Link-time optimization for the kernel

Posted Aug 21, 2012 18:09 UTC (Tue) by pj (subscriber, #4506)
Parent article: Link-time optimization for the kernel

>Andi reports that runs of the "hackbench" benchmark gain about 5%, while kernel builds don't change much at all. Some networking benchmarks improve as much as 18%.

Does this help point out that the networking code could be better link-optimized, even if the rest of the kernel isn't? I mean, if the kernel is being built with different gcc commandlines anyway, does this mean that the network-code-building bits could perhaps be better optimized?