{"id":"W4384833556","doi":"10.1145/3597031.3597057","title":"cuSCNN : an Efficient CUDA Implementation of Sparse CNNs","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Speedup; Parallel computing; CUDA; Sparse matrix; Convolutional neural network; Inference; Computation; Memory bandwidth; Kernel (algebra); Latency (audio); Throughput; Computer engineering; Algorithm; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004831988,0.00111775,0.0005553158,0.0006563666,0.0004370298,0.0008917425,0.002690516,0.0005733786,0.01183053],"category_scores_gemma":[0.002532465,0.0007081162,0.0005525298,0.0008713669,0.0004007258,0.001187455,0.0009616411,0.001324598,0.003352467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001209126,"about_ca_system_score_gemma":0.002129264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02485116,"about_ca_topic_score_gemma":0.03177163,"domain_scores_codex":[0.9995821,0.0000587523,0.00002917645,0.00007501675,0.0001888988,0.00006602172],"domain_scores_gemma":[0.9995151,0.00009224856,0.00003389604,0.0000906021,0.0002218519,0.00004640522],"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":[0.001136773,0.0003167622,0.005246239,0.0006264811,0.0003545637,0.0004791111,0.0003445423,0.3604078,0.03497454,0.03325697,0.1881963,0.3746599],"study_design_scores_gemma":[0.0000639935,0.00002896464,0.0002356239,0.00001225961,0.000009303502,0.00003447913,0.00001355339,0.9756021,0.009457905,0.002174556,0.01235105,0.00001627818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04439192,0.0006473901,0.8382535,0.000494029,0.0003612798,0.0002179244,0.003111305,0.09521687,0.01730577],"genre_scores_gemma":[0.3939365,0.0005516723,0.5702702,0.0004129003,0.00006950105,0.0006135625,0.01079707,0.006239762,0.01710873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02485116,"threshold_uncertainty_score":0.04941303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03867691439024008,"score_gpt":0.3471304006101584,"score_spread":0.3084534862199183,"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."}}