{"id":"W2037854811","doi":"10.1109/pdp.2014.40","title":"A Portable and High-Performance General Matrix-Multiply (GEMM) Library for GPUs and Single-Chip CPU/GPU Systems","year":2014,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Compiler; Parallel computing; CUDA; Central processing unit; Vendor; General-purpose computing on graphics processing units; Computer architecture; Computer hardware; Operating system; Graphics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002051494,0.0001578345,0.00021321,0.0001032831,0.0001853113,0.0004744988,0.0003157057,0.00007637397,0.000002068807],"category_scores_gemma":[0.00001575226,0.0001341924,0.00002202233,0.0001499421,0.00003593526,0.000710659,0.0002147249,0.00006313533,0.000002599643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008058201,"about_ca_system_score_gemma":0.0000219001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003839866,"about_ca_topic_score_gemma":7.945139e-7,"domain_scores_codex":[0.9989285,0.00004533866,0.0002527108,0.0003873417,0.0001171247,0.0002689723],"domain_scores_gemma":[0.9993219,0.0001150909,0.000102257,0.0003106735,0.00004340941,0.0001066083],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001344586,0.0003735742,0.0371724,0.001238178,0.0001242661,0.00001077535,0.0008737925,0.07072978,0.00487212,0.638108,0.09306219,0.1533005],"study_design_scores_gemma":[0.0004129114,0.0002061732,0.001079336,0.00003534955,0.000004347468,0.00002695762,0.000003263619,0.9860403,0.002995274,0.0007016473,0.008280014,0.0002144446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1425839,0.0003268829,0.8534151,0.0002664443,0.0002142685,0.0002753698,0.000002625585,0.000862461,0.002052858],"genre_scores_gemma":[0.6246064,0.00004712667,0.372145,0.0002061728,0.00009948264,0.00002122708,0.000005802057,0.00001289692,0.002855874],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9153105,"threshold_uncertainty_score":0.5472206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01330235752749779,"score_gpt":0.2165845142537306,"score_spread":0.2032821567262328,"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."}}