Richard Seymour

Learn More
Stencil based computation on structured grids is a common kernel to broad scientific applications. The order of stencils increases with the required precision, and it is a challenge to optimize such high-order stencils on multicore architectures. Here, we propose a multilevel parallelization framework that combines: (1) inter-node parallelism by spatial(More)
Stencil computation (SC) is of critical importance for broad scientific and engineering applications. However, it is a challenge to optimize complex, high-order SC on emerging clusters of multicore processors. We have developed a hierarchical SC parallelization framework that combines: (1) spatial decomposition based on message passing; (2) multithreading(More)
In this paper, we apply in-core optimization techniques to high-order stencil computations, including: (1) cache blocking for efficient L2 cache use; (2) register blocking and data-level parallelism via single-instruction multiple-data (SIMD) techniques to increase L1 cache efficiency; and (3) software prefetching techniques. Our generic approach is tested(More)
A metascalable (or " design once, scale on new architectures ") parallel computing framework has been developed for large spatiotemporal-scale atomistic simulations of materials based on spatiotemporal data locality principles, which is expected to scale on emerging multipetaflops architectures. The framework consists of: (1) an embedded divide-and-conquer(More)
Allograft coronary disease is the dominant cause of increased risk of death after cardiac transplantation. While the percutaneous insertion of stents is the most efficacious revascularization strategy for allograft coronary disease there is a high incidence of stent renarrowing. We developed a novel rabbit model of sex-mismatched allograft vascular disease(More)
A scalable parallel algorithm has been designed to perform large-scale flow simulations based on the lattice Boltzmann method. The algorithm combines hierarchical spatial decomposition and a critical section-free, dual representation to expose maximal concurrency and data locality, thereby achieving isogranular parallel efficiency of 0.977 on 65,536 IBM(More)
A previous modelling study predicted that the forces applied by the extensor muscles to stabilise the lumbar spine would be greater in spines that have a larger sagittal curvature (lordosis). Because the force-generating capacity of a muscle is related to its size, it was hypothesised that the size of the extensor muscles in a subject would be related to(More)
Molecular dynamics simulations were performed to study the nanoindentation of NiAl and Ni 3 Al crystals on three surfaces: (100), (110), and (111). The calculated load-displacement curves show discrete drops at certain indentation depths, indicating dislocation bursts during indentation. The hardness values for the two materials were found to depend(More)