Yu, PengWang, RuiqiLi, ChunleiLi, YuxuanZhai, XiaoHe, YuanboWu, HongyuHao, AiminGao, YangChristie, MarcHan, Ping-HsuanLin, Shih-SyunPietroni, NicoSchneider, TeseoTsai, Hsin-RueyWang, Yu-ShuenZhang, Eugene2025-10-072025-10-072025978-3-03868-295-0https://doi.org/10.2312/pg.20251267https://diglib.eg.org/handle/10.2312/pg20251267Real-time simulation of cutting is essential in fields requiring accurate interactions with digital assets, such as virtual manufacturing or surgical training. While Extended Position-Based Dynamics (XPBD) methods are valued for their numerical stability, their reliance on the Gauss-Seidel method leads to two critical limitations when facing high degrees of freedom: the residual stagnation that hinders convergence within limited temporal budget, and a fundamentally sequential nature that limits parallelization, thereby impeding real-time performance. Traditional parallelization approaches often rely on precomputed topological data that becomes outdated during mesh evolution, resulting in suboptimal performance in cutting applications. To address this limitation, this paper introduces a GPU-accelerated algorithm featuring an efficient constraint clustering preprocessing step to accelerate initial solver scheduling, combined with a novel graph coloring technique using GPU-optimized Shortcuts principles for parallel constraint resolution. Experiments show our combination of upfront clustering and dynamic graph re-coloring outperforms existing parallel XPBD implementations, empowering efficient solvers in virtual surgery, product design, and similar scenarios involving continuous geometry updates.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Computer GraphicsComputing methodologies → Computer Graphics10.2312/pg.2025126712 pages