2022 Fiscal Year Annual Research Report
Cluster-fault-tolerant routing methods in tori
| Project/Area Number |
19K11887
|
|---|
| Research Institution | Kanagawa University |
|---|
Principal Investigator |
ボサール アントワーヌ 神奈川大学, 情報学部, 教授 (20645882)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
金子 敬一 東京農工大学, 工学(系)研究科(研究院), 教授 (20194904)
|
|---|
| Project Period (FY) |
2019-04-01 – 2023-03-31
|
| Keywords | interconnection network / graph theory / routing / algorithm / dependability |
|---|
| Outline of Annual Research Achievements |
Throughout this research project, we have conducted investigations regarding the interconnection network of massively parallel systems, such as supercomputers. We have especially focused on torus-based interconnect, and considered related theoretical problems such as routing algorithms and related graph theory problems. In addition, we have considered related practical problems, for instance thinking about how to reduce power consumption of interconnection networks since power consumption of modern supercomputers is an on-going issue. Concretely, we have investigated low-power devices and the corresponding technologies, and IoT devices in general to this end.
Precisely, and amongst other works, we have described a cluster-fault tolerant routing algorithm in a torus network, a pairwise disjoint paths routing algorithm in a torus network, a set-to-set disjoint path routing algorithm in bijective connection graphs and we have considered the decycling problem in a torus network and the crossing number of a torus network. Regarding the power consumption issues of interconnection networks, we have researched memory optimisation and autonomous on-chip debugging for AVR-based microcontrollers.
|
