See it to Place it: Evolving Macro Placements with Vision-Language Models

Abstract

We propose using Vision-Language Models (VLMs) for macro placement in chip floorplanning, a complex optimization task that has recently shown promising advancements through machine learning methods. Because human designers rely heavily on spatial reasoning to arrange components on the chip canvas, we hypothesize that VLMs with strong visual reasoning abilities can effectively complement existing learning-based approaches. We introduce VeoPlace (Visual Evolutionary Optimization Placement), a novel framework that uses a VLM, without any fine-tuning, to guide the actions of a base placer by constraining them to subregions of the chip canvas. The VLM proposals are iteratively optimized through an evolutionary search strategy with respect to resulting placement quality. On open-source benchmarks, VeoPlace outperforms the best prior learning-based approach on 9 of 10 benchmarks with peak wirelength reductions exceeding 32%. We further demonstrate that VeoPlace generalizes to analytical placers, improving DREAMPlace performance on all 8 evaluated benchmarks with gains up to 4.3%. Our approach opens new possibilities for electronic design automation tools that leverage foundation models to solve complex physical design problems.

Figures (11)

• Figure 1: VeoPlace framework overview. The VLM suggests placement regions (1-2) to constrain a low-level placer (3) for macro placement (4). A history buffer that stores the existing population of placements (5) facilitates evolutionary in-context improvement, creating a feedback loop to improve placement quality.
• Figure 2: VLM guidance visualization on superblue1. Left: Final macro placement produced by VeoPlace + DREAMPlace 4.3.0. Right: The same placement with VLM-suggested regions overlaid. The VLM proposes target positions for each macro, and DREAMPlace's loss function is modified with anchor weights to keep macros close to VLM suggestions while allowing standard cells to optimize freely (standard cells removed for visual clarity).
• Figure 3: Visual comparison of placements on selected Superblue benchmarks. Top row: DREAMPlace 4.3.0. Bottom row: VeoPlace-guided DREAMPlace. Blue clouds are individual standard cells; colored rectangles are macros. VeoPlace guidance improves global HPWL on all eight superblue benchmarks.
• Figure 4: Design choice ablations on superblue1 with VeoPlace guiding DREAMPlace 4.3.0. Unless varied, ablation defaults are: top stratified (TS) strategy, $C{=}10$, $\lambda_A{=}0.01$ (note: the main Superblue results in \ref{['tab:superblue_results']} use $C{=}25$). (a) Lower anchor weights perform best, giving the analytical placer freedom to optimize standard cells around macros. (b) Longer context ($C{=}25$) achieves lower HPWL. (c) All strategies improve with further rollouts. (d) For all strategies, invalid suggestion rate converges to ${\sim}20\%$.
• Figure 5: VeoPlace's VLM-guided placement on adaptec4. (a) VLM proposes initial regions ($t=0$); policy is unconstrained for macros without valid suggestions. (b) Mid-placement ($t=T/2$). (c) Final placement ($t=T$), with the policy operating within VLM constraints.