2017 Fiscal Year Final Research Report
Auto-tuning Framework Focusing on Application Data Structure for Many-core Processors
Project/Area Number |
16H06679
|
Research Category |
Grant-in-Aid for Research Activity Start-up
|
Allocation Type | Single-year Grants |
Research Field |
High performance computing
|
Research Institution | The University of Tokyo |
Principal Investigator |
|
Project Period (FY) |
2016-08-26 – 2018-03-31
|
Keywords | メニーコアプロセッサ / GPU / SIMD |
Outline of Final Research Achievements |
Nowadays, the number of computational environment using many-core processors is increasing. To bring out the efficient performance of many-core processors, it is important to efficiently use the Vector Processing Unit (VPU). However, the knowledge of hardware and compiler is required to efficiently use the VPU, and moreover, data structural changes are often required. In this research, we propose a set of compiler directives for abstraction of data layout. We also implement a translator for the proposed directives. Furthermore, we propose a framework design to enhance the efficient vectorization. Also, we implement a BEM-BB framework using the proposed framework design.
|
Free Research Field |
高性能計算
|