Scalable Heterogeneous CPU-GPU Computations for Unstructured Tetrahedral Meshes

Heterogeneous Sparse Matrix Computations on Hybrid GPU/CPU Platforms

Hybrid GPU/CPU clusters are becoming very popular in the scientific computing community, as attested by the number of such systems present in the Top 500 list. In this paper, we address one of the key algorithms for scientific applications: the computation of sparse matrix-vector products that lies at the heart of iterative solvers for sparse linear systems. We detail how design patterns for sp...

Runtime specialization for heterogeneous CPU-GPU platforms

Cache optimization for CPU - GPU heterogeneous processors ∗

Microprocessors combining CPU and GPU cores using a common last-level cache pose new challenges to cache management algorithms. Since GPU cores feature much higher data access rates than CPU cores, the majority of the available cache space will be used by GPU applications, leaving only very limited cache capacity for CPU applications, which may be disadvantageous for overall system performance....

Force-Directed Methods for Smoothing Unstructured Triangular and Tetrahedral Meshes

MeshView: A Tool for Exploring 3D Unstructured Tetrahedral Meshes

We have developed a visualization module, MeshView, for viewing large-scale 3D un-structured tetrahedral nite element meshes. The module includes two diierent approaches for visualization and analysis, plus the capability to edit meshes after the researcher has analyzed the mesh and located problem areas. The rst approach ooers various real-time interactive manipulation options for visualizing ...