{"id":"W3007581096","doi":"10.1145/3373087.3375380","title":"HPIPE: Heterogeneous Layer-Pipelined and Sparse-Aware CNN Inference for FPGAs","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Engineering and Physical Sciences Research Council","keywords":"Stratix; Computer science; Field-programmable gate array; Digital signal processing; Compiler; Convolutional neural network; Computer architecture; Throughput; Parallel computing; Embedded system; Computer hardware; 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":[0.0003147463,0.0006955522,0.0002887922,0.0003515276,0.0002280698,0.0005376101,0.001597363,0.0003400469,0.008420499],"category_scores_gemma":[0.000768935,0.0004685042,0.0003866815,0.000344951,0.0002716398,0.001181814,0.0006669387,0.0007522047,0.001462239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007555144,"about_ca_system_score_gemma":0.001017598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007563549,"about_ca_topic_score_gemma":0.01919215,"domain_scores_codex":[0.9998438,0.00001772694,0.000006409152,0.00004420595,0.0000577812,0.00002998112],"domain_scores_gemma":[0.9998214,0.00005558743,0.00001479111,0.0000492281,0.00004147364,0.0000175698],"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":[0.001025033,0.000222037,0.003328268,0.0003936482,0.0002556948,0.0003091227,0.0001320655,0.342507,0.05717652,0.0219415,0.06046276,0.5122464],"study_design_scores_gemma":[0.00005452813,0.00008750795,0.0003818237,0.00001372303,0.00001758202,0.00004945232,0.00001529626,0.9694733,0.01644045,0.003785268,0.009666851,0.00001427809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05727099,0.000691581,0.8871964,0.000308415,0.0002094658,0.0001243052,0.001061642,0.04035785,0.01277944],"genre_scores_gemma":[0.4312776,0.0003564444,0.549215,0.0003303782,0.00005099579,0.0001495835,0.002810211,0.001436882,0.01437285],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008420499,"threshold_uncertainty_score":0.02816939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06215340409102788,"score_gpt":0.3009137902796727,"score_spread":0.2387603861886449,"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."}}