Dual-Core Framework: Eliminating the Bottleneck Effect of Scalar Kernels on SIMD Architectures
スポンサーリンク
概要
- 論文の詳細を見る
The efficiency of ubiquitous SIMD (Single Instruction Multiple Data) media processors is seriously limited by the bottleneck effect of the scalar kernels in media applications. To solve this problem, a dual-core framework, composed of a micro control unit and an instruction buffer, is proposed. This framework can dynamically decouple the scalar and vector pipelines of the original single-core SIMD architecture into two free-running cores. Thus, the bottleneck effect can be eliminated by effectively exploiting the parallelism between scalar and vector kernels. The dual-core framework achieves the best attributes of both single-core and dual-core SIMD architectures. Experimental results exhibit an average performance improvement of 33%, at an area overhead of 4.26%. What's more, with the increase of the SIMD width, higher performance gain and lower cost can be expected.
著者
-
CHEN Shuming
National University of Defense Technology
-
ZHANG Kai
National University of Defense Technology
-
WANG Yaohua
National University of Defense Technology
-
CHEN Hu
National University of Defense Technology
-
WAN Jianghua
National University of Defense Technology
-
LIU Sheng
National University of Defense Technology
関連論文
- Dual-Core Framework: Eliminating the Bottleneck Effect of Scalar Kernels on SIMD Architectures
- Cooperative communication based barrier synchronization in on-chip mesh architectures