Re: New itaniums out at 2.5x perform gain

Bill Gunshannon wrote:
In article <yvWdnR1hv-4ek13ZnZ2dnUVZ_rednZ2d@xxxxxxxxxx>,
Dave Froble <davef@xxxxxxxxxxxxx> writes:
Bill Gunshannon wrote:
In article <44BFC335.32AEF7E8@xxxxxxxxxxxx>,
JF Mezei <jfmezei.spamnot@xxxxxxxxxxxx> writes:

....

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
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.

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
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.

....


(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
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
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
.

Relevant Pages

  • Re: Revival of Alpha?
    ... > to force VMS users to purchase specific models? ... to an x86 port of VMS. ... I suppose if they can write one for Alpha and another one for Itanium, ... The cost of developing CPUs these ...
    (comp.os.vms)
  • Re: Wonderful things happen to an OS when it has an internal champion
    ... VMS to a mainstream processor? ... 3p would have to have a compelling reason for wanting the port to ... the MS wanna-bees as most likely to buy VMS and port it to x86. ... Power might be a tempting target. ...
    (comp.os.vms)
  • Re: OpenVMS Itanium port progressing well says Gorham!
    ... platform and I certainly was not defending the killing of Alpha. ... >> It would be good for VMS. ... The port to Alpha did a lot in that area. ...
    (comp.os.vms)
  • Re: Could a PC do this?
    ... architecture to immediately be competitive with x86. ... free campus licenses of VMS on ... for ISV's to port their Alpha apps to? ...
    (comp.os.vms)
  • Re: SGI files for chapter 11
    ... HP are highly unlikely to port it to x86. ... for an equally long period of time the VMS engineers that hang out here ... Presumably they still believe that IA64 is ...
    (comp.os.vms)