{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005022903,0.0009255639,0.0005114755,0.0004527097,0.001099883,0.0008532522,0.00168837,0.0006354189,0.004783705],"category_scores_gemma":[0.001788125,0.0002953567,0.0003714076,0.0007650396,0.0005608511,0.001535606,0.002023098,0.0014503,0.001494771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005734051,"about_ca_system_score_gemma":0.001169367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003844614,"about_ca_topic_score_gemma":0.006862764,"domain_scores_codex":[0.999506,0.0001107202,0.00001536966,0.00007698476,0.0002060675,0.0000849479],"domain_scores_gemma":[0.9994018,0.0001766275,0.00004053443,0.0001701353,0.0001508849,0.00006014585],"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":[0.0008012457,0.0005193395,0.01118375,0.0007678923,0.0002042005,0.001064452,0.001634761,0.2705682,0.1267344,0.04109913,0.05832127,0.4871015],"study_design_scores_gemma":[0.00009839637,0.0003377764,0.002395271,0.0000370888,0.00004250808,0.0003208964,0.0002207463,0.8936309,0.05472951,0.008433908,0.0396932,0.00005972847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1669621,0.001024768,0.7670695,0.0009250651,0.0003379168,0.0001801184,0.0002803995,0.02605738,0.03716267],"genre_scores_gemma":[0.6500253,0.0005351012,0.3348237,0.0002393884,0.0001053638,0.0002622146,0.0007181098,0.001905832,0.0113849],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004783705,"threshold_uncertainty_score":0.01600313,"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."}}