Analysis and Optimization of the Implicit Broadcasts in FPGA HLS to Improve Maximum Frequency
Licheng Guo, Jason Lau, Yuze Chi, Jie Wang, Cody Hao Yu, Zhe Chen, Zhiru Zhang, Jason Cong
摘要
Designs generated by high-level synthesis (HLS) tools typically achieve a lower frequency compared to manual RTL designs. In this work, we study the timing issues in a diverse set of realistic and complex FPGA HLS designs. (1) We observe that in almost all cases the frequency degradation is caused by the broadcast structures generated by the HLS compiler. (2) We classify three major types of broadcasts in HLS-generated designs, including high-fanout data signals, pipeline flow control signals and synchronization signals for concurrent modules. (3) We reveal a number of limitations of the current HLS tools that result in those broadcast-related timing issues. (4) We propose a set of effective yet easy-to-implement approaches, including broadcast-aware scheduling, synchronization pruning, and skid-buffer-based flow control. Our experimental results show that our methods can improve the maximum frequency of a set of nine representative HLS benchmarks by 53% on average. In some cases, the frequency gain is more than 100 MHz.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper4
- Serpens: a high bandwidth memory based accelerator for general-purpose sparse matrix-vector multiplicationLinghao Song, Yuze Chi, Licheng Guo, Jason CongDAC 2022 · 被引用 56 次
- ReGraph: Scaling Graph Processing on HBM-enabled FPGAs with Heterogeneous PipelinesXinyu Chen, Yao Chen, Feng Cheng, Hongshi Tan 等MICRO 2022 · 被引用 46 次
- HeteroRefactor: refactoring for heterogeneous computing with FPGAJason Lau, Aishwarya Sivaraman, Qian Zhang, Muhammad Ali Gulzar 等ICSE 2020 · 被引用 12 次
- Proteus: Heterogeneous FPGA VirtualizationFelix Gust, Shu Anzai, Charalampos Mainas, Atsushi Koshiba 等EuroSys 2026
它引用的顶会 Paper2
相关 Paper
- An Iterative Method for Mapping-Aware Frequency Regulation in Dataflow CircuitsCarmine Rizzi, Andrea Guerrieri, Lana JosipovicDAC 2023 · 被引用 5 次
- Optimizing Recovery Logic in Speculative High-Level SynthesisDylan Leothaud, Jean-Michel Gorius, Simon Rokicki, Steven DerrienDAC 2025
- CRUSH: A Credit-Based Approach for Functional Unit Sharing in Dynamically Scheduled HLSJiahui Xu, Lana JosipovicASPLOS 2025 · 被引用 1 次
- PipeLink: A Pipelined Resource Sharing System for Dataflow High-Level SynthesisRui Li, Lincoln Berkley, Rajit ManoharDAC 2025
- OmniSim: Simulating Hardware with C Speed and RTL Accuracy for High-Level Synthesis DesignsRishov Sarkar, Cong HaoMICRO 2025 · 被引用 3 次
