基于Cache优化的大点数FFT在TS201上的实现
doi: 10.3724/SP.J.1146.2012.01608
Cache-optimized Implementation of Long Sequences FFT on TS201
-
摘要: 该文针对现有大点数快速傅里叶变换(FFT)在TS201处理器上的实现没有充分考虑Cache丢失对执行效率影响的问题,提出了改进型Winograd算法的实现方法。该改进型方法通过优化行列读取方法,最大程度利用Cache的读写特点,避免了三次显性转置;并通过重构蝶形运算,隐藏了乘铰链因子。实例测试与现有处理方法对比结果表明,Cache优化的大点数FFT执行速度有了明显提高,可用于雷达处理系统中的脉冲压缩的快速实现。Abstract: This paper proposes an improved method for Winograd algorithm to solve the problem that the existing methods of long sequences Fast Fourier Transform (FFT) on the TS201 processor does not take full account of the Caches miss influence on efficiency. The new method makes maximum use of the Caches advantages in reading and writing by optimizing the access method of rows and columns to avoid three explicitly matrix transposition, and hiding the twiddle factor multiplication by reconfiguration butterfly computation. Test results show that the performance of Cache-optimized implementation of FFT is significantly improved, and it can be used for fast acquisition of pulse-compression in radar system.
-
Key words:
- Radar signal processing /
- Pulse-compression /
- TS201 /
- Cache /
- Winograd algorithm /
- Long sequences FFT
-
计量
- 文章访问数: 2443
- HTML全文浏览量: 96
- PDF下载量: 927
- 被引次数: 0