Image Processing on Multicore x86 Architectures
Daehyun Kim, Victor C. S. Lee, Yen-Kuang Chen · IEEE Signal Processing Magazine · 2010
As multi-core architectures overtake single-core architectures in today's and future compute systems, traditional applications with sequential algorithms can no longer rely on technology scaling to improve performance. Instead, applications must switch to parallel algorithms to take advantage of multicore system performance. Image processing applications exhibit a high degree of parallelism and are excellent candidate for multicore systems. However, simply exploiting parallelism is not enough to achieve the best performance. Optimization must take into account underlying architecture characteristics such as wide vector and limited bandwidth. This paper illustrates techniques that can be used to optimize performance for multi-core x86 systems on three key image processing kernels (fast Fourier transform, convolution and histogram).