Skip to Main Content
Benchmarking domain specific processors, compared with benchmarking general-purpose computers, has its own particularity, since the performance of domain specific processors strongly depends on target applications. System architects often face the problem of lacking benchmarks that represent the application space of a specific embedded system. Furthermore, benchmarking is often hindered from offering a clear performance analysis due to the presence of complex software, like operating system and Java virtual machine. In this paper we demonstrate a case study of benchmarking a smart card processor designed for Java applications. The benchmarking approach involves selecting suitable benchmarks from a set of given applications and analyzing the benchmarking results based on an abstract performance model to identify performance bottlenecks at the level of complex operations, each of which consists of a sequence of processor instructions. It evaluates the hardware and software in isolation and provides reliable information for system enhancement.