VCSN: Virtual Circuit-Switching Network for Flexible and Simple-to-Operate Communication in HPC FPGA Cluster
-
- Tomohiro Ueno
- RIKEN Center for Computational Science, Chuo-ku, Kobe, Hyogo, Japan
-
- Kentaro Sano
- RIKEN Center for Computational Science, Chuo-ku, Kobe, Hyogo, Japan
この論文をさがす
説明
<jats:p> FPGA clusters promise to play a critical role in <jats:bold>high-performance computing (HPC)</jats:bold> systems in the near future due to their flexibility and high power efficiency. The operation of large-scale general-purpose FPGA clusters on which multiple users run diverse applications requires flexible network topology to be divided and reconfigured. This paper proposes <jats:bold>Virtual Circuit-Switching Network (VCSN)</jats:bold> that provides an arbitrarily reconfigurable network topology and simple-to-operate network system among FPGA nodes. With virtualization, user logic on FPGAs can communicate with each other as if a circuit-switching network was available. This paper demonstrates that VCSN with 100 Gbps Ethernet achieves highly-efficient point-to-point communication among FPGAs due to its unique and efficient communication protocol. We compare VCSN with a <jats:bold>direct connection network (DCN)</jats:bold> that connects FPGAs directly. We also show a concrete procedure to realize collective communication on an FPGA cluster with VCSN. We demonstrate that the flexible virtual topology provided by VCSN can accelerate collective communication with simple operations. Furthermore, based on experimental results, we model and estimate communication performance by DCN and VCSN in a large FPGA cluster. The result shows that VCSN has the potential to accelerate gather communication up to about 1.97 times more than DCN. </jats:p>
収録刊行物
-
- ACM Transactions on Reconfigurable Technology and Systems
-
ACM Transactions on Reconfigurable Technology and Systems 16 (2), 1-32, 2023-03-11
Association for Computing Machinery (ACM)
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1360298754830937600
-
- DOI
- 10.1145/3579848
-
- ISSN
- 19367414
- 19367406
-
- 資料種別
- journal article
-
- データソース種別
-
- Crossref
- KAKEN