{"id":"W2760837370","doi":"10.1109/infocom.2017.8057205","title":"Energy efficient real-time task scheduling on CPU-GPU hybrid clusters","year":2017,"lang":"en","type":"article","venue":"","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Frequency scaling; Computer science; Energy consumption; Parallel computing; Dynamic voltage scaling; Scheduling (production processes); Real-time computing; Scaling; GPU cluster; Embedded system; CUDA; Mathematical optimization","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":[0.0003872961,0.0001902787,0.0001808044,0.0001142144,0.000812638,0.0006523605,0.001974256,0.00003434057,0.00001329444],"category_scores_gemma":[0.00002512919,0.000154256,0.000112098,0.00007495175,0.00006556236,0.00002259648,0.00137054,0.0001005921,0.0003155833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006206164,"about_ca_system_score_gemma":0.00002370202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00032378,"about_ca_topic_score_gemma":0.000004078408,"domain_scores_codex":[0.9983048,0.00005283376,0.0002141002,0.0005993709,0.0004065567,0.0004223318],"domain_scores_gemma":[0.9978089,0.00007564817,0.0001664264,0.001767825,0.00003934841,0.0001417935],"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":[0.0000269344,0.0003972556,0.00007639157,0.00002718168,0.0001048864,0.0002327973,0.0005821559,0.5971958,0.001404925,0.08518619,0.01269754,0.302068],"study_design_scores_gemma":[0.0003211596,0.00008093301,0.0003373049,0.00004737854,0.000005184016,0.000007492433,0.00001213398,0.9906201,0.000766771,0.0002893403,0.007285931,0.0002262166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5318535,0.00001739768,0.2967032,0.003652664,0.0009115199,0.0001194666,6.660817e-7,0.0005855538,0.166156],"genre_scores_gemma":[0.9790457,0.000003501631,0.009918435,0.0006853933,0.0001964741,0.000004521773,8.399656e-7,0.00001343013,0.01013164],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4471923,"threshold_uncertainty_score":0.6290727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01087496494102459,"score_gpt":0.2282107139216306,"score_spread":0.2173357489806061,"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."}}