Intel engineer discusses their dual-core design

[YKhan]

Yeah sure, my opinion of Sony has gone down too. But even back in its
heyday I was never one to go around buying Sony when there were
equivalent but cheaper products from JVC, Panasonic and others to
choose from. In fact, I don't think I have or ever had a Sony of
anything -- which is probably kind of telling of my personality, I
guess.

Regarding Intel's brand degradation, it's a little different. It's
competing against a brand that doesn't advertise (at least to the same
level). I think AMD is doing the right thing here, which they weren't
before. Nowadays they're trying to appeal to the IT professional, and
the high-performance gaming enthusiast, and building its reputation
top-down. In the past it was trying to sell everything for cheaper than
Intel, and all they were getting were the cheapskates who don't really
care about brandnames anyways.

Yousuf Khan

 

[David Schwartz]

Intel's stacking two cores in an MCM and calling it a "dual core" tells
all. They were caught with their pants down, even after *knowing* what
the score was for a couple of years.

First of all, they didn't do that. Second of all, a "dual core" is two
processors in one physical package.

DS

 

[Bill Todd]

David Schwartz wrote:

....

a "dual core" is two

processors in one physical package.

Not by any current definition that I'm aware of: it is, rather, two
cores on a single chip.

Do you call POWER an '8-core' processor because that's how many cores
its high-end systems have in one physical package?

- bill

 

[prep]

This question of perceptions is an interesting one.

I remember ten years ago I thought of Sony as a premium brand; when
I had to buy a TV or a VCR my default assumption was to buy Sony
(and pay a little more) unless there were a compelling reason not
to. A series of US-management-style clusterfucks over the last ten
years have, in my mind, completely destroyed that perception. Now if
I have to

The death of Sony Snr. Watch Honda going the same way, for the same
reasons.


--
Paul Repacholi 1 Crescent Rd.,
+61 (08) 9257-1001 Kalamunda.
West Australia 6076
comp.os.vms,- The Older, Grumpier Slashdot
Raw, Cooked or Well-done, it's all half baked.
EPIC, The Architecture of the future, always has been, always will be.

 

[Skybuck Flying]

Really? You propose a bit of marker per bit of data and you complain
about people suggesting that base-2 may not be ideal? You then go on to
swear, bitch, and moan (the latter only in your more lucid moments), and
then complain that peoplae call _you_ a waste? Note folks that I'm not
alone.

You still haven't explained why base 2 would not be ideal !

As long as you don't explain it you remain a troll.

Plain and simple.

 

[Skybuck Flying]

Oooh! A little net cop! How cute!

Nope, just pointing out a troll when I see one.

I'll go away now, cross posting slime.

Now go **** Keith the donkey ****er lol.

 

[George Macdonald]

Intel Inside was more about perception than reality. The reality might
have been tarnished for a while, but I'm now noticing too for the first
time that the general perception (outside geekier circles) is finally
taking some damage.

But by the time it really starts to bite, Intel will probably have some
nice Pentium M based stuff to offer and past mistakes will soon be
forgotten.

"Probably"?... maybe?

The main difference I see in perceptions of both AMD and Intel is that the
market will ignore or forget Intels mistakes while punishing AMD for
theirs and won't forget them quickly.

Why would that be?... because Intel is bigger? I don't see that as an
advantage as far as public popularity goes. Or is it because AMD is seen
as an intruder/pretender/copyist? If that, it is something which could
easily be repaired by exposing AMD's true history of real innovation in the
processor industry dating back to the early 80s.

Intel's mistakes have all resulted from allowing marketing depts the power
to guide product technical direction - I don't see that changing much and
in fact they're girding up to do it again; we'll see if AMD suffers from
the same hubris but so far it still looks pretty good.

 

[Dean Kent]

The main difference between today and the past is that AMD has a viable
*commercial* product, though the related consumer part is still treading
water like previous AMD products in that space. Opteron has provided AMD
with both profits and perception, and that has been Intel's (and IBM's)
forte in the past. Where Intel has in the past been able to quickly
overcome whatever advantage AMD might have eked out, today they are still
waffling between focusing on IPF and x86 hoping that IPF will provide them
with the means to commoditize the low-end server space (like they did with
the low-end desktop space 10 years ago).

What hasn't changed much is the overall market share for x86, and that does
keep Intel firmly in the driver's seat, so the crown is still theirs to
lose. While there are always those who will pull for the underdog, the
majority still give the current 'champion' the benefit of the doubt in any
contest, making Intel's job a bit easier than AMD's even with a bit of an
imbalance in price/performance. AMD must keep the imbalance large for some
time before they are considered legitimate and finally tip the scales
permanently - but relying on a single market segment is somewhat dangerous,
and that has always been AMD's Achilles heel.

Regards,
Dean

 

[YKhan]

What hasn't changed much is the overall market share for x86, and that does
keep Intel firmly in the driver's seat, so the crown is still theirs to
lose. While there are always those who will pull for the underdog, the
majority still give the current 'champion' the benefit of the doubt in any
contest, making Intel's job a bit easier than AMD's even with a bit of an
imbalance in price/performance. AMD must keep the imbalance large for some
time before they are considered legitimate and finally tip the scales
permanently - but relying on a single market segment is somewhat dangerous,
and that has always been AMD's Achilles heel.

Maybe it's just a matter of time while AMD keeps up the pressure, as
you said; afterall, AMD has had the technological advantage over Intel
for over two years now, which is a lot of time pressure. But it also
looks like the anti-trust lawsuit has now hamstrung Intel tangibly. It
can't apply the same pressures on OEMs & retailers that forced them to
"give over" the benefit of the doubt. Throughout most cities, it's
looking like there's been an increase in the number of AMD PCs,
especially laptops, something that was rarely ever seen prior to the
lawsuit.

Yousuf Khan

 

[Dean Kent]

Throughout most cities, it's

looking like there's been an increase in the number of AMD PCs,
especially laptops, something that was rarely ever seen prior to the
lawsuit.

Got a link or reference for that?

Regards,
Dean

 

[YKhan]

Throughout most cities, it's

Got a link or reference for that?

Well obviously how many AMD based systems are showing up in local
stores is entirely anecdotal, being reported by individuals dropping by
their local Best Buys, Circuit Cities, Future Shops, whatnot. People
are seeing more laptop systems showing up on display with AMD
processors than they used to. It's not hard picking out an increase in
AMD laptops; whereas previously there might have been none, but now
there might be some -- easy to notice.

But the AMD boss also announced that they recently had 60 design wins
for the Turion. So one would assume that those design wins would be
showing up for sale too.

X-bit labs - Hardware news - AMD Turion 64 Is Gaining Market Acceptance
- Company.
http://www.xbitlabs.com/news/mobile/display/20050715215841.html

Yousuf Khan

 

[Grant Schoep]

(1) The readers of this group are probably more tech savvy than
average, so would you say that you have followed my downward opinion
of Sony over the past 10 yrs?
(2) Now, going into the wider population, do you think Sony has fallen
from a premium brand to just one among many?

I may still go with Sony for a tube, but nothing else. They still make a
better tube than anyone I have seen. I'm also of the sort that still
wouldn't by a plasma or other flat panel junk as the image still blows
compared to a tube. I have the 34'' XBR 16:9 sitting downstairs, that
picture rocks.

Other than the tube TV's, yeah there are a lot better companies out there.
But I wouldn't say that is any different then its been in years. Sure, Sony
was better than most other "Best Buy" or Circuit City, type brands. But
then, for the same price, or a little more you could always buy some really
great products from the higher end compaines. Denon is really putting out
some great stuff on the low end for A/V gear.

 

[AD.]

"Probably"?... maybe?

Well it's got to be better than their current stuff

Why would that be?...

I have no idea - just observing what seems to happen around here with IT
dept seat warmers, purchasing managers and your average IT consultants.

They seem blind to recent Intel screwups, while their opinion of AMD is
purely based on some crappily made K5 system they bought for home a decade
ago.

It's not so much the general public though - I don't really think they
care which cpu they get.

because Intel is bigger? I don't see that as an
advantage as far as public popularity goes. Or is it because AMD is seen
as an intruder/pretender/copyist? If that, it is something which could
easily be repaired by exposing AMD's true history of real innovation in
the processor industry dating back to the early 80s.

Nah, these people (in IT) don't care and don't want to hear it.

Intel's mistakes have all resulted from allowing marketing depts the power
to guide product technical direction - I don't see that changing much and
in fact they're girding up to do it again; we'll see if AMD suffers from
the same hubris but so far it still looks pretty good.

Yep, but to hear Intel talk of their new leadership direction - you'd
think it was the other way around ie they were too engineering oriented
and focused too much on performance. I did get a giggle reading this in an
article about their new CEO in some business mag while waiting at the
hospital.

 

[Rob Stow]

Well obviously how many AMD based systems are showing up in local
stores is entirely anecdotal, being reported by individuals dropping by
their local Best Buys, Circuit Cities, Future Shops, whatnot. People
are seeing more laptop systems showing up on display with AMD
processors than they used to. It's not hard picking out an increase in
AMD laptops; whereas previously there might have been none, but now
there might be some -- easy to notice.

But the AMD boss also announced that they recently had 60 design wins
for the Turion. So one would assume that those design wins would be
showing up for sale too.

X-bit labs - Hardware news - AMD Turion 64 Is Gaining Market Acceptance
- Company.
http://www.xbitlabs.com/news/mobile/display/20050715215841.html

Yousuf Khan

More anecdotal evidence: I build a few custom systems every
month for friends, friends-of-friends, etc. 37 so far this year.

A year ago about one third of the people wanted me to build P4 or
Xeon systems for them. In the last 5 or 6 months I have not had
one person ask for a P4 or Xeon box: everyone wanted Opterons
or Athlon64s, except for one Pentium M and one AthlonFX.

 

[keith]

No, the package wasn't ready so they had to put both on the same die.

The fact is that they *were* going to do an MCM because they had their
head so far up their ass that they ignored the obvious.

Why don't you read the article?

I did. I've read more than one article. Go figure.

 

[keith]

First of all, they didn't do that.

Only because they couldn't. They *were* going to do an MCM.

Second of all, a "dual core" is two processors in one physical package.

Are you always this stupid?

 

[keith]

This question of perceptions is an interesting one.
I remember ten years ago I thought of Sony as a premium brand; when I
had to buy a TV or a VCR my default assumption was to buy Sony (and pay
a little more) unless there were a compelling reason not to.

I did the same, recently (five years ago). I *thought* SOny had a decent
TV, for the price. The previous TV, a high-end RCA monitor, was being
replaced (still worked, but was aging) so I bought a Sony thinking it was
in the upper echilon. Wrong. It's average, at best.

A series of US-management-style clusterfucks over the last ten years
have, in my mind, completely destroyed that perception. Now if I have to
buy an electronics item either Sony just doesn't make something that
doesn't suck (iPod space), or I'll compare them with someone like
Samsung (flat panel, DVD player), and chances are Samsung will win.

I know I won't buy a SOny again. Note that they're sucking in the TV
market these days, and for good reason.

The
last Sony thing I bought (a pair of small speakers) while they looked
very cool, were basically all look and no substance; they were too wimpy
in power output to do the job I needed, which didn't do much to improve
my perception of them. When it came to buying some high-end
noise-cancelling headphones, the net reviews agreed: go with Bose and
don't waste your time on Sony.

Bose isn't my fave either. If their "wave-radio" says anything about
them, I'd rather listen to sea shells.

My question then is:
(1) The readers of this group are probably more tech savvy than average,
so would you say that you have followed my downward opinion of Sony over
the past 10 yrs?
Certainly.

(2) Now, going into the wider population, do you think Sony has fallen
from a premium brand to just one among many?

Fallen, yes. Out of "premium"? Dunno. I don't think they command a
nickel more than Samsung, or perhaps even LG.

(Oh, I suspect that Disney, in a different demographic, has undergone
the same sort of slide as Sony over about the same period.)

Worse. Whatever happened to "Touchstone"? Eisner had a huge streak going
with that end of the business, then completely lost it.

<snip>

 

[anonymous]

David Schwartz wrote:

...

a "dual core" is two

Not by any current definition that I'm aware of: it is, rather, two
cores on a single chip.

Do you call POWER an '8-core' processor because that's how many cores
its high-end systems have in one physical package?

- bill

You might also consider an argument of ARM 32-bit Standard Model VS
16-bit THUMB mode VS an entirely different VLIW with a 16-bit/5-bit
architecture as a potential performance differance.

Why is Intel so secretive about it's research of using registers as
stacks outside of Pentium's microcode engine? ( access more data thru
stacks with a similar ( or less!) amount of chip masking and a more
efficient fabrication ( I have seen very few stack architecture
refrences for Intel, for example the IPX multi micro puter engine ,
http:A//www.intel.com/design/network/products/npfamily/ixp2800.htm&ei=fR4NQ7OrCIfK-QG8_LHGCQ
, ))

Although, Mr. Moore's 25x model is an asychronous parallel processor,
VLIW SMP MPP sychronization is unspecified.

URL:
http://groups.google.com/group/comp.lang.java.machine/msg/b400d03ddc0f5a4f?hl=en

If they would have used sixteen 16-bit/5-bit instead of sixteen
32-bit/16-bit maybe Intel would have won. Thank you IBM for Nirvana.

 

[anonymous]

You might also consider an argument of ARM 32-bit Standard Model VS
16-bit THUMB mode VS an entirely different VLIW with a 16-bit/5-bit
architecture as a potential performance differance.

Why is Intel so secretive about it's research of using registers as
stacks outside of Pentium's microcode engine? ( access more data thru
stacks with a similar ( or less!) amount of chip masking and a more
efficient fabrication ( I have seen very few stack architecture
refrences for Intel, for example the IPX multi micro puter engine ,
http:A//www.intel.com/design/network/products/npfamily/ixp2800.htm&ei=fR4NQ7OrCIfK-QG8_LHGCQ
, ))

Although, Mr. Moore's 25x model is an asychronous parallel processor,
VLIW SMP MPP sychronization is unspecified.

URL:
http://groups.google.com/group/comp.lang.java.machine/msg/b400d03ddc0f5a4f?hl=en

If they would have used sixteen 16-bit/5-bit instead of sixteen
32-bit/16-bit maybe Intel would have won. Thank you IBM for Nirvana.

www.intel.com/technology/itj/2002/volume06issue03/art01_nextgenixp/vol6iss3_art01.pdf

The type of CAM mentioned in this article is NOT the same as my usage
of the term CAM. In my usage CAM is automatically executed as a
machine intruction , re-mapping back from 5-bit fedback into 16-like,
similar to Inmos Transputer type F instruction except my usage of CAM
permits 15 such mappings.

EITHER a sixteen ( actully fifteen with zero reserved for an
instruction type safety fault) 5-bit CAM instructs ( as described
previously) OR a simpler ( and faster) hardwire-ed 5-bit is referenced
in VLIM SMP MPP here, url ,
http://groups.google.com/group/comp.lang.java.machine/msg/38236e7c4267bb08?dmode=source&hl=en
( , since 1999 )

 

[anonymous]

www.intel.com/technology/itj/2002/volume06issue03/art01_nextgenixp/vol6iss3_art01.pdf

The type of CAM mentioned in this article is NOT the same as my usage
of the term CAM. In my usage CAM is automatically executed as a
machine intruction , re-mapping back from 5-bit fedback into 16-like,
similar to Inmos Transputer type F instruction except my usage of CAM
permits 15 such mappings.

EITHER a sixteen ( actully fifteen with zero reserved for an
instruction type safety fault) 5-bit CAM instructs ( as described
previously) OR a simpler ( and faster) hardwire-ed 5-bit is referenced
in VLIM SMP MPP here, url ,
http://groups.google.com/group/comp.lang.java.machine/msg/38236e7c4267bb08?dmode=source&hl=en
( , since 1999 )

Too short of a day, I guess, thirty one CAM or hardwired mappings, not
fifteen.