Name
Abstract | ||
|---|---|---|
Vector-SIMD architectures have gained increasing attention because of their high performance in signal-processing applications. However, the performance of existing vector-SIMD architectures remains limited because of their inefficiency in the coordinated exploitation of different hardware units. To solve this problem, this article proposes the FT-Matrix architecture, which improves the coordination of traditional vector-SIMD architectures from three aspects: the cooperation between the scalar and SIMD unit is refined with the dynamic coupling execution scheme, the communication among SIMD lanes is enhanced with the matrix-style communication, and data sharing among vector memory banks is accomplished by the unaligned vector memory accessing scheme. Evaluation results show an average performance gain of 58.5 percent against vector-SIMD architectures without the proposed improvements. A four-core chip with each core built on the FT-Matrix architecture is also under fabrication. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/MM.2013.129 | IEEE Micro |
Keywords | Field | DocType |
simdu,signal processing,data communication,vector-simd architecture,coordination,vector-simd,scalar unit,vector memory accessing scheme,matrix algebra,matrix-style communication,dynamic coupling execution scheme,ft-matrix:,simd unit,su,coordination-aware architecture,data sharing,memory management,registers,kernel,hardware,vectors | Kernel (linear algebra),Memory bank,Signal processing,Architecture,Computer science,Data sharing,Parallel computing,SIMD,Chip,Memory management | Journal |
Volume | Issue | ISSN |
34 | 6 | 0272-1732 |
Citations | PageRank | References |
3 | 0.43 | 7 |
Authors | ||
9 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shuming Chen | 1 | 138 | 38.21 |
| Yaohua Wang | 2 | 44 | 14.23 |
| Sheng Liu | 3 | 7 | 4.06 |
| Jiang-Hua Wan | 4 | 15 | 5.86 |
| Haiyan Chen | 5 | 4 | 1.52 |
| Hengzhu Liu | 6 | 86 | 23.28 |
| Kai Zhang | 7 | 3 | 0.43 |
| Xiang-Yuan Liu | 8 | 11 | 2.45 |
| Xi Ning | 9 | 4 | 3.15 |