Is Itanium the first 64-bit casualty?

[Yousuf Khan]

Interesting reading here, and very common-sense. Itanium may be the next
casualty in the 64-bit wars, when Itanium was the one that caused the 64-bit
wars to start in the first place.

http://www.infoworld.com/article/04/06/25/26enterwin_1.html

Yousuf Khan

 

[Greg Lindahl]

Interesting reading here, and very common-sense.

Pretty much lacking on the factual side, and nothing new in the rest
of it.

Why'd you cross-post so widely?

Followups away from comp.arch.

-- greg

 

[George Macdonald]

Pretty much lacking on the factual side, and nothing new in the rest
of it.

Yes, I'm curious why he mentioned none of the known hard facts. I guess
the ones like this
http://www.ptc.com/partners/hardware/current/itanium_letter.htm didn't want
to be held up as examples of the iNfidel. "Decertification" sounds
kinda serious coming from a major workstation software vendor. I wonder
how long before customers umm, decertify 32-bit only x-86 systems.

Why'd you cross-post so widely?

Followups away from comp.arch.

RD&H?

Rgds, George Macdonald

"Just because they're paranoid doesn't mean you're not psychotic" - Who, me??

 

[Warren Spencer]

(e-mail address removed) (Yousuf Khan) wrote in

Interesting reading here, and very common-sense. Itanium may be the next
casualty in the 64-bit wars, when Itanium was the one that caused the
64-bit wars to start in the first place.

http://www.infoworld.com/article/04/06/25/26enterwin_1.html

Yousuf Khan

Perhaps this is the first case of a processor acting as a catalyst: The
Itanium sparked the 64-bit-for-consumer trend, but isn't actually going to
take part in it ;-)

ws

 

[Nick Maclaren]

Perhaps this is the first case of a processor acting as a catalyst: The
Itanium sparked the 64-bit-for-consumer trend, but isn't actually going to
take part in it ;-)

Yer whaa?

It was INTENDED to do that - back in 1994, it was intended to replace
x86 in the consumer market by 2001 - but NO WAY did it have a significant
influence on it. The trend was due to the passage of time, involving
Moore's law and Gates's law (bloatware expands at 60% per annum), and
the main chips that started 64-bit use by consumers were the SPARC
and PowerPC. And they didn't have much influence on that market.


Regards,
Nick Maclaren.

 

[Nate Edel]

Interesting reading here, and very common-sense. Itanium may be the next
casualty in the 64-bit wars, when Itanium was the one that caused the 64-bit
wars to start in the first place.

Errr... hype about Itanium may have brought the interest from the Unix world
to the destkop, but Dec and Sun both came closer to getting Alpha and
UltraSparc on the desktop than Intel's come to putting Itanic there.

The 64-bit war for the desktop is still a non-starter; right you can either
get software without consumer hardware (Windows for Itanic) or consumer
hardware without a mass-market OS (x86-64).

 

[del cecchi]

Errr... hype about Itanium may have brought the interest from the Unix world
to the destkop, but Dec and Sun both came closer to getting Alpha and
UltraSparc on the desktop than Intel's come to putting Itanic there.

The 64-bit war for the desktop is still a non-starter; right you can either
get software without consumer hardware (Windows for Itanic) or consumer
hardware without a mass-market OS (x86-64).

--

Or you can get both, Apple G5. duh.

del cecchi

 

[AD.]

Or you can get both, Apple G5. duh.

Exactly what 64bit capabilities does Panther have? That's just a question,
I don't really know

I was under the impression that Apple won't have a 'proper' 64bit OS
until Tiger (10.4) early next year.

Cheers
Anton

 

[CJT]

the 64-bit


Or you can get both, Apple G5. duh.

del cecchi

64 bit really isn't useful for typical (or even most atypical) desktops,
anyway.

 

[David Magda]

Exactly what 64bit capabilities does Panther have? That's just a
question, I don't really know

Certainly not a 64-bit memory model.

I was under the impression that Apple won't have a 'proper' 64bit
OS until Tiger (10.4) early next year.

Which was just previewed yesterday at Apple's WWDC 2004. Apple will
be going to an LP64 model in "Tiger":

http://www.apple.com/macosx/tiger/64bit.html

Apple's development tools also have support for "Fat Binaries":
allowing for both 32- and 64-bit instructions in the same
executable. I've heard it mentioned that the binary format would also
allow different architecture code (e.g., both PowerPC and x86) in the
same binary as well.

So we'll have UltraSPARC, 'AMD64' and PowerPC as the most popular
64-bit platforms?

 

[glen herrmannsfeldt]

Nate Edel wrote:

(snip)

The 64-bit war for the desktop is still a non-starter; right you can either
get software without consumer hardware (Windows for Itanic) or consumer
hardware without a mass-market OS (x86-64).

There is Windows (2003 server, I believe) for x86-64.

There is even a free 1 year evaluation version available.

-- glen

 

[Peter Dickerson]

Nate Edel wrote:

(snip)


There is Windows (2003 server, I believe) for x86-64.

There is even a free 1 year evaluation version available.

-- glen

Not a released product, just a beta. And it is for AMD64 - apparently it
doesn't work with the Intel flavour yet. (lack of IOMMU hardware?)

Peter

 

[Keith R. Williams]

Errr... hype about Itanium may have brought the interest from the Unix world
to the destkop, but Dec and Sun both came closer to getting Alpha and
UltraSparc on the desktop than Intel's come to putting Itanic there.

The 64-bit war for the desktop is still a non-starter; right you can either
get software without consumer hardware (Windows for Itanic) or consumer
hardware without a mass-market OS (x86-64).

If "mass market" == Windows, sure. Linux runs AMD64 quite well. SuSE
9.1 is running on an Opteron quite happily at home.

 

[RusH]

64 bit really isn't useful for typical (or even most atypical)
desktops, anyway.

UT2003 has >2GB of stuff on disk it uses for rendering
Next UT engine will use >2GB of stuff in RAM for the rendering, they
are waiting for a 64bit platform in the mean time becouse Windows as it
is sucks above 2GB (unusable).


Pozdrawiam.

 

[CJT]

UT2003 has >2GB of stuff on disk it uses for rendering
Next UT engine will use >2GB of stuff in RAM for the rendering, they
are waiting for a 64bit platform in the mean time becouse Windows as it
is sucks above 2GB (unusable).


Pozdrawiam.

I suppose if you write bad enough code, you need that much linear
memory for essentially parallel tasks. But typical applications
don't.

 

[Rupert Pigott]

I suppose if you write bad enough code, you need that much linear
memory for essentially parallel tasks. But typical applications
don't.

I'd guess a fair chunk of that is textures, models and the like.

Cheers,
Rupert

 

[RusH]

I suppose if you write bad enough code, you need that much linear
memory for essentially parallel tasks. But typical applications
don't.

Its not the code, its data.


Pozdrawiam.

 

[Nate Edel]

Or you can get both, Apple G5. duh.

Well, you can kinda-sorta get the OS on the G5, as others have noted. And
Apple, while consumer hardware, is only kinda-sorta in the mass-market game.
Even within the Apple market, are the G5s down throughout the line yet, or
are they just the top-end model?

The educational-priced Sun Blade 100 was under $1000 well before the G5s
shipped, and Solaris 9 personal licenses are free. That doesn't make Solaris
on UltraSparc (or the UDB/Multia Alphas, long long ago) any more of a
mass-market 64-bit platform.

 

[Nate Edel]

Nate Edel wrote:
(snip)

There is Windows (2003 server, I believe) for x86-64.
There is even a free 1 year evaluation version available.

Unless it's shipped quite recently when I wasn't looking, it's still a
beta/pre-release version of the software.

http://www.microsoft.com/windowsxp/64bit/evaluation/upgrade.mspx

 

[Yousuf Khan]

Perhaps this is the first case of a processor acting as a catalyst:
The Itanium sparked the 64-bit-for-consumer trend, but isn't actually
going to take part in it ;-)

Interesting way of looking at it, I'll admit.

Yousuf Khan