Skip to Main Content
By examining the speed-up resulting from using Pentium 4 SIMD instructions for DSP kernels (FFT) and two different multimedia programs (the MPEG-2 codec and a matching pursuit video codec), we discuss the hardware and software issues that limit performance. The cost of unaligned memory accesses and the lack of instructions summing the different parts of an XMM register in the present implementation of Intel SIMD instructions limit the efficiency of dot products. C programmer's habits often prevent compiler vectorization or complicate in-lining of assembly code in many DSP and multimedia applications.
Multimedia and Expo, 2002. ICME '02. Proceedings. 2002 IEEE International Conference on (Volume:2 )
Date of Conference: 2002