Re: Intel Core2Duo (T7400)

2007-11-07 Thread Bernd Petrovitsch
On Die, 2007-11-06 at 20:54 -0500, Douglas A. Tutty wrote:
 On Wed, Nov 07, 2007 at 12:05:26AM +0100, Bernd Petrovitsch wrote:
[...]
  that probably doesn't hurt much.
  Fact is that I run pure 64bit Linux since months on my home desktop
  (though I'm not the typical desktop user;-).
  
   specific, just 64bit system specific), but other than that generally no
   disadvantages.
  
   I guess you could say that the fact the programs are slightly bigger
   (since all pointers become 8 bytes rather than 4) is a disadvantage, but
   on the other hand a lot of code runs slightly faster with 64bit, with a
  
  Yes, x86_64 has more registers than i386.
  
   few types of programs running much faster.  A few very very pointer
   heavy programs might run slightly slower, although I don't know of any
   where this is the case.
  
  In short: FUD?!
 
 Len Sorensen knows a lot about running amd64.  Consider that before you
 write off what he says as FUD.

Well, without any real examples or details?

I would have formulated the above paragraph differently (it it's
actually a correct interpretation): Very pointer-heavy apps may run
slightly slower. But since we don't know any real example, it is not
an issue until someone comes with an convincing case.

[...]
   The main missing programs seem to be things which are closed source, so
   adobe flash, acrobat reader, etc.  Some of these do have more or less
   functional open source replacements.  Video codecs can also be a
  
  Some browsers (konqueror, firefox as far as I've been told) allow to run
  32bit plugins from the 64bit version. Since the flash-plugin and others
  is not really important for me, I don't really care.
 
 Well, you're wrong.  In Lenny, there's a wrapper that does this but in
 Etch it doesn't exist and can't be backported.  So flash in Etch needs
 the ia-32 chroot.  I don't know if anything else does since I don't use
 them.

Thanks for first hand information and details. Well, sooner or later
Lenny will be stable and the problem vanishes ...

Bernd
-- 
Firmix Software GmbH   http://www.firmix.at/
mobil: +43 664 4416156 fax: +43 1 7890849-55
  Embedded Linux Development and Services



-- 
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: Still bugs in Nvidias binary drivers

2007-11-07 Thread A J Stiles
On Tuesday 06 Nov 2007, Jack Malmostoso wrote:
 Before the flamewar starts: the solution is to either use free drivers
 and/or switch to a vendor (i.e. Intel) that provides free drivers for its
 range.
 There is absolutely nothing the xorg or the Debian developers can do
 about this, and they most likely won't even if they could. And, for the
 record, I agree with them.

With you 100%, Jack.

I also think we should write to our Elected Representatives and ask why it 
cannot be made a legal requirement for manufacturers to provide full 
specifications for any hardware they sell.  As things stand, a dishonest 
manufacturer is in a position to use copyright law to prevent anyone exposing 
misleading claims made in respect of their products -- and that is not fair 
according to any sane definition.

 Please note I have an Nvidia card on my desktop, but after the good
 experience on my laptop, my next motherboard will be a fully integrated
 Intel. Unless AMD comes up with free drivers, but that's another story.

I too have an nVidia card in my desktop, which works beautifully with the 
free nv Xorg driver.  I'm sorely tempted by the thought of an Intel for my 
next motherboard, though .  they currently seem to be ahead of AMD in 
terms of bang for your buck.

-- 
AJS
delta echo bravo six four at earthshod dot co dot uk


-- 
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: Intel Core2Duo (T7400)

2007-11-07 Thread Rob Sims
On Tue, Nov 06, 2007 at 08:54:17PM -0500, Douglas A. Tutty wrote:
 On Wed, Nov 07, 2007 at 12:05:26AM +0100, Bernd Petrovitsch wrote:
  On Tue, 2007-11-06 at 13:35 -0500, Lennart Sorensen wrote:
   On Tue, Nov 06, 2007 at 06:58:15PM +0100, Jonas Meurer wrote:
Do you have any reasons for that suggestion? Which disadvantages does
the amd64 port have on system with up to 2GB of RAM?
   
   A few programs still don't compile or work on 64bit systems (not amd64
  
  Any real-world examples?
  Even OpenOffice runs as 64bit since months.
  The only which I remember rumors are grub. But being a bootloader,
 
 Grub on Etch amd64 works just fine.

Not just fine.  In particular,
http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=423235
is quite annoying.
-- 
Rob


signature.asc
Description: Digital signature


Re: Intel Core2Duo (T7400)

2007-11-07 Thread Jerome BENOIT



Jonas Meurer wrote:

On 07/11/2007 Jerome BENOIT wrote:


the issue with grub is that it does not yet support EFI64 


Can you point me to some documentation which explains EFI64? I searched
for it with google, but the only real information I got, was that for
booting a EFI64 kernel, the bootloader needs to support it.

What is an EFI64 kernel? Is EFI64 a CPU flag?


This is not a CPU flag,
but the possibility to boot your computer through EFI
as OS X does. Currently, you can boot 32bit kernel via
EFI provided that the kernel was built with some EFI (EFI32) stuff.
In this case, on Mac Intel computers, you do not need to install
BootCamp and to play with `refit': nevertheless some information
expected from the BIOS are no more furnished (in particular X stuff)
--- this approach can be used when you box is meant to be
a server or a number cruncher.

With last kernel withs favour (?) mm come some documentations.
You may look for `elilo' as well.

greetings,
Jerome



greetings,
 jonas



--
Jerome BENOIT
jgmbenoit_at_mailsnare_dot_net


--
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: Intel Core2Duo (T7400)

2007-11-07 Thread Lennart Sorensen
On Wed, Nov 07, 2007 at 12:05:26AM +0100, Bernd Petrovitsch wrote:
 Any real-world examples?
 Even OpenOffice runs as 64bit since months.
 The only which I remember rumors are grub. But being a bootloader,
 that probably doesn't hurt much.
 Fact is that I run pure 64bit Linux since months on my home desktop
 (though I'm not the typical desktop user;-).

I know people were working on openoffice, but it has been sufficiently
unstable both 32bit and 64bit that it's hard to ever tell when
openoffice is really working right. :)

How is mplayer with w32codecs doing on 64bit?  How about java plugin?
flash v9 plugin?

 Yes, x86_64 has more registers than i386.

That probably doesn't really matter, since all modern i386 systems have
register file renaming and other tricks that avoid going to memory for
many stack operations so not really likely to matter.  Exterminating MMX
and x87 on the other hand speeds up context switches and makes floating
point way faster than it is on i386.

 In short: FUD?!

No, theoretically you could have code with so many pointers that the
doubling of size of pointers actually costs enough memory bandwidth to
make a difference.  I hope nobody writes code like that.  I was just
trying to be thorough on any disadvantages too.  Probably irrelevant on
an AMD, but might hurt on a multi cpu intel since they still have much
more limited memory bandwidth available.

 Some browsers (konqueror, firefox as far as I've been told) allow to run
 32bit plugins from the 64bit version. Since the flash-plugin and others
 is not really important for me, I don't really care.

Well they are important to a lot of people.  The new ability to run
32bit plugins certainly helps too.

 Or install 32bit libs and run a 32bit browser/application on the x86_64
 installation.

Except that is a bit of a pain and doesn't fit dpkg/apt very well.

 Yes, but that implies Vista there and God knows how compatible (even
 to pre-Vista Windoze) the result will be.

Well there was 64bit xp although few used it (often due to lack of
drivers for their hardware.  Hooray for closed source drivers!), and
certainly a number of programs do not officially support 64bit vista yet
even though they support 32bit vista and 32 and 64bit XP.  I guess in a
year or two when people start wanting to use 4 or 8GB ram on their
desktops they won't have a choice anymore and things might start working
in 64bit windows world.

--
Len Sorensen


-- 
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: Intel Core2Duo (T7400)

2007-11-07 Thread Lennart Sorensen
On Wed, Nov 07, 2007 at 02:34:20PM +0100, Jonas Meurer wrote:
 Can you point me to some documentation which explains EFI64? I searched
 for it with google, but the only real information I got, was that for
 booting a EFI64 kernel, the bootloader needs to support it.
 
 What is an EFI64 kernel? Is EFI64 a CPU flag?

EFI is intels replacement for the legacy BIOS.  intel Macs use EFI for
example.  Since it isn't a BIOS it uses a different partition table
format (GPT = GUID Partition Table) instead of the old DOS partition
table.  GPT supports partitions larger than 2^32 sectors, which the DOS
format does not so we will have to switch within a few years on new
machines given disks are approaching the multi TB size.

EFI also has a different interface and boot method, so a boot loader
would have to know how EFI works to boot at all on such a machine.
Supposedly vista will get EFI support in SP1, at which point it should
technically be possible to boot and install directly on an intel Mac
(and other EFI intel systems) without any bootcamp or other trickiness
involved.

--
Len Sorensen


-- 
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: Intel Core2Duo (T7400)

2007-11-07 Thread Lennart Sorensen
On Wed, Nov 07, 2007 at 09:41:23AM +0100, fred wrote:
 povray 3.6 ?

Isn't there a 3.7 beta that is supposed to be 64bit safe?

--
Len Sorensen


-- 
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: Intel Core2Duo (T7400)

2007-11-07 Thread Lennart Sorensen
On Wed, Nov 07, 2007 at 02:38:27PM +0100, Jonas Meurer wrote:
 Ok, the fact that pointers and long/double variables on 64bit systems do
 take twice as much RAM as on ia32 systems sounds reasonable. Thanks for
 information.

Pointers do.  long's happen to be defined as 64bit on x86_64 while they
are defined as 32bit on i386.  Any program that uses longs better be
aware that sizeof(int) != sizeof(long) on all systems.  doubles are
64bit in all cases as far as I remember.  I think there is a new 128bit
floating point format available with 64bit that wasn't there on 32bit
systems.  I don't deal with floating point enough to be sure.

 30% is quite a lot. Can you point me to postings/articles/etc. which
 claim to have discovered this?

Well here is a randomly picked example:
rceng02:~# ls -l /data/.chroot/debian-pure64/bin/ls
-rwxr-xr-x 1 root root 85536 Jan 30  2007 /data/.chroot/debian-pure64/bin/ls
rceng02:~# ls -l /bin/ls
-rwxr-xr-x 1 root root 77352 Jan 30  2007 /bin/ls

So /bin/ls appears to be 10% larger.

rceng02:~# ls -l /bin/gzip
-rwxr-xr-x 4 root root 52672 Sep 19  2006 /bin/gzip
rceng02:~# ls -l /data/.chroot/debian-pure64/bin/gzip
-rwxr-xr-x 4 root root 60216 Sep 19  2006
/data/.chroot/debian-pure64/bin/gzip

So /bin/gzip appears to be 14% larger.  I seem to recall gzip also runs
quite a bit faster on 64bit.

--
Len Sorensen


-- 
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: Still bugs in Nvidias binary drivers

2007-11-07 Thread Robert Isaac
 I also think we should write to our Elected Representatives and ask why it
 cannot be made a legal requirement for manufacturers to provide full
 specifications for any hardware they sell.

Don't we have enough laws already?  You'll have a quicker and less
invasive response by sending snail-mail requests to nVidia
http://www.nvidia.com/page/contact_information.html


-- 
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: Intel Core2Duo (T7400)

2007-11-07 Thread Jonas Meurer
On 07/11/2007 Jerome BENOIT wrote:
 Douglas A. Tutty wrote:
 On Wed, Nov 07, 2007 at 12:05:26AM +0100, Bernd Petrovitsch wrote:
 On Tue, 2007-11-06 at 13:35 -0500, Lennart Sorensen wrote:
 On Tue, Nov 06, 2007 at 06:58:15PM +0100, Jonas Meurer wrote:
 Do you have any reasons for that suggestion? Which disadvantages does
 the amd64 port have on system with up to 2GB of RAM?
 A few programs still don't compile or work on 64bit systems (not amd64
 Any real-world examples?
 Even OpenOffice runs as 64bit since months.
 The only which I remember rumors are grub. But being a bootloader,

 Grub on Etch amd64 works just fine.

 the issue with grub is that it does not yet support EFI64 

Can you point me to some documentation which explains EFI64? I searched
for it with google, but the only real information I got, was that for
booting a EFI64 kernel, the bootloader needs to support it.

What is an EFI64 kernel? Is EFI64 a CPU flag?

greetings,
 jonas


-- 
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: Intel Core2Duo (T7400)

2007-11-07 Thread Jonas Meurer
On 06/11/2007 Basile STARYNKEVITCH wrote:
 Jonas Meurer wrote:
 On 06/11/2007 Hartmut Manz wrote:
 The correct debian port for INTEL Core2Duo is amd64 or i386.
 If your system has not more than 2 GB of memory installed I would recommend
 to still use the 32bit Linux (i386), If you have more memory installed use
 the 64-bit Linux (amd64) 

 Do you have any reasons for that suggestion? Which disadvantages does
 the amd64 port have on system with up to 2GB of RAM?

 a 64 bits system consume more memory than a 32 bits system for each pointer 
 and long (going from 32 bits = 4 bytes to 64 bits = 8 bytes) and also have 
 higher alignment requirements.

Ok, the fact that pointers and long/double variables on 64bit systems do
take twice as much RAM as on ia32 systems sounds reasonable. Thanks for
information.

 Rumors say that most processes consume about 30% more RAM

 Hence the hint (even if the 2Gb RAM threshold is arbitrary)

30% is quite a lot. Can you point me to postings/articles/etc. which
claim to have discovered this?

greetings,
 jonas


-- 
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: what happened to incoming?

2007-11-07 Thread Muammar El Khatib
Hi,

On 11/7/07, Giacomo Mulas [EMAIL PROTECTED] wrote:
 Since a couple of days, I have been unable to reach incoming.debian.org and,
 in addition, there have been no updated packages appearing on unstable for
 both amd64 and i386. Does anyone know whether there was some failure in the
 buildd's or whatever? Was the system crushed under the weight of some
 OOo+xorg+cernlib simultaneous uploads?


http://lists.debian.org/debian-devel-announce/2007/11/msg1.html

 thanks in advance,

Regards,

-- 
Muammar El Khatib.
Linux user: 403107.
Key fingerprint = 90B8 BFC4 4A75 B881 39A3  1440 30EB 403B 1270 29F1
http://muammarelkhatib.net | http://teorex.org | http://taciturna.com
  ,''`.
 : :' :
 `. `'
   `-


-- 
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: Intel Core2Duo (T7400)

2007-11-07 Thread Jonas Meurer
On 06/11/2007 Lennart Sorensen wrote:
 On Tue, Nov 06, 2007 at 06:58:15PM +0100, Jonas Meurer wrote:
  Do you have any reasons for that suggestion? Which disadvantages does
  the amd64 port have on system with up to 2GB of RAM?
 
 A few programs still don't compile or work on 64bit systems (not amd64
 specific, just 64bit system specific), but other than that generally no
 disadvantages.

but at least that doesn't depend on the RAM you use ;-)

 I guess you could say that the fact the programs are slightly bigger
 (since all pointers become 8 bytes rather than 4) is a disadvantage, but
 on the other hand a lot of code runs slightly faster with 64bit, with a
 few types of programs running much faster.  A few very very pointer
 heavy programs might run slightly slower, although I don't know of any
 where this is the case.
 
 With 64bit you can memory map much bigger files than with 32bit which
 can make implementing some programs much simpler and probably more
 efficient too, so there seems to be many good reasons to move to 64bit.

that's the relevant information here ;-) Thanks for pointing me to it.

...
 jonas


-- 
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: Intel Core2Duo (T7400)

2007-11-07 Thread Mark Komarinski

On 11/07/2007 02:30 PM, Lennart Sorensen wrote:


Well here is a randomly picked example:
rceng02:~# ls -l /data/.chroot/debian-pure64/bin/ls
-rwxr-xr-x 1 root root 85536 Jan 30  2007 /data/.chroot/debian-pure64/bin/ls
rceng02:~# ls -l /bin/ls
-rwxr-xr-x 1 root root 77352 Jan 30  2007 /bin/ls

So /bin/ls appears to be 10% larger.


On my Fedora 7 systems, /bin/ls is 5% larger on 32-bit than 64-bit:

[EMAIL PROTECTED] ~]$ ls -l /bin/ls ; file /bin/ls
-rwxr-xr-x 1 root root 99468 2007-06-13 10:06 /bin/ls
/bin/ls: ELF 32-bit LSB executable, Intel 80386, version 1 (SYSV), 
dynamically linked (uses shared libs), for GNU/Linux 2.6.9, stripped

[EMAIL PROTECTED] ~]$


[EMAIL PROTECTED] ~]$ ls -l /bin/ls ; file /bin/ls
-rwxr-xr-x 1 root root 95056 2007-06-13 10:31 /bin/ls
/bin/ls: ELF 64-bit LSB executable, x86-64, version 1 (SYSV), 
dynamically linked (uses shared libs), for GNU/Linux 2.6.9, stripped

[EMAIL PROTECTED] ~]$


rceng02:~# ls -l /bin/gzip
-rwxr-xr-x 4 root root 52672 Sep 19  2006 /bin/gzip
rceng02:~# ls -l /data/.chroot/debian-pure64/bin/gzip
-rwxr-xr-x 4 root root 60216 Sep 19  2006
/data/.chroot/debian-pure64/bin/gzip

So /bin/gzip appears to be 14% larger.  I seem to recall gzip also runs
quite a bit faster on 64bit.


gzip is about 5% larger on 64-bit (67120 bytes) than 32-bit (64116 bytes).

Go figure.

-Mark

--
Mark Komarinski [EMAIL PROTECTED]
Sr. Research Systems Architect  http://ritg.med.harvard.edu
Research IT Group
Harvard Medical School


--
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



what happened to incoming?

2007-11-07 Thread Giacomo Mulas

Since a couple of days, I have been unable to reach incoming.debian.org and,
in addition, there have been no updated packages appearing on unstable for
both amd64 and i386. Does anyone know whether there was some failure in the
buildd's or whatever? Was the system crushed under the weight of some
OOo+xorg+cernlib simultaneous uploads?

thanks in advance,
Giacomo

--
_

Giacomo Mulas [EMAIL PROTECTED]
_

OSSERVATORIO ASTRONOMICO DI CAGLIARI
Str. 54, Loc. Poggio dei Pini * 09012 Capoterra (CA)

Tel. (OAC): +39 070 71180 248 Fax : +39 070 71180 222
Tel. (UNICA): +39 070 675 4916
_

When the storms are raging around you, stay right where you are
 (Freddy Mercury)
_

--
This message has been scanned for viruses and
dangerous content by MailScanner, and is
believed to be clean.


--
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]



Re: Intel Core2Duo (T7400)

2007-11-07 Thread Douglas A. Tutty
On Wed, Nov 07, 2007 at 11:54:48AM -0700, Rob Sims wrote:
 On Tue, Nov 06, 2007 at 08:54:17PM -0500, Douglas A. Tutty wrote:
  
  Grub on Etch amd64 works just fine.
 
 Not just fine.  In particular,
 http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=423235
 is quite annoying.

I never noticed it since I have everything I need right in the menu.



-- 
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]