{"id":"W4386896826","doi":"10.1145/3625004","title":"Advancing Direct Convolution Using Convolution Slicing Optimization and ISA Extensions","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Architecture and Code Optimization","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Parallel computing; Kernel (algebra); Kernelization; Speedup; x86; Convolution (computer science); Algorithm; Computational science; Artificial intelligence; Parameterized complexity; Programming language; Mathematics; Artificial neural network","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":[0.0006075331,0.0009481812,0.0005125868,0.0003811656,0.0003833636,0.0008571592,0.001043135,0.0003707853,0.004263404],"category_scores_gemma":[0.002231358,0.0004179514,0.0009511658,0.000404705,0.0005630506,0.00133043,0.001023129,0.001016755,0.001426692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00090671,"about_ca_system_score_gemma":0.002060088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005577111,"about_ca_topic_score_gemma":0.006609458,"domain_scores_codex":[0.9995926,0.00006757591,0.00003135145,0.00007901019,0.0001478215,0.00008158054],"domain_scores_gemma":[0.9992266,0.0002527427,0.00006550599,0.000243337,0.0001793855,0.00003240618],"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":[0.0003237065,0.0001321584,0.004372305,0.0003217816,0.0001082139,0.0002357616,0.0004059569,0.4920263,0.04280592,0.0653356,0.01576506,0.3781672],"study_design_scores_gemma":[0.00001449012,0.00003992493,0.0002173495,0.00001333737,0.00001373365,0.00004514515,0.00002530716,0.9668624,0.01590449,0.01101774,0.005837223,0.000008907469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05193672,0.00042472,0.9205692,0.0002170567,0.0001037492,0.00005612298,0.0001965841,0.0148773,0.01161853],"genre_scores_gemma":[0.3402211,0.0002434203,0.6529434,0.0002006601,0.00004654473,0.0001006935,0.0007715205,0.001678174,0.003794482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005577111,"threshold_uncertainty_score":0.0142625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01661212601399944,"score_gpt":0.2620384360743739,"score_spread":0.2454263100603745,"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."}}