{"id":"W4392240387","doi":"10.1145/3649510","title":"Low-Overhead Trace Collection and Profiling on GPU Compute Kernels","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Parallel Computing","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Profiling (computer programming); Computer science; Parallel computing; Overhead (engineering); TRACE (psycholinguistics); Computational science; Operating system","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":[0.0005811343,0.0008634527,0.0005664604,0.001099171,0.0006486918,0.001041957,0.001621093,0.0005340152,0.002610907],"category_scores_gemma":[0.005520784,0.0004997584,0.000336043,0.0015853,0.000655866,0.001290766,0.00091658,0.001004615,0.001163688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009564989,"about_ca_system_score_gemma":0.001442183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005283982,"about_ca_topic_score_gemma":0.006919139,"domain_scores_codex":[0.9983753,0.0002824639,0.00007969311,0.0002570377,0.0007727278,0.0002326376],"domain_scores_gemma":[0.9968044,0.0009750545,0.0002652732,0.001272137,0.0005156806,0.0001675304],"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":[0.002330378,0.0007393068,0.03369973,0.0006927939,0.0001732115,0.0008834052,0.001457581,0.0749855,0.3482297,0.01394248,0.02446977,0.4983961],"study_design_scores_gemma":[0.00009560247,0.0004934851,0.01679657,0.00006605746,0.00006626056,0.0003851564,0.0002671207,0.6077432,0.3504131,0.005220606,0.01834088,0.0001118774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5040509,0.0008062455,0.4164268,0.0003772134,0.0002438675,0.0002209908,0.001416411,0.0662725,0.01018496],"genre_scores_gemma":[0.8946955,0.0002108243,0.09904346,0.0001097263,0.00003087352,0.0001016122,0.001253821,0.001638001,0.002916335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005283982,"threshold_uncertainty_score":0.01050645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02225276152485731,"score_gpt":0.2809724329742405,"score_spread":0.2587196714493831,"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."}}