7 search results - page 2 / 2 » Performance Improvement of Multimedia Kernels by Alleviating... |
CF
2005
ACM
13 years 7 months ago
2005
ACM
In this paper we employ two techniques suitable for embedded media processors. The first technique, extended subwords, uses four extra bits for every byte in a media register. Th...
PPOPP
2010
ACM
14 years 2 months ago
2010
ACM
Loop vectorization, a key feature exploited to obtain high performance on Single Instruction Multiple Data (SIMD) vector architectures, is significantly hindered by irregular memo...