high performance computing on graphics processing units: hgpu.org

In this paper, we focus on the signal precoding stage in multiuser multicarrier systems, which can be often a computationally expensive task. In order to reduce their computational time, the implementation of some of the most employed multiuser precoding algorithms on a general purpose Graphic Processing Unit (GPU) is presented. These devices allow for a high level of parallel processing that can accelerate the time required for the signal precoding calculation. Results show that a speed-up of up to 4 is achieved when comparing the implementation on GPU with the conventional execution on a high performance CPU.