Jump to : Download | Note | Abstract | BibTex reference | EndNote reference |

bertran-micro2015

Jingwen Leng, Alper Buyuktosunoglu, Ramon Bertran, Pradip Bose, Vijay Janapa Reddi. Safe Limits on Voltage Reduction Efficiency in GPUs: a Direct Measurement Approach. In MICRO '15: Proceedings of the 46th Annual IEEE/ACM International Symposium on Microarchitecture (Acceptance Ratio: ??. Conf. Rank: A), Pages 0-0, Waikiki, HI, USA, December 2015.

Download

Download paper: Adobe portable document (pdf) PDF

Copyright notice:This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Note on this paper

To appear

Abstract

Energy efficiency of GPU architectures has emerged as an important aspect of computer system design. In this paper, we explore the energy benefits of reducing the GPU chip's voltage to the safe limit, i.e. Vmin point. We perform such a study on several commercial of-the-shelf GPU cards. We find that there exists about 20% voltage guardband on those GPUs spanning two architectural generations, which, if "eliminated" completely, can result in up to 25% energy savings on one of the studied GPU cards. The exact improvement magnitude depends on the program's available guardband, because our measurement results unveil a program dependent Vmin behavior across the studied programs. We aim to make fundamental observations about the program-dependent Vmin behavior. We experimentally determine that the voltage noise has a larger impact on Vmin compared to the process and temperature variation, and the activities during the kernel execution cause large voltage droops. From these findings, we show how to use a kernel's microarchitectural performance counters to predict its Vmin value accurately. The average and maximum prediction error is 0.5% and 3%, respectively. The accurate Vmin prediction opens up new possibilities of a cross-layer dynamic guardbanding scheme for GPUs, in which software predicts and manages the voltage guardband, while the functional correctness is ensured by hardware safety net mechanism

BibTex Reference

@InProceedings{bertran-micro2015,
   Author = {Leng, Jingwen and Buyuktosunoglu, Alper and Bertran, Ramon and Bose, Pradip and Janapa Reddi, Vijay},
   Title = {Safe Limits on Voltage Reduction Efficiency in {GPU}s: a Direct Measurement Approach},
   BookTitle = {MICRO '15: Proceedings of the 46th Annual IEEE/ACM International Symposium on Microarchitecture (Acceptance Ratio: ??. Conf. Rank: A)},
   Pages = {0--0},
   Publisher = {IEEE Computer Society},
   Address = {Waikiki, HI, USA},
   Month = {December},
   Year = {2015}
}

EndNote Reference [help]

Get EndNote Reference (.ref)

Home | Presentation | Teaching | Research | Related Institutions | News Top

Last update: Jan 2, 2015
Copyright © 2000-2015 Departament d'Arquitectura de Computadors
 


It has been automatically generated using the bib2html program.