high performance computing on graphics processing units: hgpu.org

We have ported an implementation of the spin-up for marine ecosystem models based on the "Transport Matrix Method" to graphics processing units (GPUs). The original implementation was designed for distributed-memory architectures and uses the PETSc library that is based on the "Message Passing Interface (MPI)" standard. The spin-up computes a steady seasonal cycle of the ecosystem tracers with climatological ocean circulation data as forcing. Since the transport is linear with respect to the tracers, the resulting operator is represented in so-called "transport matrices". Each iteration of the spin-up involves two matrix-vector multiplications and the evaluation of the used biogeochemical model. The original code was written in C and Fortran. On the GPU, we use the CUDA standard, a specialized version of the PETSc toolkit and a CUDA Fortran compiler. We describe the extensions to PETSc and the modifications of the original C and Fortran codes that had to be done. Here we make use of freely available libraries for the GPU. We analyze the computational effort of the main parts of the spin-up for two exemplary ecosystem models and compare the overall computational time to those necessary on different CPUs. The results show that a consumer GPU can beat a significant number of cluster CPUs without further code optimization.