KokkosKernels is a library for node-level, performance-portable, computational kernels for sparse/dense linear algebra and graph operations, using the Kokkos shared-memory parallel programming model. The focus is on computational kernels that are coarse-grained operations; they take a lot of work and make sense to parallelize inside using Kokkos. KokkosKernels can be the building block of a solver, linear algebra library that uses MPI and threads for parallelism, or it can be used stand-alone in an application.


Karen Devine

Sandia National Laboratories, P.O. Box 5800, MS 1318, Albuquerque, NM 87185-1318