{"id":"W2056966287","doi":"10.1109/cluster.2014.6968778","title":"To checkpoint or not to checkpoint: Understanding energy-performance-I/O tradeoffs in HPC checkpointing","year":2014,"lang":"en","type":"article","venue":"","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Los Alamos National Laboratory; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Fault tolerance; Scheduling (production processes); Overhead (engineering); Exploit; Energy consumption; Distributed computing; Supercomputer; Efficient energy use; Parallel computing; Embedded system; Operating system; Computer security","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007727087,0.0006311165,0.0004749093,0.0006636999,0.000382814,0.0009595449,0.0006524007,0.0006461365,0.0009403693],"category_scores_gemma":[0.004389445,0.0003497262,0.0002488267,0.0009053788,0.0007857265,0.001896879,0.000511636,0.0006990273,0.0001535703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001004231,"about_ca_system_score_gemma":0.0005202102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003090665,"about_ca_topic_score_gemma":0.003052443,"domain_scores_codex":[0.9997104,0.00007203369,0.00001421386,0.0000526003,0.00008648635,0.00006421484],"domain_scores_gemma":[0.9984965,0.001013668,0.000195453,0.000117388,0.0001298677,0.0000471337],"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":[0.0001192145,0.00009590636,0.005112709,0.0001153354,0.00002345888,0.00006119397,0.00007322778,0.9617117,0.01033627,0.004481426,0.0003431979,0.01752635],"study_design_scores_gemma":[0.000008737351,0.0000811674,0.004571948,0.00002272048,0.00001648157,0.00002770083,0.0001231143,0.980087,0.006937186,0.007567327,0.0005377354,0.00001887675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8197142,0.005669074,0.1636437,0.001438775,0.00005571055,0.00007739831,0.0002862569,0.0005132857,0.008601475],"genre_scores_gemma":[0.9900394,0.0009656309,0.008192508,0.00004490813,0.00001727674,0.00002393291,0.000080111,0.00008218076,0.0005541515],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003090665,"threshold_uncertainty_score":0.007286251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04731972437339088,"score_gpt":0.2645134748651125,"score_spread":0.2171937504917216,"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."}}