| Project/Area Number |
24K20782
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 60090:High performance computing-related
|
|---|
| Research Institution | Institute of Physical and Chemical Research |
|---|
Principal Investigator |
白 正陽 国立研究開発法人理化学研究所, 計算科学研究センター, 特別研究員 (70986992)
|
|---|
| Project Period (FY) |
2024-04-01 – 2026-03-31
|
| Project Status |
Granted (Fiscal Year 2024)
|
| Budget Amount *help |
¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2025: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2024: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | ray-casting / task splitting / ray-tracing core / HPC |
|---|
| Outline of Research at the Start |
An effective task splitting algorithm should allocate tasks to Processing Elements with improved data locality. Traditionally, this is performed using a task graph, which is hard to scale. In this study, we introduce a fundamentally distinct approach aimed at task splitting. This involves analyzing the task dependency as a visibility problem. We employ ray-casting methods to uncover dependencies, with Ray-Tracing cores acceleration in the latest GPUs. We will evaluate this methodology by integrating it into existing task-based runtime systems within real-world applications.
|
