Dynamic GMMU Bypass for Address Translation in Multi-GPU Systems - Network and Parallel Computing Access content directly
Conference Papers Year : 2021

Dynamic GMMU Bypass for Address Translation in Multi-GPU Systems

Jinhui Wei
  • Function : Author
  • PersonId : 1161013
Jianzhuang Lu
  • Function : Author
  • PersonId : 1161014
Qi Yu
  • Function : Author
  • PersonId : 1161015
Chen Li
  • Function : Author
  • PersonId : 1161016
Yunping Zhao
  • Function : Author
  • PersonId : 1161017

Abstract

The ever increasing application footprint raises challenges for GPUs. As Moore’s Law reaches its limit, it is not easy to improve single GPU performance any further; instead, multi-GPU systems have been shown to be a promising solution due to its GPU-level parallelism. Besides, memory virtualization in recent GPUs simplifies multi-GPU programming. Memory virtualization requires support for address translation, and the overhead of address translation has an important impact on the system’s performance. Currently, there are two common address translation architectures in multi-GPU systems, including distributed and centralized address translation architectures. We find that both architectures suffer from performance loss in certain cases. To address this issue, we propose GMMU Bypass, a technique that allows address translation requests to dynamically bypass GMMU in order to reduce translation overhead. Simulation results show that our technique outperforms distributed address translation architecture by 6% and centralized address translation architecture by 106% on average.
Fichier principal
Vignette du fichier
511910_1_En_13_Chapter.pdf (292.27 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03768734 , version 1 (04-09-2022)

Licence

Attribution

Identifiers

Cite

Jinhui Wei, Jianzhuang Lu, Qi Yu, Chen Li, Yunping Zhao. Dynamic GMMU Bypass for Address Translation in Multi-GPU Systems. 17th IFIP International Conference on Network and Parallel Computing (NPC), Sep 2020, Zhengzhou, China. pp.147-158, ⟨10.1007/978-3-030-79478-1_13⟩. ⟨hal-03768734⟩
15 View
5 Download

Altmetric

Share

Gmail Facebook X LinkedIn More