University of North Texas Digital Library (University of North Texas) · 1993 · 22 citations · 2 references
Open access
ComputingComputer ScienceHigh-performance ComputingComputer ArchitectureDistributed SystemsParallel ComputingDistributed ComputingDistributed Memory ParallelismDistributed Memory SystemsMatrix ComputationNumerical Linear AlgebraParallel ArchitecturesComputational Linear AlgebraDense Linear AlgebraDistributed Linear AlgebraDistributed MemoryDistributed-memory ArchitecturesHigh PerformanceSparse Linear AlgebraSparse Matrix Computation
We describe the design of ScaLAPACK++, an object oriented C++ library for implementing linear algebra computations on distributed memory multicomputers. This package, when complete, will support distributed matrix operations for symmetric, positive-definite, and non-symmetric cases. In ScaLAPACK++ we have employed object oriented design methods to enchance scalability, portability, flexibility, and ease-of-use. We illustrate some of these points by describing the implementation of basic algorithms and comment on tradeoffs between elegance, generality, and performance.
2
Data redistribution and concurrency
Eric F. Van de Velde · Parallel Computing · 1990 · 23 citations