{"id":"W4404609150","doi":"10.1109/tc.2024.3500369","title":"Mix-GEMM: Extending RISC-V CPUs for Energy-Efficient Mixed-Precision DNN Inference Using Binary Segmentation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Computers","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Computer science; Binary number; Parallel computing; Inference; Segmentation; Algorithm; Arithmetic; Artificial intelligence; Mathematics","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":[0.00009783428,0.0001782512,0.0001455454,0.0002054952,0.0001893602,0.0001088188,0.0001188174,0.00006372024,0.00001433151],"category_scores_gemma":[0.000001828707,0.0001803516,0.0001453818,0.0003977491,0.00002428001,0.0001095926,0.000001884118,0.0001459964,0.00002601893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000143333,"about_ca_system_score_gemma":0.00001807523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001696296,"about_ca_topic_score_gemma":0.000002267678,"domain_scores_codex":[0.9990871,0.00003151551,0.0002257495,0.0002917786,0.0001444867,0.0002193465],"domain_scores_gemma":[0.9991565,0.0005239132,0.00001900189,0.0001890938,0.00003094556,0.00008050607],"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":[0.000004345698,0.00004424869,1.103258e-7,0.0000390513,0.00002823525,0.000001142815,0.00006790846,0.6976028,0.04742369,0.000244021,0.0001372473,0.2544072],"study_design_scores_gemma":[0.0001473701,0.00005885876,0.00002144664,0.0001567466,0.0000487032,0.000003612683,0.00003485084,0.9572661,0.04040635,0.0004578132,0.001209326,0.0001888176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08558284,0.00009245433,0.910944,0.00004754965,0.002620215,0.0002216527,0.00004815136,0.0004058799,0.00003730469],"genre_scores_gemma":[0.877904,0.00003500249,0.1217368,0.00002415167,0.0001042505,0.0001161276,0.000007680516,0.00003717009,0.00003479062],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7923211,"threshold_uncertainty_score":0.7354527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03109361440580557,"score_gpt":0.3064758833789454,"score_spread":0.2753822689731398,"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."}}