Modern Graphics Processing Units (GPUs) commonly found in today's PCs feature multiple processing units and can be used for general purpose computations and in particular, parallel numerical algorithms. But the available level of abstraction is still very low. Typically, GPU programs are written in assembly language. In this paper, the architecture which is still tightly coupled to the rasterisation algorithm that GPUs are originally meant to implement, and some of the algorithms efficiently implemented on GPUs so far, will be presented. The strengths and weaknesses of GPUs and approaches towards the goal of an easily programmable GPU are presented.
展开▼
