Large scale scientific instrumentation-and-control FPGA gateware designs have numerous run-time settable parameters. These can be used either for user-level control or by automated processes (e.g., calibration). The number of such parameters in a single design can reach on the order of 1000, and keeps evolving as the gateware and its functionality evolves. One must keep track of which module the registers belong to, where the registers need to be decoded, and how to express the properties (or even semantics) of the register to the next level of user or software. Note, the registers maybe embedded anywhere throughout the module hierarchy. Purely manual handling of these tasks by HDL developers is considered burdensome and error-prone at this scale. Typically these registers are writable via an on-chip bus, vaguely VME-like, that is controlled by an on-chip or off-chip CPU. There have been several attempts in the community to address this task at different levels. However, we have found no tool that is able to generate a register map, generate decoders and encoders with minimal overhead to the developer. So, here we present a tool that scours native HDL source files and looks for specific language-supported attributes and automatically generates a register map and bus decoders, respecting multiple clock domains, and presents a JSON file to the network that maps register names to addresses.
EvoVerilog: Large Langugage Model Assisted Evolution of Verilog Code
Department of Computer Science, City University of Hong Kong, Hong Kong(香港城市大学计算机科学系);Department of Electrical Engineering, University of Maryland, Maryland, United States(马里兰大学电气工程系);Amazon, Seattle, United States(亚马逊公司)
Think with Self-Decoupling and Self-Verification: Automated RTL Design with Backtrack-ToT
State Key Lab of Processors, Institute of Computing Technology, CAS(处理器重点实验室,计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);Beijing Normal University(北京师范大学);Peking University(北京大学);Chinese University of Hong Kong(香港中文大学)
Natural language is not enough: Benchmarking multi-modal generative AI for Verilog generation
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences(中国科学院大学杭州高等研究院);Shanghai Jiao Tong University(上海交通大学)
RealBench: Benchmarking Verilog Generation Models with Real-World IP Designs
State Key Lab of Processors, Institute of Computing Technology, CAS(处理器国家重点实验室,计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);University of Science and Technology of China(中国科学技术大学);Shanghai Innovation Center for Processor Technologies(上海处理器技术创新中心);Cambricon Technologies(Cambricon技术公司)
Comprehensive Verilog Design Problems: A Next-Generation Benchmark Dataset for Evaluating Large Language Models and Agents on RTL Design and Verification
Large Language Model for Verilog Code Generation: Literature Review and the Road Ahead
Zhejiang University \& Northwestern Polytechnical University China;Northwestern Polytechnical University China;Nantong University China;Zhejiang University China;Monash University Australia;Singapore Management University Singapore;Zhejiang University \& Northwestern Polytechnical University;Northwestern Polytechnical University;Nantong University;Zhejiang University;Monash University;Singapore Management University
Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Nanjing University(南京大学);Shanghai University(上海大学);Zhejiang University(浙江大学);Shanghai Innovation Center for Processor Technologies(上海处理器技术创新中心);FuDan University(复旦大学);Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences(中国科学院大学杭州高等研究院);University of Illinois at Urbana Champaign(伊利诺伊大学厄巴纳-香槟分校);Shanghai Jiao Tong University(上海交通大学);Zhejiang Lab(之江实验室)
ChipSeek: Optimizing Verilog Generation via EDA-Integrated Reinforcement Learning
SKLP, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所智能计算机研究中心);University of Chinese Academy of Sciences(中国科学院大学);University of Electronic Science and Technology of China(电子科技大学);Beijing Institute of Technology(北京理工大学)
RTLSeek: Boosting the LLM-Based RTL Generation with Multi-Stage Diversity-Oriented Reinforcement Learning
State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所处理器国家重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Peking University(北京大学);CASTEST Co., Ltd.(中科芯测科技有限公司)
UCAgent: An End-to-End Agent for Block-Level Functional Verification
State Key Lab of Processors, Institute of Computing Technology, CAS(中国科学院计算技术研究所处理器国家重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Beijing Institute of Open Source Chip(北京开源芯片研究院)
Veri-Sure: Multi-Agent RTL Code Generation with Temporal Tracing, Slicing and Formal Verification
School of Physics and Astronomy, The University of Edinburgh, Edinburgh, UK(物理与天文学院,爱丁堡大学,爱丁堡,英国);State Key Laboratory of Analog and Mixed-Signal VLSI, University of Macau, Macau(模拟与混合信号VLSI国家重点实验室,澳门大学,澳门);School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China(科学与工程学院,香港中文大学(深圳))