{"id":"W3197603378","doi":"10.1109/tcad.2021.3109863","title":"RLPlace: Using Reinforcement Learning and Smart Perturbations to Optimize FPGA Placement","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","topic":"VLSI and FPGA Design Techniques","field":"Engineering","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Huawei Technologies; VMware; Google","keywords":"Field-programmable gate array; Computer science; Reinforcement learning; Simulated annealing; Quality (philosophy); Parallel computing; Algorithm; Artificial intelligence; Embedded system","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":[0.0005699274,0.0009002532,0.0005436635,0.000387957,0.0002409485,0.0004874276,0.001277941,0.0007100036,0.001905255],"category_scores_gemma":[0.001858188,0.0003425185,0.0003934884,0.0002610681,0.0005705514,0.0006035857,0.0007330666,0.0008278038,0.0004648677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006606001,"about_ca_system_score_gemma":0.000864944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003475331,"about_ca_topic_score_gemma":0.004194981,"domain_scores_codex":[0.999668,0.00009108852,0.00001642333,0.00007549063,0.0001073138,0.00004161306],"domain_scores_gemma":[0.9994061,0.0002629997,0.0001132484,0.00009212123,0.00008521397,0.0000403047],"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":[0.0001113045,0.00006641262,0.0006445932,0.00005202674,0.00004032822,0.00006991548,0.00003729331,0.9024764,0.008778417,0.002395184,0.0009858494,0.08434227],"study_design_scores_gemma":[0.00001756795,0.00007146657,0.00007698964,0.00000358663,0.000006372328,0.00001550028,0.000004560648,0.9957996,0.002749172,0.0006836547,0.0005664179,0.000005092338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05607278,0.0003415787,0.9352574,0.0001765621,0.00008790765,0.00008989084,0.00005137177,0.00472385,0.003198665],"genre_scores_gemma":[0.755364,0.0001383037,0.2412208,0.0001504916,0.00003616928,0.0001239153,0.00009599129,0.0002755456,0.002594878],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003475331,"threshold_uncertainty_score":0.006910205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03147460674607729,"score_gpt":0.237124561965308,"score_spread":0.2056499552192307,"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."}}