{"id":"W2884288768","doi":"10.1109/fpl.2018.00077","title":"DLA: Compiler and FPGA Overlay for Neural Network Inference Acceleration","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Ferroelectric and Negative Capacitance Devices","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Compiler; Very long instruction word; Overlay; Field-programmable gate array; Computer architecture; Deep learning; Overhead (engineering); Recurrent neural network; Embedded system; Parallel computing; Artificial neural network; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003656416,0.001211794,0.0003308841,0.0006979775,0.0003465508,0.0008692635,0.001473571,0.0005006064,0.01284101],"category_scores_gemma":[0.002242902,0.0005860226,0.0006730619,0.0005536036,0.0004226833,0.001836689,0.001070859,0.001429232,0.004479643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009154803,"about_ca_system_score_gemma":0.001517823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004523158,"about_ca_topic_score_gemma":0.008566884,"domain_scores_codex":[0.9995798,0.00006213797,0.00003713483,0.0001131522,0.0001328329,0.00007477179],"domain_scores_gemma":[0.9992749,0.0002246673,0.00004407861,0.0002085822,0.0001994036,0.00004836308],"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":[0.001062137,0.0004530563,0.006956218,0.0009486348,0.0002219069,0.0006583813,0.0004775618,0.1516897,0.074169,0.04061365,0.1724919,0.5502578],"study_design_scores_gemma":[0.0001784116,0.0002169058,0.001401042,0.00006378411,0.0000619656,0.0002131655,0.0001209491,0.8012463,0.08881745,0.02076308,0.08684853,0.00006836514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05075163,0.0006803569,0.6979717,0.0005256895,0.0005427044,0.0001979961,0.001827909,0.2301369,0.01736502],"genre_scores_gemma":[0.409375,0.0004581357,0.5524921,0.0005961936,0.0001050238,0.0004126748,0.005427025,0.01693731,0.01419643],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01284101,"threshold_uncertainty_score":0.04295748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03578349572180349,"score_gpt":0.2690577582981956,"score_spread":0.2332742625763921,"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."}}