An Extensible Infrastructure for Benchmarking Multi-Core Processors based Systems

摘要

With wide adoption of multi-core processor based systems, there is a need for benchmarking such systems at both application and operating system levels. Developing benchmarks for multi-core systems is a cumbersome task due to underlying parallel architecture and complexity of parallel programming paradigms. In this paper, we introduce Multi-core Processor Architecture and Communication (MPAC) benchmarking library, which provides a common infrastructure for developing specification-driven micro-benchmarks, application benchmarks, and network traffic load generators. We describe the software architecture of MPAC and demonstrate its efficacy by implementing the specifications of well-known Stream and Netperf micro-benchmarks. We use these benchmarks to validate MPAC based performance measurements for single thread on Intel, AMD, and Cavium multi-core processors based platforms. We also develop a CPU micro-benchmark using our own specifications. In addition, we extend these micro-benchmarks through MPAC library to measure the scaling characteristics of our target multi-core processors based platforms.