CPU–GPU Parallel Framework for Real‐Time Interactive Cutting of Adaptive Octree‐Based Deformable Objects

Simple item page
dc.contributor.authorJia, Shiyuen_US
dc.contributor.authorZhang, Weizhongen_US
dc.contributor.authorYu, Xiaokangen_US
dc.contributor.authorPan, Zhenkuanen_US
dc.contributor.editorChen, Min and Benes, Bedrichen_US
dc.date.accessioned2018-04-05T12:48:35Z
dc.date.available2018-04-05T12:48:35Z
dc.date.issued2018
dc.description.abstractA software framework taking advantage of parallel processing capabilities of CPUs and GPUs is designed for the real‐time interactive cutting simulation of deformable objects. Deformable objects are modelled as voxels connected by links. The voxels are embedded in an octree mesh used for deformation. Cutting is performed by disconnecting links swept by the cutting tool and then adaptively refining octree elements near the cutting tool trajectory. A surface mesh used for visual display is reconstructed from disconnected links using the dual contour method. Spatial hashing of the octree mesh and topology‐aware interpolation of distance field are used for collision. Our framework uses a novel GPU implementation for inter‐object collision and object self collision, while tool‐object collision, cutting and deformation are assigned to CPU, using multiple threads whenever possible. A novel method that splits cutting operations into four independent tasks running in parallel is designed. Our framework also performs data transfers between CPU and GPU simultaneously with other tasks to reduce their impact on performances. Simulation tests show that when compared to three‐threaded CPU implementations, our GPU accelerated collision is 53–160% faster; and the overall simulation frame rate is 47–98% faster.A software framework taking advantage of parallel processing capabilities of CPUs and GPUs is designed for real‐time interactive cutting simulation of adaptive octree‐based deformable objects. The framework uses a novel GPU implementation for inter‐object collision and object self collision, while other tasks are assigned to CPU, using multiple threads whenever possible. A novel method that splits cutting operations into 4 independent tasks running in parallel is designed. Simulation tests show that when compared to 3‐threaded CPU implementations, our GPU accelerated collision is 53% to 160% faster; and the overall simulation frame rate is 47% to 98% faster.en_US
dc.description.number1
dc.description.sectionheadersArticles
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume37
dc.identifier.doi10.1111/cgf.13162
dc.identifier.issn1467-8659
dc.identifier.pages45-59
dc.identifier.urihttps://doi.org/10.1111/cgf.13162
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13162
dc.publisher© 2018 The Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectdeformable object
dc.subjectphysics‐based modelling
dc.subjectinteractive cutting
dc.subjectadaptive octree mesh
dc.subjectGPU acceleration
dc.subjectmulti‐threading
dc.subjectComputing methodologies—Massively parallel and high‐performance simulations
dc.subjectPhysical simulation
dc.titleCPU–GPU Parallel Framework for Real‐Time Interactive Cutting of Adaptive Octree‐Based Deformable Objectsen_US
Files
Collections
37-Issue 1