Adaptive Auto-tuning Technology Aiming Complex Multicore and Multiprocessor Environments
Project/Area Number |
21300013
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Computer system/Network
|
Research Institution | The University of Electro-Communications |
Principal Investigator |
IMAMURA Toshiyuki 電気通信大学, 大学院・情報理工学研究科, 准教授 (60361838)
|
Co-Investigator(Kenkyū-buntansha) |
KATAGIRI Takahiro 東京大学, 情報基盤センター, 准教授 (40345434)
SUDA Reiji 東京大学, 情報理工学系研究科, 教授 (40251392)
TAKAHASHI Daisuke 筑波大学, システム情報工学研究科, 准教授 (00292714)
YAMAMOTO Yusaku 神戸大学, システム情報学研究科, 教授 (20362288)
NAKAJIMA Kengo 東京大学, 情報基盤センター, 教授 (20376528)
|
Project Period (FY) |
2009 – 2011
|
Project Status |
Completed (Fiscal Year 2011)
|
Budget Amount *help |
¥17,550,000 (Direct Cost: ¥13,500,000、Indirect Cost: ¥4,050,000)
Fiscal Year 2011: ¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Fiscal Year 2010: ¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2009: ¥7,020,000 (Direct Cost: ¥5,400,000、Indirect Cost: ¥1,620,000)
|
Keywords | マルチコア / 実行時最適化 / 動的負荷分散 / ハイブリッド並列プログラミングモデル / GPGPU / QR分解 / 固有値計算 / 高性能BLAS / 性能データベース |
Research Abstract |
To establish a key component of"automatic tuning technology"on multi-core processors and multi-GPU's for a next-generation supercomputer system, we conducted this research project. In this work, we developed an"automatic tuning technique employing performance stabilization on GPU's"and an"automatic tuning technique which utilizes a performance database". Furthermore, we successfully gave the semioptimal experimental design based on a Bayesian model through the mathematical research of the automatic tuning when the environmental conditions change dynamically. AT(automatic-tuning) for eigenvalue solvers, Fast Fourier Transform, and iterative solver with preconditioning were exploited on a cluster system or a multicore computer system.
|
Report
(4 results)
Research Products
(99 results)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Presentation] High Performance Computing of Density Matrix Renormalization Group Method for 2-Dimensional Model : Parallelization Strategy toward Peta Computing2010
Author(s)
Yamada, S., Imamura, T., Okumura, M., Igarashi, R., Onishi, H., Machida, M.
Organizer
Joint International Conference on Supercomputing in Nuclear Applications and Monte Carlo 2010(SNA+MC2010)
Place of Presentation
Tokyo, Japan
Related Report
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-