{"id":"W2129343865","doi":"10.1109/tpds.2012.286","title":"Parallel Sparse Approximate Inverse Preconditioning on Graphic Processing Units","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Parallel and Distributed Systems","topic":"Matrix Theory and Algorithms","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Preconditioner; Computer science; Biconjugate gradient stabilized method; Solver; Parallel computing; Computational science; Rate of convergence; Sparse matrix; Iterative method; Biconjugate gradient method; Linear system; Convergence (economics); Algorithm; Mathematics; Conjugate residual method; Gradient descent; Channel (broadcasting); Artificial intelligence","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":[0.0002988407,0.0007589514,0.0005871268,0.0005577174,0.0004627438,0.000711043,0.001189955,0.0005025448,0.01165333],"category_scores_gemma":[0.001465458,0.000350815,0.0006036561,0.001381978,0.0004145879,0.0006117247,0.0009841035,0.0008164579,0.003568548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005295928,"about_ca_system_score_gemma":0.001166181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00523126,"about_ca_topic_score_gemma":0.007818359,"domain_scores_codex":[0.9994457,0.0001100785,0.00002531753,0.00006930732,0.0002773388,0.00007219196],"domain_scores_gemma":[0.9993836,0.0001148154,0.00004000289,0.0002194028,0.0002087983,0.00003335717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001086709,0.0001563753,0.002149879,0.0004172681,0.000104833,0.0005743541,0.0002584751,0.2718699,0.1029274,0.04270305,0.068528,0.5092237],"study_design_scores_gemma":[0.0001541888,0.0001766698,0.001334193,0.00002591213,0.00002810987,0.0001811998,0.00005013201,0.9142967,0.03887251,0.01150934,0.0333436,0.00002750465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04588474,0.0004747311,0.9130146,0.0003985336,0.0002365996,0.0001549841,0.0003898741,0.01566372,0.02378224],"genre_scores_gemma":[0.2736414,0.0003426524,0.7099572,0.0002839231,0.00008869547,0.0002802452,0.00139116,0.0008159808,0.01319877],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01165333,"threshold_uncertainty_score":0.0389843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03125104163723649,"score_gpt":0.2396300781156609,"score_spread":0.2083790364784245,"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."}}