Presentation | 2015-08-04 Acceleration of Large-scale Interconnection Network Simulator by Using GPU Yuki Suzuki, Takashi Yokota, Kanemitsu Ootsu, Takeshi Ohkawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | When the large-scale parallel computing system that uses a lot of computing nodes aims at performance improvement, interconnection network that realizes communication among computing nodes is one of the key factor which affects the performance of whole system. Therefore performance evaluation of interconnection network is necessary, but the evaluation environment of network that built using actual equipment is unreal in terms of cost. Thus we think that performance simulation by software is one of the effective way. When the behavior of large-scale interconnection network is simulated by simulator, the problem is that the quantity of process is enormous and performance evaluation requires a lot of time. In this paper, we tried to reduce the simulation time by parallelization using GPU. Since the change to simple parallelization don't elicit the enough performance of GPU, we aim at acceleration of simulation speed by tuning for GPU. For example it is the improvement of efficiency of memory access. The result of performance evaluation, the parallelized simulator achieved the speed up ratio of maximum 37.8 times. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | GPU / large-scale interconnection network / simulator / tuning |
Paper # | CPSY2015-25 |
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) | Acceleration of Large-scale Interconnection Network Simulator by Using GPU |
Sub Title (in English) | |
Keyword(1) | GPU |
Keyword(2) | large-scale interconnection network |
Keyword(3) | simulator |
Keyword(4) | tuning |
1st Author's Name | Yuki Suzuki |
1st Author's Affiliation | Utsunomiya University(Utsunomiya Univ.) |
2nd Author's Name | Takashi Yokota |
2nd Author's Affiliation | Utsunomiya University(Utsunomiya Univ.) |
3rd Author's Name | Kanemitsu Ootsu |
3rd Author's Affiliation | Utsunomiya University(Utsunomiya Univ.) |
4th Author's Name | Takeshi Ohkawa |
4th Author's Affiliation | Utsunomiya University(Utsunomiya Univ.) |
Date | 2015-08-04 |
Paper # | CPSY2015-25 |
Volume (vol) | vol.115 |
Number (no) | CPSY-174 |
Page | pp.pp.97-102(CPSY), |
#Pages | 6 |
Date of Issue | 2015-07-28 (CPSY) |