Exploring Graphics Processor Performance for General Purpose Applications

Abstract

Graphics processors are designed to perform many floating-point operations per second. Consequently, they are an attractive architecture for high-performance computing at a low cost. Nevertheless, it is still not very clear how to exploit all their potential for general-purpose applications.In this work we present a comprehensive study of the performance of an application executing on the GPU. In addition, we analyze the possibility of using the graphics card to extend the life-time of a computer system.In our experiments we compare the execution on a midclass GPU (NVIDIA GeForce FX 5700LE) with a high-end CPU (Pentium 4 3.2GHz). The results show that to achieve high speedup with the GPU you need to: (1) format the vectors into two-dimensional arrays;(2) process large data arrays; and (3) perform a considerable amount of operations per data element. Finally, we study the performance when upgrading a low-end system by simply adding a GPU. This solution is cheaper, results in smaller power consumption and achieves higher speedup (8.1x versus 1.3x) than a full upgrade to a new high-end system.

A History-Based Performance Prediction Model with Profile Data Classification for Automatic Task Allocation in Heterogeneous Computing Systems

“…Trancoso et al [7] have reported that the difference in performance between CPUs and GPUs varies depending on the size of processed data and the number of operations on the data. As the data size determined by the problem size is usually decided at runtime, their paper indicates that it is impossible to statically estimate the speedup ratio obtained by using GPUs.…”

“…There are two major performance prediction approaches: analytic approach [4] [5] and history-based empirical approach [6] [7]. The former one requires a hardware model of each accelerator, and is not applicable to accelerators whose hardware details are not disclosed.…”

Graphics Processor-based High Performance Pattern Matching Mechanism for Network Intrusion Detection

“…As discussed in the previous section, commodity graphics processing units are becoming increasingly powerful. Researchers have developed various algorithms and systems based on GPUs to improve the performance of CPU-oriented programs (Trancoso & Charalambous, 2005). Cook (Cook et al, 2005) is the first to apply GPU to cryptography.…”

SAR simulation for large scenes by ray tracing technique based on GPU

“…GPUs are currently very powerful platforms, provided for tens or hundreds of cores with acceptable clock frequencies (500-600MHz) [ 8 ]. The GPU performance has been increasing at a rate of 2.5 to 3.0 × annually, compared with CPUs of 1.41 × annual performance growth rate [9]. Thus, it is reasonable to transfer the calculation process from CPU to GPU.…”