|
|
|
|
|
|
| Author |
Message |
Bill Gunshannon
*nix forums Guru
Joined: 21 Jul 2005
Posts: 1019
|
 Posted: Thu Jul 20, 2006 11:38 am Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
In article <44BEE900.A45B5062@teksavvy.com>,
JF Mezei <jfmezei.spamnot@teksavvy.com> writes:
| Quote: | Neil Rieck wrote:
http://news.zdnet.com/2100-9595_22-6096207.html?tag=nl.e589
Intel has just announced a 57 percent drop in income.
I wonder what those suits will chop first?
IA64 is safe. It is a fair bet that HP is subsidizing IA64 to keep it
alive for now. And if an exit strategy has already been decided and
slowly being implemented, by next year, the 8086 will probably be much
faster than that IA64 contraption and it will be much easier for HP to
announce it is moving to simplify its platforms and standardizing on
industry standard 8086s.
|
And exactly why wold they announce that they were moving VMS to x86-64
rather than just announcing that they are concentrating on their real
business, Windows boxes, and pulling the plug on VMS?
| Quote: |
Right now, the cost of prematurely cancelling IA64 would be probably
higher for Intel than the costs of continuing it.
|
I fail to see the logic int his. IA64 is costing them buckets of
money. Cance3ling it would end stop the bleeding and let them cut
even more jobs making them look even better to the Casino Analysts.
| Quote: | But it is a fair bet
that Intel will not be hiring extra engineers to speed up development
work of IA64 and the opposite may happen which will make each remaining
iteration of IA64 even later and thus less relevant to the industry.
The big question is at what level within HP are they aware of the true
strategy and working to plan on the transition to 8086.
|
You keep assuming that they have any plan or even desire to migrate VMS
any further. If that were likely, considering how long it can take to
go from desire to a viable commercial product, the work would have already
begun. There is no sign that it has, regardless of what you see on your
vision quest when your smoking whatever it is the shaman gives you in the
lodge.
bill
--
Bill Gunshannon | de-moc-ra-cy (di mok' ra see) n. Three wolves
bill@cs.scranton.edu | and a sheep voting on what's for dinner.
University of Scranton |
Scranton, Pennsylvania | #include <std.disclaimer.h> |
|
| Back to top |
|
 |
Bill Gunshannon
*nix forums Guru
Joined: 21 Jul 2005
Posts: 1019
|
| Posted: Thu Jul 20, 2006 11:40 am Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
In article <44BF1669.FBC2E630@teksavvy.com>,
JF Mezei <jfmezei.spamnot@teksavvy.com> writes:
| Quote: | BBC's World Business Report had an interview with Intel's CFO. He said
that within the next 3 to 6 months, there will be many small changes to
reduce costs, but no single large event that analysts will be able to
point to, however, he said that 6 months from now, peopple who look back
will see that significant changes will have been made.
In other words, they may downsize the IA64 teams, but they won't
announce its death yet.
|
Maybe by this point even they see IA64 as so dead that they think
announcing its death would not be a "significant change". Only
making public what the public already new.
bill
--
Bill Gunshannon | de-moc-ra-cy (di mok' ra see) n. Three wolves
bill@cs.scranton.edu | and a sheep voting on what's for dinner.
University of Scranton |
Scranton, Pennsylvania | #include <std.disclaimer.h> |
|
| Back to top |
|
|
david20@alpha2.mdx.ac.uk
*nix forums Guru Wannabe
Joined: 16 May 2005
Posts: 205
|
| Posted: Thu Jul 20, 2006 2:43 pm Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
In article <44BEE900.A45B5062@teksavvy.com>, JF Mezei <jfmezei.spamnot@teksavvy.com> writes:
| Quote: | Neil Rieck wrote:
http://news.zdnet.com/2100-9595_22-6096207.html?tag=nl.e589
Intel has just announced a 57 percent drop in income.
I wonder what those suits will chop first?
IA64 is safe. It is a fair bet that HP is subsidizing IA64 to keep it
alive for now. And if an exit strategy has already been decided and
slowly being implemented, by next year, the 8086 will probably be much
faster than that IA64 contraption and it will be much easier for HP to
announce it is moving to simplify its platforms and standardizing on
industry standard 8086s.
Right now, the cost of prematurely cancelling IA64 would be probably
higher for Intel than the costs of continuing it. But it is a fair bet
that Intel will not be hiring extra engineers to speed up development
work of IA64 and the opposite may happen which will make each remaining
iteration of IA64 even later and thus less relevant to the industry.
The big question is at what level within HP are they aware of the true
strategy and working to plan on the transition to 8086.
|
I just wish they would extend the end of sale deadline for Alpha.
(Not that difficult to come up with some reason).
Otherwise you are going to have a load of customers forced to buy IA64
extremely upset when the inevitable happens.
David Webb
Security team leader
CCSS
Middlesex University |
|
| Back to top |
|
|
Bob Koehler
*nix forums Guru
Joined: 25 Jul 2005
Posts: 1078
|
| Posted: Thu Jul 20, 2006 4:52 pm Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
In article <44beb1c0$0$989$9a6e19ea@news.newshosting.com>, "Neil Rieck" <n.rieck@sympatico.ca> writes:
| Quote: | quote-on
"We're working pretty hard to get it to a profitable product," said Pat
Gelsinger, senior VP of Intel's digital enterprise group, in an interview
following a press conference in San Francisco Tuesday. "If we could unwind
the clock, I would have just built a RAS version of Xeon to attack the
market," he said, using an industry term for "reliable, highly available,
and scalable" chips, and referring to Intel's Xeon server chips, which
employ the widely used x86 instruction set. Itanium uses a less popular
design called EPIC.
quote-off
When a company makes this kind of statement in public, they are testing the
waters. Now let's see what the investment community says about this.
|
Hopefully it will be "let's port everything to x86". In which case
the decision to not bother with Galaxy on IA-64 would be fine with
me. HP can stop all development on IA-64 if they port EVERYTHING
Alpha could run to x86. |
|
| Back to top |
|
|
Bob Koehler
*nix forums Guru
Joined: 25 Jul 2005
Posts: 1078
|
| Posted: Thu Jul 20, 2006 4:54 pm Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
In article <44bf5a0e$0$18489$9a6e19ea@news.newshosting.com>, "Neil Rieck" <n.rieck@sympatico.ca> writes:
| Quote: |
Yes but on this side of Y2K, corporate execs have "rock star" egos. They
almost never admit they make mistakes (even when in court).
|
This side of Y2K corporate managers should wake up to AOL's
problem with the 2038 "bug". I just read in the Risks Digest that
it hit them already. |
|
| Back to top |
|
|
JF Mezei
*nix forums Guru
Joined: 21 Jul 2005
Posts: 2556
|
| Posted: Thu Jul 20, 2006 5:35 pm Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
etmsreec@yahoo.co.uk wrote:
| Quote: | Haff. "HP can not afford to put its customers through another
instruction-set transition." '
That makes the most sense of any of this discussion. Everything within
HP's high end relies on Itanium. HP can't let that happen, whether it
means signing blank cheques to Intel or buying them and dropping them
in the bottom of the bay to increase volumes.
|
There is one big caveat to that Haff statement: most HP customers have
not transitioned to that IA64 thing. So announce that HP is moving to
8086 today, and customers will then migrate from MIPS, Alpha and PaRisc
to the 8086, totally bypassing that IA64 mistake.
Customers do not like uncertainty.
As he said, HP's enterirpise products currently rely on a product whose
future is uncertain and performance curve starting to lag the 8086
simply because the 8086 is being upgraded at a faster rate.
Personally, I think that the HPUX HPVM thing is a base for something
greater. They will get that machine to run on the 8086 and give it the
dynamic codd translation abilities like Apple's Rosetta to run PaRisc
code in big endian. This way, customers will be able to run 80-86 native
apps direct on the base HPUX instance, and run older code on emulated
HPUX running on that base instance. |
|
| Back to top |
|
|
JF Mezei
*nix forums Guru
Joined: 21 Jul 2005
Posts: 2556
|
| Posted: Thu Jul 20, 2006 5:53 pm Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
Bill Gunshannon wrote:
| Quote: | And exactly why wold they announce that they were moving VMS to x86-64
rather than just announcing that they are concentrating on their real
business, Windows boxes, and pulling the plug on VMS?
|
Pride and money.
Lets look at pride: HP has to admit IA64 was a big mistake, but to make
up for it, it promises to port all its IA64 based systems to the 8086.
Lets look at money:
First, porting VMS to the 8086 should be less expensive than Alpha to
IA64. They now have setup the abililty to have common code base, cleaned
up the code to make porting easier, AND have already gotten the EFI
stuff installed and running on VMS. So the port to the 8086 should cost
less and take less time.
Also, while the IA64 port may have been a surprise to all but a very few
VMS engineers, the writing has been on the wall for years now that the
8086 is (unfortunatly) the way to go, and I would be very disapointed if
nobody within VMS engineering had taken a serious look at what it would
take.
I would also not be surprised if the folks at HP-UX, NSK and VMS had
talks with Intel on what features they might need in the 8086 to make
porting much easier. Such features are likely to appear in the 2007 timeframe.
| Quote: | I fail to see the logic int his. IA64 is costing them buckets of
money. Cance3ling it would end stop the bleeding and let them cut
even more jobs making them look even better to the Casino Analysts.
|
It all ddpends on what sort of contracts were signed. Remember that HP
sent 3 billion bucks to Intel not too long ago (along with its remaining
chip engineers), and is also building that 10 billion fund allegedly to
help port software to that IA64 contraption. This may be structured in
such a way that you cannot cancel IA64 until a certain date.
Also, in 2004 when Carly would have set this in motion, it is likely
that she would have wanted to keep the door open should, by miracle,
IA64 become popular. "Give it a couple of years and then can it".
Should Intel kill IA64 prematurely, it might cost Intel mega bucks to
compensate HP, much more than paying a few engineers to thinker with the
contraption and produce a faster one every couple of years.
| Quote: | You keep assuming that they have any plan or even desire to migrate VMS
any further. If that were likely, considering how long it can take to
go from desire to a viable commercial product, the work would have already
begun.
|
Yes, it had begun and was happening in the basement of ZKO, until I
uncovered it and they quickly replaced the office furniture with
sporting equipment, removing any traces that there was ever a covert
porting effort going on  ;-)
The VMS engineers have all the tools already to manage a porting effort.
If, in 2007, Intel/HP announce the end of the line for IA64, it will
probably includd one more iteration of that "thing" and last a few
years, during which VMS can be ported. (this is where the killing of
Alpha sales at this point in time is a very wrong mistake).
Face it, toy controller or high end chip, the 8086 is solid as a rock
with no rumours of it going away anytime soon. Move VMS to the 8086,
and you all once and for all any rumours of VMS's demise because as long
as it is profitable, there is no reason to kill it. And customers having
more confidence in a VMS rejuvenation will stay or buy in to VMS and
you'll see real growth.
Right now, the sad reality is that a weakened VMS is using its last
energies to try to support IA64. Move to 8086 and it is the strong 8086
(in the marketplace) that will help and support VMS and let it grow.
IA64 is a liability to VMS. 8086 would be an asset to VMS. |
|
| Back to top |
|
|
Bill Gunshannon
*nix forums Guru
Joined: 21 Jul 2005
Posts: 1019
|
| Posted: Thu Jul 20, 2006 7:13 pm Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
In article <44BFC335.32AEF7E8@teksavvy.com>,
JF Mezei <jfmezei.spamnot@teksavvy.com> writes:
| Quote: | Bill Gunshannon wrote:
And exactly why wold they announce that they were moving VMS to x86-64
rather than just announcing that they are concentrating on their real
business, Windows boxes, and pulling the plug on VMS?
Pride and money.
Lets look at pride: HP has to admit IA64 was a big mistake, but to make
up for it, it promises to port all its IA64 based systems to the 8086.
|
Too late for that. Intel already publicly admited it was a mistake and
if they had the chance to go back they wouldn't have done it. And they
have never promised to port VMS to anything beyond IA64.
| Quote: |
Lets look at money:
First, porting VMS to the 8086 should be less expensive than Alpha to
IA64. They now have setup the abililty to have common code base, cleaned
up the code to make porting easier, AND have already gotten the EFI
stuff installed and running on VMS. So the port to the 8086 should cost
less and take less time.
|
Your smokin' again. There is little that has been made public so far that
would lead one to believe that because they ported VMS to IA64 it is now
somehow easier to port it to x86-64. The two have little if anything in
common, architecturally.
| Quote: |
Also, while the IA64 port may have been a surprise to all but a very few
VMS engineers, the writing has been on the wall for years now that the
8086 is (unfortunatly) the way to go,
|
And yet HP has never even hinted at th possibility of porting VMS to
x86-64. As a matter of fact, HP people here have constantly stated
it was not going to happen.
| Quote: | and I would be very disapointed if
nobody within VMS engineering had taken a serious look at what it would
take.
|
My guess is they would look at it as soon as HP paid them to. Being
as they have repeatedly stated, right here, that there is no x86 port
in the works, why would any of them take the time to" look at what it
would take"?
| Quote: |
I would also not be surprised if the folks at HP-UX, NSK and VMS had
talks with Intel on what features they might need in the 8086 to make
porting much easier. Such features are likely to appear in the 2007 timeframe.
|
Why would Intel care? Their only interest right now is figuring out
how to catch back up to AMD. If VMS, HP-UX and NSK go belly up
tomorrow, it doesn't affect Intel's bottom line. Of course, that
IA64 boat anchor does!!
| Quote: |
I fail to see the logic int his. IA64 is costing them buckets of
money. Cance3ling it would end stop the bleeding and let them cut
even more jobs making them look even better to the Casino Analysts.
It all ddpends on what sort of contracts were signed. Remember that HP
sent 3 billion bucks to Intel not too long ago (along with its remaining
chip engineers), and is also building that 10 billion fund allegedly to
help port software to that IA64 contraption. This may be structured in
such a way that you cannot cancel IA64 until a certain date.
|
Still smokin'. No one knows what this mythical agreement said or even
if there really is one. Of course, it could just as easily have been
an agreement to pay Intel the 10 billion dollars as reparations for
the damage keeping that IA64 thing alive this long has done.
My theory is just as believable (and verifiable) as yours.
| Quote: |
Also, in 2004 when Carly would have set this in motion, it is likely
that she would have wanted to keep the door open should, by miracle,
IA64 become popular. "Give it a couple of years and then can it".
|
Sure glad they don't let that weed you smoke over the border.
| Quote: |
Should Intel kill IA64 prematurely, it might cost Intel mega bucks to
compensate HP, much more than paying a few engineers to thinker with the
contraption and produce a faster one every couple of years.
|
Not knowing what was in any of the agreements between them, it is really
impossible to say who would end out owing who if IA64 gets killed.
| Quote: |
You keep assuming that they have any plan or even desire to migrate VMS
any further. If that were likely, considering how long it can take to
go from desire to a viable commercial product, the work would have already
begun.
Yes, it had begun and was happening in the basement of ZKO, until I
uncovered it and they quickly replaced the office furniture with
sporting equipment, removing any traces that there was ever a covert
porting effort going on 
|
Keep smokin'......
| Quote: |
The VMS engineers have all the tools already to manage a porting effort.
|
Now there's another big assumption on your part. Being as they have
repeatedly said there is no port to x86-64, why would HP have paid
for all these tools?
| Quote: | If, in 2007, Intel/HP announce the end of the line for IA64, it will
probably includd one more iteration of that "thing" and last a few
years,
|
Nobody is buying it now, who would buy it if they announced it was a
deadend? Any further "iteration" would just be money down the toilet.
| Quote: | during which VMS can be ported.
|
And during all this time you think the IT and business world is just going
to stand still? You thhink MS won't be out there raiding what is left of
HP's customers? Or Sun? Or IBM? Or any of dozen Linux brokers?
| Quote: | (this is where the killing of
Alpha sales at this point in time is a very wrong mistake).
|
Maybe, but it is a done deal as well.
| Quote: |
Face it, toy controller or high end chip, the 8086 is solid as a rock
with no rumours of it going away anytime soon. Move VMS to the 8086,
and you all once and for all any rumours of VMS's demise because as long
as it is profitable, there is no reason to kill it. And customers having
more confidence in a VMS rejuvenation will stay or buy in to VMS and
you'll see real growth.
|
Keep on smokin'......
| Quote: |
Right now, the sad reality is that a weakened VMS is using its last
energies to try to support IA64. Move to 8086 and it is the strong 8086
(in the marketplace) that will help and support VMS and let it grow.
IA64 is a liability to VMS. 8086 would be an asset to VMS.
|
Probably way too little, way too late. But in any event, it isn't even
a blip on the radar and businesses are not going to wait around to see
what comes next. If we are truly seeing the last hurrah for IA64 then
we should be very concerned about the future of VMS.
bill
--
Bill Gunshannon | de-moc-ra-cy (di mok' ra see) n. Three wolves
bill@cs.scranton.edu | and a sheep voting on what's for dinner.
University of Scranton |
Scranton, Pennsylvania | #include <std.disclaimer.h> |
|
| Back to top |
|
|
Bob Koehler
*nix forums Guru
Joined: 25 Jul 2005
Posts: 1078
|
| Posted: Thu Jul 20, 2006 9:14 pm Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
In article <44BFBEDA.EEE63B3A@teksavvy.com>, JF Mezei <jfmezei.spamnot@teksavvy.com> writes:
| Quote: |
Personally, I think that the HPUX HPVM thing is a base for something
greater. They will get that machine to run on the 8086 and give it the
dynamic codd translation abilities like Apple's Rosetta to run PaRisc
code in big endian. This way, customers will be able to run 80-86 native
apps direct on the base HPUX instance, and run older code on emulated
HPUX running on that base instance.
|
Yeah, they're going to have a problem porting HP-UX to x86 unless
someone builds a bi-endian x86.
Which is fine. They just port Tru64 UNIX to x86, ship the previously
optional SVID package as standard and make it the default interface.
Then everyboy's happy except the customers who wrote big-endian
dependant code. They either jump to Sun or port to little endian
machines from somebody.
And VMS still doesn't crash, or get hacked, or go non-deterministic. |
|
| Back to top |
|
|
Dave Froble
*nix forums Guru
Joined: 21 Jul 2005
Posts: 1172
|
| Posted: Thu Jul 20, 2006 11:21 pm Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
Bill Gunshannon wrote:
| Quote: | In article <44BFC335.32AEF7E8@teksavvy.com>,
JF Mezei <jfmezei.spamnot@teksavvy.com> writes:
Bill Gunshannon wrote:
And exactly why wold they announce that they were moving VMS to x86-64
rather than just announcing that they are concentrating on their real
business, Windows boxes, and pulling the plug on VMS?
Pride and money.
Lets look at pride: HP has to admit IA64 was a big mistake, but to make
up for it, it promises to port all its IA64 based systems to the 8086.
Too late for that. Intel already publicly admited it was a mistake and
if they had the chance to go back they wouldn't have done it. And they
have never promised to port VMS to anything beyond IA64.
|
That one statement from Intel is the worst thing I've seen since the
killing of Alpha. As the desire in Intel grows to dump the itanic, the
arguments to do so will grow, and it will happen.
| Quote: | Lets look at money:
First, porting VMS to the 8086 should be less expensive than Alpha to
IA64. They now have setup the abililty to have common code base, cleaned
up the code to make porting easier, AND have already gotten the EFI
stuff installed and running on VMS. So the port to the 8086 should cost
less and take less time.
Your smokin' again. There is little that has been made public so far that
would lead one to believe that because they ported VMS to IA64 it is now
somehow easier to port it to x86-64. The two have little if anything in
common, architecturally.
|
There have been more than a few things mentioned. Moving hardware
capabilities into code within VMS and things like that.
| Quote: | Also, while the IA64 port may have been a surprise to all but a very few
VMS engineers, the writing has been on the wall for years now that the
8086 is (unfortunatly) the way to go,
And yet HP has never even hinted at th possibility of porting VMS to
x86-64. As a matter of fact, HP people here have constantly stated
it was not going to happen.
|
Small correction, they have stated that it was not currently happening
or in planning. They don't have the authority to state that it will not
happen.
| Quote: | and I would be very disapointed if
nobody within VMS engineering had taken a serious look at what it would
take.
My guess is they would look at it as soon as HP paid them to. Being
as they have repeatedly stated, right here, that there is no x86 port
in the works, why would any of them take the time to" look at what it
would take"?
|
Such a port is far from a 'midnight projects' thing.
| Quote: | I would also not be surprised if the folks at HP-UX, NSK and VMS had
talks with Intel on what features they might need in the 8086 to make
porting much easier. Such features are likely to appear in the 2007 timeframe.
Why would Intel care? Their only interest right now is figuring out
how to catch back up to AMD. If VMS, HP-UX and NSK go belly up
tomorrow, it doesn't affect Intel's bottom line. Of course, that
IA64 boat anchor does!!
|
Gee, sounds like many of my posts from the 2001-2004 time frame.
| Quote: | I fail to see the logic int his. IA64 is costing them buckets of
money. Cance3ling it would end stop the bleeding and let them cut
even more jobs making them look even better to the Casino Analysts.
It all ddpends on what sort of contracts were signed. Remember that HP
sent 3 billion bucks to Intel not too long ago (along with its remaining
chip engineers), and is also building that 10 billion fund allegedly to
help port software to that IA64 contraption. This may be structured in
such a way that you cannot cancel IA64 until a certain date.
Still smokin'. No one knows what this mythical agreement said or even
if there really is one. Of course, it could just as easily have been
an agreement to pay Intel the 10 billion dollars as reparations for
the damage keeping that IA64 thing alive this long has done.
|
That's correct.
| Quote: | My theory is just as believable (and verifiable) as yours.
Also, in 2004 when Carly would have set this in motion, it is likely
that she would have wanted to keep the door open should, by miracle,
IA64 become popular. "Give it a couple of years and then can it".
Sure glad they don't let that weed you smoke over the border.
|
None left after JF gets to it.
| Quote: | Should Intel kill IA64 prematurely, it might cost Intel mega bucks to
compensate HP, much more than paying a few engineers to thinker with the
contraption and produce a faster one every couple of years.
Not knowing what was in any of the agreements between them, it is really
impossible to say who would end out owing who if IA64 gets killed.
You keep assuming that they have any plan or even desire to migrate VMS
any further. If that were likely, considering how long it can take to
go from desire to a viable commercial product, the work would have already
begun.
Yes, it had begun and was happening in the basement of ZKO, until I
uncovered it and they quickly replaced the office furniture with
sporting equipment, removing any traces that there was ever a covert
porting effort going on ;-)
Keep smokin'......
|
You can count on it. :-)
| Quote: | The VMS engineers have all the tools already to manage a porting effort.
Now there's another big assumption on your part. Being as they have
repeatedly said there is no port to x86-64, why would HP have paid
for all these tools?
If, in 2007, Intel/HP announce the end of the line for IA64, it will
probably includd one more iteration of that "thing" and last a few
years,
Nobody is buying it now, who would buy it if they announced it was a
deadend? Any further "iteration" would just be money down the toilet.
during which VMS can be ported.
And during all this time you think the IT and business world is just going
to stand still? You thhink MS won't be out there raiding what is left of
HP's customers? Or Sun? Or IBM? Or any of dozen Linux brokers?
(this is where the killing of
Alpha sales at this point in time is a very wrong mistake).
Maybe, but it is a done deal as well.
|
This is a business decision. If the decision was changed, continuing to
manufacture and sell the current Alphas is definitely doable from a
technical perspective.
| Quote: | Face it, toy controller or high end chip, the 8086 is solid as a rock
with no rumours of it going away anytime soon. Move VMS to the 8086,
and you all once and for all any rumours of VMS's demise because as long
as it is profitable, there is no reason to kill it. And customers having
more confidence in a VMS rejuvenation will stay or buy in to VMS and
you'll see real growth.
Keep on smokin'......
Right now, the sad reality is that a weakened VMS is using its last
energies to try to support IA64. Move to 8086 and it is the strong 8086
(in the marketplace) that will help and support VMS and let it grow.
IA64 is a liability to VMS. 8086 would be an asset to VMS.
Probably way too little, way too late. But in any event, it isn't even
a blip on the radar and businesses are not going to wait around to see
what comes next. If we are truly seeing the last hurrah for IA64 then
we should be very concerned about the future of VMS.
|
Very!
--
David Froble Tel: 724-529-0450
Dave Froble Enterprises, Inc. E-Mail: davef@tsoft-inc.com
DFE Ultralights, Inc.
170 Grimplin Road
Vanderbilt, PA 15486 |
|
| Back to top |
|
|
Neil Rieck
*nix forums Guru Wannabe
Joined: 13 May 2005
Posts: 274
|
| Posted: Thu Jul 20, 2006 11:25 pm Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
"Bob Koehler" <koehler@eisner.nospam.encompasserve.org> wrote in message
news:+VsvlB6+v25f@eisner.encompasserve.org...
| Quote: | In article <44bf5a0e$0$18489$9a6e19ea@news.newshosting.com>, "Neil Rieck"
n.rieck@sympatico.ca> writes:
Yes but on this side of Y2K, corporate execs have "rock star" egos. They
almost never admit they make mistakes (even when in court).
This side of Y2K corporate managers should wake up to AOL's
problem with the 2038 "bug". I just read in the Risks Digest that
it hit them already.
Most companies became aware of the "2038 bug" when they were doing their Y2K |
testing. If this bug was left in place, it happened because somebody thought
they could make some more money sometime in the future (provided they are
still alive).
http://www3.sympatico.ca/n.rieck/docs/calendar_time_y2k_etc.html
Neil Rieck
Kitchener/Waterloo/Cambridge,
Ontario, Canada.
http://www3.sympatico.ca/n.rieck/links/cool_openvms.html
http://www3.sympatico.ca/n.rieck/links/openvms_demos.html |
|
| Back to top |
|
|
Bill Gunshannon
*nix forums Guru
Joined: 21 Jul 2005
Posts: 1019
|
| Posted: Fri Jul 21, 2006 12:26 am Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
In article <yvWdnR1hv-4ek13ZnZ2dnUVZ_rednZ2d@libcom.com>,
Dave Froble <davef@tsoft-inc.com> writes:
| Quote: | Bill Gunshannon wrote:
In article <44BFC335.32AEF7E8@teksavvy.com>,
JF Mezei <jfmezei.spamnot@teksavvy.com> writes:
Bill Gunshannon wrote:
And exactly why wold they announce that they were moving VMS to x86-64
rather than just announcing that they are concentrating on their real
business, Windows boxes, and pulling the plug on VMS?
Pride and money.
Lets look at pride: HP has to admit IA64 was a big mistake, but to make
up for it, it promises to port all its IA64 based systems to the 8086.
Too late for that. Intel already publicly admited it was a mistake and
if they had the chance to go back they wouldn't have done it. And they
have never promised to port VMS to anything beyond IA64.
That one statement from Intel is the worst thing I've seen since the
killing of Alpha. As the desire in Intel grows to dump the itanic, the
arguments to do so will grow, and it will happen.
Lets look at money:
First, porting VMS to the 8086 should be less expensive than Alpha to
IA64. They now have setup the abililty to have common code base, cleaned
up the code to make porting easier, AND have already gotten the EFI
stuff installed and running on VMS. So the port to the 8086 should cost
less and take less time.
Your smokin' again. There is little that has been made public so far that
would lead one to believe that because they ported VMS to IA64 it is now
somehow easier to port it to x86-64. The two have little if anything in
common, architecturally.
There have been more than a few things mentioned. Moving hardware
capabilities into code within VMS and things like that.
|
Maybe so, but after years of hearing how the x86 architecture was
unsuitable for running VMS it seems highly unlikely that the addition
of 64 bit extensions has somehow corrected all those shortcomings.
Not saying it can't be done, just that the idea that porting VMS
to IA64 somehow made it easier to port to x86 is quite a stretch.
| Quote: |
Also, while the IA64 port may have been a surprise to all but a very few
VMS engineers, the writing has been on the wall for years now that the
8086 is (unfortunatly) the way to go,
And yet HP has never even hinted at th possibility of porting VMS to
x86-64. As a matter of fact, HP people here have constantly stated
it was not going to happen.
Small correction, they have stated that it was not currently happening
or in planning. They don't have the authority to state that it will not
happen.
|
True, but JF has always had this pipe dream that a bunch of engineers
are kept chained up in the basement of ZKO working 24/7 on some
mystery x86 port. Many people from HP (in a better position to know than
JF) have repeatedly stated there are no plans, at this time, to do an
x86 port.
| Quote: |
and I would be very disapointed if
nobody within VMS engineering had taken a serious look at what it would
take.
My guess is they would look at it as soon as HP paid them to. Being
as they have repeatedly stated, right here, that there is no x86 port
in the works, why would any of them take the time to" look at what it
would take"?
Such a port is far from a 'midnight projects' thing.
|
When (and if) such a port is to be attempted it will likely get the same
fanfare as all the other ports. It is not the kind of thing that can be
kept hidden away, even if there was some business reason for doing so.
| Quote: |
I would also not be surprised if the folks at HP-UX, NSK and VMS had
talks with Intel on what features they might need in the 8086 to make
porting much easier. Such features are likely to appear in the 2007 timeframe.
Why would Intel care? Their only interest right now is figuring out
how to catch back up to AMD. If VMS, HP-UX and NSK go belly up
tomorrow, it doesn't affect Intel's bottom line. Of course, that
IA64 boat anchor does!!
Gee, sounds like many of my posts from the 2001-2004 time frame.
|
You and many other people here who were not required to toe the HP-line.
| Quote: |
I fail to see the logic int his. IA64 is costing them buckets of
money. Cance3ling it would end stop the bleeding and let them cut
even more jobs making them look even better to the Casino Analysts.
It all ddpends on what sort of contracts were signed. Remember that HP
sent 3 billion bucks to Intel not too long ago (along with its remaining
chip engineers), and is also building that 10 billion fund allegedly to
help port software to that IA64 contraption. This may be structured in
such a way that you cannot cancel IA64 until a certain date.
Still smokin'. No one knows what this mythical agreement said or even
if there really is one. Of course, it could just as easily have been
an agreement to pay Intel the 10 billion dollars as reparations for
the damage keeping that IA64 thing alive this long has done.
That's correct.
My theory is just as believable (and verifiable) as yours.
Also, in 2004 when Carly would have set this in motion, it is likely
that she would have wanted to keep the door open should, by miracle,
IA64 become popular. "Give it a couple of years and then can it".
Sure glad they don't let that weed you smoke over the border.
None left after JF gets to it.
|
Good thing too. We already have enough spaced-out people down here.
Some of them running major corporations. :-)
| Quote: |
Should Intel kill IA64 prematurely, it might cost Intel mega bucks to
compensate HP, much more than paying a few engineers to thinker with the
contraption and produce a faster one every couple of years.
Not knowing what was in any of the agreements between them, it is really
impossible to say who would end out owing who if IA64 gets killed.
You keep assuming that they have any plan or even desire to migrate VMS
any further. If that were likely, considering how long it can take to
go from desire to a viable commercial product, the work would have already
begun.
Yes, it had begun and was happening in the basement of ZKO, until I
uncovered it and they quickly replaced the office furniture with
sporting equipment, removing any traces that there was ever a covert
porting effort going on ;-)
Keep smokin'......
You can count on it. :-)
The VMS engineers have all the tools already to manage a porting effort.
Now there's another big assumption on your part. Being as they have
repeatedly said there is no port to x86-64, why would HP have paid
for all these tools?
If, in 2007, Intel/HP announce the end of the line for IA64, it will
probably includd one more iteration of that "thing" and last a few
years,
Nobody is buying it now, who would buy it if they announced it was a
deadend? Any further "iteration" would just be money down the toilet.
during which VMS can be ported.
And during all this time you think the IT and business world is just going
to stand still? You thhink MS won't be out there raiding what is left of
HP's customers? Or Sun? Or IBM? Or any of dozen Linux brokers?
(this is where the killing of
Alpha sales at this point in time is a very wrong mistake).
Maybe, but it is a done deal as well.
This is a business decision. If the decision was changed, continuing to
manufacture and sell the current Alphas is definitely doable from a
technical perspective.
|
Again, I have to defer to the HP people who are in a better position
to know and they have repeatedly stated here that the resources no
longer exist at HP to revive the Alpha line. And, we have been told
that there was also some agreement regarding Alpha in the HP-Intel
deal. It is equally possible that the agreement was that they could
no longer continue development of the Alpha. If that turned out to
be so, what incentive would Intel have to release HP from it? No, I
think as the HP denizens here have stated, Alpha is a dead issue.
| Quote: |
Face it, toy controller or high end chip, the 8086 is solid as a rock
with no rumours of it going away anytime soon. Move VMS to the 8086,
and you all once and for all any rumours of VMS's demise because as long
as it is profitable, there is no reason to kill it. And customers having
more confidence in a VMS rejuvenation will stay or buy in to VMS and
you'll see real growth.
Keep on smokin'......
Right now, the sad reality is that a weakened VMS is using its last
energies to try to support IA64. Move to 8086 and it is the strong 8086
(in the marketplace) that will help and support VMS and let it grow.
IA64 is a liability to VMS. 8086 would be an asset to VMS.
Probably way too little, way too late. But in any event, it isn't even
a blip on the radar and businesses are not going to wait around to see
what comes next. If we are truly seeing the last hurrah for IA64 then
we should be very concerned about the future of VMS.
Very!
|
So, Dave, how's the injury?
bill
--
Bill Gunshannon | de-moc-ra-cy (di mok' ra see) n. Three wolves
bill@cs.scranton.edu | and a sheep voting on what's for dinner.
University of Scranton |
Scranton, Pennsylvania | #include <std.disclaimer.h> |
|
| Back to top |
|
|
JF Mezei
*nix forums Guru
Joined: 21 Jul 2005
Posts: 2556
|
| Posted: Fri Jul 21, 2006 1:31 am Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
Bill Gunshannon wrote:
| Quote: | Maybe so, but after years of hearing how the x86 architecture was
unsuitable for running VMS it seems highly unlikely that the addition
of 64 bit extensions has somehow corrected all those shortcomings.
|
Remember that the 8086 has gone from a 16 bit toy controller with 640k
memory limit and segment registers into a 32 bit CPU with full features
and now 64 bit machine. In the process, it has gained many more
features. So while the 8086 circa 1990 was definitely ill suited to run
VMS, the CPUs made today for that architecture have gained respectability.
| Quote: | Not saying it can't be done, just that the idea that porting VMS
to IA64 somehow made it easier to port to x86 is quite a stretch.
|
Posting to IA64 specifically gave VMS the ability to do EFI. That meant
tweaking the file system to allow a FAT partition-in-a-VMS-file with
updates to BACKUP, INIT etc to support this.
But the port just made, no matter what the target was, game VMS the
ability to have a common code base supporting multiple architectures at
the same time, and this allowed engineers to continue to work on VMS
while the port was being done. And a lot fo stuff was cleaned up and as
someone else said, many hardware features were moved to software, thus
making VMS less dependant on hardware.
So the next port will be easier.
| Quote: | True, but JF has always had this pipe dream that a bunch of engineers
are kept chained up in the basement of ZKO working 24/7 on some
mystery x86 port.
|
I never said they were chained :-)
| Quote: | Many people from HP (in a better position to know than
JF) have repeatedly stated there are no plans, at this time, to do an
x86 port.
|
Yes, and that is perfectly normal. Until the second when HP/Intel
announce the end of IA64, expect everyone within HP/Intel to deny any
plans to abandon IA64. Announcing plans to port VMS to the 8086 would be
tantamount to announcing the end of IA64.
And while I may be hoping for a Covert port of VMS to the 8086 going on
right now, (the faster, the better), I think it would be realistic to
think that someone within VMS engineering has looked into the
feasability of porting VMS to a 64 bit 8086 based on EFI and reported
back to very high management and kept this very discreet.
Note that this had happened prior to the announcement of the prematire
euthanasia of Alpha. I think it was 2 engineers that were tasked to
secretely make a feasability study of porting VMS to IA64. The rest of
the engineers were totally oblivbious to those plans.
| Quote: | When (and if) such a port is to be attempted it will likely get the same
fanfare as all the other ports. It is not the kind of thing that can be
kept hidden away, even if there was some business reason for doing so.
|
Once it is announced, you are right. But until that time, it is quite
possible to see VMS engineers talk to Intel engineers about what
features they may want in the generation of chips that would come circa
2007. Also, someone would also be talking about the types of features
that would allow one to build an 8086 based Wildfire/Galaxy class machine.
| Quote: | Again, I have to defer to the HP people who are in a better position
to know and they have repeatedly stated here that the resources no
longer exist at HP to revive the Alpha line.
|
Horse manure. Where there is a will, there is a way. But there is
clearly no will at HP to revive Alpha, no will to even postpone the end
of sales date. And if the will existed, it would take a lot of creative
accounting to cost justify restarting Alpha with a huge amount of
resources to catch up. |
|
| Back to top |
|
|
perfnerd@yahoo.com
*nix forums beginner
Joined: 16 Sep 2005
Posts: 7
|
| Posted: Fri Jul 21, 2006 1:40 am Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
Bill Todd wrote:
| Quote: | bob@instantwhip.com wrote:
http://www.informationweek.com/news/showArticle.jhtml?articleID=190500823
Ah, me - even an article that starts by bending over backward to try to
make Itanic look good has a lot of difficulty doing so these days - at
least if it doesn't play somewhat fast and loose with its wording.
Examples:
"Say this for Intel-after five years of [initially negligible and later
only] modest sales and [dramatically] scaled-down ambitions, it's not
[at least not yet] giving up on Itanium [at least not publicly]."
(bracketed clarifications added)
"The chips deliver more than twice the database performance of
previous-generation Itaniums [at the *chip* level, though only slightly
more *per-core* performance despite years of new development, 5x as much
L2 cache and 1.33x as much L3 cache, and significant core enhancements
like multi-threading: the rest comes from having two cores on the
chip], and draw 2.5 times less electric power [if you nimbly and
ever-so-tacitly switch the subject from the *chip* to *per-core* power:
the per-chip power is only moderately reduced]"
|
You are right, but it does really depend on whether you want to look at
the differences on a per core, per socket, per box, or per dollar
basis.
Montecito does draw less per socket than Mad9M. The Mad9M is rated at
130Watts, while the Montecito is rated at 104Watts. That is 26% less
wattage on a per socket basis. Which is significant if you are buying
based on a core count, since the same number of CPUs draw 40% the
power.
At the box level, the new Montecito SuperDome is shown on the SPEC site
as being able to achieve a SPECint_rate2000 base of 2367 with 128 CPUs
/ 64 sockets (Jul 2006), vs 1108 for the 64/64 for the Mad9M Superdome
(Jan 2005) and 1063 for the 64/32 IBM P5 595 (Oct 2004).
| Quote: | "But..." it then continues, and actually isn't all that biased thereafter.
- bill |
|
|
| Back to top |
|
|
Bill Todd
*nix forums Guru
Joined: 24 Jul 2005
Posts: 408
|
| Posted: Fri Jul 21, 2006 1:44 am Post subject:
Re: New itaniums out at 2.5x perform gain
|
|
|
Bill Gunshannon wrote:
| Quote: | In article <yvWdnR1hv-4ek13ZnZ2dnUVZ_rednZ2d@libcom.com>,
Dave Froble <davef@tsoft-inc.com> writes:
Bill Gunshannon wrote:
In article <44BFC335.32AEF7E8@teksavvy.com>,
JF Mezei <jfmezei.spamnot@teksavvy.com> writes:
|
....
| Quote: | First, porting VMS to the 8086 should be less expensive than Alpha to
IA64. They now have setup the abililty to have common code base, cleaned
up the code to make porting easier, AND have already gotten the EFI
stuff installed and running on VMS. So the port to the 8086 should cost
less and take less time.
Your smokin' again. There is little that has been made public so far that
would lead one to believe that because they ported VMS to IA64 it is now
somehow easier to port it to x86-64. The two have little if anything in
common, architecturally.
There have been more than a few things mentioned. Moving hardware
capabilities into code within VMS and things like that.
Maybe so, but after years of hearing how the x86 architecture was
unsuitable for running VMS
|
Wow - some people will believe anything, I guess.
Given that active investigation of porting VMS to x86 was actually under
way in the early '90s, suggesting that there's any insurmountable
obstacle (beyond major amounts of mostly-standard grunt work) involved
seems a bit unreasonable - especially now that x86 has become 64-bit.
it seems highly unlikely that the addition
| Quote: | of 64 bit extensions has somehow corrected all those shortcomings.
|
All *what* shortcomings? Please be specific. x86-64 now has as many
registers as VAX did (not that the earlier investigation I mentioned
above seemed to have considered having only 32-bit x86's eight register
to be a show-stopper). The 'number of modes' issue has been pretty
thoroughly shown to be a non-issue AFAICT.
| Quote: | Not saying it can't be done, just that the idea that porting VMS
to IA64 somehow made it easier to port to x86 is quite a stretch.
|
You don't think that, e.g., rewriting assembler routines in HLLs makes
porting easier? ISTR one or more of the associated engineers making
precisely this point a while ago - and explicitly stating that they took
advantage of the Itanic port to make a possible subsequent port easier.
....
Many people from HP (in a better position to know than
| Quote: | JF) have repeatedly stated there are no plans, at this time, to do an
x86 port.
|
Many people at Intel (in an excellent position to have known the truth -
from the CEO on down) repeatedly stated that there were no plans for
extending x86 to support 64-bit operation - at a time when the support
already existed (albeit fuse-disabled) in silicon.
Companies tell customers what they want customers to believe: it
doesn't necessarily bear any close relationship with the truth.
....
| Quote: |
(this is where the killing of
Alpha sales at this point in time is a very wrong mistake).
Maybe, but it is a done deal as well.
This is a business decision. If the decision was changed, continuing to
manufacture and sell the current Alphas is definitely doable from a
technical perspective.
Again, I have to defer to the HP people who are in a better position
to know and they have repeatedly stated here that the resources no
longer exist at HP to revive the Alpha line.
|
Had you read more carefully you would have noticed that neither JF nor
Dave was talking about continuing Alpha development in any significant
sense: they were (quite explicitly, even in the material you yourself
quoted above) talking only about continuing manufacture and sales of
existing product.
And, we have been told
| Quote: | that there was also some agreement regarding Alpha in the HP-Intel
deal.
|
We have? When, and where, and what were the details, and was there any
reason to consider the source credible?
Assuming that you're in fact referring to the Compaq-Intel deal, the
only direct assertion that *I* recall in this area was that Compaq sold
Intel only the rights to *use* the Alpha intellectual property, not
control over that property - retaining the right to do with it as it
pleased.
It is equally possible that the agreement was that they could
| Quote: | no longer continue development of the Alpha.
|
Not IIRC according to the only people here who purported to know the
facts of the matter.
- bill |
|
| Back to top |
|
|
Google
|
|
| Back to top |
|
|
|
|
The time now is Thu Dec 04, 2008 3:54 am | All times are GMT
|
|
Myspace Layouts | Credit Cards UK | Car Loan | Credit Card | Xbox Mod Chip
|
|
Copyright © 2004-2005 DeniX Solutions SRL
|
|
|
|
Other DeniX Solutions sites:
Unix/Linux blog |
electronics forum |
medicine forum |
science forum |
|
|
Privacy Policy
|
Powered by phpBB © 2001, 2005 phpBB Group
|
|
FAQ
Search
Memberlist
Usergroups
Register
Profile
Log in to check your private messages
Log in
Forum index
»
Not Unix
»
VMS
