>>I may be mistaken, but my understanding was that the Itanium was not
really x86. It is RISC that has a hardware instruction emulator for x86,
which was proven at one time to be much slower than a similar speed Pentium.
You are correct. The Itanium is based on HP's PA-RISC long instruction word
architecture. X86 was emulated in microcode. Had it been emulated in
hardware, it might have been accepted better. But since the Pentium runs
x86 code faster, and was cheaper, most folks took a wait-and-see attitude.
Intel put less effort into making the Pentium fast, expecting it would have
a short life as we all embraced the Itanium, and that allowed AMD to
leapfrog them.
But Apple's OS/X is CPU independent, so I believe they would find it easier
to move to Itanium than Microsoft. In theory, NT (W2K, XP) is also
CPU-independent. But someone more knowledgeable than me suggested that they
have added x86 code to XP in order to better run older apps.
Apple's Steve Jobs says the move is about processor power per watt, and that
makes sense from a laptop standpoint. But I suspect there is far more to it
than that.
Secure64 is on record saying the Itanium can be made to run about 20x faster
than x86, and far more securely. And Jobs never once said "x86", "Pentium"
or anything else to indicate what Intel chip. Since the Itanium can run
big-endiam and little-endiam code, it should emulate the PowerPC far better
than the Pentium could. HP moved from Motorola CPUs to PA-RISC, then to
Itanium - all big-endiam CPUs. Apple moved from the same Motorola CPUs to
PowerPC - also big-endiam. But Intel uses little-endiam CPUs, so the
Itanium had to be able to run both.
A page on little-endiam vs big-endiam:
http://www.noveltheory.com/techpapers/endian.asp
Ken Elliott
=====================
-----Original Message-----
From: slug@nks.net [mailto:slug@nks.net] On Behalf Of Andrew Barber
Sent: Sunday, June 12, 2005 3:23 AM
To: slug@nks.net
Subject: RE: [SLUG] Apple shifts to Intel
I may be mistaken, but my understanding was that the Itanium was not really
x86. It is RISC that has a hardware instruction emulator for x86, which was
proven at one time to be much slower than a similar speed Pentium.
Andy
--- Ken Elliott <kelliott4@tampabay.rr.com> wrote:
> >>Has anyone noticed no mention of AMD or is it just
> me?
>
> I just finished watching the keynote speech for the Developers
> conference.
>
> - OS/X has been compiled for Power PC and Intel for last 5 years.
> - X Code 2.1 can produce universal binary that can run on both
> processors.
> - Rosetta converts PowerPC binaries on the fly. In other words, the
> Intel system can run current software right now.
> - Demo'd on Pentium 4 3.5GHz. Photos on the presentation were of a
> Pentium 4. Clearly x86.
> - Selling development unit for $999. Shipping in two weeks. Have to
> give it back in a year. No mention of a refund or replacement.
>
> Clearly, they have expected this and planned for it all along. No
> mention of AMD or which Intel processor they expect to run on.
> However, since they have been running on Intel for the last 5 years,
> there's not anything in OS/X that requires a 64-bit CPU. I expect
> you'll see Pentium-M laptops (perhaps the real focus) and Itaniumn
> workstations and servers.
>
> Jobs said: "The sole of a Mac is it's operating system"
>
> I take this to mean "don't worry about what's in the box"
>
> Today, it's Intel. But in two years, you might see both Intel and AMD
> processors. Apple is not stupid and surely realizes that they can
> use AMD to keep Intel in line. I expect they will approach Intel and
> say they need a true 64-bit processor, and if Intel can't give them an
> affordable Itanium, they will have to go with the AMD-64.
>
> Ken Elliott
>
> =====================
> -----Original Message-----
> From: slug@nks.net [mailto:slug@nks.net] On Behalf Of James Haydon
> Sent: Saturday, June 11, 2005 12:30 PM
> To: slug@nks.net
> Subject: Re: [SLUG] Apple shifts to Intel
>
>
> On Friday, June 10, 2005, at 06:09 PM, Ken Elliott
> wrote:
>
> >>> If I was in the market for a Mac, I'd still get
> a G4/G5. I would
> >>> probably
> > get one from the Apple outlet after the x86
> versions came out, to save
> > a buck and get a more stable system.
> >
> > I doubt it will be "more" stable.
> >
> > The graphics board, hard disc drive, keyboard,
> mouse, power supply,
> > DVD drive, RAM and PCI bus are already the same as
> a PC. So the
> > difference is down to the CPU and motherboard
> chips. There's plenty
> > of evidence that Intel's chipsets are at least as
> stable as the
> > PowerPC stuff. Most stability issues are driver
> problems, or use of
> > non-certified hardware.
> > There's plenty of rock-solid Intel-based servers
> out there running
> > various forms of Unix/BSD/Linux.
> >
> > I have no doubt that Apple will restrict their OS
> to the products they
> > supply, and that will allow them to be as stable
> as current hardware.
> > Would
> > you really want a PowerPC, knowing that
> development will stop on that
> > platform?
> >
> > Ken Elliott
> >
> > =====================
> > -----Original Message-----
> > From: slug@nks.net [mailto:slug@nks.net] On Behalf
> Of Andrew Barber
> > Sent: Friday, June 10, 2005 4:44 PM
> > To: slug@nks.net
> > Subject: Re: [SLUG] Apple shifts to Intel
> >
> >
> > The biggest problem I see with this shift will be
> the expectations
> > that OS X will work on generic/other PCs.
> > The stability of Mac OS has relied on the lack of
> available,
> > "uncontrolled"
> > hardware. x86 PCs OTOH can vary widely in
> chipsets and expansion
> > capability. One only has to look at the Linux
> kernel configuration to
> > see how many different drivers are available for
> the different
> > hardware for just the typical desktop PC.
> > This doesn't include servers and server expansion
> boards (SCSI, etc.).
> >
> > And there is this interesting fact about the G4.
> > From
> >
>
http://it.asia1.com.sg/newsdaily/news002_20040119.html
> > Based on the wickedly speedy next-generation
> > processor, the G4 was so powerful that the US
> > government classified the supercomputer as a
> > weapon, restricting its export to 'sensitive'
> > countries which could use it to theoretically
> > design nuclear weapons.
> >
> > I don't recall any single x86 CPU being rated like
> this.
> >
> > If I was in the market for a Mac, I'd still get a
> G4/G5. I would
> > probably get one from the Apple outlet after the
> x86 versions came
> > out, to save a buck and get a more stable system.
> >
> > Though, how much bloat does having binaries
> supporting both
> > architectures incur?
> >
> > Apple's just happy that can get away with having
> another dual-CPU
> > server with one socket;) For those unaware,
> dual-G4's are available as
> > a single-socket unit. Not technically dual-core,
> though, as there are
> > 2 separate CPUs on the "chip".
> >
> > Andrew Barber
> >
>
----------------------------------------------------------------------
> > - This list is provided as an unmoderated internet
> service by
> > Networked Knowledge Systems (NKS). Views and
> opinions expressed in
> > messages posted are those of the author and do not
> necessarily reflect
> > the official policy or position of NKS or any of
> its employees.
> >
> >
>
----------------------------------------------------------------------
> > - This list is provided as an unmoderated internet
> service by
> > Networked Knowledge Systems (NKS). Views and
> opinions expressed in
> > messages posted are those of the author and do not
> necessarily reflect
> > the official policy or position of NKS or any of
> its employees.
>
> Has anyone noticed no mention of AMD or is it just me?
>
> James
>
>
-----------------------------------------------------------------------
> This list is provided as an unmoderated internet service by Networked
> Knowledge Systems (NKS). Views and opinions expressed in messages
> posted are those of the author and do not necessarily reflect the
> official policy or position of NKS or any of its employees.
>
>
-----------------------------------------------------------------------
> This list is provided as an unmoderated internet service by Networked
> Knowledge Systems (NKS). Views and opinions expressed in messages
> posted are those of the author and do not necessarily reflect the
> official policy or position of NKS or any of its employees.
>
=== message truncated ===
-----------------------------------------------------------------------
This list is provided as an unmoderated internet service by Networked
Knowledge Systems (NKS). Views and opinions expressed in messages posted
are those of the author and do not necessarily reflect the official policy
or position of NKS or any of its employees.
-----------------------------------------------------------------------
This list is provided as an unmoderated internet service by Networked
Knowledge Systems (NKS). Views and opinions expressed in messages
posted are those of the author and do not necessarily reflect the
official policy or position of NKS or any of its employees.
This archive was generated by hypermail 2.1.3 : Fri Aug 01 2014 - 20:07:17 EDT