.png){kind=icon}
.png){kind=icon}
Return
Wireless Interconnection Network for Post-Exascale High-Performance Computing
.png){kind=icon}
PRE
AI
DOI：10.1109/MWC.018.2300524.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Interconnection networks, or interconnects, play a crucial role in administering communication among computing units of high-performance computing (HPC) systems. Efficient provisioning of interconnects minimizes the processing delay wherein computing units await information sharing between each other, thereby enhancing the overall computation efficiency. Ideally, interconnects are designed with topologies tailored to match specific workflows, requiring diverse structures for different applications. However, since modifying their structures mid-operation is impractical, indirect communication incurs across distant units. In managing numerous long-routed data deliveries, heavy burdens on the network side may lead to the under-utilization of computing resources. In view of state-of-the-art HPC paradigms that solicit dense interconnections for diverse computation-hungry applications, this article presents a versatile wireless interconnecting framework, coined wireless interconnection network (WINE). The framework exploits cutting-edge wireless technologies that promote workload adaptability and scalability of modern interconnects. Design and implementation of wirelessly reliable links are strategized under network-oriented scrutiny of HPC architectures. A virtual HPC platform is developed to assess WINE's feasibilities, verifying its practicality for integration into modern HPC infrastructures.
Keywords:
High performance computing
Multiprocessor interconnection
Scalability
Reliability engineering
Network topology
Information sharing
Computational efficiency
Delays