DiffRouter speeds up FPGA routing with new gradient method

DiffRouter: A Differentiable Routing Framework for UltraScale FPGAs

Hardware Architecture

Summary

Routing electrical connections on very large FPGAs can be slow and inefficient because traditional methods handle one connection at a time and rely on trial-and-error fixes. The authors created DiffRouter, which treats routing as a continuous problem that can be solved all at once using gradients and GPUs, making it much faster. After this smooth optimization, it converts the solution back into real, usable FPGA connections. Tests show DiffRouter runs several times faster than existing tools while keeping wiring efficient.

What this means in practice

  • For fpga design engineers: Use DiffRouter to significantly reduce the time needed for routing large FPGA designs while maintaining efficient wire layouts.
  • For electronic design automation teams: Integrate DiffRouter’s differentiable routing framework into FPGA toolchains to improve parallel routing workflows and optimize routing resources at scale.

Authors

Xiaohan Gao, Zhili Xiong, Yusu Wang, David Z. Pan

Abstract

Routing has become a major bottleneck in large-scale FPGA design flows, where traditional routers rely on sequential net-by-net processing and rip-up-reroute heuristics. This inherent sequentialism limits parallelism, leads to suboptimal utilization of routing resources, and significantly increases runtime on modern FPGAs. This paper introduces DiffRouter, the first differentiable, gradient-based FPGA routing framework with GPU acceleration. By lifting routing into a continuous optimization space, DiffRouter enables highly concurrent routing and improved global optimality before projecting solutions back onto the discrete fabric. The framework consists of three key stages: (1) Resource-pruned preprocessing, which extracts compact routing variables per net to reduce memory footprint and problem complexity; (2) Differentiable global routing via gradient descent, which formulates routing as a Lagrangian-relaxed optimization that minimizes wirelength while iteratively enforcing connectivity and congestion constraints as relaxed terms; and (3) Postprocessing, which maps the continuous wire distributions to a valid UltraScale routing solution and completes solutions by detailed routing. Experiments on the FPGA 2024 Routing Contest benchmarks show that DiffRouter outperforms state-of-the-art parallel routers, achieving over 5x speedup over RWRoute and 2x over Vivado, and running 18% faster than the state-of-the-art academic FPGA router Potter while delivering competitive critical path wirelength.