Is Itanium the first 64-bit casualty?

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/...nterwin_1.html

Yousuf Khan

--
Humans: contact me at ykhan at rogers dot com
Spambots: just reply to this email address ;-)

On Jun 2, 10:36*pm, mivpl wrote:
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/...nterwin_1.html


Thin and ancient, and the link is wrong,

http://www.infoworld.com/t/hardware/...y-494?page=0,0

To ask what's going to happen today, you really have to look at the
realities of the market today.

It seems that the only realistic option for Intel is to gradually
equip Xeon with the RAS features of Itanium, a process that has
already started. Until VMS is backported to x86, Itanium will still
be very much alive.

On the other hand, does HP *really* want to be competing with Rackable
Systems, or is it now SGI, for high socket count x86 installations?
Even IBM might want to rethink it's anti-Itanium strategy, since it
has killed not only an architecture, but probably also done serious
damage to what used to be a very profitable market segment. Will
Sparc outlive Itanium? Now there are two players (Intel and Oracle)
with big egos playing in the anything but Power and x86 market.

From my POV, the lot of them killed off necessary progress in software
(compilers and languages that don't have the inherent limits to
compiler optimization that c does).

On the AMD fanboy front, I continue to watch the stock price

http://www.bloomberg.com/apps/cbuilder?ticker1=amd

as probably knowing a lot more than I do. You have to manually add
INTC to see an interesting story. Adding NVDA gives you more
interesting scenery to ponder.

Robert.

In article
,
Robert Myers wrote:

On the AMD fanboy front, I continue to watch the stock price

http://www.bloomberg.com/apps/cbuilder?ticker1=amd

as probably knowing a lot more than I do. You have to manually add
INTC to see an interesting story. Adding NVDA gives you more
interesting scenery to ponder.

The only question I have about NVDA is who is going to buy the remains
when the company craters in two years.
I would short them, but a buyout could be announced tomorrow. (Only
Intel has the bucks and desire at todays price. Intel can wait till next
year and pay ~$3 a share.)
Right now AMD/ATI is crushing NVDA on cost/performance, and next year
the graphics chip starts the move onto the CPU chip.
If Larrabee is successful then Intel might not even buy NVDA at fire
sale prices. Then who could possibly want NVDA?

Robert.

Brett Davis wrote:
The only question I have about NVDA is who is going to buy the remains
when the company craters in two years.

Nvidia still has the cash to buy VIA many times over. VIA owns an x86
core that can be made to compete in more markets with some adequate R&D
budget.

Right now AMD/ATI is crushing NVDA on cost/performance, and next year
the graphics chip starts the move onto the CPU chip.

Which is why Nvidia really needs to get into the x86 CPU business for
itself.


Yousuf Khan

Robert Myers wrote:
It seems that the only realistic option for Intel is to gradually
equip Xeon with the RAS features of Itanium, a process that has
already started. Until VMS is backported to x86, Itanium will still
be very much alive.

HP-UX too. But Linux and Solaris already exist for this market.

On the other hand, does HP *really* want to be competing with Rackable
Systems, or is it now SGI, for high socket count x86 installations?

Sure, why not? I'm sure HP could kill them.

Even IBM might want to rethink it's anti-Itanium strategy, since it
has killed not only an architecture, but probably also done serious
damage to what used to be a very profitable market segment. Will
Sparc outlive Itanium? Now there are two players (Intel and Oracle)
with big egos playing in the anything but Power and x86 market.

Oracle will hem and haw, over what to do with Sparc, and in the end keep
it. A revenue stream is a revenue stream. It gives them a differentiated
product. Fujitsu is doing most of the design work on this architecture
these days anyways.

As for IBM, why would they rethink anything about Itanium? They figured
it was not going to be able to compete against Power, and they were
right. Why show mercy now?


Yousuf Khan

On Jun 4, 10:34*am, Yousuf Khan wrote:
Robert Myers wrote:
It seems that the only realistic option for Intel is to gradually
equip Xeon with the RAS features of Itanium, a process that has
already started. *Until VMS is backported to x86, Itanium will still
be very much alive.

HP-UX too. But Linux and Solaris already exist for this market.

That's a bit like saying that Linux and Solaris are available for
applications where only Z/OS will do.

On the other hand, does HP *really* want to be competing with Rackable
Systems, or is it now SGI, for high socket count x86 installations?

Sure, why not? I'm sure HP could kill them.

Don't know about that. HP wants a flagship, differentiated product.
I assume that rackable is going to be pushing the SGI track record
with numa-link. What is HP going to be selling?

Even IBM might want to rethink it's anti-Itanium strategy, since it
has killed not only an architecture, but probably also done serious
damage to what used to be a very profitable market segment. *Will
Sparc outlive Itanium? *Now there are two players (Intel and Oracle)
with big egos playing in the anything but Power and x86 market.

Oracle will hem and haw, over what to do with Sparc, and in the end keep
it. A revenue stream is a revenue stream. It gives them a differentiated
product. Fujitsu is doing most of the design work on this architecture
these days anyways.

As for IBM, why would they rethink anything about Itanium? They figured
it was not going to be able to compete against Power, and they were
right. Why show mercy now?

There's very little point in IBM rethinking anything. The proposition
was made tongue in cheek. The golden goose (tne non-x86 market) is
already dead. They (IBM) just don't know it yet. IBM brought a non-
native species with no natural predators into their garden, and it's
going to eat everything.

Robert.

In article , Brett
Davis writes

The only question I have about NVDA is who is going to buy the remains
when the company craters in two years.

It'll take that long?

--
(\__/)
(='.'=) Bunny says Windows 7 is Vi$ta reloaded.
(")_(") http://imgs.xkcd.com/comics/windows_7.png

In article ,
Mike Tomlinson wrote:

In article , Brett
Davis writes

The only question I have about NVDA is who is going to buy the remains
when the company craters in two years.

It'll take that long?

NVidea was one of the first movers in graphics, so assume they have a
lot of the valuable core patents.
Intel would like to buy them at a reasonable price, AMD paid $5 billion
for ATI, NVideas market cap is $6 billion today at $11/share.
Down at ~$2 billion Sony would buy NVidea for the Playstation and PSP
lines. Also Apple would be interested for iPhone and iConsole/iTV.
Microsoft bought the SGI patents for ~0.5 billion, and might be
interested for XBox and XPhone/MusicPlayer.

Lots of bidders to keep the price up even after the collapse.

I could argue that the recent run up in NVidea was Wall Street in a
panic putting the screws on Intel to make a deal now, before the price
goes "higher". When everyone knows the price is going down. Look at the
top ten holders of NVidea, these big Wall Street firms cannot sell
without collapsing the price, so they are pushing hard for someone to
buy NVidea, or they will end up with big losses.
http://finance.yahoo.com/q/mh?s=NVDA

Brett - PS: I added the comp.arch newsgroup, to see what that smart
group thinks.

In article , Yousuf Khan
wrote:

Brett Davis wrote:
The only question I have about NVDA is who is going to buy the remains
when the company craters in two years.

Nvidia still has the cash to buy VIA many times over. VIA owns an x86
core that can be made to compete in more markets with some adequate R&D
budget.

Lots of people have the money to buy VIA, its just an engineering firm
with 2,000 people. VIA is years and billions away from being a real
threat to Intel, and Intel having learned its lesson from letting AMD
live is not about to make that mistake twice.
Intel is using Engineering (Atom and 45nm) and marketing/bribes/threats
to VIAs supply chain shut VIA down. I do not see how VIA survives as an
independent.
The firm that buys VIA might just want the engineers, and would get a
under the table bonus from Intel for shutting down x86 development.
Otherwise Intel will just keep the pressure up with Atom, etc.

There is also the Renesas RX series CPUs which is already almost an
exact copy down to including string opcodes. The opcode encoding is
completely different, but that is just a detail.

http://documentation.renesas.com/eng...b0435_rxsm.pdf

The big problem for both these firms is OutOfOrder design and getting
all the details right, which took AMD a decade. Also the portfolio of
patents needed to actually implement OoO for x86 in a competitive way.

It takes someone like Jerry Sanders (AMD) with huge brass balls, but
also with tens of billions to spend, to play in "Intels sandbox".

Brett - PS: I added comp.arch to see what those smart people have to say.

Right now AMD/ATI is crushing NVDA on cost/performance, and next year
the graphics chip starts the move onto the CPU chip.

Which is why Nvidia really needs to get into the x86 CPU business for
itself.


Yousuf Khan

In article ,
(Brett Davis) wrote:

There is also the Renesas RX series CPUs which is already almost an
exact copy down to including string opcodes. The opcode encoding is
completely different, but that is just a detail.

No it isn't. It means that you can't break out of the embedded market
into the high-volume desktop/laptop market, because you won't have
Windows. When Intel first planned EM64T, they were going to have a
different encoding to AMD64, so that 64-bit software would have to be
built separately for Intel and AMD. Microsoft just said "no".

They weren't prepared to support a different encoding for the sake of
artificial market segmentation, even when Intel asked nicely, so they
seem quite unlikely to do so when a small CPU company with far less
market muscle asks them.

The big problem for both these firms is OutOfOrder design and getting
all the details right, which took AMD a decade. Also the portfolio of
patents needed to actually implement OoO for x86 in a competitive way.

OK, so they're doomed to uncompetitive performance for the desktop and
laptop market too. Definitely not going to break out of the embedded
market. AMD have significant patents that they license to Intel and
vice-versa. Until those patents expire, anyone else trying to get into
the high-end x86 chip business is going to have to have some major
inventions and be prepared to cross-license them, or have very deep
pockets to buy their way in.

--
John Dallman, , HTML mail is treated as probable spam.