{"id":"W1979527452","doi":"10.1109/ispass.2009.4919648","title":"Analyzing CUDA workloads using a detailed GPU simulator","year":2009,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":1660,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Parallel computing; CUDA; Thread (computing); Graphics; Microarchitecture; Instruction set; SIMD; Computer architecture; General-purpose computing on graphics processing units; Memory bandwidth; Multithreading; Supercomputer; Operating system","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02341184931854888,"score_gpt":0.2874748231294658,"score_spread":0.2640629738109169,"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."}}