arXiv Open Access 2024

Characterizing Network Requirements for GPU API Remoting in AI Applications

Tianxia Wang Zhuofu Chen Xingda Wei Jinyu Gu Rong Chen +1 lainnya

Lihat Sumber

Abstrak

GPU remoting is a promising technique for supporting AI applications. Networking plays a key role in enabling remoting. However, for efficient remoting, the network requirements in terms of latency and bandwidth are unknown. In this paper, we take a GPU-centric approach to derive the minimum latency and bandwidth requirements for GPU remoting, while ensuring no (or little) performance degradation for AI applications. Our study including theoretical model demonstrates that, with careful remoting design, unmodified AI applications can run on the remoting setup using commodity networking hardware without any overhead or even with better performance, with low network demands.

Topik & Kata Kunci

cs.OS cs.NI

Penulis (6)

Tianxia Wang

Zhuofu Chen

Xingda Wei

Jinyu Gu

Rong Chen

Haibo Chen

Format Sitasi

APA MLA BibTeX

Wang, T., Chen, Z., Wei, X., Gu, J., Chen, R., Chen, H. (2024). Characterizing Network Requirements for GPU API Remoting in AI Applications. https://arxiv.org/abs/2401.13354

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2024
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓