Presentation | 2015-08-04 An Effective Scheduling of Data Transfer for GPU Applications Kazuma Ono, Ryo Takeshima, Tomoaki Tsumura, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Utilizing a GPU to perform general purpose computation is called GPGPU. The high theoretical performance of GPU draws attention to GPGPU. For the GPU programming, CUDA supplies an architecture model for parallel processing. A CUDA-enabled GPU has hardware supports for executing different functions concurrently. For using the hardware supports efficiently, developers should troublesomely schedule the execution order of functions appropriately. Kernel Reordering is one of the studies for supporting the function-scheduling. However, Kernel Reordering does not handle data transfer, and data transfer and function execution are serialized even if they have no dependency each other. To address this problem, we improve Kernel Reordering to schedule not onlyfunctions but also data transfer. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | GPGPU / CUDA / Concurrent Kernel Execution |
Paper # | CPSY2015-23 |
Date of Issue | 2015-07-28 (CPSY) |
Conference Information | |
Committee | CPSY / DC / IPSJ-ARC |
---|---|
Conference Date | 2015/8/4(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | B-Con Plaza (Beppu) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Parallel, Distributed and Cooperative Processing |
Chair | Yasuhiko Nakashima(NAIST) / Nobuyasu Kanekawa(Hitachi) |
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) | An Effective Scheduling of Data Transfer for GPU Applications |
Sub Title (in English) | |
Keyword(1) | GPGPU |
Keyword(2) | CUDA |
Keyword(3) | Concurrent Kernel Execution |
1st Author's Name | Kazuma Ono |
1st Author's Affiliation | Nagoya Institute of Technology(Nagoya Inst. of Tech.) |
2nd Author's Name | Ryo Takeshima |
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 | 2015-08-04 |
Paper # | CPSY2015-23 |
Volume (vol) | vol.115 |
Number (no) | CPSY-174 |
Page | pp.pp.85-90(CPSY), |
#Pages | 6 |
Date of Issue | 2015-07-28 (CPSY) |