{"id":"W4285504014","doi":"10.1109/ipdps53621.2022.00055","title":"Co-Designing an OpenMP GPU Runtime and Optimizations for Near-Zero Overhead Execution","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Lawrence Livermore National Laboratory","keywords":"Computer science; Software portability; Compiler; CUDA; Parallel computing; Runtime system; Overhead (engineering); Programming paradigm; Operating system; Programming language","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":[0.0007604634,0.0008631579,0.0004430398,0.0004206091,0.0004345518,0.001138819,0.002276148,0.0005644724,0.001608404],"category_scores_gemma":[0.003247068,0.0006799016,0.0005612152,0.0004595461,0.0006766701,0.001560643,0.001363626,0.001978729,0.001123116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005602028,"about_ca_system_score_gemma":0.001391124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009887674,"about_ca_topic_score_gemma":0.002309951,"domain_scores_codex":[0.9986449,0.0002336307,0.0001088173,0.0002339119,0.0005816408,0.000197056],"domain_scores_gemma":[0.9983479,0.0002843529,0.0001561469,0.0006822143,0.0004553377,0.00007406394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009741568,0.0008424758,0.01076382,0.0006775696,0.0002683068,0.0007388673,0.0008408763,0.1867229,0.3676743,0.0277707,0.01278627,0.3899397],"study_design_scores_gemma":[0.00009302178,0.0003939153,0.002867673,0.00005155359,0.0001094437,0.0003656514,0.0001137841,0.6729926,0.2825728,0.008405012,0.03194501,0.00008963768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08913554,0.00025299,0.8785847,0.0002214515,0.0001145095,0.0001880263,0.00009221036,0.02459347,0.00681719],"genre_scores_gemma":[0.4061474,0.000148898,0.5828063,0.0002075407,0.0000430922,0.0002650678,0.0003495673,0.00530182,0.004730275],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002276148,"threshold_uncertainty_score":0.00538063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02112686276357748,"score_gpt":0.2952386818613041,"score_spread":0.2741118190977266,"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."}}