A GPU Memory System Comparison for an Elliptic Test Problem
UMBC High Performance Computing Facility, University of Maryland, Baltimore County
UMBC High Performance Computing Facility, University of Maryland, Baltimore County, 2012
@techreport{WangEtAlGPGPU2012,
author={Yu Wang and Marc Olano and Matthias K. Gobbert and Wesley Griffin},
title={A {GPU} Memory System Comparison for an Elliptic Test Problem},
number={HPCF–2012–1},
institution={UMBC High Performance Computing Facility, University of Maryland, Baltimore County},
year={2012},
url={http://userpages.umbc.edu/~gobbert/papers/WangEtAlHPCF2012.pdf},
note={(HPCF machines used: tara.)}
}
This paper presents GPU-based solutions to the Poisson equation with homogeneous Dirichlet boundary conditions in two spatial dimensions. This problem has well-understood behavior, but similar computation to many more complex real-world problems. We analyze the GPU performance using three types of memory access in the CUDA memory model (direct access to global memory, texture access, and shared memory). Based on data locality, different CUDA algorithms are designed to accommodate the different device memory performance behaviors. We present a performance study on the speedup of our GPU-based solutions on an NVIDIA Tesla C2070 over serial code. By relating the data access pattern and its spatial locality, our results show that an algorithm using global memory with coalesced reads outperforms the other memory systems and allows effective solvers using single precision floating points.
April 13, 2012 by hgpu
