[cperciva]

Remember that turbo boost increases the core clock speed but not the bus clock or the speed of devices. A 10% increase in the core clock may yield a 10% increase in benchmark performance, but for macrobenchmarks the effect is liable to be significantly less.

[tachyonbeam]

Still, I'm assuming all layers of your cache are running 10% faster as well. Definitely useful for some work. I'm working on a JavaScript JIT compiler and I would say that dynamic languages tend to generate much bulkier code in terms of instruction count because of dynamic type tests, inline caches and such, but they don't necessarily need to access more data (outside of program instructions). For this kind of bulky code, faster single core performance definitely does matter.