On the limits of GPU acceleration

  • Authors:

  • Richard Vuduc;Aparna Chandramowlishwaran;Jee Choi;Murat Guney;Aashay Shringarpure

  • Affiliations:

  • Georgia Institute of Technology, School of Computational Science and Engineering;Georgia Institute of Technology, School of Computational Science and Engineering;Georgia Institute of Technology, School of Electrical and Computer Engineering;Georgia Institute of Technology, School of Civil and Environmental Engineering;Georgia Institute of Technology, School of Computer Science

  • Venue:
  • HotPar'10 Proceedings of the 2nd USENIX conference on Hot topics in parallelism
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper throws a small "wet blanket" on the hot topic of GPGPU acceleration, based on experience analyzing and tuning both multithreaded CPU and GPU implementations of three computations in scientific computing. These computations--(a) iterative sparse linear solvers; (b) sparse Cholesky factorization; and (c) the fast multipole method--exhibit complex behavior and vary in computational intensity and memory reference irregularity. In each case, algorithmic analysis and prior work might lead us to conclude that an idealized GPU can deliver better performance, but we find that for at least equal-effort CPU tuning and consideration of realistic workloads and calling-contexts, we can with two modern quad-core CPU sockets roughly match one or two GPUs in performance. Our conclusions are not intended to dampen interest in GPU acceleration; on the contrary, they should do the opposite: they partially illuminate the boundary between CPU and GPU performance, and ask architects to consider application contexts in the design of future coupled on-die CPU/GPU processors.