GPU-Based High-Performance Computing in Science and Economics

Abstract

In the past few years, a new class of high-performance computing (HPC) systems has emerged. These systems employ unconventional processor architectures – such as cell accelerator and graphics processing units (GPUs) – for heavy computations and use conventional central processing units (CPUs) mostly for non-compute-intensive tasks, such as I/O and communication. General Purpose GPUs (GPGPUs) appear for scientific computing. A new concept is to use a GPGPU as a modified form of stream processor. This paper gives an overview of the state-of-the-art of the developments and applications in GPU-based high-performance computing for all platforms: applications, hardware and software technologies, languages and development environments.