{"id":"W4412987079","doi":"10.1109/ispass64960.2025.00018","title":"ConCCL: Optimizing ML Concurrent Computation and Communication with GPU DMA Engines","year":2025,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Computer science; Parallel computing; Computation; Computational science; Algorithm","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001805185,0.0001038518,0.0001243584,0.0001218447,0.0001700713,0.0002010262,0.0003225165,0.00003714945,0.000001782424],"category_scores_gemma":[0.00001318988,0.00008721329,0.00001511938,0.0003110055,0.00005876908,0.000248882,0.0002066165,0.00008770997,0.000001647229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002104801,"about_ca_system_score_gemma":0.00004184357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002243339,"about_ca_topic_score_gemma":0.000003841114,"domain_scores_codex":[0.9993254,0.00006969563,0.0001696138,0.0002229729,0.00009531892,0.0001170147],"domain_scores_gemma":[0.9993408,0.000143914,0.00006888442,0.0002678375,0.0001435135,0.00003505391],"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":[0.00001021434,0.00009409488,0.001434068,0.00006321347,0.00005908133,0.000002443061,0.001188469,0.09277848,0.00007948023,0.5720518,0.007522709,0.324716],"study_design_scores_gemma":[0.0003590758,0.00004561683,0.0005491975,0.00008761753,0.000005581315,0.000005768474,0.00003452351,0.9948606,0.001097054,0.001307906,0.001519585,0.0001274155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001285579,0.0007781394,0.9878812,0.001281798,0.00005901834,0.0001505817,2.781497e-7,0.0006661837,0.007897219],"genre_scores_gemma":[0.4591515,0.0001263818,0.5402767,0.0002465065,0.000003960925,0.000008373317,0.000004786245,0.000002987266,0.0001788323],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9020821,"threshold_uncertainty_score":0.3556455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01249028519323225,"score_gpt":0.2728611370550623,"score_spread":0.26037085186183,"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."}}