{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001072013,0.001022875,0.0005002679,0.000490642,0.0008559659,0.00125438,0.00254452,0.0005823847,0.003641332],"category_scores_gemma":[0.003750153,0.0003813105,0.0004419168,0.0007476449,0.0008788317,0.001424639,0.001922672,0.001188248,0.0007422574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001527302,"about_ca_system_score_gemma":0.003463744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01214879,"about_ca_topic_score_gemma":0.01906978,"domain_scores_codex":[0.9991642,0.0001558284,0.00004575401,0.0001923393,0.0002473799,0.000194539],"domain_scores_gemma":[0.9979619,0.000707285,0.0001926193,0.0004798126,0.0004231074,0.0002352422],"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":[0.001089078,0.0004815721,0.00954861,0.0002892345,0.0001074229,0.0002879344,0.0004937847,0.6760353,0.0510516,0.01359816,0.01640071,0.2306166],"study_design_scores_gemma":[0.00007112428,0.00009470427,0.000421595,0.000006014481,0.00001483852,0.00002614269,0.00005488228,0.9809688,0.01380334,0.00178539,0.00274086,0.00001218084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2823336,0.0005438759,0.6790224,0.0006700003,0.0002141586,0.0002225673,0.00026715,0.02054028,0.01618611],"genre_scores_gemma":[0.7388102,0.00009225777,0.2553695,0.0002027906,0.00005298262,0.0001772584,0.0003771532,0.001002347,0.003915351],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01214879,"threshold_uncertainty_score":0.02415615,"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."}}