Developing a Smart Storage based on a Succinct Data Structure that Processes Compressed Data
| Project/Area Number |
15K15958
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Computer system
|
|---|
| Research Institution | Tohoku University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2015-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2016: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2015: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
|
|---|
| Keywords | 簡潔データ構造 / 文字列処理 / 高速ストレージ / ビッグデータ処理 / ビッギデータ応用 / ビッグデーター応用 |
|---|
| Outline of Final Research Achievements |
Big-data are used in many text processing applications. As a result, data access often becomes a bottleneck. This research is focused on data access reduction using a succinct data structure and its processor architecture. The data amount is reduced to 27% using wavelet tree based succinct data structure. In addition, memory access is reduced to 73%.
A smart storage and its processor architecture is designed based on the proposed succinct data structure to reduce the data access. Using this storage, accelerators are designed for genome data alignment and text data search processes. The designed system that contains accelerators and storage is implemented using an FPGA. A speed-up of over 21 times is achieved compared to the conventional CPU-based implementation.
|
Report
(3 results)
Research Products
(16 results)
