Meta-programming and Multi-stage Programming for GPGPUs
Ian Masliah, Marc Baboulin, Joël Falcou · 2016
GPGPUs and other accelerators are becoming a mainstream asset for high-performance computing. Raising the programmability of such hardware is essential to enable users to discover, master and subsequently use accelerators in day-to-day simulations. Furthermore, tools for high-level programming of parallel architectures are becoming a great way to simplify the exploitation of such systems. For this reason, we have extended NT2 - the Numerical Template Toolbox - a C++ scientific computing library which can generate code for SIMD and multithreading systems in a transparent way using a MATLAB like syntax. In this paper, we study how to introduce an accelerator based programming model into this library to allow developers to reap the benefits of such an architecture. After a brief description of the NT2 framework, we explain how our accelerator programming model has been designed and integrated in a pure C++ library. We conclude by showing the applicability and performance of this tool on some practical applications.