Performance and Power Analysis of ATI GPU: A Statistical Approach

We present a comprehensive study on the performance and power consumption of a recent ATI GPU. By employing a rigorous statistical model to analyze execution behaviors of representative general-purpose GPU (GPGPU) applications, we conduct insightful investigations on the target GPU architecture. Our results demonstrate that the GPU execution throughput and the power dissipation are dependent on different architectural variables. Furthermore, we design a set of micro-benchmarks to study the power consumption features of different function units on the GPU. Based on those results, we derive instructive principles that can guide the design of power-efficient high performance computing systems.

1. Introduction

Due to the emergence of Terascale and Petascale computing, people begin to concentrate on developing powerful and efficient systems to accelerate the solving of these problems. Among the current platforms, supercomputers consisting of numerous modern graphics processing units (GPUs) are obtaining substantial attention. In recent years, with the development of massive parallel programming language including CUDA [5] and OpenCL [6], high performance GPUs are widely used to settle large scale computation problems from different domains. By appropriately parallelizing the execution, GPU-based implementations are able to reduce the processing time by up to thousands of times compared to the sequential counterparts.