{"id":"W2588449239","doi":"10.1145/3038228.3038236","title":"Launch-Time Optimization of OpenCL GPU Kernels","year":2017,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Qualcomm","keywords":"Kernel (algebra); Computer science; Compiler; Constant (computer programming); Loop unrolling; Parallel computing; Computational science; Reduction (mathematics); CUDA; General-purpose computing on graphics processing units; Computer graphics (images); Operating system; Programming language; Geometry; Graphics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005926772,0.00118364,0.0007099907,0.0009312215,0.0006704016,0.001323724,0.002483457,0.0006365372,0.008193898],"category_scores_gemma":[0.003831732,0.0005527447,0.0007508586,0.0009808881,0.0006145862,0.001198585,0.001614569,0.00136331,0.002888966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001510657,"about_ca_system_score_gemma":0.00183889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005097581,"about_ca_topic_score_gemma":0.008232001,"domain_scores_codex":[0.9987777,0.0001226766,0.00006079502,0.000143693,0.0005447508,0.0003504159],"domain_scores_gemma":[0.9980281,0.0005240595,0.0001167311,0.0003725176,0.0008036786,0.0001548736],"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":[0.001762171,0.0005134677,0.009567643,0.0007325918,0.0001846172,0.0008883632,0.001089638,0.4281009,0.182059,0.03842212,0.05591355,0.2807659],"study_design_scores_gemma":[0.0001406006,0.0001384371,0.001513382,0.00002680527,0.0000323088,0.00009448532,0.000122638,0.8958122,0.07901994,0.006992581,0.016053,0.00005376648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3158171,0.0009478842,0.5828304,0.0004891401,0.0003914996,0.0002752704,0.000960321,0.05116595,0.04712249],"genre_scores_gemma":[0.7561148,0.0002105075,0.2136253,0.0002094785,0.00005336354,0.0002646689,0.002373134,0.01322156,0.01392705],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008193898,"threshold_uncertainty_score":0.02741134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02062422930730713,"score_gpt":0.2772195945092754,"score_spread":0.2565953652019683,"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."}}