{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009655508,0.001213303,0.0006027105,0.001038517,0.0009023421,0.001124726,0.003773346,0.0009996302,0.01262136],"category_scores_gemma":[0.003592354,0.0008843392,0.00118812,0.001496751,0.0004840491,0.001963153,0.001751855,0.002039705,0.005999272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009801759,"about_ca_system_score_gemma":0.001662507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003027717,"about_ca_topic_score_gemma":0.006247582,"domain_scores_codex":[0.9991535,0.000146278,0.00006033425,0.0001243056,0.0004133756,0.0001020839],"domain_scores_gemma":[0.998596,0.0003282811,0.0001181828,0.0004452089,0.000415794,0.00009647316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008160628,0.0004590281,0.007037471,0.001020363,0.00036735,0.0008156135,0.0004645187,0.06795231,0.08270465,0.03514344,0.2671029,0.5361164],"study_design_scores_gemma":[0.0003620253,0.0004409385,0.004233407,0.000156239,0.000128086,0.001057932,0.0001018426,0.5352636,0.174142,0.02165489,0.2622299,0.0002291275],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.02509443,0.0007237843,0.7368611,0.0003722814,0.0002085008,0.0002023806,0.001402582,0.2193246,0.01581043],"genre_scores_gemma":[0.1971785,0.0006848787,0.7410997,0.000781222,0.0001306237,0.0006027513,0.007809494,0.02839961,0.02331321],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01262136,"threshold_uncertainty_score":0.04222268,"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."}}