| Presentation | 2016-05-09 Optimization of Data Transfer and Kernel Execution for Video Processing Library RaVioli Kazuki Furuhashi, Kazuma Ono, Tomoaki Tsumura, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Programmers need to understand the complicated GPU structure deeply to utilize GPUs that can efficiently execute image and video processing. We have proposed a video processing library RaVioli/CUDA thatis an improvement of RaVioli for supporting a GPU platform called CUDA. RaVioli/CUDA frees programmersfrom special notations for CUDA programming. However, it still leaves place for utilizing GPUs. For solving thisproblem, we propose improvements of RaVioli/CUDA for utilizing GPUs by optimizing data transfer and kernelfunction execution. By the result of experiments with a video processing program, we show that the proposed method improves performance 3-fold against the traditional RaVioli/CUDA. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | image and video processing / CUDA |
| Paper # | CPSY2016-4,DC2016-4 |
| Date of Issue | 2016-05-02 (CPSY, DC) |
| Conference Information | |
| Committee | CPSY / DC / IPSJ-ARC |
|---|---|
| Conference Date | 2016/5/9(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Unaduki Suginoi Hotel |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Dependable Computing Systems, etc. (HotSPA: Hot SPring Annual meeting) |
| Chair | Yasuhiko Nakashima(NAIST) / Nobuyasu Kanekawa(Hitachi) / Masahiro Goshima(NII) |
| Vice Chair | Koji Nakano(Hiroshima Univ.) / Hidetsugu Irie(Univ. of Tokyo) / Michiko Inoue(NAIST) |
| Secretary | Koji Nakano(Fujitsu Labs.) / Hidetsugu Irie(NII) / Michiko Inoue(RTRI) / (Kyoto Sangyo Univ.) |
| Assistant | Shinya Takameda(NAIST) / Takeshi Ohkawa(Utsunomiya Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Computer Systems / Technical Committee on Dependable Computing / Special Interest Group on System Architecture |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Optimization of Data Transfer and Kernel Execution for Video Processing Library RaVioli |
| Sub Title (in English) | |
| Keyword(1) | image and video processing |
| Keyword(2) | CUDA |
| 1st Author's Name | Kazuki Furuhashi |
| 1st Author's Affiliation | Nagoya Institute of Technology(Nagoya Inst. of Tech.) |
| 2nd Author's Name | Kazuma Ono |
| 2nd Author's Affiliation | Nagoya Institute of Technology(Nagoya Inst. of Tech.) |
| 3rd Author's Name | Tomoaki Tsumura |
| 3rd Author's Affiliation | Nagoya Institute of Technology(Nagoya Inst. of Tech.) |
| Date | 2016-05-09 |
| Paper # | CPSY2016-4,DC2016-4 |
| Volume (vol) | vol.116 |
| Number (no) | CPSY-19,DC-20 |
| Page | pp.pp.15-20(CPSY), pp.15-20(DC), |
| #Pages | 6 |
| Date of Issue | 2016-05-02 (CPSY, DC) |