Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 06 Dec 2011 18:03:42 +0100
From:      rank1seeker@gmail.com
To:        hackers@freebsd.org
Subject:   Re: CPUTYPE and friends, from 'make.conf' benchmark
Message-ID:  <20111206.170342.731.2@DOMY-PC>
In-Reply-To: <CAGH67wTjGyhWAMYsCtzp8X7nN=yswOGntO=46AmT7yxymHSQ%2Bg@mail.gmail.com>
References:  <20111205.171654.020.1@DOMY-PC> <CAGH67wTjGyhWAMYsCtzp8X7nN=yswOGntO=46AmT7yxymHSQ%2Bg@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help

# /bin/sh -c "gcc -v -x c -E -mtune=native /dev/null -o /dev/null 2>&1 | grep mtune | sed -e 's/.*mtune=//'"

generic



For target machine, it returned 'generic'



Now only with CPUTYPE in 'make.conf':

--

CPUTYPE?=core2

--



> Also, you should set these in src.conf.  Sticking them in make.conf is

> going to annoy people when you ask why your ports are breaking ;)

> 

> Chris



I want my ports, to also be optimized for target CPU, not just base.

None of my ports got broken yet.



Rebuilded can ...



Tests are started AFTER a reboot!

There is no bgfsck, as per rc.conf:

--

background_fsck=NO

fsck_y_enable=YES

fsck_y_flags=-C

--



Same multiuser enviroment

Test done once.



After running: '# time unixbench', final score was:

   395.4

Completed in 22.8 min



Time is SAME as with generic binaries, but score is just a 1.2 higher, which is too small to be relevant.

What do you think about this?







Domagoj Smolčić



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20111206.170342.731.2>