{"id":"W4289828123","doi":"10.1109/ipdpsw55747.2022.00026","title":"Optimization of Compiler-Generated OpenCL CNN Kernels and Runtime for FPGAs","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Compiler; Stratix; Field-programmable gate array; Parallel computing; CAS latency; Latency (audio); Computer architecture; Embedded system; Computer hardware; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000262407,0.0002263429,0.0002678241,0.0001245803,0.0006469592,0.000230735,0.000794414,0.00006270206,0.000042529],"category_scores_gemma":[0.00003092898,0.0002410184,0.00006006151,0.0006257268,0.0001144341,0.0005591012,0.0004883078,0.0002215447,0.000001079237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008753814,"about_ca_system_score_gemma":0.0000958232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000803719,"about_ca_topic_score_gemma":0.000002112867,"domain_scores_codex":[0.9981104,0.00006774874,0.0005017863,0.0006345562,0.0004050257,0.0002804929],"domain_scores_gemma":[0.9987602,0.0001814943,0.0003908309,0.0002611331,0.0002956233,0.0001107329],"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":[0.0001013316,0.0001451885,0.0003157798,0.00003708202,0.00004683998,0.000003063259,0.0002031038,0.9808633,0.003473457,0.007658132,0.002598468,0.004554222],"study_design_scores_gemma":[0.0009609061,0.00007541527,0.0002517187,0.00003850343,0.00002450284,0.000042866,0.00007725584,0.9899057,0.0005667986,0.003941919,0.003828998,0.0002854454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007563206,0.00067404,0.9853604,0.004794519,0.0003780121,0.0005194952,0.0003367039,0.0001220858,0.0002515444],"genre_scores_gemma":[0.922321,0.0002148767,0.07453974,0.0004027297,0.0001314129,0.0006086807,0.001098689,0.00002810126,0.0006547506],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9147578,"threshold_uncertainty_score":0.9828444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02072030816206441,"score_gpt":0.2766303517242872,"score_spread":0.2559100435622228,"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."}}