,0.01031372,0.1949121,0.001144868,0.7682481],"study_design_scores_gemma":[0.0001111959,0.0001432021,0.0002923982,0.00004048933,0.000008596247,0.00001746777,0.00001583017,0.9433235,0.00759468,0.04500015,0.003148047,0.000304449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05216711,0.0005063642,0.9425695,0.002853126,0.000335308,0.0007629294,0.000002860953,0.000567147,0.0002356447],"genre_scores_gemma":[0.7614304,0.00002488288,0.2368655,0.0007436445,0.0003013216,0.0004926489,0.000001986238,0.00001671688,0.0001228745],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9192578,"threshold_uncertainty_score":0.6054809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03837820572122609,"score_gpt":0.3305765482937758,"score_spread":0.2921983425725497,"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."}}