| Project/Area Number |
25330067
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Computer system
|
|---|
| Research Institution | University of the Ryukyus |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
AMANO Hideharu 慶應義塾大学, 理工学部, 教授 (60175932)
FUJITA Naoyuki 宇宙航空研究開発機構, 航空本部, 主幹研究員 (70358480)
NAKAJO Hironori 東京農工大学, 大学院工学研究院, 准教授 (80217736)
|
|---|
| Project Period (FY) |
2013-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2015: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2013: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | FPGA / 数値計算 / アクセラレーション技術 / 高位合成 / 計算機システム / 再構成型アーキテクチャ / 計算流体力学 / マルチFPGAシステム / ハードウェア・ソフトウェア協調処理 / 科学技術計算 / 数値流体力学 / 設計自動化 / 部分再構成 / 可変構造型計算機 |
|---|
| Outline of Final Research Achievements |
FPGAs are attractive candidate of accelerator device of next generation, because of its high power efficiency. However, FPGA based accelerator requires custom circuit design for each applications. This project choose CFD as the main target, to establish basic technics and methods to: automatically divide a large problem onto multiple FPGAs, and to apply FPGA acceleration on an existing source code by exploiting power of high-level synthesis (HLS) tools with minimal modifications on the source code. Because most HLS tools don't support Fortran (while Fortran is still popular in scientific computing), a Fortran HLS tool had developed in this project, too. The methods and tools are not limited to CFD, but also widely applicable to various area of scientific computation.
|
