MPI programs are more difficult to debug than other programs because of their parallel nature. The MPI programming model follows the single program multiple data paradigm or the multiple program multiple data paradigm. Debugging MPI programs is complicated by the following characteristics: Several processes run in parallel in a coordinated way. These processes may all… Continue reading MPI debugging
In earlier posts I gave an introduction to the Message Passing Library (MPL). With MPL processes can send and receive messages with data of different data types. What kind of data types are supported by MPL? MPL supports the same kinds of elementary data types as MPI does. These are: the integer types char, short… Continue reading MPL – Data types
In a previous post I gave a very short introduction to the Message Passing Library (MPL), which is a C++ message passing library based on MPI. Although it does not provide a direct mapping of the C API to C++ it comes with all modes of collective communication as defined be the MPI standard, e.g.,… Continue reading MPL – Collective communication
The Message Passing Interface (MPI) Standard defines a message passing library, which serves as the basis for many high-performance computing applications today. It provides portable scalable functions for data exchange in parallel computations for various parallel computing architectures. Originally application programing interfaces had been defined for C and Fortran as well as for C++. In… Continue reading MPL – A message passing library
CUDA and MPI provide two different APIs for parallel programming that target very different parallel architectures. While CUDA allows to utilize parallel graphics hardware for general purpose computing, MPI is usually employed to write parallel programs that run on large SMP systems or on cluster computers. In order to improve a cluster’s overall computational capabilities… Continue reading CUDA-aware MPI
In a recent paper (see arXiv:1012.3911) we showed how to solve the time-dependent Schrödinger equation and the time-dependent Dirac equation by a Fourier split operator method on GPU hardware. For the Fourier split operator method one has to compute a fast Fourier transform (FFT) in each time step and the FFT dominates the overall computing… Continue reading GPU FFT performance
In past postings I wrote on fast Fourier transform (FFT) performance and on GPU computing. In a new project both topics meet. We evaluated the FFT performance on GPUs. We found performance gains of more than one order of magnitude as compared to traditional (non-parallel) CPU codes. The FFT is a core algorithm that finds… Continue reading Accelerating the Fourier split operator method
A new version of TRNG (Tina’s Random Number Generator Library) has been released. TRNG may be utilized in sequential as well as in parallel Monte Carlo simulations. It does not depend on a specific parallelization technique, e.g., POSIX threads, MPI or others. As an outstanding new feature of the latest TRNG release 4.11 it also… Continue reading New TRNG release
A few days ago, I started to gather a survey on GPU computing literature. The survey is non-exhaustive and has strong bias to computational physics applications. However, it might be useful for other GPU computing enthusiasts as well. Therefore, I publish my survey in this post. The list will be updated from time to time.… Continue reading GPU computing literature
Would you like to test your parallel programming skills? Then you might participate in the Intel Threading Challenge 2010 and demonstrate your skills in one of two levels of participation. Apprentice level gives programmers new to multithreading and parallelism. Master level targets developers with multithreading experience. Problem 1 of the 1st phase in Apprentice level… Continue reading Intel Threading Challenge 2010