Performance Evaluation of Cauchy Reed-Solomon Coding on Multicore Systems

We have evaluated the performance of Cauchy Reed-Solomon (CRS) encoding of data blocks with sizes 32 kB to 256 MB. The performance measurements are done on an Intel processor with 4 cores and integrated graphics support. We also used an AMD graphics card in our performance evaluations. Three versions of the CRS algorithm are developed: one sequential version and two OpenCL versions. The OpenCL versions have been targeted to the CPU, the integrated GPU and the AMD graphics card. The measurements show that the graphics card performs better than CPU for large buffers. However, the highest throughput is obtained for one of the CPU versions and moderate buffer sizes (around 1 MB).