Name
Abstract | ||
|---|---|---|
•We propose a register blocking method for GEMV on GPU.•The proposed method can improve the parallelism and reuse data on chip at the same time.•Different block sizes are tested to found the best block size on a GPU platform. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1016/j.jvcir.2014.06.002 | Journal of Visual Communication and Image Representation |
Keywords | Field | DocType |
GEMV,Register blocking,Data reuse,Memory bandwidth,GPU,Many-core,Parallelization,CUDA | Kernel (linear algebra),Memory bandwidth,Matrix (mathematics),Computer science,CUDA,Parallel computing,Image processing,Thread (computing),Multiplication,Speedup | Journal |
Volume | Issue | ISSN |
25 | 7 | 1047-3203 |
Citations | PageRank | References |
2 | 0.45 | 8 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jian Yin | 1 | 861 | 97.01 |
| Hui Yu | 2 | 2 | 0.45 |
| XU Wei-Zhi | 3 | 36 | 8.65 |
| Yuxuan Wang | 4 | 2 | 0.45 |
| Zhu Tian | 5 | 2 | 0.45 |
| Yingping Zhang | 6 | 2 | 0.45 |
| Bochuan Chen | 7 | 2 | 0.45 |