{"id":"W3148573243","doi":"10.1145/2858788.2688521","title":"On optimizing machine learning workloads via kernel fusion","year":2015,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada)","funders":"Nvidia","keywords":"Computer science; Kernel (algebra); Scalability; Locality; Parallel computing; Matrix multiplication; Computation; Range (aeronautics); Algorithm","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":[0.0009215807,0.0008191718,0.0006679313,0.0004521458,0.000463375,0.0009408824,0.001039917,0.0005481069,0.001484628],"category_scores_gemma":[0.004707038,0.0002693538,0.0003850187,0.001127106,0.0005478196,0.002043889,0.001084782,0.0008422001,0.0007431163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008102175,"about_ca_system_score_gemma":0.001409124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002776769,"about_ca_topic_score_gemma":0.003449333,"domain_scores_codex":[0.9991034,0.0002377746,0.00005268254,0.0001162822,0.0003334364,0.0001563806],"domain_scores_gemma":[0.9983418,0.0007947963,0.0001018618,0.0003576273,0.0003282937,0.00007554132],"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":[0.0002807308,0.0002048304,0.001937625,0.00007749915,0.00003321332,0.00007037641,0.0001136113,0.7921014,0.02056157,0.01281795,0.002602102,0.169199],"study_design_scores_gemma":[0.000004427543,0.0000192694,0.00009605317,0.000001591621,0.000002409276,0.000008693157,0.000008769422,0.9937766,0.003080202,0.002666665,0.0003326381,0.000002716967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1378842,0.0004402265,0.8526396,0.0002985323,0.00004928556,0.00007246491,0.00008540082,0.003752641,0.004777718],"genre_scores_gemma":[0.7601757,0.0002591855,0.2366837,0.00009953039,0.00004557042,0.000079649,0.0002830456,0.0003455277,0.002028031],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002776769,"threshold_uncertainty_score":0.005878568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03233663507408029,"score_gpt":0.2699771110886107,"score_spread":0.2376404760145304,"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."}}