{"id":"W4388581147","doi":"10.1145/3624062.3624605","title":"Specialized Kernels for Optimizing GPU Offload in OpenMP","year":2023,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Computer science; CUDA; Compiler; Parallel computing; Software portability; Grid; General-purpose computing on graphics processing units; Programming language; Overhead (engineering); Programming paradigm; Computational science; Operating system; Graphics","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":[0.0003639416,0.0007014507,0.0004563118,0.0004791952,0.0005850476,0.0009546812,0.001631212,0.0005388886,0.004224834],"category_scores_gemma":[0.002392843,0.0003535589,0.0004298579,0.0007451156,0.0003715988,0.0009873619,0.001186106,0.001131424,0.001933781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006325039,"about_ca_system_score_gemma":0.001068204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003933495,"about_ca_topic_score_gemma":0.005358455,"domain_scores_codex":[0.9995453,0.00005493905,0.0000277878,0.00005769628,0.0002096694,0.0001046193],"domain_scores_gemma":[0.9992222,0.0001829565,0.00006053355,0.000183839,0.0002785837,0.00007192014],"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":[0.0008128661,0.0006932797,0.008444147,0.0005372865,0.0001210324,0.000971315,0.0008083596,0.4271554,0.06913324,0.05485272,0.037885,0.3985854],"study_design_scores_gemma":[0.00005408278,0.00005922557,0.001212616,0.00002461634,0.00001786644,0.0001007994,0.00005781715,0.956151,0.02395948,0.007481293,0.01085871,0.00002249025],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1424577,0.0007366438,0.8053527,0.0002709814,0.0002224916,0.0002133871,0.0005014086,0.02326698,0.02697762],"genre_scores_gemma":[0.5841419,0.0002817885,0.4008351,0.0001587816,0.00005464546,0.0002791357,0.001640425,0.004084246,0.008524052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004224834,"threshold_uncertainty_score":0.01413351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04442171553774023,"score_gpt":0.3142708873354492,"score_spread":0.269849171797709,"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."}}