Benchmarking of a Real-Time System that utilises a booster

摘要

Application speedups can be achieved by speeding up the hardware, e.g. by utilising an Operating System co-processor. The paper present results from a comparison of executing benchmark programs on a system with and without a coprocessor, but which otherwise are identical. The observed speedup is mostly due to the fact that there is no need for clock tick administration, in the system with co-processor, and that the booster scheduler is faster than the software based one. In general the system calls are faster without the coprocessor for the benchmark considered in this paper. This is mostly due to the slow bus accesses when communicating with the co-processor.