| Popis: |
In this paper, we present a parallel algorithm for enumerating joint weight of a binary linear (n, k) code, aiming at accelerating assessment of its decoding error probability for network coding. To reduce the number of pairs of code words to be investigated, our parallel algorithm reduces dimension k by focusing on the all-one vector included in many practical codes. We also employ a population count instruction to compute joint weight of code words with a less number of instructions. Our algorithm is implemented on a multi-core CPU system and an NVIDIA GPU system using Open MP and compute unified device architecture (CUDA), respectively. We apply our implementation to a sub code of a (127,22) BCH code to evaluate the impact of acceleration. |
