Search papers, labs, and topics across Lattice.
VPR-Evolve introduces a multi-agent framework that evolves the source code of the Versatile Place and Route (VPR) engine to optimize FPGA designs, moving beyond traditional hyperparameter tuning. By leveraging LLM agents to propose and evaluate code modifications, the framework achieves significant improvements in critical-path delay, routed wirelength, and tool runtime across various benchmark circuits. The results show up to a 2.7% enhancement in a composite score compared to stock VPR, with reductions in critical-path delay by up to 9.8% and tool runtime by up to 79.3%.
Evolving the source code of FPGA placement and routing tools can yield up to 2.7% better performance than conventional hyperparameter tuning.
CAD tools typically apply the same fixed, hand-designed algorithms across circuits with widely different structural and timing characteristics. A common way to specialize these one-size-fits-all flows to a target design is to tune the CAD tool's hyperparameters. However, hyperparameter tuning can only select among behaviors already implemented by the fixed algorithm, limiting the achievable quality of results while requiring many expensive place-and-route evaluations. We present VPR-Evolve, a multi-agent framework that specializes Versatile Place and Route (VPR), the open-source FPGA pack-place-and-route engine in the Verilog-to-Routing (VTR) flow, by evolving its source code for each design. VPR-Evolve uses LLM agents to propose, implement, and evaluate code-level modifications, while a shared memory records prior outcomes and guides subsequent evolution. Every candidate is evaluated through a complete VPR build and run, directly optimizing a composite score measured as a weighted function of critical-path delay (CPD), routed wirelength (WL), and tool runtime (RT). Across five VTR-9 benchmark circuits, VPR-Evolve improves the composite score by up to 2.7% over stock VPR in VTR-9. Relative to stock VPR, it reduces CPD by up to 9.8%, routed WL by up to 18.1%, and tool RT by up to 79.3%. VPR-Evolve reduces CPD by up to 6.0%, routed WL by up to 2.2%, and tool RT by up to 7.8% compared with a hyperparameter-tuning baseline.
