Developing a Map-Reduce Algorithm Translator to Ease GPGPU Programming
| Project/Area Number |
26330088
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Software
|
|---|
| Research Institution | Osaka Prefecture University |
|---|
Principal Investigator |
Noriyuki Fujimoto 大阪府立大学, 工学(系)研究科(研究院), 教授 (90294165)
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2016: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2014: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | 超高速情報処理 / 並列処理 / GPGPU / MapReduce |
|---|
| Outline of Final Research Achievements |
For common programmers unfamiliar with parallel processing and GPGPU to easily utilize the high performance of GPUs, we designed concise and convenient MapReduce API which enables us to write MapReduce programs in serial C language. Moreover, based on the MapReduce API, we developed prototype compilers: (1) a compiler for serial C language, (2) a compiler for OpenMP, (3) a compiler for a single GPU, (4) a compiler for multiple GPUs in a PC.
|
Report
(4 results)
Research Products
(23 results)
