AI 中文总结
本文提出PACT框架，用于Vivado设计检查点的后路由调优，在35个UltraScale+检查点上将F_max几何平均提升22.30%，速度较DATuner快6.4倍，令牌成本仅0.16美元/ DCP。
AI 中文摘要
后期FPGA时序收敛通常从已实现的设计开始，其时序报告中仍存在可见的违例。工程变更单（ECO）优化是对这类设计应用局部变更而无需重启完整实现流程的标准机制。自动化后路由ECO优化仍具挑战性，因为后路由变更必须在不违反路由合法性、保持或脉冲宽度时序约束、检查点可重放性或功能等价性的前提下改善时序。本文提出PACT，这是一种针对Vivado设计检查点（DCP）的后路由代理检查点调优框架。PACT将后路由调优表示为已接受与候选检查点之间经验证门控的转换。基于检查点衍生的证据，代理通过基于配置文件的规划器，从Vivado和RapidWright的各类工具技能中选择局部后端操作，并在隔离工作空间中探测工具行为。PACT将每次试验记录为证据门控案例，以指导候选生成并抑制不安全、不支持或无效的操作。在35个UltraScale+后路由检查点上，PACT使验证通过的最大工作频率（F_max）的几何平均提升了+22.30%，而原始实现的对应基准为，DATuner的提升为+15.14%，Codex Agent的提升为+9.78%。在共享设计上，PACT的运行速度比无上限的DATuner快6.4倍，且每个DCP的平均令牌成本仅为0.16美元，比自由形式的Codex Agent低24.5倍。源代码可在匿名代码库中获取。
英文摘要
Late-stage FPGA timing closure often starts from an implemented design whose remaining violations are visible in timing reports. Engineering change order (ECO) optimization is a standard mechanism for applying localized changes to such designs without restarting the full implementation flow. Automating post-route ECO optimization remains challenging. A post-route change must improve timing without violating routing legality, hold or pulse-width timing constraints, checkpoint replayability or functional equivalence. This paper presents PACT, a Post-route Agentic Checkpoint Tuning framework for Vivado design checkpoints (DCP). PACT represents post-route tuning as validation-gated transitions between accepted and candidate checkpoints. From checkpoint-derived evidence, an agent selects localized backend actions through a profile-driven recipe planner over typed Vivado and RapidWright skills, and probes tool behavior in isolated workspaces. PACT records each trial as an evidence-gated case to guide candidate generation and suppress unsafe, unsupported or ineffective actions. Across 35 UltraScale+ post-route checkpoints, PACT improves validation-clean $F_{\max}$ (maximum operating frequency) by a geometric mean of $+22.30\%$ over the original implementations, compared with $+15.14\%$ for DATuner and $+9.78\%$ for the Codex Agent. On shared designs, PACT achieves these gains $6.4\times$ faster than the uncapped DATuner and at an average token cost of only \$0.16 per DCP ($24.5\times$ lower than the free-form Codex Agent). The source code is available in an anonymous repository
CommentsAccepted to the 2026 International Conference on Field-Programmable Technology (FPT 2026)
