Ouch indeed. That's pretty bad. It's believable when I think back to the purpose of these chips: handling workloads that were more I/O and concurrency bound than CPU bound. So, probably identify and eliminate these problems early on even if developer has to drop some threads or cores.

Note: There's always my other recommendation of turning open-source Leon3 into a multicore. Im curious what it or Leon4 get on such a benchmark versus Intels on similar process nodes.