High Quality Real-Time Image-to-Mesh Conversion for Finite Element Simulations

Abstract

In this poster, we present a parallel Image-to-Mesh Conversion (I2M) algorithm with quality and fidelity guarantees achieved by dynamic point insertions and removals. Starting directly from an image, it is able to recover the surface and mesh the volume with tetrahedra of good shape. Our tightly-coupled shared-memory parallel speculative execution paradigm employs carefully designed memory and contention managers, load balancing, synchronization and optimizations schemes, while it maintains high single-threaded performance: our single-threaded performance is faster than CGAL, the state of the art sequential I2M software we are aware of. Our meshes come also with theoretical guarantees: the radius-edge is less than 2 and the planar angles of the boundary triangles are more than 30 degrees. The effectiveness of our method is shown on Blacklight, the large cache-coherent NUMA machine of Pittsburgh Supercomputing Center. We observe a more than 74% strong scaling efficiency for up to 128 cores and a super-linear weak scaling efficiency for up to 128 cores.