skip to main content

SciTech ConnectSciTech Connect

Title: SFU-Driven Transparent Approximation Acceleration on GPUs

Approximate computing, the technique that sacrifices certain amount of accuracy in exchange for substantial performance boost or power reduction, is one of the most promising solutions to enable power control and performance scaling towards exascale. Although most existing approximation designs target the emerging data-intensive applications that are comparatively more error-tolerable, there is still high demand for the acceleration of traditional scientific applications (e.g., weather and nuclear simulation), which often comprise intensive transcendental function calls and are very sensitive to accuracy loss. To address this challenge, we focus on a very important but often ignored approximation unit on GPUs.
Authors:
; ; ; ;
Publication Date:
OSTI Identifier:
1322522
Report Number(s):
PNNL-SA-117058
KJ0402000
DOE Contract Number:
AC05-76RL01830
Resource Type:
Conference
Resource Relation:
Conference: Proceedings of the International Conference on Supercomputing (ICS 2016), June 1-3, 2016, Istanbul, Turkey, Paper No. 15
Publisher:
Association for Computing Machinery, New York, New York
Research Org:
Pacific Northwest National Laboratory (PNNL), Richland, WA (US)
Sponsoring Org:
USDOE
Country of Publication:
United States
Language:
English
Subject:
Approximate computing; energy/performance and accuracy trade-offs