{"id":"W4412960910","doi":"10.1145/3749986","title":"HLSRewriter: Efficient Refactoring and Optimization of C/C++ Code with LLMs for High-Level Synthesis","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Design Automation of Electronic Systems","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"International Graduate School of Science and Engineering; Deutsche Forschungsgemeinschaft","keywords":"Code refactoring; Computer science; High-level synthesis; Pipeline (software); Code generation; Code (set theory); Process (computing); Programming language; Parallel computing; Embedded system; Software; Operating system; Field-programmable gate array","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":[0.001315705,0.00194434,0.0006357175,0.001178973,0.0005028805,0.001071035,0.002238763,0.0009838018,0.00639942],"category_scores_gemma":[0.003557404,0.0008314482,0.001400259,0.0004791401,0.001032366,0.001141025,0.001943545,0.001749524,0.003337032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008632187,"about_ca_system_score_gemma":0.002037947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003349369,"about_ca_topic_score_gemma":0.004287432,"domain_scores_codex":[0.9986186,0.0002100901,0.0001144826,0.0003394396,0.0005528246,0.0001644908],"domain_scores_gemma":[0.9986174,0.0004555805,0.0001601454,0.0004628745,0.0002463367,0.00005775134],"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":[0.0005529863,0.0002429461,0.003202178,0.001086523,0.0001316116,0.0007970297,0.0007885025,0.1342318,0.1582978,0.02064244,0.03367404,0.6463522],"study_design_scores_gemma":[0.0001450792,0.0002957451,0.0009212801,0.0001292601,0.00007719678,0.0004251447,0.00008944843,0.755685,0.1797571,0.01264428,0.04970445,0.0001260509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01122035,0.000349026,0.8800514,0.0001300161,0.0000608316,0.0001805855,0.0003449736,0.105287,0.002375871],"genre_scores_gemma":[0.1246169,0.0002929913,0.8569846,0.0002251995,0.00003440037,0.00030471,0.002027907,0.01091909,0.004594175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00639942,"threshold_uncertainty_score":0.0214082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02432252241982122,"score_gpt":0.2569261122839225,"score_spread":0.2326035898641013,"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."}}