Literature DB >> 33851145

AutoBridge: Coupling Coarse-Grained Floorplanning and Pipelining for High-Frequency HLS Design on Multi-Die FPGAs.

Licheng Guo1, Yuze Chi1, Jie Wang1, Jason Lau1, Weikang Qiao1, Ecenur Ustun2, Zhiru Zhang2, Jason Cong1.   

Abstract

Despite an increasing adoption of high-level synthesis (HLS) for its design productivity advantages, there remains a significant gap in the achievable frequency between an HLS design and a handcrafted RTL one. A key factor that limits the timing quality of the HLS outputs is the difficulty in accurately estimating the interconnect delay at the HLS level. This problem becomes even worse when large HLS designs are implemented on the latest multi-die FPGAs. To tackle this challenge, we propose AutoBridge, an automated framework that couples a coarse-grained floorplanning step with pipelining during HLS compilation. First, our approach provides HLS with a view on the global physical layout of the design, allowing HLS to more easily identify and pipeline the long wires, especially those crossing the die boundaries. Second, by exploiting the flexibility of HLS pipelining, the floorplanner is able to distribute the design logic across multiple dies on the FPGA device without degrading clock frequency. This prevents the placer from aggressively packing the logic on a single die which often results in local routing congestion that eventually degrades timing. Since pipelining may introduce additional latency, we further present analysis and algorithms to ensure the added latency will not compromise the overall throughput. AutoBridge can be integrated into the existing CAD toolflow for Xilinx FPGAs. In our experiments with a total of 43 design configurations, we improve the average frequency from 147 MHz to 297 MHz (a 102% improvement) with no loss of throughput and a negligible change in resource utilization. Notably, in 16 experiments we make the originally unroutable designs achieve 274 MHz on average. The tool is available at https://github.com/Licheng-Guo/AutoBridge.

Entities:  

Keywords:  Dataflow; Floorplan; Frequency; High-Level Synthesis; Latency Insensitive Design; Multi-Die FPGA; Pipeline; Timing Closure

Year:  2021        PMID: 33851145      PMCID: PMC8041363          DOI: 10.1145/3431920.3439289

Source DB:  PubMed          Journal:  FPGA


  2 in total

1.  Accelerating SSSP for Power-Law Graphs.

Authors:  Yuze Chi; Licheng Guo; Jason Cong
Journal:  FPGA       Date:  2022-02-11

2.  A Soft Coprocessor Approach for Developing Image and Video Processing Applications on FPGAs.

Authors:  Tiantai Deng; Danny Crookes; Roger Woods; Fahad Siddiqui
Journal:  J Imaging       Date:  2022-02-11
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.