{"id":"W2888980102","doi":"10.1002/cpe.4667","title":"Design considerations for GPU‐aware collective communications in MPI","year":2018,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Computer science; CUDA; Parallel computing; Message passing; Efficient energy use; Process (computing); Distributed computing; Operating system","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003202314,0.00009548254,0.0001130298,0.00008747086,0.0005985652,0.0002621837,0.0001839631,0.0000389234,0.00000258143],"category_scores_gemma":[0.000572432,0.00009932189,0.00001499285,0.0002328437,0.0002166768,0.001229003,0.0001299013,0.0001007095,0.000003439702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002430279,"about_ca_system_score_gemma":0.000161521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005082198,"about_ca_topic_score_gemma":0.00002106254,"domain_scores_codex":[0.9990621,0.0001932757,0.0002106121,0.0003037666,0.00008891586,0.0001413369],"domain_scores_gemma":[0.9970387,0.00224389,0.0001073973,0.0002291986,0.0003239574,0.0000568302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002674704,0.0007492087,0.001630803,0.00006326465,0.00008995456,0.00002401382,0.3332175,0.0007118137,0.002126449,0.3715732,0.005422654,0.2841237],"study_design_scores_gemma":[0.00100823,0.0004475832,0.0006357944,0.00005370166,0.00001563436,0.0001023409,0.005854437,0.9644986,0.0002784778,0.02456255,0.002264554,0.0002780388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01214915,0.0008583129,0.9829208,0.002834248,0.0002113167,0.0003510246,0.000003002802,0.00005586621,0.0006162371],"genre_scores_gemma":[0.9589602,0.0001813908,0.03973714,0.0009244701,0.00002437559,0.0001345433,0.000002501433,0.000003307497,0.00003210558],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9637868,"threshold_uncertainty_score":0.460374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.126396185496318,"score_gpt":0.3780448226195618,"score_spread":0.2516486371232439,"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."}}