{"id":"W4393931333","doi":"10.1145/3642961.3643800","title":"Enhancing Intra-Node GPU-to-GPU Performance in MPI+UCX through Multi-Path Communication","year":2024,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Computer science; PCI Express; Speedup; Parallel computing; Node (physics); CUDA; Host (biology); Solver; Path (computing); Message passing; Computer network; Embedded system; Field-programmable gate array","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":[0.0005147858,0.0001398681,0.0001437349,0.0001715087,0.0001217033,0.0002682261,0.0009673474,0.00006798242,0.0000132211],"category_scores_gemma":[0.00003739614,0.0001289414,0.00003549912,0.0008328377,0.00002566227,0.0007307059,0.0004141146,0.000239602,0.0001330925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009370576,"about_ca_system_score_gemma":0.00007142023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001076667,"about_ca_topic_score_gemma":0.0000529822,"domain_scores_codex":[0.9987929,0.00008660387,0.0003226529,0.0003719776,0.0001644873,0.0002613537],"domain_scores_gemma":[0.9990669,0.0001004159,0.00003766547,0.0006862955,0.00005800839,0.00005067042],"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":[0.00003449646,0.0008619557,0.007142359,0.0007160313,0.00009098869,0.00006646678,0.07224093,0.2648507,0.008626114,0.329226,0.02322756,0.2929164],"study_design_scores_gemma":[0.0001103669,0.00003787054,0.001123075,0.0002808608,0.000001451352,0.000007201835,0.00003088398,0.9768862,0.01568113,0.0006027504,0.005031463,0.0002067884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01009681,0.0004126118,0.9803236,0.001335964,0.0001663414,0.0001811458,4.654612e-7,0.001249287,0.006233811],"genre_scores_gemma":[0.4950429,0.000170444,0.5038455,0.0005208144,0.00001407115,0.00001773977,0.000002279043,0.000007524685,0.0003786783],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7120355,"threshold_uncertainty_score":0.5258079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02452949154640401,"score_gpt":0.2937328634984525,"score_spread":0.2692033719520485,"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."}}