電子情報通信学会 = The Institute of Electronics, Information and Communication Engineers
抄録
This paper presents efficient implementa- tion of RLS-based adaptive filters with a large number of taps on nVIDIA GeForce graphics processing unit (GPU) and CUDA software development environment. Modification of the order and the combination of calcu- lations reduces the number of accesses to slow off-chip memory. Assigning tasks into multiple threads also takes memory access order into account. Multiple shader pro- cessor arrays are used to handle a large matrix. For a 8192-tap case, a GPU program is almost 30-times faster than a CPU program. Real-time processing is possible for an 8kHz-sampling and 512-tap case by us- ing 32 shader processors, which is only 25% of GeForce 8800GTS.
Efficient Implementation of RLS-Based Adaptive Filterson nVIDIA GeForce Graphics Processing Unit
TE-PR-HIRANO-A-241.pdf
(104.19KB)
