Future of GPGPU Micro-Architectural Parameters
Eindhoven University of Technology, The Netherlands
Design, Automation and Test in Europe (DATE ’13), 2013
@article{nugteren2013future,
title={Future of GPGPU Micro-Architectural Parameters},
author={Nugteren, Cedric and van den Braak, Gert-Jan and Corporaal, Henk},
year={2013}
}
As graphics processing units (GPUs) are becoming increasingly popular for general purpose workloads (GPGPU), the question arises how such processors will evolve architecturally in the near future. In this work, we identify and discuss tradeoffs for three GPU architecture parameters: active thread count, compute-memory ratio, and cluster and warp sizing. For each parameter, we propose changes to improve GPU design, keeping in mind trends such as dark silicon and the increasing popularity of GPGPU architectures. A key-enabler is dynamism and workload-adaptiveness, enabling among others: dynamic register file sizing, latency aware scheduling, roofline-aware DVFS, runtime cluster fusion, and dynamic warp sizing.
February 25, 2013 by hgpu
