{"id":"W3177672515","doi":"10.1109/tcad.2020.3031240","title":"Enhancing the Utilization of Processing Elements in Spatial Deep Neural Network Accelerators","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Dataflow; Speedup; Computation; Pruning; Bandwidth (computing); Overhead (engineering); Artificial neural network; Memory bandwidth; Efficient energy use; Computer engineering; Computer architecture; Distributed computing; Embedded system; Parallel computing; Artificial intelligence; Computer network; Algorithm; Engineering","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":[0.000192172,0.0005009001,0.000198882,0.0004117033,0.0002524981,0.0004214726,0.001020765,0.0002606164,0.003785317],"category_scores_gemma":[0.0005036991,0.00020245,0.0003139075,0.0004675903,0.0002206003,0.001035325,0.0004116793,0.0003519335,0.0006359048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005481338,"about_ca_system_score_gemma":0.00089022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001692368,"about_ca_topic_score_gemma":0.004447702,"domain_scores_codex":[0.999819,0.00001869532,0.00001509443,0.00004008816,0.00006754417,0.00003950031],"domain_scores_gemma":[0.9997421,0.00006464009,0.00004052998,0.00005383337,0.00008420477,0.00001464956],"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":[0.000672153,0.0003073121,0.004719378,0.0006725226,0.0001157792,0.0004308271,0.0001625347,0.1411906,0.3031721,0.01788326,0.009070963,0.5216026],"study_design_scores_gemma":[0.00006483113,0.0007796916,0.002501872,0.00005468974,0.000102528,0.0004469291,0.00007407352,0.7649131,0.200012,0.006394659,0.02462261,0.00003301485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2874242,0.001424281,0.6886255,0.0004527114,0.0002303369,0.0000853185,0.0002315874,0.004697549,0.01682859],"genre_scores_gemma":[0.7790716,0.0003709341,0.2135264,0.0001983026,0.0000301793,0.00007770176,0.0003098446,0.0001183268,0.006296656],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003785317,"threshold_uncertainty_score":0.01266313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06024876581410656,"score_gpt":0.2657554840574726,"score_spread":0.205506718243366,"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."}}