{"id":"W4323777068","doi":"10.2139/ssrn.4382942","title":"Pipeline Dnn Model Parallelism for Improving Performance of Embedded Applications","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Parallelism (grammar); Pipeline (software); Computer science; Parallel computing; Data parallelism; Task parallelism; Computer architecture; Operating system","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":[0.001335337,0.0001061902,0.0001486823,0.0001919642,0.0002406332,0.0000480332,0.0007708194,0.0000534736,4.917349e-7],"category_scores_gemma":[0.00003382843,0.00009955891,0.00009192526,0.0004402668,0.00002103733,0.0002471659,0.0001008511,0.000423868,0.000006006601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001417884,"about_ca_system_score_gemma":0.00100951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003216178,"about_ca_topic_score_gemma":0.000003897122,"domain_scores_codex":[0.9982458,0.0000222228,0.0003297098,0.0002045371,0.0001797629,0.001017983],"domain_scores_gemma":[0.9991805,0.00005468236,0.0002234579,0.0002865935,0.0002061051,0.00004865182],"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":[0.00002550768,0.00006297263,0.0000705495,0.00004662524,0.00003439174,2.621168e-7,0.0002876095,0.4806277,0.0008331221,0.3526966,0.001629173,0.1636854],"study_design_scores_gemma":[0.0002520001,0.00009586983,0.000009435507,0.000007317466,0.000005977131,0.0000215618,0.00002724434,0.8933167,0.0007732043,0.1051218,0.0002691149,0.00009967695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006856033,0.0002085661,0.9916771,0.0004621662,0.00004437777,0.0002197027,0.000001434329,0.0003088898,0.000221737],"genre_scores_gemma":[0.8486708,0.001098954,0.1479299,0.00008233559,0.0001185027,0.00006755649,0.00000649444,0.00001584768,0.002009596],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8437472,"threshold_uncertainty_score":0.4059895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.013506858523938,"score_gpt":0.2659282799848425,"score_spread":0.2524214214609045,"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."}}