high performance computing on graphics processing units: hgpu.org

In this paper, we further develop a family of parallel time integrators known as Revisionist Integral Deferred Correction methods (RIDC) to allow for the semi-implicit solution of time dependent PDEs. Additionally, we show that our semi-implicit RIDC algorithm can harness the computational potential of multiple general purpose graphical processing units (GPGPUs) by utilizing existing CUBLAS libraries for matrix linear algebra routines in our implementation. In the numerical experiments, we show that our implementation computes a fourth order solution using four GPGPUs and four CPUs in approximately the same wall clock time as a first order solution computed using a single GPGPU and a single CPU.