Constrained meshes play an important role in freeform architectural design, as they can represent panel layouts on freeform surfaces. It is challenging to perform realtime manipulation on such meshes, because all constraints need to be respected during the deformation while the shape quality needs to be maintained. This usually leads to nonlinear constrained optimization problems, which are challenging to solve in real time. In this paper, we present a GPU-based shape manipulation tool for constrained meshes, using the parallelizable algorithm proposed in [8]. We discuss the main challenges and solutions for the GPU implementation, and provide timing comparison against a CPU implementation of the algorithm. Our GPU implementation significantly outperforms the CPU version, allowing realtime handle-based deformation for large constrained meshes.