Multicore processors are the main computing platform in laptops, desktop, and servers today, and are making their way into the embedded systems market also. Using benchmarks is a common approach to evaluate the performance of a system. However, benchmarks for embedded systems have so far been either targeted for a uni-processor environment, e.g., MiBench, or have been commercial, e.g., MultiBench by EEMBC. In this paper, we propose and implement an open source benchmark, ParMiBench, targeted for multiprocessor-based embedded systems. ParMiBench consists of parallel implementations of seven compute intensive algorithms from the uni-processor benchmark suite MiBench. The applications are selected from four domains: Automation and Industry Control, Network, Office, and Security.