{"id":"W3033506121","doi":"10.1145/3393668","title":"FPGA Logic Block Architectures for Efficient Deep Learning Inference","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Reconfigurable Technology and Systems","topic":"Low-power high-performance VLSI design","field":"Engineering","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Adder; Lookup table; Logic block; Field-programmable gate array; Single-precision floating-point format; Critical path method; Parallel computing; Reduction (mathematics); Multiplier (economics); Floating point; Computer hardware; Block (permutation group theory); Computer engineering; Algorithm; Mathematics","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":[0.0001295282,0.000229679,0.0003194649,0.0003657905,0.0002678353,0.00004131727,0.0002901721,0.0003139036,0.00003162994],"category_scores_gemma":[0.00007721889,0.0002119273,0.00005602558,0.0004753995,0.00008820462,0.0000279276,0.00000303189,0.000593311,0.00005390668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003444847,"about_ca_system_score_gemma":0.00001360983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005460064,"about_ca_topic_score_gemma":0.000005054509,"domain_scores_codex":[0.9989116,0.00002806382,0.0002960964,0.0003135641,0.00008978161,0.000360939],"domain_scores_gemma":[0.999308,0.0002186848,0.00004537226,0.0002965633,0.00004391437,0.00008748802],"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":[0.00002731416,0.00001874094,0.00009411347,0.0002583621,0.00008559415,0.000003705206,0.000330083,0.9534995,0.004609098,0.0003693022,0.0000285064,0.04067567],"study_design_scores_gemma":[0.001228202,0.0009362993,0.000106692,0.0001799178,0.00008536477,0.00011586,0.001138969,0.9188374,0.06622729,0.0007655079,0.009690869,0.0006875659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4734359,0.002474282,0.5174192,0.001216577,0.000687357,0.00102522,0.00002181225,0.002547318,0.001172342],"genre_scores_gemma":[0.9986792,0.0001144284,0.0006874209,0.00005261554,0.00003124349,0.0002886621,0.000002349321,0.00003537922,0.0001086709],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5252433,"threshold_uncertainty_score":0.8642144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01796500708939768,"score_gpt":0.2233346015277115,"score_spread":0.2053695944383138,"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."}}