{"id":"W3003197669","doi":"10.1109/icfpt47387.2019.00025","title":"Partitioning FPGA-Optimized Systolic Arrays for Fun and Profit","year":2019,"lang":"en","type":"article","venue":"","topic":"VLSI and FPGA Design Techniques","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Systolic array; Field-programmable gate array; Computer science; Parallel computing; Partition (number theory); Latency (audio); Throughput; Algorithm; Computer hardware; Embedded system; Very-large-scale integration; 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":[0.00008269781,0.00008378079,0.0001307238,0.00004039045,0.00002652312,0.00003104911,0.00004022721,0.00005235914,0.0001242745],"category_scores_gemma":[0.000005940843,0.0000724791,0.00003007186,0.00004020512,0.000007611662,0.00009411958,0.000007737587,0.00004432052,0.00003561785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001354866,"about_ca_system_score_gemma":0.00000345043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003751929,"about_ca_topic_score_gemma":0.000001030618,"domain_scores_codex":[0.9996035,0.000004668957,0.0001026633,0.00009873485,0.00004093891,0.000149505],"domain_scores_gemma":[0.9997972,0.00003443845,0.00001030477,0.0001054866,0.00001676012,0.00003577879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002198946,0.00008889587,0.01302711,0.005861775,0.000651783,0.00001222568,0.002510774,0.03694016,0.5398493,0.1855484,0.1254968,0.08979288],"study_design_scores_gemma":[0.002475655,0.0002759277,0.0008121599,0.0002223315,0.00006287844,0.00003055171,0.0002532475,0.6547359,0.3199518,0.00446427,0.01580391,0.0009113768],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1013037,0.0002743168,0.8622015,0.00005846481,0.0001683801,0.0009759631,0.000006964648,0.001599578,0.03341113],"genre_scores_gemma":[0.9570535,0.00003414933,0.04126163,0.00004654979,0.00004364565,0.0001615727,0.000006816153,0.0000250338,0.001367145],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8557498,"threshold_uncertainty_score":0.2955612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009325196011428774,"score_gpt":0.2038684983375453,"score_spread":0.1945433023261166,"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."}}