paperbot · PL 论文追踪

全部论文 待读 收藏

P2 FPGA Technology Mapping Using Sketch-Guided Program Synthesis

基于草图引导程序合成的 FPGA 技术映射
ASPLOS Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 22024匹配度 2/10 · 论文属于程序合成与 FPGA 技术映射，虽有形式正确性保证，但未涉及用户核心关注的 LLM/Agent 与静态分析交叉、浮点程序分析或贝叶斯程序分析。其应用场景为硬件综合而非机器学习系统或 Agentic 程序分析，因此与研究方向匹配度很低。引用 10 inbox
Gus Henry Smith, Benjamin Kushigian, Vishal Canumalla, Andrew Cheung, Steven Lyubomirsky, Sorawee Porncharoenwase, René Just, Gilbert Louis Bernstein, Zachary Tatlock
程序合成语言与体系结构
crossref: 2026-09-12dblp: 2026-09-12arxiv: 2026-09-12

AI 速览

一句话：提出 Lakeroad，用架构无关草图模板与 HDL 语义提取引导程序合成，实现可扩展且带正确性保证的 FPGA 技术映射。

FPGA 技术映射将高层 HDL 设计实现为目标 FPGA 的底层架构相关原语。随着 FPGA 日益异构，映射到 DSP 等复杂可配置原语需要更好的综合工具；现有工具依赖手写特例规则，费力、易错且常漏掉映射机会。本文提出 Lakeroad，一种基于草图引导程序合成的技术映射方法。它利用架构无关的草图模板和从 HDL 中提取语义，使映射可扩展，并提供比现有工具更强的正确性保证和更高的映射机会覆盖率。在代表性微基准上，Lakeroad 生成的最优映射数量约为专有最先进工具的 2–3.5 倍、主流开源工具的 6–44 倍，同时提供其他工具不具备的正确性保证。

问题
如何自动、正确且高覆盖地将 HDL 设计映射到异构 FPGA 的复杂可配置原语（如 DSP），避免依赖繁琐且易错的手写特例映射规则。
方法
提出 Lakeroad，采用架构无关的草图模板和从 HDL 提取的语义，通过草图引导的程序合成来生成目标 FPGA 原语上的映射。
评估
在代表性微基准上，将 Lakeroad 生成的最优映射数量与专有及开源最先进工具比较，并检查其正确性保证。
原文摘要（Abstract）

FPGA technology mapping is the process of implementing a hardware design expressed in high-level HDL (hardware design language) code using the low-level, architecture-specific primitives of the target FPGA. As FPGAs become increasingly heterogeneous, achieving high performance requires hardware synthesis tools that better support mapping to complex, highly configurable primitives like digital signal processors (DSPs). Current tools support DSP mapping via handwritten special-case mapping rules, which are laborious to write, error-prone, and often overlook mapping opportunities. We introduce Lakeroad, a principled approach to technology mapping via sketch-guided program synthesis. Lakeroad leverages two techniques---architecture-independent sketch templates and semantics extraction from HDL---to provide extensible technology mapping with stronger correctness guarantees and higher coverage of mapping opportunities than state-of-the-art tools. Across representative microbenchmarks, Lakeroad produces 2--3.5× the number of optimal mappings compared to proprietary state-of-the-art tools and 6--44× the number of optimal mappings compared to popular open-source tools, while also providing correctness guarantees not given by any other tool.

链接与引用

DOI 原文 · arXiv · PDF（开放获取） · DBLP

BibTeX 
@inproceedings{SmithKCCLPJBT24,
  title = {FPGA Technology Mapping Using Sketch-Guided Program Synthesis},
  author = {Gus Henry Smith and Benjamin Kushigian and Vishal Canumalla and Andrew Cheung and Steven Lyubomirsky and Sorawee Porncharoenwase and René Just and Gilbert Louis Bernstein and Zachary Tatlock},
  booktitle = {ASPLOS},
  year = {2024},
  doi = {10.1145/3620665.3640387}
}