HINT：面向大语言模型驱动的RTL生成的可执行硬件意图表示层
HINT: Toward an Executable Hardware-Intent Representation Layer for LLM-Driven RTL Generation
浏览论文内容
中文总结 AI 辅助
本文提出HINT可执行硬件意图表示层，用于LLM驱动的RTL生成，在7个算子案例中全量生成合规可综合RTL，面积较人工实现及直接C2RTL结果显著降低，还验证了其在各类复杂设计中的有效性。
中文摘要 AI 辅助
利用大语言模型（LLM）生成符合实现质量要求的RTL（寄存器传输级）代码仍然存在困难，因为直接生成过程需要在解决微架构问题的同时编写和调试底层代码。本文提出HINT，这是一种介于行为规范或可执行预言机与RTL之间的可执行硬件意图中间表示层。HINT明确了与RTL相关的微架构，支持RTL生成前的检查，并提供明确的RTL转换约束。我们通过最小化单智能体流程和完整的分阶段工作流对HINT进行评估：在7个算子案例中，无需后综合QoR（质量与结果）优化的HINT介导路径在全部7个案例中生成了符合契约要求的可综合RTL；直接C2RTL适用于5个案例，成功率为5/5；C2HLS适用于5个案例，成功率为1/5。在使用Design Compiler进行匹配综合的条件下，与5个人工RTL实现相比，HINT将面积减少了5.0%至26.2%；与5个已接受的直接C2RTL结果相比，面积减少了8.9%至86.1%。RealBench AES、SDC，以及综合至561.67kμm²的Vortex VPU，进一步展示了HINT在规范驱动、协议丰富、内存丰富及分层设计方面的能力。在受控算子研究中，HINT介导路径展现出更好的收敛性，且避免了直接生成结果中出现的严重实现质量下降问题。
英文摘要
Generating implementation-quality RTL with large language models (LLMs) remains difficult because direct generation must resolve microarchitecture while simultaneously producing and debugging low-level code. We present HINT, an executable hardware-intent intermediate representation layer between behavioral specifications or executable oracles and RTL. HINT makes RTL-relevant microarchitecture explicit, supports pre-RTL checking, and supplies explicit RTL-lowering obligations. We evaluate HINT using both a minimal single-agent flow and a full staged workflow. Across seven operator cases, the HINT-mediated route, with no post-synthesis QoR refinement, produces contract-compliant synthesizable RTL on 7/7 cases; Direct C2RTL and C2HLSC apply to five cases and succeed on 5/5 and 1/5, respectively. Under matched Design Compiler synthesis, HINT reduces area by 5.0\%--26.2\% relative to five manual RTL implementations and by 8.9\%--86.1\% relative to five accepted Direct C2RTL results. RealBench AES and SDC, together with a Vortex VPU synthesizing to 561.67k~$μ\mathrm{m}^2$, further demonstrate specification-driven, protocol-rich, memory-rich, and hierarchical designs. In the controlled operator study, the HINT-mediated route shows better observed convergence and avoids the severe implementation-quality degradation seen in several direct-generation results.
