{"id":"W4388837988","doi":"10.1109/tc.2023.3334140","title":"Fast Inner-Product Algorithms and Architectures for Deep Neural Network Accelerators","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Computers","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Pipeline (software); Convolutional neural network; Systolic array; Algorithm; Throughput; Matrix multiplication; Floating point; Parallel computing; Gate array; Field-programmable gate array; Computer hardware; Embedded system; Very-large-scale integration; Artificial intelligence; Wireless","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":[0.000666366,0.001094622,0.0004804549,0.0007352448,0.0004182533,0.001155912,0.001875258,0.0005804542,0.008034461],"category_scores_gemma":[0.002389325,0.0005298046,0.0005932229,0.0009757799,0.0006290906,0.002524999,0.001185849,0.001657613,0.002553958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001107878,"about_ca_system_score_gemma":0.001465684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002069148,"about_ca_topic_score_gemma":0.00357245,"domain_scores_codex":[0.9994689,0.00007817704,0.00004265338,0.00009185067,0.000247884,0.00007050634],"domain_scores_gemma":[0.9993068,0.000195127,0.00006509779,0.0001676309,0.0002319311,0.00003347564],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005116185,0.0001506223,0.0009989829,0.0003536158,0.0001049446,0.0001388456,0.000195207,0.1349028,0.03297304,0.1499777,0.02060014,0.6590925],"study_design_scores_gemma":[0.00007320672,0.000270905,0.0002824359,0.00005257316,0.00003819304,0.0001500054,0.00003419233,0.8595511,0.04686724,0.0610171,0.03162028,0.00004278968],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005826531,0.0003760603,0.987214,0.0001151662,0.0000865324,0.00002932711,0.00008082909,0.002853506,0.003418121],"genre_scores_gemma":[0.1292762,0.0004926162,0.861283,0.0002006534,0.00009697785,0.0001553189,0.0005479606,0.0006447186,0.007302617],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008034461,"threshold_uncertainty_score":0.026878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02154743184328495,"score_gpt":0.2450600107958905,"score_spread":0.2235125789526056,"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."}}