Re: CVS commit: src/sys/arch/news68k/conf

2014-07-08 Thread Izumi Tsutsui
dholland@ wrote: > ok, so naively I would think that *reordering* blocks wouldn't change > their size, or at least not much... does anyone know where this 10% > overhead comes from? Is it all jump instructions? Probably it moves and aligns reordered "branch taken" blocks at cacheline and there mi

Re: CVS commit: src/sys/arch/news68k/conf

2014-07-08 Thread David Holland
On Sat, Jul 05, 2014 at 09:14:02AM +, Izumi Tsutsui wrote: > Modified Files: > src/sys/arch/news68k/conf: GENERIC GENERIC_TINY > > Log Message: > Use COPTS="-O2 -fno-reorder-blocks" as defined in sys.mk for userland. > > with "-O2": >textdata bss dec hex filen