View previous topic :: View next topic |
Author |
Message |
d2_racing Bodhisattva
Joined: 25 Apr 2005 Posts: 13047 Location: Ste-Foy,Canada
|
Posted: Sat Sep 13, 2008 1:54 am Post subject: |
|
|
int2str wrote: | Martux wrote: | GCC alone took over 8h compile time... |
That's not right at all...
|
Hi, can you post your lspci plz.
Also, did you run hdparm on your HDD ? |
|
Back to top |
|
|
SDNick484 Apprentice
Joined: 05 Dec 2005 Posts: 231
|
Posted: Sat Sep 13, 2008 4:58 am Post subject: |
|
|
Well I just finished getting my C2Q up and running (I'm using an Intel mobo with the new G45 chipset and it was a pain -- networking doesn't work in the 2008.0-r1 kernel), and am using the native flag. I've done some minimal testing and no issues thus far on running apps compiled on the C2Q with the atom.
Below is how the flags from the Atom compare to the C2Q:
Atom: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx constant_tsc arch_perfmon pebs bts pni monitor ds_cpl est tm2 ssse3 xtpr lahf_lm
C2Q: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx lm constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr sse4_1 lahf_lm
diff: pse36 lm vmx smx cx16 sse4_1
As you can see, all the additional flags are on the C2Q, and they're all relative new. Since I don't believe GCC has any optimizations yet that utilize though flags, native will likely yield close results.
I'm heading camping tomorrow, but will likely make the swap from Xubuntu to Gentoo on my Acer One next week. I don't really plan to compile anything there unless it's a last resort. |
|
Back to top |
|
|
int2str Guru
Joined: 29 Sep 2003 Posts: 362
|
Posted: Sat Sep 13, 2008 3:58 pm Post subject: |
|
|
Check out this difference:
Same command, two different machines.
Command is "emerge -s mozilla-firefox".
Intel Core2 Duo E6850 @ 3Ghz; 4GB RAM; SATA hard drive
Code: | office ~ # time emerge -s mozilla-firefox
real 0m15.710s
user 0m0.566s
sys 0m0.397s |
Intel Atom @ 1.6Ghz; 2GB RAM; Compact flash card
Code: | terra ~ # time emerge -s mozilla-firefox
real 0m2.488s
user 0m2.306s
sys 0m0.155s |
Pretty sweet _________________ Adpot an unanswered post today! |
|
Back to top |
|
|
int2str Guru
Joined: 29 Sep 2003 Posts: 362
|
Posted: Sat Sep 13, 2008 4:10 pm Post subject: |
|
|
To explain my setup a bit better:
I have the MSI Wind barebones. The main "hard drive" (SDA) is a 16GB compact flash card that hosts the main operating system and is what I'm booting off of. The secondary hard drive (SDB) is a 160GB SATA hard drive used for data storage. I mount some of the temp directories etc. on the hard drive, not to wear out the CF card write cycles while compiling Gentoo.
Here is part of my /etc/fstab:
Code: | /dev/sda1 / ext2 noatime 0 1
/dev/sdb1 /home/shared ext3 noatime 0 0
/home/shared/Linux/Terra/log /var/log none bind 0 0
/home/shared/Linux/Terra/portage /var/tmp/portage none bind 0 0
/home/shared/Linux/Terra/distfiles /usr/portage/distfiles none bind 0 0
tmpfs /tmp tmpfs noatime 0 0 |
Some information that was requested above:
My CFLAGS are simple:
Code: | CFLAGS="-march=prescott -O2 -pipe -fomit-frame-pointer" |
Code: | terra ~ # hdparm -i /dev/sda /dev/sdb
/dev/sda:
Model= , FwRev=20071116, SerialNo=CF CARD 0001562C
Config={ HardSect NotMFM Fixed DTR>10Mbs }
RawCHS=16383/15/63, TrkSize=0, SectSize=576, ECCbytes=4
BuffType=DualPort, BuffSize=1kB, MaxMultSect=1, MultSect=?0?
CurCHS=16383/15/63, CurSects=15481935, LBA=yes, LBAsects=31719424
IORDY=no, tPIO={min:120,w/IORDY:120}, tDMA={min:120,rec:120}
PIO modes: pio0 pio1 pio2 pio3 pio4
DMA modes: *mdma0 mdma1 mdma2
AdvancedPM=no
* signifies the current active mode
/dev/sdb:
Model=WDC WD1600AAJS-00B4A0 , FwRev=01.03A01, SerialNo= WD-WMAT20947254
Config={ HardSect NotMFM HdSw>15uSec SpinMotCtl Fixed DTR>5Mbs FmtGapReq }
RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=50
BuffType=unknown, BuffSize=8192kB, MaxMultSect=16, MultSect=?16?
CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=312581808
IORDY=on/off, tPIO={min:120,w/IORDY:120}, tDMA={min:120,rec:120}
PIO modes: pio0 pio3 pio4
DMA modes: mdma0 mdma1 mdma2
UDMA modes: udma0 udma1 udma2 udma3 udma4 udma5 *udma6
AdvancedPM=no WriteCache=enabled
Drive conforms to: Unspecified: ATA/ATAPI-1,2,3,4,5,6,7
* signifies the current active mode |
Code: | terra ~ # hdparm -tT /dev/sda /dev/sdb
/dev/sda:
Timing cached reads: 1138 MB in 2.00 seconds = 568.71 MB/sec
Timing buffered disk reads: 44 MB in 3.12 seconds = 14.10 MB/sec
/dev/sdb:
Timing cached reads: 1206 MB in 2.00 seconds = 603.21 MB/sec
Timing buffered disk reads: 332 MB in 3.00 seconds = 110.62 MB/sec |
Code: | 00:00.0 Host bridge: Intel Corporation 82945G/GZ/P/PL Memory Controller Hub (rev 02)
00:02.0 VGA compatible controller: Intel Corporation 82945G/GZ Integrated Graphics Controller (rev 02)
00:1c.0 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 1 (rev 01)
00:1c.1 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 2 (rev 01)
00:1c.2 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 3 (rev 01)
00:1c.3 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 4 (rev 01)
00:1d.0 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI Controller #1 (rev 01)
00:1d.1 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI Controller #2 (rev 01)
00:1d.2 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI Controller #3 (rev 01)
00:1d.3 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI Controller #4 (rev 01)
00:1d.7 USB Controller: Intel Corporation 82801G (ICH7 Family) USB2 EHCI Controller (rev 01)
00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev e1)
00:1f.0 ISA bridge: Intel Corporation 82801GB/GR (ICH7 Family) LPC Interface Bridge (rev 01)
00:1f.1 IDE interface: Intel Corporation 82801G (ICH7 Family) IDE Controller (rev 01)
00:1f.2 IDE interface: Intel Corporation 82801GB/GR/GH (ICH7 Family) SATA IDE Controller (rev 01)
00:1f.3 SMBus: Intel Corporation 82801G (ICH7 Family) SMBus Controller (rev 01)
01:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168B PCI Express Gigabit Ethernet controller (rev 02) |
_________________ Adpot an unanswered post today! |
|
Back to top |
|
|
kernelOfTruth Watchman
Joined: 20 Dec 2005 Posts: 6111 Location: Vienna, Austria; Germany; hello world :)
|
Posted: Sat Sep 13, 2008 4:18 pm Post subject: |
|
|
SDNick484 wrote: | ...
diff: pse36 lm vmx smx cx16 sse4_1
As you can see, all the additional flags are on the C2Q, and they're all relative new. Since I don't believe GCC has any optimizations yet that utilize though flags, native will likely yield close results.
I'm heading camping tomorrow, but will likely make the swap from Xubuntu to Gentoo on my Acer One next week. I don't really plan to compile anything there unless it's a last resort. |
Quote: | # Support for SSE4.1 built-in functions and code generation are available via -msse4.1.
# Support for SSE4.2 built-in functions and code generation are available via -msse4.2.
# Both SSE4.1 and SSE4.2 support can be enabled via -msse4. |
http://www.gnu.org/software/gcc/gcc-4.3/changes.html
int2str, you tried out reiser4 with cryptcompress/lzo or just standard reiser4 ?
I believe ext3 might wear out your flash-drive pretty fast
for the record:
time emerge -s mozilla-firefox
Quote: | real 0m6.758s
user 0m1.965s
sys 0m0.338s |
_________________ https://github.com/kernelOfTruth/ZFS-for-SystemRescueCD/tree/ZFS-for-SysRescCD-4.9.0
https://github.com/kernelOfTruth/pulseaudio-equalizer-ladspa
Hardcore Gentoo Linux user since 2004 |
|
Back to top |
|
|
int2str Guru
Joined: 29 Sep 2003 Posts: 362
|
Posted: Sat Sep 13, 2008 4:39 pm Post subject: |
|
|
[quote="kernelOfTruth"] SDNick484 wrote: | I believe ext3 might wear out your flash-drive pretty fast |
I'm using ext2 on the flash card _________________ Adpot an unanswered post today! |
|
Back to top |
|
|
Etal Veteran
Joined: 15 Jul 2005 Posts: 1931
|
Posted: Sat Sep 13, 2008 9:02 pm Post subject: |
|
|
int2str wrote: | kernelOfTruth wrote: | I believe ext3 might wear out your flash-drive pretty fast |
I'm using ext2 on the flash card |
I think it would be a better idea to use use the specialized JFFS2 or LogFS if you're worried about wearing out the drive. _________________ “And even in authoritarian countries, information networks are helping people discover new facts and making governments more accountable.”– Hillary Clinton, Jan. 21, 2010 |
|
Back to top |
|
|
kernelOfTruth Watchman
Joined: 20 Dec 2005 Posts: 6111 Location: Vienna, Austria; Germany; hello world :)
|
|
Back to top |
|
|
Martux Veteran
Joined: 04 Feb 2005 Posts: 1917
|
Posted: Sun Sep 14, 2008 7:47 pm Post subject: |
|
|
I found out why compiles take forever here: I've got a problem with acpi, it takes up to 50% of my cpu time _________________ "Coincidence is God's way of remaining anonymous."
Albert Einstein
"The road to success is always under construction" |
|
Back to top |
|
|
joaopft Tux's lil' helper
Joined: 20 Oct 2003 Posts: 86 Location: Lisbon, Portugal
|
Posted: Tue Sep 23, 2008 11:00 pm Post subject: |
|
|
Atom switches off units needed for 64 bit operation when working in 32 bit mode, so if battery time is a concern, it may be better to stick to a build for the x86 arch. Also, memory access is limited by 533MHz FSB, so this low bandwidth does not benefit the amd64 arch.
Edit: it seems the N270 Atom, the one used in laptops, cannot run x86_64 code, anyway...
-O3 sets unroll loops, which will produce code with lengthy, non-looped, instruction sequences. We must consider that an in-order core heavily relies on its L1 and L2 caches to avoid stalled pipelines. _________________ Fiction is obliged to stick to possibilities. Truth isn't.
Mark Twain |
|
Back to top |
|
|
joaopft Tux's lil' helper
Joined: 20 Oct 2003 Posts: 86 Location: Lisbon, Portugal
|
Posted: Wed Sep 24, 2008 1:18 pm Post subject: |
|
|
From Intel's site http://www.intel.com/cd/software/products/asmo-na/eng/386925.htm, their compiler optimizes code very aggressively by doing out-of-order scheduling of instructions by software (by the compiler), instead of hardware:
Quote: | The new low-power IA does not provide an integrated out-of-order scheduler that schedules instruction dispatch into the execution pipeline to take optimum advantage of the architecture and minimize dependency stalls. The Intel® C++ Compiler models the low-power IA pipeline and execution flow, thus enabling it to produce code with the optimum instruction execution sequence for low-power IA. |
As of yet, gcc can't optimize code in this fashion, and it is clear it will be very difficult to do this in an arch independent fashion.
Replacing a just-in-time out-of-order hardware scheduler with an arch indep. out-of-order compiler is no simple task. For one thing, the compiler does not have the live data flow to assist it.
Intel's compiler code only works in their particular hardware alone: "modeling the low-power IA pipeline and exec. flow, thus enabling it to produce code with the optimum instruction execution sequence". And they are talking here about modeling a CISC x86 exec flow! _________________ Fiction is obliged to stick to possibilities. Truth isn't.
Mark Twain |
|
Back to top |
|
|
ocbMaurice Tux's lil' helper
Joined: 14 Feb 2003 Posts: 90 Location: Switzerland
|
Posted: Fri Nov 07, 2008 9:35 pm Post subject: |
|
|
Hi all,
Just wanted to mention this thread:
https://forums.gentoo.org/viewtopic-p-5274124.html#5274124
There seems to be a serious issue on those D945GCLF/D945GCLF2 boards.
You should probably not enable automatic fan throtteling (kacpid will hog your cpu).
I'm currently using:
D945GCLF2
RTL 8139 PCI Card
Gentoo Hardened 2008.0 amd64 release
Kernel linux-2.6.25-hardened-r9
GCC x86_64-pc-linux-gnu-3.4.6
Code: | CFLAGS="-march=nocona -O2 -pipe -fomit-frame-pointer"
CXXFLAGS="${CFLAGS}"
MAKEOPTS="-j3"
CHOST="x86_64-pc-linux-gnu"
ALSA_CARDS="intel_hda"
INPUT_DEVICES="keyboard mouse"
VIDEO_CARDS="i810" |
I'm still trying out this baby, so I'm still interested if there are better cflags.
It may will replace my home server when I have the time on xmas
Greetings, Maurice |
|
Back to top |
|
|
nerdbert l33t
Joined: 09 Feb 2003 Posts: 981 Location: Berlin
|
Posted: Tue Jan 13, 2009 2:26 pm Post subject: |
|
|
Has someone made benchmarks in the meantime?
Right now I'm using the following for the N270
Code: |
CFLAGS="-march=prescott -O2 -pipe -fomit-frame-pointer"
CXXFLAGS="${CFLAGS}"
CHOST="i686-pc-linux-gnu"
MAKEOPTS="-j3" #to make use of HT!?
|
I'm thinking about switching to -march=i586 -mmmx -sse -sse2 -sse3 ...
I'd recompile gcc and check compile times for a specific package before and after. Or is there a better/quicker way to find out which is faster? _________________ I'm really wondering what Lovechild is doing nowadays... |
|
Back to top |
|
|
brian33x51 Tux's lil' helper
Joined: 16 Jun 2002 Posts: 118
|
Posted: Wed Jan 14, 2009 8:27 pm Post subject: |
|
|
The N330 ends up being a different processor...there's no reason to not go 64bit...
CFLAGS="-Os -march=native -fomit-frame-pointer -pipe"
ACCEPT_KEYWORDS="~amd64"
MAKEOPTS="-j5"
before that I was using -march=core2
Based on my benchmarks
multi thread compiles (j5)about 1/2 the speed of an athlon64 x2 4200+ (j3)
single thread triangulation (10240 vertices):
- n330 10.88s
- athlon64 x2 4200+: 4.12s
- clovertown 1.6: 2.48s |
|
Back to top |
|
|
nerdbert l33t
Joined: 09 Feb 2003 Posts: 981 Location: Berlin
|
Posted: Wed Jan 14, 2009 9:04 pm Post subject: |
|
|
Yes, they belong to the same family (Diamondville), but the 230 and 330 come with Intel 64. The N270 on the other hand supports enhanced speedstep.
Meanwhile I've done some very basic tests for the N270 with nbench, which seems to run faster with march=prescott -O2 -fomit-frame-pointer than -march=i586 -O2 -mmmx -msse -msse2 -msse3 -fomit-frame-pointer
I've posted the results here, if anyone is interested. _________________ I'm really wondering what Lovechild is doing nowadays... |
|
Back to top |
|
|
dakster Apprentice
Joined: 26 Jul 2004 Posts: 178 Location: New England
|
Posted: Sun Apr 05, 2009 2:09 pm Post subject: |
|
|
I've got the 330 atom processor as well, and am considering upgrading to gcc 4.3 and recompiling my whole system with the march=native (currently with 32bit march prescott). However, I noticed somehow I've ended up with 486 in my chost, and not 686 (doh!). Looks like a pain in the arse to fix according to the chost changing guide. Is it even worth changing the system to 686, or will upgrading the compiler and flipping to march-native and rebuilding the system be the biggest performance gain? |
|
Back to top |
|
|
gcasillo l33t
Joined: 23 Sep 2003 Posts: 739 Location: Cincinnati, Ohio, USA
|
Posted: Tue May 19, 2009 6:09 pm Post subject: |
|
|
I recently bought an Asus 1000HE netbook. It comes with an Atom N280 processor. I'm trying to determine what the appropriate CHOST, CFLAGS, etc. are for this. Also, I am strongly considering using a couple machines on my network (C2D E6300 and C2Q Q6600) to assist with large compiles using distcc and crossdev. Has anyone done this in a similar manner? What target would I choose for building my crossdev tools? i586, i686, or something else? |
|
Back to top |
|
|
rufnut Apprentice
Joined: 16 May 2005 Posts: 247
|
Posted: Thu May 21, 2009 9:06 am Post subject: |
|
|
gcasillo wrote: | Has anyone done this in a similar manner? What target would I choose for building my crossdev tools? i586, i686, or something else? |
I do similar to what you are suggesting.
i686 crossdev setup is fine as my q6600 is running x86_64
If your q6600 and the other are just x86 (i686) you wont need crossdev just setup distcc as you need.
One thing to be careful though is that the use of "native" as a cpuflag did conflict when using distcc, maybe they could have fixed it now ?
Good Luck. |
|
Back to top |
|
|
gringo Advocate
Joined: 27 Apr 2003 Posts: 3793
|
Posted: Thu May 21, 2009 10:24 am Post subject: |
|
|
Quote: | One thing to be careful though is that the use of "native" as a cpuflag did conflict when using distcc, maybe they could have fixed it now ? |
if you have -march=native, distcc won´t work ( and it shouldn´t work, because using distcc and -march=native just doesn´t make any sense at all).
Or just setup a chroot in your quad system and build all your stuff there and setup a binhost. Only if you are running a multilib system of course.
I used -march=core2 -mtune=generic on my eeepc and it went fine afaict.
The gcc guys are going to provide a dedicated atom target, maybe we are lucky and it will be ready for gcc-4.5.
cheers _________________ Error: Failing not supported by current locale |
|
Back to top |
|
|
WuDDjA n00b
Joined: 30 Aug 2005 Posts: 42
|
Posted: Fri May 22, 2009 1:29 pm Post subject: |
|
|
I am using gcc-4.5 from toolchain overlay with -march=atom
and it works perfect on my system.
but its a bit tricky to compile the gcc 4.5
take a look at my bug report
https://bugs.gentoo.org/show_bug.cgi?id=270558
you also should enable the atom processor in the kernel
with a little patch from here:
http://patchwork.kernel.org/patch/23085/
I'm already on testing but will report later if it works.
emerge -e world
takes a long time on intel atom N270 |
|
Back to top |
|
|
rufnut Apprentice
Joined: 16 May 2005 Posts: 247
|
Posted: Sat May 23, 2009 7:18 am Post subject: |
|
|
gringo wrote: |
if you have -march=native, distcc won´t work ( and it shouldn´t work, because using distcc and -march=native just doesn´t make any sense at all).
|
I don't see why not, it works for gcc so should for distcc ?
https://bugs.gentoo.org/223159
A little work may be needed on distcc to test a few things that's all.
|
|
Back to top |
|
|
gringo Advocate
Joined: 27 Apr 2003 Posts: 3793
|
Posted: Mon May 25, 2009 3:32 pm Post subject: |
|
|
Quote: | I don't see why not, it works for gcc so should for distcc ?
https://bugs.gentoo.org/223159
A little work may be needed on distcc to test a few things that's all. |
i´m not sure i get what you mean, that bug explicitly states that distcc will be disabled if -march=native is used, and that´s how it should work IMO.
Quote: | I am using gcc-4.5 from toolchain overlay with -march=atom
and it works perfect on my system. |
nice !
Quote: | takes a long time on intel atom N270 |
sure it will
thanks for the info WuDDjA, i wasn´t aware the atom stuff was already merged !
cheers _________________ Error: Failing not supported by current locale |
|
Back to top |
|
|
gcasillo l33t
Joined: 23 Sep 2003 Posts: 739 Location: Cincinnati, Ohio, USA
|
Posted: Tue May 26, 2009 1:30 am Post subject: |
|
|
Just wanted to report my success with a Gentoo install on my new Asus Eee 1000HE netbook. Here's my emerge info for reference: Code: | Portage 2.2_rc33 (!/usr/portage/profiles/default/linux/x86/2008.0/desktop, gcc-4.3.3, glibc-2.10.1-r0, 2.6.28-gentoo-r5 i686)
=================================================================
System uname: Linux-2.6.28-gentoo-r5-i686-Intel-R-_Atom-TM-_CPU_N280_@_1.66GHz-with-gentoo-2.0.1
Timestamp of tree: Tue, 26 May 2009 00:15:01 +0000
distcc 3.1 i686-pc-linux-gnu [enabled]
ccache version 2.4 [enabled]
app-shells/bash: 4.0_p24
dev-lang/python: 2.5.4-r2, 2.6.2
dev-util/ccache: 2.4-r8
dev-util/cmake: 2.6.4
sys-apps/baselayout: 2.0.1
sys-apps/openrc: 0.4.3-r2
sys-apps/sandbox: 1.9
sys-devel/autoconf: 2.63-r1
sys-devel/automake: 1.7.9-r1, 1.8.5-r3, 1.9.6-r2, 1.10.2
sys-devel/binutils: 2.19.1-r1
sys-devel/gcc-config: 1.4.1
sys-devel/libtool: 2.2.6a
virtual/os-headers: 2.6.29
ACCEPT_KEYWORDS="x86 ~x86"
CBUILD="i686-pc-linux-gnu"
CFLAGS="-march=prescott -O2 -pipe -fomit-frame-pointer"
CHOST="i686-pc-linux-gnu"
CONFIG_PROTECT="/etc /usr/kde/4.2/env /usr/kde/4.2/share/config /usr/kde/4.2/shutdown /usr/share/config"
CONFIG_PROTECT_MASK="/etc/ca-certificates.conf /etc/env.d /etc/eselect/postgresql /etc/fonts/fonts.conf /etc/gconf /etc/gentoo-release /etc/revdep-rebuild /etc/sandbox.d /etc/terminfo /etc/udev/rules.d"
CXXFLAGS="-march=prescott -O2 -pipe -fomit-frame-pointer"
DISTDIR="/usr/portage/distfiles"
FEATURES="ccache distcc distlocks fixpackages parallel-fetch preserve-libs protect-owned sandbox sfperms strict unmerge-orphans userfetch"
GENTOO_MIRRORS="ftp://ftp.ussg.iu.edu/pub/linux/gentoo ftp://ftp.gtlib.gatech.edu/pub/gentoo http://www.gtlib.gatech.edu/pub/gentoo http://gentoo.mirrors.pair.com/ ftp://gentoo.mirrors.pair.com/ http://gentoo.mirrors.tds.net/gentoo ftp://gentoo.mirrors.tds.net/gentoo http://mirror.datapipe.net/gentoo ftp://mirror.datapipe.net/gentoo"
LDFLAGS="-Wl,-O1"
MAKEOPTS="-j16"
PKGDIR="/mnt/nfs_portage/distfiles"
PORTAGE_COMPRESS="gzip"
PORTAGE_COMPRESS_FLAGS="-9"
PORTAGE_CONFIGROOT="/"
PORTAGE_RSYNC_OPTS="--recursive --links --safe-links --perms --times --compress --force --whole-file --delete --stats --timeout=180 --exclude=/distfiles --exclude=/local --exclude=/packages"
PORTAGE_TMPDIR="/var/tmp"
PORTDIR="/mnt/nfs_portage"
SYNC="rsync://rsync.namerica.gentoo.org/gentoo-portage"
USE="X a52 aac acl acpi alsa amarok asf audiofile avi bash-completion berkdb bluetooth branding bzip2 cdr cli cracklib crypt ctype cups dbus dirac dlloader dri dts encode faac faad fam ffmpeg firefox flac foomaticdb frontendonly ftp gdbm gif hal imap imlib innodb ip4100 isdnlog joystick jpeg kde kdehiddenvisibility kdeprefix lcms libg++ libwww live lm_sensors logrotate mad maildir matroska midi mikmod mime mmx mmxext mng mp3 mpeg mudflap mysql ncurses nls nptl nptlonly nsplugin ogg oggvorbis openal opengl openmp pcre pdf perl plasma png postgres ppds python qt3support qt4 quicktime readline reflection samba sasl scanner sdl semantic-desktop session smp speex spell spl sse sse2 ssl ssse3 startup-notification subversion svg sysfs syslog taglib tcpd theora tiff transcode truetype unicode usb vhosts vorbis webkit win32codecs x264 x86 xcomposite xine xml xml2 xorg xulrunner xv xvid zlib" ALSA_CARDS="hda-intel" ALSA_PCM_PLUGINS="adpcm alaw asym copy dmix dshare dsnoop empty extplug file hooks iec958 ioplug ladspa lfloat linear meter mmap_emul mulaw multi null plug rate route share shm softvol" APACHE2_MODULES="actions alias auth_basic authn_alias authn_anon authn_dbm authn_default authn_file authz_dbm authz_default authz_groupfile authz_host authz_owner authz_user autoindex cache dav dav_fs dav_lock deflate dir disk_cache env expires ext_filter file_cache filter headers include info log_config logio mem_cache mime mime_magic negotiation rewrite setenvif speling status unique_id userdir usertrack vhost_alias" CAMERAS="ptp2" ELIBC="glibc" INPUT_DEVICES="evdev keyboard mouse synaptics" KERNEL="linux" LCD_DEVICES="bayrad cfontz cfontz633 glk hd44780 lb216 lcdm001 mtxorb ncurses text" USERLAND="GNU" VIDEO_CARDS="intel"
Unset: CPPFLAGS, CTARGET, EMERGE_DEFAULT_OPTS, FFLAGS, INSTALL_MASK, LANG, LC_ALL, LINGUAS, PORTAGE_RSYNC_EXTRA_OPTS, PORTDIR_OVERLAY |
As you can see, I'm using gcc-4.3.3 and glibc-2.10.1. My CFLAGS are per the recommendation in the safe cflags page for an Atom N270 (almost the same CPU). For my kernel build, I selected the Core2 processor family. Seems to be okay, though that was unintuitive and required some googling.
Believe it or not, I'm running KDE-4.2.3 on this little puppy, and so far, I'm happy. Very usable, though I have to acclimate to KDE4 since I've been a stubborn, heavy user of KDE-3.5 until now. |
|
Back to top |
|
|
pigeon768 l33t
Joined: 02 Jan 2006 Posts: 683
|
Posted: Tue May 26, 2009 8:49 pm Post subject: |
|
|
nerdbert wrote: | than -march=i586 -O2 -mmmx -msse -msse2 -msse3 -fomit-frame-pointer | The -msse and -msse2 are redundant. You only need to include the highest level of sse you have - gcc will fill in the rest. Run 'gcc -c -Q -O3 -msse3 --help=target' and compare to 'gcc -c -Q -O3 -msse -msse2 -msse3 --help=target'.
For those (including myself) using -march=prescott: You probably want to include "-mssse3". (three s's) The Atom supports ssse3, while the prescott did not. |
|
Back to top |
|
|
gringo Advocate
Joined: 27 Apr 2003 Posts: 3793
|
Posted: Wed May 27, 2009 8:58 am Post subject: |
|
|
um, does anyone here know if there is a backport of the atom specific bits for gcc-4.4 ??
edit : just found this - > https://bugs.gentoo.org/262603
thanks ! _________________ Error: Failing not supported by current locale |
|
Back to top |
|
|
|