| Presentation | 2018-11-10 Parallel processing area extraction and data transfer number reduction for automatic GPU offloading of IoT applications Yoji Yamato, Hirofumi Noguchi, Misao Kataoka, Takuma Isoda, Tatsuya Demizu, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | For Open IoT, we have proposed Tacit Computing technology to discover the devices that have data users need on demand and use them dynamically and an automatic GPU offloading technology as an elementary technology of Tacit Computing. However, it can improve limited applications because it only optimizes parallelizable loop statements extraction. Thus, in this paper, to improve performances of more applications automatically, we propose an improved method with reduction of data transfer between CPU and GPU. We evaluate our proposed offloading method by applying it to Darknet and find that it can process it 3 times as quickly as only using CPU. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Open IoT / GPGPU / Data Transfer Optimization / Genetic Algorithm / Automatic Offloading |
| Paper # | KBSE2018-37,SC2018-32 |
| Date of Issue | 2018-11-02 (KBSE, SC) |
| Conference Information | |
| Committee | KBSE / SC |
|---|---|
| Conference Date | 2018/11/9(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Fumihiro Kumeno(Nippon Inst. of Tech.) / Masahide Nakamura(Kobe Univ.) |
| Vice Chair | Hiroyuki Nakagawa(Osaka Univ.) / Shinji Kikuchi(Univ. of Aizu) / Yoji Yamato(NTT) |
| Secretary | Hiroyuki Nakagawa(NTT) / Shinji Kikuchi(Fujitsu labs.) / Yoji Yamato(NEC) |
| Assistant | Ryuichi Takahashi(Ibaraki Univ.) / Yoshinori Tanabe(Tsurumi Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Knowledge-Based Software Engineering / Technical Committee on Service Computing |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Parallel processing area extraction and data transfer number reduction for automatic GPU offloading of IoT applications |
| Sub Title (in English) | |
| Keyword(1) | Open IoT |
| Keyword(2) | GPGPU |
| Keyword(3) | Data Transfer Optimization |
| Keyword(4) | Genetic Algorithm |
| Keyword(5) | Automatic Offloading |
| 1st Author's Name | Yoji Yamato |
| 1st Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 2nd Author's Name | Hirofumi Noguchi |
| 2nd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 3rd Author's Name | Misao Kataoka |
| 3rd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 4th Author's Name | Takuma Isoda |
| 4th Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 5th Author's Name | Tatsuya Demizu |
| 5th Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| Date | 2018-11-10 |
| Paper # | KBSE2018-37,SC2018-32 |
| Volume (vol) | vol.118 |
| Number (no) | KBSE-292,SC-293 |
| Page | pp.pp.53-58(KBSE), pp.53-58(SC), |
| #Pages | 6 |
| Date of Issue | 2018-11-02 (KBSE, SC) |