Ken Moffat wrote:
The SBU from gcc-6.3 / 2017-05-01 was 77.151s, my unreliable repeat-SBU is 90.892s which is only a 17% worsening (haswell i7). I note that is unreliable because my own scripts always seem to take a lot longer when running a repeat-SBU calculation - I've sat looking at them, but I can't see what takes the extra time.
77 seconds seems pretty fast to me if it is -j1. Mine is also a Haswell (i7-5820K) and my time with gcc6.3 was 107 seconds.
I did do some testing and got the time down to 82 seconds by passing -O0 (no optimization), but that hosed the build times of virtually everything afterward. That's not something I'd recommend.
-- Bruce -- http://lists.linuxfromscratch.org/listinfo/blfs-dev FAQ: http://www.linuxfromscratch.org/blfs/faq.html Unsubscribe: See the above information page
