Interesting read about upcoming K9 processors

  • Thread starter Thread starter Yousuf Khan
  • Start date Start date
Hank said:
But the fact that I think these things is probably rather
uninteresting, since I cannot produce any actual
documents that say the specific things I think will be true ;-)

Well, now the historical documents have been produced.

Yousuf Khan
 
I am finding it harder and harder to believe that Intel said anything about
replacing x86 with IA-64 in the 1996 and beyond timeframe (might have said

For all.

Who really gives a shit.:-)
 
I am finding it harder and harder to believe that Intel said anything about
replacing x86 with IA-64 in the 1996 and beyond timeframe (might have said

Hell, I saw it predicted in 1979, Now that I've removed the group I read
from this crossposted rediculous thread, have at it.:-)
 
Wes said:
For all.

Who really gives a shit.:-)

My sentiments exactly! This dead horse has been beat so much there's
nothing left to bury! Probably nothing the buzzards could subsist on
either!!
 
It's possible but we have no way of knowing that right now. Anyways, that
would sound more like dual-processing than Hyperthreading.

That is understating the case. No, that hypothesis is not plausible.

Hyperthreading is so intimate that it would be foul to implement for
two architectures as different as x86 and IA64. The sane approach
would be two separate CPUs with a shared Lx cache on the same die.
I have hypothesised that a FUTURE Intel design may be a Crusoe-like
one where two logical CPUs could be x86 and IA64, but even then I
suspect that it won't run both at once.


Regards,
Nick Maclaren.
 
You're not going to find any viable links in this thread because all
that are participating, or throwing their 2 cents worth in, are either
"armchair quarterbacks" or "shit house lawyers", or whatever you want to
call them, and none of them really know their ass from a hole in the
ground!!!
 
Well, that isn't the only reason IBM became a giant.

Actually, Dean, yes it is. SOftware that's lost its source decades ago
still runs. Software rules enterprise hardware, not the other way around.
I'm really surprised, given your background that you don't understand
simple reality. IBM's FS was still-born precisely because backwards
compatablility is far more important than hardware.


There were a bunch of
salespeople, and some rather draconian contracts before the anti-trust
lawsuits.

Oh, Pkease Dean! This all stopped dead with the '56 consent decree.
Neither of us were in the business (I was almost ready for kindergarten
and I doubt you were alive_ when this was entered into.
I can recall when I worked at ADP in 1978/79 that IBM threatened
to cancel the lease and yank the 370/155 if the 3203 printers were
replaced with a competitors.

There was obviously far more to it than that. The OEMI interface was a
standard long before (see above). Printers were not part of the system.
Yes, I'm calling you misinformed (benefit of the doubt given, reluctantly).
I left there in 1980, and when I went back
they had replaced the entire system with one from a company called
Magnuson (or something to that effect). Needless to say, they were
*not* happy with IBM tactics.

The allowable "tactics" were well laid out by the '56 consent decree.
I also recall some interesting
interactions when Amdahl sold them a half-meg memory upgrade. IBM
refused to allow Amdahl to touch the box, and IBM would not touch the
Amdahl unit - so our system programmer had to hook everything up.

My bet is that the box was leased. Otherwise you were free to have anyone
blow it up. Yes, there were *many* problems with add-on memory. Some
understood, some not so. In any case GM doesn't warrant a Ford engine in
thier cars. If you blow the tranny, too bad.

Yeah, IBM has always been your friend. ;-).

Has always worked for me! ;-)
Hmm. At my job we 'rent' the OS we run today from IBM - I think it is
called zOS. Perhaps that is why IBM became a giant, too? ;-).

I know you dropped out of the groups for a while. Perhaps you were having
a lobotomy? IBM hasn't been able to force *anyone* to lease since the
'56 consent decree. If your management chooses to lease, then it's their
business decision. M$ will force everyone to "rent" their OS. Indeed
their data will no longer belong to them, if you believe the license
agreements. No, you're being "disingenuous" again Dean.
 
Am I part of that market?

If you have to ask that question, then no you certainly are not.
Speaking as a customer, I don't care whether it has some silly logo
on it. I *know*, from bitter experience, that I can buy graphics cards
from the likes of ATI or nVidea, put them on a Win2K or XP system,
and be unable to boot up because the driver faults.

That's the point. You are *not* M$'s customer. They don't sell to the
common folk like us. You get whatever they package to the company that
sells the box. You take the logo (and all that goes with it) because
everyone else does. Yes, the market (and by extension the marketeers)
really do care. You're forced to go along, as long as you use M$ products
(for which you are *not* the customer).
OK, I'm a developer so I'm using the debug kernel, but so should they be
-- where "they" are both "whoever wrote the driver" and "whoever gave it
the shiny logo". The fact that *clearly* *neither* have tried it on a
sufficiently wide range of PCs (I expect it is motherboard- dependent,
or something) tells me all I need to know about the Device Driver Tax.

I haven't a clue what you're rambling on about here.
Off the top of my head, I know of annoying but less serious problems
with Creative sound cards and just about anything from HP. (The latter
appear to sub-contract their driver writing, which may be relevant.)
Presumably this "certified" hardware does work on the vast majority of
systems. However, so does non-certified hardware. The logo isn't giving
us anything new.

Again, you aren't M$'s customer. Try working for an IHV sometime and see
how high you jump when M$ shouts. You really are naieve.
I'm also using the latest service pack, which may not have been around
at the time of certification, but whilst that may excuse the vendor and
WHQL, it hardly praises the team at MS who produce service packs and it
does point to a fundamental flaw in the certification process.

I don't think anyone is accusing M$ of being competent, only that they
make the rules.
The logo costs a few thousand (small beer for a major manufacturer) so
yes, it's a while since I saw a vendor of mainstream hardware who wasn't
displaying the logo. It probably comes out of the marketing budget and
is a relatively good return on investment in that sense.

You really are naieve. The cost of the qualification isn't the point.
It's the fact that you must follow the rules to even be considered. M$'s
rules. OTOH, I was a great fan when M$ ruled ISA out.
For more obscure hardware, the logo compliance would only cover things
like "doesn't prevent booting up or hibernation" and "superficially
appears to let the demo app access the device without blue screening".
There's little point in getting the logo and for the (usually small)
companies concerned, the few thousand quid just isn't worth it. The
customers' purchasing decisions are based on very different criteria.

You really ought to sell some hardware into this segment sometime. You'll
see the process a tad differently.
 
Hank said:
I found no documents, nor any URLs to documents.

If there are other threads, whast are they?

I only read one of the groups this troll was cross posted
to, so perhaps those documents were in some other group?

You didn't read the these archival webpages from 98 and 99?

http://www.theregister.co.uk/1998/10/22/madison_and_deerfield_to_split/

http://www.theregister.co.uk/1998/10/15/intel_doctors_foster_to_extend/

http://www.theregister.co.uk/1999/04/28/secrets_of_intels_ia64_roadmap/

Basically, these are the examples of why the perception that Intel had said
that IA-64 would be replacing IA-32 sooner rather than later.

Yousuf Khan
 
Keith said:
On Thu, 05 Aug 2004 04:17:33 +0000, Dean Kent wrote:


Actually, Dean, yes it is. SOftware that's lost its source decades ago
still runs. Software rules enterprise hardware, not the other way around.
I'm really surprised, given your background that you don't understand
simple reality. IBM's FS was still-born precisely because backwards
compatablility is far more important than hardware.

Keith, given my background I think I have fair visibility into the
*customer* side of things. This is something you obviously do not have.
Though it doesn't surprise me that you believe the IBM press releases. IBM
did not become a giant solely because of backward compatibility. It became
a giant because of anti-competitive business practices as well, which caused
a *lot* of angry customers to hail MS and Intel as the saviors of the
computing industry in the '80s. Arguing that MS is only a giant because of
evil practices, while IBM got there due to nothing but goodness is either
naive or extremely disingenuous. As you indicate below, I am willing to
give you the benefit of the doubt... :-)
Oh, Pkease Dean! This all stopped dead with the '56 consent decree.
Neither of us were in the business (I was almost ready for kindergarten
and I doubt you were alive_ when this was entered into.

Excuse me? The anti-trust lawsuits against IBM I am referring to are from
the 70's and 80's. If you actually care to be knowledgable, you can read a
bit about them here: http://www.hagley.lib.de.us/1912.htm#series1
There was obviously far more to it than that. The OEMI interface was a
standard long before (see above). Printers were not part of the system.
Yes, I'm calling you misinformed (benefit of the doubt given,
reluctantly).

Sorry Keith. I was there, you were not. I am not misinformed - you are. I
realize that this is a very difficult thing to accept, sometimes.
The allowable "tactics" were well laid out by the '56 consent decree.

Laid out or not, IBM angered many customers with their tactics, but since
they were effectively a monopoly until the PC era there was little customers
could do. It is no coincidence that IBM lost much of their industry
influence when many fled to other platforms when they realized they could.
I was a customer then, you were not. I was a member of IBM user groups. I
know what the sentiment was. Denial ain't just a river in Egypt!!!
My bet is that the box was leased. Otherwise you were free to have anyone
blow it up. Yes, there were *many* problems with add-on memory. Some
understood, some not so. In any case GM doesn't warrant a Ford engine in
thier cars. If you blow the tranny, too bad.

Yes, the box was leased. The problem wasn't that IBM wouldn't touch it - it
was that they wouldn't allow Amdahl to touch it but had no problem with the
customer doing it himself. Sort of like telling you that you can't use
anyone but a GM mechanic to install aftermarket parts, unless you do it
yourself. Wacky. This was simply an annoyance, of course, but helped
contribute to the attitude that IBM was not so customer oriented as the
press releases want you to believe.
Has always worked for me! ;-)

You should get out more often. It helps to get a dose of reality on
occasion. ;-).
I know you dropped out of the groups for a while.

Only those infected with politics, where the main discussion tactics are ad
hominems, innuendo, character assasination and arguments based upon deceit
and fallacy. I also avoid most web forums for the same reason. There are
a few relatively untainted ones left, however. While I have a great deal
of respect for you, and your knowledge, I am also somewhat surprised that
there are a few subjects where reason seems to get left behind.
Perhaps you were having
a lobotomy? IBM hasn't been able to force *anyone* to lease since the
'56 consent decree.

Again, I suggest you read the IBM press releases with a grain of salt. You
aren't in Kansas anymore, Toto.
If your management chooses to lease, then it's their
business decision. M$ will force everyone to "rent" their OS. Indeed
their data will no longer belong to them, if you believe the license
agreements. No, you're being "disingenuous" again Dean.

Since when has MS *forced* you to buy Windows, or upgrade? It is a business
decision as well. One can always choose not to use the software. But, just
as with zOS, it is very difficult to find a replacement, so as long as you
have the hardware investment you are pretty stuck on the OS vendor. Fact
is, from what I can tell, MS is wanting to use the mainframe software
license model for their business. It provides a *huge* profit for IBM.
Let's see, last I heard zOS related revenues were close to 50% of all IBM
revenues (hardware, software and services), yet there are only about 11K IBM
mainframes in the world. How odd! BTW, have you heard of 'computing on
demand'? IBM will own the hardware, and you can 'rent' what you need -
along with the expertise to manage it, and any software necessary to run it.

Have you heard of Hercules? Funny thing is that it is virtually impossible
to get a license to run zOS on it, even though it works perfectly well. You
*can*, however, get a license for running it on top of Flex-ES - for a huge
fee. While IBM wishes to give the impression that they are supporting Open
Software, and are the saviors of the software world by helping to free us
from MS, they only support it where it competes with Microsoft. Now, why
would that be? Couldn't be another business decision, could it?

The point is this: When you license the software, you cannot assume support
and upgrades will be free. MS *will* provide support if you pay for it -
and so will IBM. Are you suggesting that IBM will provide *free* support
for any OS that they own? How about hardware? Either you pay for it as
part of your license, or you pay for it when you need it. MS is little
different here, from what I can tell. Buying shrink-wrapped software for
$99 certainly does not pay for any support.

Yes, I understand that MS is the devil incarnate to all IBM employees.
:-). Anyway, end of discussion. I know where it is headed, and I won't
follow it down. You know my email address if you care to discuss it
privately.

Regards,
Dean
 
Yousuf Khan said:
You didn't read the these archival webpages from 98 and 99?

http://www.theregister.co.uk/1998/10/22/madison_and_deerfield_to_split/

http://www.theregister.co.uk/1998/10/15/intel_doctors_foster_to_extend/

http://www.theregister.co.uk/1999/04/28/secrets_of_intels_ia64_roadmap/

Basically, these are the examples of why the perception that Intel had
said
that IA-64 would be replacing IA-32 sooner rather than later.


Oh, I'm all confused.
I thought you meant Intel documents.
Didn't understand you meant "Rumors and Raw Random Data."

--

... Hank

http://horedson.home.att.net
http://w0rli.home.att.net
 
Keith said:
If you have to ask that question, then no you certainly are not.

That's the point. You are *not* M$'s customer. They don't sell to the
common folk like us. You get whatever they package to the company that
sells the box. You take the logo (and all that goes with it) because
everyone else does. Yes, the market (and by extension the marketeers)
really do care. You're forced to go along, as long as you use M$ products
(for which you are *not* the customer).


Now I'm all confused again, seems to happen a lot in these
cross-posted troll threads. When I last purchased Windows
(XP Home) I bought it directly from Microsoft, and got
support directly from them as well. No OEM involved.

I just went to their web site, gave 'em a credit card number,
and et voila it arrived in a nice pretty green box.

So I'm confused as to how I might *not* be a Microsoft customer.

--

... Hank

http://horedson.home.att.net
http://w0rli.home.att.net
 
Hank Oredson said:
Oh, I'm all confused. I thought you meant Intel documents.
Didn't understand you meant "Rumors and Raw Random Data."

Well, I know the Register may not be the most accurate of sources, but
if we're talking about public perception, I bet more people read the
Register (and similar sites) than official Intel documentation.

-kzm
 
Yousuf Khan said:
We've now even dug up some old historical webpages (possibly written in
parchment or papyrus or something) from the early days of the commercial
Internet which states exactly why we thought Intel's plans were to go
towards IA-64. Yet, he still needs to argue. Some people are just beyond
quixotic!

1) The usual tactics of .chips denizens who use character assasination,
innuendo and fallacy to present an argument instead of actually using facts
and evidence. Add to that the cries of "I been wronged" while using
uncomplimentary names and implied accusations, and the pattern is complete.

2) The 'proof' presented is, as usual, not proof at all of Intel's stated
plans. I don't expect that those whose heels are dug in so deeply to their
egos would be able to recognize this, but it is possible that more objective
and rational people will. Foster, Cascades and Tanner were server chips -
and it was *well known* that they were server chips to *anyone* following
the industry. The roadmaps were very *clearly* segmented into server,
workstation, desktop and mobile parts by then. The Register articles even
mention this, but don't emphasize it - so I suppose it is somewhat
understandable that you would completely miss it. But then, if you didn't
know it then, and you didn't know it until I mentioned it, what credibility
does that give to the argument that you saw roadmaps, and understood what
they were telling you?

3) The issue is not about the *perception of the public*, which is clearly
of the opinion that Intel had publicly stated the intent to do away with
IA-32 by the turn of the century, or soon after. The issue is providing
*proof* that they actually did intend this. That was the nature of the
question - not whether you were justified in holding your beliefs,
regardless of how valid they might or might not be. The delusions of a
million people is no proof that an event actually occurred - and any *real*
scientist know this. What is required for proof is that some objective,
tangible evidence be produced... but no! Instead we are to believe that it
all just disappeared. It can't be found on Google Groups. It can't be
found on the Web. It can't be found in printed publications. It can't even
be found on the official documents that Intel provided at the time. It
*must* be that some nefarious Intel plot has been executed, and the usual
suspects are there to defend that theory to the death.

As for the previous comments, since I have George killfiled - I wasn't
paying attention, eh? I was writing a monthly column about the industry in
1999 - once considered one of the better web-based columns. I was a top 25
reseller of Intel, Cyrix and AMD processors in 1997/1998. I got personal
visits from Intel and Cyrix marketing and PR people. I talked with Intel,
AMD, Cyrix, and various motherboard manufacturers. I went to Comdex and
spoke personally with engineers and executives from 1997 thru 2001. I got
their roadmaps. I got emails from industry insiders. I didn't even discuss
Itanium in in my articles then, because it was so far in the high end, and
the move to the lower end so far away that my audience didn't even care.
Perhaps the ones not paying attention were those who now steadfastly insist
that they are right despite the total lack of evidence? Nah, the people
posting here were *obviously* much more clued in, and privvy to ... (shhh)
secret, unpublished roadmaps... than I was. Yeah. You got a credible
argument going...

I argued against Corse's fallacious arguments, and I argue against these.
And yes - your argument is, as usual, fallacious. You want to infer that I
called you a liar? That's your problem, not mine - and not my words. I
said your arguments are typically fallacious, and they are. Too bad you
can't handle it with grace and integrity any more than Corse could. And all
the vitriol, name calling and innuendo you can muster won't change it. I
expect that responses will contain more personal attacks, more
rationalizations, more belittling and insinuation, more cries of being a
'victim' and more back-patting of those who agree with the community-based
opinion. That would, unfortunately, be typical, and the reason I don't
read 'your' group anymore. It has very frankly become a gang of thugs who
pounce on all who disagree with the group-think. I only saw this because
it was cross posted. Don't like my opinion? Don't cross post. Pretty
simple for those with anything approaching an average-level thought
process...

Regards,
Dean
 
Ketil Malde said:
Well, I know the Register may not be the most accurate of sources, but
if we're talking about public perception, I bet more people read the
Register (and similar sites) than official Intel documentation.

I'm not sure at what point the discussion turned, but my original question
was whether anyone had factual evidence that Intel had plans to 'replace'
x86 in the near future - not whether people believed it to be true. I've
already made my position clear, I think, about perception and flawed
recollections...

Regards,
Dean
 
Hank said:
Now I'm all confused again, seems to happen a lot in these
cross-posted troll threads. When I last purchased Windows
(XP Home) I bought it directly from Microsoft, and got
support directly from them as well. No OEM involved.

I just went to their web site, gave 'em a credit card number,
and et voila it arrived in a nice pretty green box.

So I'm confused as to how I might *not* be a Microsoft customer.

That was my thought when I posted.

If I understand Keith correctly, the market he was referring to
is "vendors selling fairly common hardware to the likes of Dell".
It is quite possible that Dell won't touch hardware that hasn't
been blessed by WHQL.

Yes, Keith, I'm not part of that market so you may call me naive
in this matter. However, my company's products do include hardware
and WHQL certification of that hardware isn't on the radar for
*our* customers, so I hope you can now understand where I was
coming from with my original question.
 
The near-monopoly Windows has enjoyed is damaging to Microsoft's coders'
skills. They haven't been required to maintain portable code all along,
just to develop for the latest platform and once or twice a decade do a
complete rewrite when the platform changes. OSS developers have to deal
with portability every day and the transition from i386 to amd64 has been
almost a non-event because of it.

The Win32 API and SDK was pretty well designed to handle the eventual
transition to Win64, but most coders didn't take advantage of those features
because a decade ago there was no obvious motivation. Based on how quickly
the _kernel_ was ported, at least some of MS' developers did it right, but
most did not -- nor did most ISVs.
I surely *hope* M$'s architects learned something from OS/2 days. NT was
a complete re-write and one would suspect that they learned a few lessons
along the way.

M$ spent a lot of effort moving from 16-bit to 32-bit code, and it's
possible at the time they expected their code to be obsolete before 64-bit
systems took over -- 4GB is enough for anybody, right? I'm sure they didn't
expect their newly-ported 32-bit code to require porting again in less than
a decade, given 16-bit x86 code had been around for two decades. And, given
that most programmers don't stay in the same job for a decade, why would one
expect them to plan for the future (other than style)?

S
 
Back
Top