{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005434292,0.0003818256,0.0003306142,0.0005223714,0.0007756423,0.0006969869,0.0007878908,0.0001710401,0.0000109375],"category_scores_gemma":[0.00003867379,0.0003838436,0.000160015,0.00107959,0.00006923766,0.0004310523,0.00006153479,0.0006796393,0.00008474609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001437388,"about_ca_system_score_gemma":0.0001091512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001971362,"about_ca_topic_score_gemma":0.000003035766,"domain_scores_codex":[0.9974107,0.0001773035,0.0005000863,0.001010593,0.0004100092,0.0004912802],"domain_scores_gemma":[0.9981244,0.000755342,0.0001020887,0.0007611975,0.00009513754,0.000161784],"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":[0.00004207213,0.0002457316,0.00002586783,0.0001302704,0.0001020675,0.00004459492,0.00113584,0.7407441,0.0002356002,0.01149232,0.001049018,0.2447525],"study_design_scores_gemma":[0.0004165994,0.0003601692,0.0002078602,0.0004257885,0.0000172259,0.0000929184,0.00002773224,0.9902096,0.003823874,0.003082029,0.0009049143,0.0004313258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01158732,0.0003670695,0.9814714,0.001448746,0.0009290744,0.0004311524,0.000003982734,0.002676866,0.001084424],"genre_scores_gemma":[0.6767836,0.0001160268,0.3222595,0.0003287235,0.00009050198,0.00001631199,0.000003429318,0.00003213657,0.000369822],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6651962,"threshold_uncertainty_score":0.9998614,"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."}}