article · 2021
Improving Address Translation in Multi-GPUs via Sharing and Spilling aware TLB Design
Bingyao Li, Jieming Yin, Youtao Zhang, Xulong Tang
Cited by 28Abstract and details only
Abstract
In recent years, the ever-growing application complexity and input dataset sizes have driven the popularity of multi-GPU systems as a desirable computing platform for many application domains. While employing multiple GPUs intuitively exposes substantial parallelism for the application acceleration, the delivered performance rarely scales with the number of GPUs. One of the major challenges behind is the address translation efficiency. Many prior works focus on CPUs or single GPU execution scenarios while the address translation in multi-GPU systems receives little attention. In this paper, we conduct a comprehensive investigation of the address translation efficiency in both “single-application-multi-GPU” and “multi-application-multi-GPU” execution paradigms. Based on our observations, we propose a new TLB hierarchy design, called least-TLB, tailored for multi-GPU systems and effectively improves the TLB performance with minimal hardware overheads. Experimental results on 9 single-application workloads and 10 multi-application workloads indicate the proposed least-TLB improves the performances, on average, by 23.5% and 16.3%, respectively.
Cite this paper
Li, B., Yin, J., Zhang, Y., & Tang, X. (2021). Improving Address Translation in Multi-GPUs via Sharing and Spilling aware TLB Design. https://doi.org/10.1145/3466752.3480083
Li, Bingyao, et al. “Improving Address Translation in Multi-GPUs via Sharing and Spilling aware TLB Design.” 2021, pp. 1154–68, https://doi.org/10.1145/3466752.3480083.
Li, Bingyao, Jieming Yin, Youtao Zhang, and Xulong Tang. 2021. “Improving Address Translation in Multi-GPUs via Sharing and Spilling aware TLB Design.” https://doi.org/10.1145/3466752.3480083.
Li, B. et al. (2021) ‘Improving Address Translation in Multi-GPUs via Sharing and Spilling aware TLB Design’. Available at: https://doi.org/10.1145/3466752.3480083.
@article{li2021improving,
title = {{Improving Address Translation in Multi-GPUs via Sharing and Spilling aware TLB Design}},
author = {Li, Bingyao and Yin, Jieming and Zhang, Youtao and Tang, Xulong},
pages = {1154--1168},
year = {2021},
doi = {10.1145/3466752.3480083}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.