English

Implementation of float-float operators on graphics hardware

Hardware Architecture 2007-05-23 v1 Graphics

Abstract

The Graphic Processing Unit (GPU) has evolved into a powerful and flexible processor. The latest graphic processors provide fully programmable vertex and pixel processing units that support vector operations up to single floating-point precision. This computational power is now being used for general-purpose computations. However, some applications require higher precision than single precision. This paper describes the emulation of a 44-bit floating-point number format and its corresponding operations. An implementation is presented along with performance and accuracy results.

Keywords

Cite

@article{arxiv.cs/0603115,
  title  = {Implementation of float-float operators on graphics hardware},
  author = {Guillaume Da Graçca and David Defour},
  journal= {arXiv preprint arXiv:cs/0603115},
  year   = {2007}
}