{"id":"W7133031893","doi":"","title":"Mist: Co-Optimize Memory Optimizations with Parallelism for Large Scale Distributed Training","year":2024,"lang":"","type":"dissertation","venue":"TSpace","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Toronto","keywords":"Pipeline (software); Schedule; Speedup; Parallelism (grammar); Distributed memory; Key (lock); Scale (ratio); Integer programming","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004436308,0.0009810751,0.0004324152,0.0003553378,0.0004179966,0.0005336417,0.001548215,0.0004480183,0.005132256],"category_scores_gemma":[0.001432993,0.0003269887,0.0004065202,0.0005284187,0.0004891757,0.001075452,0.0009188175,0.001121829,0.000921802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006104137,"about_ca_system_score_gemma":0.00188927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004898572,"about_ca_topic_score_gemma":0.009368295,"domain_scores_codex":[0.9996965,0.00005729637,0.00001640298,0.00008042397,0.00009300792,0.00005644638],"domain_scores_gemma":[0.9994955,0.0002015085,0.0000473554,0.0001228637,0.00008796054,0.00004486385],"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":[0.0003580516,0.0002691092,0.001918038,0.0002353119,0.00007490812,0.0001117781,0.000147676,0.6641849,0.02534223,0.009536264,0.01327133,0.2845503],"study_design_scores_gemma":[0.00003335577,0.00005995233,0.0001675422,0.000005741584,0.000008242325,0.00001654564,0.00001857502,0.9908963,0.004523282,0.002228379,0.002036452,0.00000572387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04443584,0.0003863175,0.9331988,0.0002250291,0.00007842927,0.0001095913,0.0001877796,0.01356988,0.007808351],"genre_scores_gemma":[0.5174733,0.000210979,0.4753405,0.0001801996,0.00004143273,0.0002603822,0.0007164121,0.001056496,0.004720267],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005132256,"threshold_uncertainty_score":0.01716912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02881691282966678,"score_gpt":0.3375832647109168,"score_spread":0.30876635188125,"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."}}