{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003401317,0.001205529,0.0003476718,0.0005395287,0.000264874,0.0006571093,0.001451503,0.000348893,0.0061996],"category_scores_gemma":[0.001637589,0.0004902096,0.0006299468,0.0003914805,0.000347626,0.0007400202,0.0005039753,0.0007475188,0.001579057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001290597,"about_ca_system_score_gemma":0.001371728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004755037,"about_ca_topic_score_gemma":0.006495737,"domain_scores_codex":[0.9996337,0.00004031472,0.00002543971,0.00007208409,0.0001244783,0.000103978],"domain_scores_gemma":[0.9994227,0.0001819227,0.00005091366,0.0001277053,0.0001832136,0.00003360748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001471672,0.0004061863,0.009500172,0.0006485611,0.0002165077,0.0007195507,0.0002976625,0.5564756,0.1547331,0.01260731,0.03448756,0.2284361],"study_design_scores_gemma":[0.00011854,0.0001537057,0.001236014,0.00002214231,0.00003663952,0.00006467424,0.00004744429,0.8976647,0.09018733,0.001853684,0.008588539,0.00002651316],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5278897,0.0004805566,0.3503853,0.0003050112,0.0003401466,0.0002804265,0.001639101,0.09273349,0.02594632],"genre_scores_gemma":[0.8173297,0.0001410049,0.1663322,0.0001731351,0.00002137076,0.0002328968,0.002870124,0.006760138,0.006139379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0061996,"threshold_uncertainty_score":0.02073973,"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."}}