HAVEN:基于LLMs的混合自动验证引擎用于UVM测试平台综合
HAVEN: Hybrid Automated Verification ENgine for UVM Testbench Synthesis with LLMs
AI总结:
HAVEN通过结合LLM与协议特定模板生成UVM测试平台,实现100%编译成功和高覆盖率。
摘要:
集成电路验证消耗了几乎70%的IC开发周期,最近的研究利用大语言模型(LLMs)自动生成测试平台以减少验证负担。然而,LLMs在生成测试平台时存在困难。与高级编程语言不同,硬件描述语言(HDL)在LLMs训练数据中极为罕见,导致LLMs生成错误代码。为克服使用LLMs生成通用验证方法(UVM)测试平台和序列的挑战,我们提出了HAVEN(混合自动验证引擎),以防止LLMs直接编写HDL。对于UVM测试平台生成,HAVEN利用LLM代理分析设计规范以生成结构化的架构计划。HAVEN模板引擎随后结合预定义的协议特定模板生成所有UVM组件,正确处理总线握手时序。对于UVM序列生成,HAVEN引入了一种协议感知的序列领域特定语言(DSL),将序列分解为细粒度的步骤类型。一组预定义的DSL模式首先建立高覆盖率的序列,无需LLM参与。HAVEN通过迭代利用LLM代理分析覆盖率差距报告并生成额外的针对性DSL序列来进一步提高覆盖率。与先前工作不同,HAVEN是第一个利用预定义的、协议特定的Jinja2模板生成所有UVM组件和UVM序列的系统,使用我们提出的协议感知DSL和基于规则的代码生成器。我们在19个开源IP设计上进行了实验,涵盖三种接口协议(直接、Wishbone、AXI4-Lite),结果显示HAVEN实现了100%的编译成功,平均90.6%的代码覆盖率和87.9%的功能覆盖率,并在LLM辅助测试平台生成系统中处于领先位置。
英文摘要:
Integrated Circuit (IC) verification consumes nearly 70% of the IC development cycle, and recent research leverages Large Language Models (LLMs) to automatically generate testbenches and reduce verification overhead. However, LLMs have difficulty generating testbenches correctly. Unlike high-level programming languages, Hardware Description Languages (HDLs) are extremely rare in LLMs training data, leading LLMs to produce incorrect code. To overcome challenges when using LLMs to generate Universal Verification Methodology (UVM) testbenches and sequences, wepropose HAVEN (Hybrid Automated Verification ENgine) to prevent LLMs from writing HDL directly. For UVM testbench generation, HAVEN utilizes LLM agents to analyze design specifications to produce a structured architectural plan. The HAVEN Template Engine then combines with predefined and protocol-specific templates to generate all UVM components with correct bus-handshake timing. For UVM sequence generation, HAVEN introduces a Protocol-Aware Sequence Domain-Specific Language (DSL) that decomposes sequences into fine-grained step types. A set of predefined DSL patterns first establishes sequences that achieve a high coverage rate without LLM involvement. HAVEN continues to improve the coverage rate by iteratively leveraging LLM agents to analyze coverage gap reports and compose additional targeted DSL sequences. Unlike previous works, HAVEN is the first system that utilizes pre-defined, protocol-specific Jinja2 templates to generate all UVM components and UVM sequences using our proposed Protocol-Aware DSL and rule-based code generator. Our experimental results on 19 open-source IP designs spanning three interface protocols (Direct, Wishbone, AXI4-Lite) show that HAVEN achieves 100% compilation success, 90.6% code coverage, and 87.9% functional coverage on average, and is SOTA among LLM-assisted testbench generation systems.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。