Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

AnandTech News: NVIDIA nForce 4 SLI Redefines Digital Media Experience
on Intel-Based PCs
http://www.anandtech.com/news/shownews.aspx?i=24057

Interesting note, the Nforce 4 SLI for Intel has one more feature than
the original Nforce 4 for AMD, which is a bootable RAID5 feature.

NVIDIA nForce4
http://www.nvidia.com/page/nforce4_family.html

Yousuf Khan

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

YKhan <yjkhan@gmail.com> wrote:
>AnandTech News: NVIDIA nForce 4 SLI Redefines Digital Media Experience
>on Intel-Based PCs
>http://www.anandtech.com/news/shownews.aspx?i=24057
>
>Interesting note, the Nforce 4 SLI for Intel has one more feature than
>the original Nforce 4 for AMD, which is a bootable RAID5 feature.

I wouldn't be surprised if this shows in a new revision of the
nF4/AMD, possibly chipset stepping or new edition (SLI+)?. Heck, it
could even show up as software upgrade, it COULD be that they were
just waiting to get all the software ironed out (case in point: There
are RAID 5 drivers for SIL-3114 out now from some manufacturers now,
and it IS bootable/installable)

HotHardware has more information and a full review of a reference
motherboard against , they've must've worked hard to get it out the
same day, though they "helped" the Intel processors a bit by using a
much cheaper AMD processor than the Intel processor used (925XE vs
nF4/i vs nF4/A, top of the line P4EE's should arguably be benchmarked
against the latest AMD FX model).

http://www.hothardware.com/viewart [...] icleid=658

FiringSquad appears to have similar information and also has some
tests, but only lists P4EE/nF4i scores. This makes it hard to tell
much from them, it might be possible to figure something out by
crossreferencing other earlier tests of other platforms.

http://www.firingsquad.com/hardwar [...] l_edition/

The first results is looking pretty good, especially if they can
deliver on supporting both single and dual-core P4's.

The new Intel chipsets coming might help the Intel chipset side a bit
though, but early indications seems to be not that much difference
from 925XE, at best it might equalize with nF4i (more testing though
than nF4i, so less uncertainty in how much to trust the values).

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Tue, 05 Apr 2005 17:58:43 +0000, Torbjorn Lindgren wrote:

> YKhan <yjkhan@gmail.com> wrote:
<snip>
> I wouldn't be surprised if this shows in a new revision of the
> nF4/AMD, possibly chipset stepping or new edition (SLI+)?. Heck, it
> could even show up as software upgrade, it COULD be that they were
> just waiting to get all the software ironed out (case in point: There
> are RAID 5 drivers for SIL-3114 out now from some manufacturers now,
> and it IS bootable/installable)
>
> HotHardware has more information and a full review of a reference
> motherboard against , they've must've worked hard to get it out the
> same day, though they "helped" the Intel processors a bit by using a
> much cheaper AMD processor than the Intel processor used (925XE vs
> nF4/i vs nF4/A, top of the line P4EE's should arguably be benchmarked
> against the latest AMD FX model).
>
> http://www.hothardware.com/viewart [...] icleid=658
>
> FiringSquad appears to have similar information and also has some
> tests, but only lists P4EE/nF4i scores. This makes it hard to tell
> much from them, it might be possible to figure something out by
> crossreferencing other earlier tests of other platforms.
>
> http://www.firingsquad.com/hardwar [...] l_edition/
>
> The first results is looking pretty good, especially if they can
> deliver on supporting both single and dual-core P4's.
>
> The new Intel chipsets coming might help the Intel chipset side a bit
> though, but early indications seems to be not that much difference
> from 925XE, at best it might equalize with nF4i (more testing though
> than nF4i, so less uncertainty in how much to trust the values).

Who is the intended market for these boards, as the articles point out,
the AMD solution is much faster, so a serious gamer would go with AMD. Not
to mention the price performance aspect, heat aspect, everything else. Ok
it might be the fastest Intel solution, the only thing I could see as the
target market is the big OEM's, or those who are Intel only who want a
fast gaming machine.

Gnu-Raiz

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

In article <1112805180.d899a15a2ca6a449f8db2776b2a4ed78@teranews>,
Gnu_Raiz <Gnu_Raiz@uptime.notlost.net> wrote:
>On Wed, 06 Apr 2005 09:12:12 -0400, Tony Hill wrote:
>> I don't know about the rest of you, but my interest at the moment lies
>> squarely in dual-core processors. If early rumors are true, then it
>> looks like we'll be waiting a good 6-12 months before we'll get
>> *affordable* dual-core desktop chips from AMD, while Intel is looking
>> to release low-ish cost dual-core chips in the next couple months.
>
>I am excited about dual core too, but I have a hard time living down the
>power requirements of smithfield. I do like the idea that Intel will
>target all markets with its dual core. Since no major software is
>multithreaded the benefits won't show up anytime soon.
>
>I am also glad that Nvidia has such a good chipset, and hope it puts
>pressure on Intel, in all markets. I also think that ATI will not roll
>over and will join in the competition, as it already has a big stake in
>the mobile arena. As far as gaming machines go I really doubt that dual
>core will make a big differene, unless they start making games that are
>multithreaded. Just consider how many games are 64 bit not many, since
>Windows 64 was released to manufacturing, it still up in the air.

There's more to computing than just gaming. Things like video/photo editors
and video encoders tend to be fairly aggressively multithreaded and can make
effective use of as much processor power as you can throw at them. If
you're cleaning up your home videos or archiving TV shows to DVD, a
dual-core processor ought to deliver a decent performance boost.

Even if most of your apps aren't multithreaded, you should still see some
improvement from having a 2nd core on which the scheduler can run processes.
With two cores and two monitors, you could run a FPS full-screen on one
monitor and a videoconference program in a window on the other monitor. You
can taunt your foes as you frag them into oblivion, and the videoconference
program should have minimal (if any) impact on the performance of your game.

(Not that I would waste my time with such an endeavor, but some people
would.)

_/_
/ v \ Scott Alfter (remove the obvious to send mail)
(IIGS( http://alfter.us/ Top-posting!
\_^_/ rm -rf /bin/laden >What's the most annoying thing on Usenet?

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.0 (GNU/Linux)

iD8DBQFCVCRdVgTKos01OwkRAkKPAJ4iTkE2lP05ISjD9Y3L4/0LKojjsQCgrSZ1
rtMpreL7k1of8Zq/W9YEoeA=
=b68M
-----END PGP SIGNATURE-----

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Bitstring <1112805180.d899a15a2ca6a449f8db2776b2a4ed78@teranews>, from
the wonderful person Gnu_Raiz <Gnu_Raiz@uptime.notlost.net> said
<snip>
> Since no major software is
>multithreaded the benefits won't show up anytime soon.

The OS itself is multithreaded, which means I can have Photoshop image
processing a huge .tif file and still be able to browse the web (subject
to my disk channels not having choked and died).

Actually a lot of software is multithreaded (open up task manager and
look) but usually not designed for proper concurrent thread execution.
Except the stuff I wrote, of course, (for 'flying into' Mandlebrot/Julia
fractals). 4, or 8, or 16 cores? .. bring them on .. as long as they can
do proper (80 bit) floating point at high speed. 8>.

--
GSV Three Minds in a Can
SC recommends the use of Firefox; Get smart, or get assimilated.

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Wed, 06 Apr 2005 09:12:12 -0400, Tony Hill
<hilla_nospam_20@yahoo.ca> wrote:

>I don't know about the rest of you, but my interest at the moment lies
>squarely in dual-core processors. If early rumors are true, then it
>looks like we'll be waiting a good 6-12 months before we'll get
>*affordable* dual-core desktop chips from AMD, while Intel is looking
>to release low-ish cost dual-core chips in the next couple months.
....snip...
>-------------
>Tony Hill
>hilla <underscore> 20 <at> yahoo <dot> ca
I am under impression that dual-core Opterons are about to be released
not much later than Pentiums, if not earlier. Please don't tell me
that Opteron is *not* a desktop CPU - I have two Opty242 running on
mine, and they together with the motherboard cost me less than top of
the line A64FX/P4EE and LanParty-type board would. These dual core
Opterons are expected to be anything but *affordable* when just
released, but the same is expected of Pentium D-EE, and the board for
it - be it NF4ie or i955X based - will likely cost an arm and a leg.
The cheaper 2.8GHz Pentium D is expected to be released significantly
later, will require the same expensive motherboard as EE, and hardly
will be faster than my year old Opterons. I'd rather wait until the
next speed grade of dual core Opteron 2xx is released - the price on
the original ones will go closer to reasonable level. Hope by that
time there will be the BIOS update for my mobo.

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Wed, 6 Apr 2005 19:23:36 +0100, GSV Three Minds in a Can
<GSV@quik.clara.co.uk> wrote:

>Bitstring <1112805180.d899a15a2ca6a449f8db2776b2a4ed78@teranews>, from
>the wonderful person Gnu_Raiz <Gnu_Raiz@uptime.notlost.net> said
><snip>
>> Since no major software is
>>multithreaded the benefits won't show up anytime soon.
>
>The OS itself is multithreaded, which means I can have Photoshop image
>processing a huge .tif file and still be able to browse the web (subject
>to my disk channels not having choked and died).

You bring up an rather interesting point with that disk channel bit.
It would seem that in recent testing, Anandtech found that Native
Command Queuing seems to kind of come into it's own with a dual-core
processor for just this reason:

http://www.anandtech.com/cpuchipse [...] i=2389&p=8


-------------
Tony Hill
hilla <underscore> 20 <at> yahoo <dot> ca

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Thu, 07 Apr 2005 03:07:04 GMT, "nobody@nowhere.net"
<mygarbage2000@hotmail.com> wrote:

>On Wed, 06 Apr 2005 09:12:12 -0400, Tony Hill
><hilla_nospam_20@yahoo.ca> wrote:
>
>>I don't know about the rest of you, but my interest at the moment lies
>>squarely in dual-core processors. If early rumors are true, then it
>>looks like we'll be waiting a good 6-12 months before we'll get
>>*affordable* dual-core desktop chips from AMD, while Intel is looking
>>to release low-ish cost dual-core chips in the next couple months.
>
>I am under impression that dual-core Opterons are about to be released
>not much later than Pentiums, if not earlier. Please don't tell me
>that Opteron is *not* a desktop CPU - I have two Opty242 running on
>mine, and they together with the motherboard cost me less than top of
>the line A64FX/P4EE and LanParty-type board would.

You're definition of "affordable" is obviously quite different than
mine in this case. Even now you would be looking at about $600 for
just the motherboard and processors for such a setup, plus the extra
cost of using registered memory on top of that. For comparison I can
pick up an Athlon64 3200+ and motherboard for under $300.

> These dual core
>Opterons are expected to be anything but *affordable* when just
>released, but the same is expected of Pentium D-EE, and the board for
>it - be it NF4ie or i955X based - will likely cost an arm and a leg.

Of course, which is why I have absolutely no interest in the Pentium D
Extremely Expensive Edition.

>The cheaper 2.8GHz Pentium D is expected to be released significantly
>later,

My understanding is that Intel plans on releasing these slower speed
Pentium D chips at exactly the same time as the EE chips.

> will require the same expensive motherboard as EE,

They will work just fine on the much lower cost i945 chipsets and
presumable also a much more reasonably priced non-SLI version of the
nForce4 Intel chipset.

-------------
Tony Hill
hilla <underscore> 20 <at> yahoo <dot> ca

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

GSV Three Minds in a Can wrote:

>Bitstring <1112805180.d899a15a2ca6a449f8db2776b2a4ed78@teranews>, from
>the wonderful person Gnu_Raiz <Gnu_Raiz@uptime.notlost.net> said
><snip>
>> Since no major software is
>>multithreaded the benefits won't show up anytime soon.
>
>The OS itself is multithreaded, which means I can have Photoshop image
>processing a huge .tif file and still be able to browse the web (subject
>to my disk channels not having choked and died).

Can't we already do that? I've been multitasking since 1985 on Amiga.

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Bitstring <b6ra5190b0qjftmqq3ik663kkm3l7qtk2p@4ax.com>, from the
wonderful person chrisv <chrisv@nospam.invalid> said
<snip>
>>The OS itself is multithreaded, which means I can have Photoshop image
>>processing a huge .tif file and still be able to browse the web (subject
>>to my disk channels not having choked and died).
>
>Can't we already do that? I've been multitasking since 1985 on Amiga.

No, we can't =reliably= do that yet (and I've been multitasking since
1970, on a Titan) with a PC. There are still too many ways for the
supposed 'background' task to pull the rest of the machine down to
unacceptable crawl (lots, but not all, of which has to do with CPU
loading).

--
GSV Three Minds in a Can
SC recommends the use of Firefox; Get smart, or get assimilated.

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Thu, 07 Apr 2005 10:24:43 -0400, Tony Hill
<hilla_nospam_20@yahoo.ca> wrote:

>On Thu, 07 Apr 2005 03:07:04 GMT, "nobody@nowhere.net"
><mygarbage2000@hotmail.com> wrote:
>
>>On Wed, 06 Apr 2005 09:12:12 -0400, Tony Hill
>><hilla_nospam_20@yahoo.ca> wrote:
>>
>>>I don't know about the rest of you, but my interest at the moment lies
>>>squarely in dual-core processors. If early rumors are true, then it
>>>looks like we'll be waiting a good 6-12 months before we'll get
>>>*affordable* dual-core desktop chips from AMD, while Intel is looking
>>>to release low-ish cost dual-core chips in the next couple months.
>>
>>I am under impression that dual-core Opterons are about to be released
>>not much later than Pentiums, if not earlier. Please don't tell me
>>that Opteron is *not* a desktop CPU - I have two Opty242 running on
>>mine, and they together with the motherboard cost me less than top of
>>the line A64FX/P4EE and LanParty-type board would.
>
>You're definition of "affordable" is obviously quite different than
>mine in this case. Even now you would be looking at about $600 for
>just the motherboard and processors for such a setup, plus the extra
>cost of using registered memory on top of that. For comparison I can
>pick up an Athlon64 3200+ and motherboard for under $300.
$600 is about what I paid in May'04. Today it would be (data from
Pricewatch):
MSI MASTER2-FAR board: $209
Opty242(oem) $158 * 2 = $316
---------------------------
Total: $525
Also quite a chunk of change, but not exactly 600. For comparison,
A64 4000+ (not even FX!) alone is listed at more than that - $535. Or
how about the utterly obscene $950 they list P4EE 3.4 GHz for?
>
>> These dual core
>>Opterons are expected to be anything but *affordable* when just
>>released, but the same is expected of Pentium D-EE, and the board for
>>it - be it NF4ie or i955X based - will likely cost an arm and a leg.
>
>Of course, which is why I have absolutely no interest in the Pentium D
>Extremely Expensive Edition.
>
>>The cheaper 2.8GHz Pentium D is expected to be released significantly
>>later,
>
>My understanding is that Intel plans on releasing these slower speed
>Pentium D chips at exactly the same time as the EE chips.
As you said above, "next couple months". My prognosis is that only
Dell will get them right about that time *in quantities*. HP and
other big OEMs probably a few weeks later. To reach retailers, it
would take another few weeks. How *significantly* later it is -
depends on how long one is willing to wait. Also I was under
impression that EE launches first to a drum roll, and lower-priced
parts will quietly follow somewhat later (I may be wrong on this).
>
>> will require the same expensive motherboard as EE,
>
>They will work just fine on the much lower cost i945 chipsets and
>presumable also a much more reasonably priced non-SLI version of the
>nForce4 Intel chipset.
My understanding is that NF4ie will be, at least in the beginning,
only of SLI variety because INTC has no desire to give to NVDA its
market share in midrange boards (could be wrong on this one, too).
>
>-------------
>Tony Hill
>hilla <underscore> 20 <at> yahoo <dot> ca

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Thu, 7 Apr 2005 21:44:52 +0100, GSV Three Minds in a Can
<GSV@quik.clara.co.uk> wrote:

>Bitstring <b6ra5190b0qjftmqq3ik663kkm3l7qtk2p@4ax.com>, from the
>wonderful person chrisv <chrisv@nospam.invalid> said
><snip>
>>>The OS itself is multithreaded, which means I can have Photoshop image
>>>processing a huge .tif file and still be able to browse the web (subject
>>>to my disk channels not having choked and died).
>>
>>Can't we already do that? I've been multitasking since 1985 on Amiga.
>
>No, we can't =reliably= do that yet (and I've been multitasking since
>1970, on a Titan) with a PC. There are still too many ways for the
>supposed 'background' task to pull the rest of the machine down to
>unacceptable crawl (lots, but not all, of which has to do with CPU
>loading).

Oh, let me be stupid and ask. On the whole, Linux seems to do much
better than Windows. Both seem to get dragged down by "background"
tasks that involve lots of disk activity, and I think the problem is
interrupts. A second CPU is going to help with that?

RM

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

Bitstring <q3kb51latd6t4nm1a6t1tcgqqr7p3mrruc@4ax.com>, from the
wonderful person Robert Myers <rmyers1400@comcast.net> said
>On Thu, 7 Apr 2005 21:44:52 +0100, GSV Three Minds in a Can
><GSV@quik.clara.co.uk> wrote:
>
>>Bitstring <b6ra5190b0qjftmqq3ik663kkm3l7qtk2p@4ax.com>, from the
>>wonderful person chrisv <chrisv@nospam.invalid> said
>><snip>
>>>>The OS itself is multithreaded, which means I can have Photoshop image
>>>>processing a huge .tif file and still be able to browse the web (subject
>>>>to my disk channels not having choked and died).
>>>
>>>Can't we already do that? I've been multitasking since 1985 on Amiga.
>>
>>No, we can't =reliably= do that yet (and I've been multitasking since
>>1970, on a Titan) with a PC. There are still too many ways for the
>>supposed 'background' task to pull the rest of the machine down to
>>unacceptable crawl (lots, but not all, of which has to do with CPU
>>loading).
>
>Oh, let me be stupid and ask. On the whole, Linux seems to do much
>better than Windows. Both seem to get dragged down by "background"
>tasks that involve lots of disk activity, and I think the problem is
>interrupts. A second CPU is going to help with that?

The problem appears to be system code (which may indeed be running as a
result of interrupts) and which is run at such high priority that
nothing else gets a look in. The actual interrupt handling these days is
usually very little code - it just queues up something for a WinXP
'service' to handle ASAP. The service is what then chokes the system.

(e.g.) I've got an intermittent problem which seems to be caused by my
USB GPS handset being mis-recognised as a graphics device (possibly
caused by Photoshop Elements service which auto-starts when it thinks it
sees some sort of graphics activity)

Event Type: Error
Event Source: Service Control Manager
Event Category: None
Event ID: 7011
Date: 28/01/2005
Time: 18:53:49
User: N/A
Computer: QUIK5
Description:
Timeout (30000 milliseconds) waiting for a transaction response from the
stisvc service.

After than happens (thankfully rarely) the system runs like a 15Khz
(yes, Khz) cpu, with 100% CPU dedicated to one of the 73 'system'
threads. Not even task manager can get a look in (well, it can, if you
wait 20 minutes! Usually I just hit reset).

That sort of cr&p doesn't usually happen on a dualie.

--
GSV Three Minds in a Can
SC recommends the use of Firefox; Get smart, or get assimilated.

Archived from groups: comp.sys.ibm.pc.hardware.chips,comp.sys.intel (More info?)

On Fri, 8 Apr 2005 12:56:17 +0100, GSV Three Minds in a Can
<GSV@quik.clara.co.uk> wrote:

>Bitstring <q3kb51latd6t4nm1a6t1tcgqqr7p3mrruc@4ax.com>, from the
>wonderful person Robert Myers <rmyers1400@comcast.net> said
>>On Thu, 7 Apr 2005 21:44:52 +0100, GSV Three Minds in a Can
>><GSV@quik.clara.co.uk> wrote:
>>
>>>Bitstring <b6ra5190b0qjftmqq3ik663kkm3l7qtk2p@4ax.com>, from the
>>>wonderful person chrisv <chrisv@nospam.invalid> said
>>><snip>
>>>>>The OS itself is mult