{"id":"W4210863326","doi":"10.1109/mm.2022.3148670","title":"Accelerating Deep Learning Using Interconnect-Aware UCX Communication for MPI Collectives","year":2022,"lang":"en","type":"article","venue":"IEEE Micro","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Western Canada Research Grid; Compute Canada","keywords":"Computer science; PCI Express; Speedup; Graphics processing unit; Parallel computing; Message Passing Interface; Network topology; Message passing; Bandwidth (computing); Computer architecture; Embedded system; Field-programmable gate array; Computer network","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0004524798,0.0001050975,0.0001332064,0.000136573,0.001409398,0.0001928704,0.0008260782,0.00003116899,0.00001371512],"category_scores_gemma":[0.00004885289,0.0001244158,0.00006388527,0.0003685596,0.00002291862,0.0002156609,0.0004147047,0.0002408539,0.00000147508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001549719,"about_ca_system_score_gemma":0.00005525017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003286974,"about_ca_topic_score_gemma":0.000005820104,"domain_scores_codex":[0.9989511,0.0002673018,0.0002113353,0.0002706108,0.000102354,0.0001972617],"domain_scores_gemma":[0.9991359,0.0002385415,0.0001655228,0.0003178415,0.0001132472,0.00002898641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003956286,0.0001629621,0.0009283054,0.00004219852,0.00006757894,0.000004039394,0.01435208,0.8684802,0.06603494,0.002631644,0.003759666,0.04349681],"study_design_scores_gemma":[0.0002446726,0.00008908523,0.00002458412,0.00001744446,0.000003901255,0.00001927143,0.0002946546,0.9738827,0.02078822,0.0005825657,0.003884303,0.000168611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03695906,0.0002734452,0.9613566,0.0001683998,0.0001824285,0.0002399741,0.000001845479,0.0004259361,0.0003923556],"genre_scores_gemma":[0.6445911,0.00001039134,0.3548683,0.000206083,0.00002661839,0.00005626481,0.0000072036,0.00001274118,0.0002213163],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.607632,"threshold_uncertainty_score":0.9998906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04396272083031036,"score_gpt":0.297140060445731,"score_spread":0.2531773396154207,"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."}}