high performance computing on graphics processing units: hgpu.org

Future computing systems, from handhelds all the way to supercomputers, will be more parallel and more heterogeneous than today’s systems to provide more performance without an increase in power consumption. Therefore, GPUs are increasingly being used to accelerate general-purpose applications, including applications with data-dependent, irregular memory access patterns and control flow. The growing complexity, non-uniformity, heterogeneity, and parallelism will make these systems, i.e., GPGPU-accelerated systems, progressively more difficult to program. In the foreseeable future, the vast majority of programmers will no longer be able to extract additional performance or energy-savings from next-generation systems because their programming will be too difficult, i.e., the programmer will no longer possess the necessary expertise to understand and exploit the systems effectively. In this project, the characteristics of GPU codes will be quantified and, based on these metrics, different optimization suggestions will be made.