{"id":"W2984139344","doi":"10.1109/pact.2019.00028","title":"Analyzing and Leveraging Remote-Core Bandwidth for Enhanced Performance in GPUs","year":2019,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Computer science; Bandwidth (computing); Exploit; Memory bandwidth; Multi-core processor; Graphics; General-purpose computing on graphics processing units; Parallel computing; Computer architecture; Operating system; Computer network","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":[0.0008103047,0.000717699,0.0005471876,0.0007569391,0.0005069214,0.001044249,0.00105807,0.000484645,0.001087052],"category_scores_gemma":[0.003761597,0.0002955004,0.0003273898,0.0009661088,0.0005906192,0.001760128,0.0008770082,0.0007549454,0.0003654466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005868843,"about_ca_system_score_gemma":0.0007629422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00269248,"about_ca_topic_score_gemma":0.004882553,"domain_scores_codex":[0.9993136,0.0001440298,0.00002660578,0.0001234112,0.00020424,0.0001881807],"domain_scores_gemma":[0.9985347,0.0005847829,0.0001701397,0.000349622,0.0002690633,0.00009180237],"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":[0.0009462321,0.0005316833,0.03396791,0.0004515153,0.0001436369,0.0005103371,0.0005024327,0.5144225,0.1842197,0.01558668,0.003700259,0.2450172],"study_design_scores_gemma":[0.00002761766,0.0002552026,0.007533493,0.00002313524,0.00005757387,0.0001193196,0.0001241615,0.9393038,0.0428423,0.006520277,0.003162246,0.00003095971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8349331,0.002636933,0.1528202,0.0004440239,0.00007980475,0.00005734351,0.0001088846,0.00185075,0.007068945],"genre_scores_gemma":[0.9797233,0.000275363,0.01917581,0.00004050549,0.00002157966,0.00001831725,0.00009548034,0.0001464354,0.0005032533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00269248,"threshold_uncertainty_score":0.00535357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01864229354530964,"score_gpt":0.258099745046452,"score_spread":0.2394574515011424,"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."}}