Pentium M desktops ???

[RusH]

WTF ? The word was that Intel dont want that to happen. So what is this
? :

http://www.hitachi.co.jp/New/cnews/040316.html

in short :

HJ-2010-5EWJA
???? ????(R)Pentium(R)M?????(1.6GHz)?
??????—(???????)??2GB(ECC?)?
IDE??HDD80GB???FDD?CD-ROM?
PCI(??—?)×2?RGB×1?DVI-D×1?RS-232C×1?????×1?
USB×3(??1ch/??2ch)?LAN×2?RAS-LSI?RAS?????

Yes, its in Japanese

Pozdrawiam.

 

[GSV Three Minds in a Can]

WTF ? The word was that Intel dont want that to happen

<snip>

So why would Intel care (apart from some of the marketing types). They
sell a chip for $x, what does it matter to them whether it comes out as
a desktop, a laptop, or popcorn maker??

OK, if were eating into the market for more expensive chips, I would
expect them to bitch and moan and drag feet (c.f. P4 vs. Xeon), but in
this case I thought the P4-M sold at a premium?

 

[Rob Stow]

<snip>

So why would Intel care (apart from some of the marketing types). They
sell a chip for $x, what does it matter to them whether it comes out as
a desktop, a laptop, or popcorn maker??

OK, if were eating into the market for more expensive chips, I would
expect them to bitch and moan and drag feet (c.f. P4 vs. Xeon), but in
this case I thought the P4-M sold at a premium?

The P4-M is Intel's el-cheapo brand "mobile" processor.
It is the Pentium M that you pay through the nose for.

 

[GSV Three Minds in a Can]

The P4-M is Intel's el-cheapo brand "mobile" processor.
It is the Pentium M that you pay through the nose for.

Cheaper than a 'real' P4?
Cheaper than a Celeron? (spit!)

 

[Tony Hill]

WTF ? The word was that Intel dont want that to happen. So what is this
? :

http://www.hitachi.co.jp/New/cnews/040316.html

I don't know what's going on there, but I did notice just yesterday
that my regular on-line vendor is now selling Retail boxed Pentium M
processors. It still says that these are designed for i855 based
notebooks though, so I'm not quite sure what to make of it... Here's a
link:

http://www.ncix.com/products/index.php?sku=10633&vpn=BXM80535GC1600E

 

[Rob Stow]

Cheaper than a 'real' P4?

A 2.4 GHz P4-M is more expensive than 2.4 GHz P4,
but *much* less expensive than a 1.6 GHz Pentium M.

And a 1.6 GHz Pentium M will run circles around
either of those 2.4 GHz processors.

Cheaper than a Celeron? (spit!)

Attach a Celery to a stick and you should have a
great brush for dogs/cats with woolly coats.

 

[Tony Hill]

That, of course, is the question a lot of people have been asking for
some time now. For whatever reason though Intel seems to have been
rather strongly opposed to selling Pentium-M desktop chips. There
definitely seems to be a market for them, but until very recently
there haven't been any products.

The P4-M is Intel's el-cheapo brand "mobile" processor.
It is the Pentium M that you pay through the nose for.

The "Mobile Pentium4-M" is actually a fairly expensive processor, it's
the "Mobile Pentium4" that is Intel's el-cheapo brand "mobile"
processor (using the term loosely).

 

[Nate Edel]

I don't know what's going on there, but I did notice just yesterday
that my regular on-line vendor is now selling Retail boxed Pentium M
processors. It still says that these are designed for i855 based
notebooks though, so I'm not quite sure what to make of it... Here's a
link:

http://www.ncix.com/products/index.php?sku=10633&vpn=BXM80535GC1600E

Ex-post-facto upgrade for 1.3ghz and 1.4ghz notebooks? White-box notebooks
sans processor?

And the small number of embedded-market Pentium M based boards that Intel
conveniently ignores.

 

[GSV Three Minds in a Can]

Bitstring <[email protected]>, from the wonderful

A 2.4 GHz P4-M is more expensive than 2.4 GHz P4,
but *much* less expensive than a 1.6 GHz Pentium M.

Right, so why would Intel care if someone chose to build desktops with a
P4-M, or Pentium-M, instead of a P4 (which was the original comment).
Basically whatever mobile processor you use in the desktop, Intel gets
=more= $$ than if you used the 'approved' vanilla P4.

 

[chrisv]

A 2.4 GHz P4-M is more expensive than 2.4 GHz P4,
but *much* less expensive than a 1.6 GHz Pentium M.

And a 1.6 GHz Pentium M will run circles around
either of those 2.4 GHz processors.

"Circles" around a 2.4C? I think not.

 

[chrisv]

That, of course, is the question a lot of people have been asking for
some time now. For whatever reason though Intel seems to have been
rather strongly opposed to selling Pentium-M desktop chips. There
definitely seems to be a market for them, but until very recently
there haven't been any products.

There's many reasons, from a marketing standpoint, not the least of
which is the resulting confusion of which chip is faster/higher-end.
It's confusing enough as it is, with Celerons, Northwoods, and
Prescotts of various FSB speed, without throwing this "slower but
faster" set of chips into the mix...

 

[Tony Hill]

There's many reasons, from a marketing standpoint, not the least of
which is the resulting confusion of which chip is faster/higher-end.
It's confusing enough as it is, with Celerons, Northwoods, and
Prescotts of various FSB speed, without throwing this "slower but
faster" set of chips into the mix...

I'm not sure that this is 100% accurate for the market in question, ie
non-OEM parts. Presumably people buying retail boxed chips know at
least something about the processors (or they are buying based on the
recommendations of someone who knows something).

In any case though, perhaps the new processor model numbers will
change this? Intel is planning on switching all their model specs in
a couple of weeks.

 

[Paul Tiseo]

That, of course, is the question a lot of people have been asking for
some time now. For whatever reason though Intel seems to have been
rather strongly opposed to selling Pentium-M desktop chips. There
definitely seems to be a market for them, but until very recently
there haven't been any products.

If you spend umpteen million in R&D to design the P4, and the P-M
comes along with less R&D and runs slightly faster in some scenarios,
what do you do? Chuck all your P4 R&D out the window?

- PT

 

[Robert Redelmeier]

If you spend umpteen million in R&D to design the P4, and the P-M
comes along with less R&D and runs slightly faster in some scenarios,
what do you do? Chuck all your P4 R&D out the window?

Actually, I believe the Pentium4 was done as a rush job,
on the cheap after it became apparant that ia64 (aka
Itanium) would not take over. IMHO it's an original
Pentium plus SSE2, deeply pipelined for inflated clocks.

The Pentium-M is little more than the venerable P6 core,
tweaked and clocked higher on smaller processes.

-- Robert

 

[Tony Hill]

If you spend umpteen million in R&D to design the P4, and the P-M
comes along with less R&D and runs slightly faster in some scenarios,
what do you do? Chuck all your P4 R&D out the window?

I'd suggest that you listen to what your customers want and sell
whatever that is. My guess is that the majority of people will prefer
the P4, but there is certainly a market for the Pentium-M. No need to
chuck any R&D out the window, just fill market demand. However, for
whatever reason, Intel has thus far refused to do that.

 

[KR Williams]

If you spend umpteen million in R&D to design the P4, and the P-M
comes along with less R&D and runs slightly faster in some scenarios,
what do you do? Chuck all your P4 R&D out the window?

At that point it's sunk cost. It doesn't matter what you do with
it. You optimize your profit/revenue (whatever is important
today) based on what you have. What you've spent and where is
totally irrelevant (to everyone but the product manager getting
axed ;-).

 

[Anonymous Joe]

Actually, I believe the Pentium4 was done as a rush job,
on the cheap after it became apparant that ia64 (aka
Itanium) would not take over. IMHO it's an original
Pentium plus SSE2, deeply pipelined for inflated clocks.

The Pentium-M is little more than the venerable P6 core,
tweaked and clocked higher on smaller processes.

-- Robert

It does seem as though the P4 is just that. A P3 with SSE2, with very long
pipelines (extended further thanks to Prescott) for a hyper-inflated clock
speed that eventually is pretty decent, but only when you get to a
ridiculous level of clock speed, and some of that is due to the quadrupled
bandwidth bus speed combined with the memory speeds (dual channel anyways).
As the P4 increases in clock speed, so does the L1/L2 cache, which can only
help but improve performance further.

What strikes me is that a P4 @ 3GHz is generally on par with an Athlon
3000+, which depending on the bus speed chosen is either 2.16GHz (333Mhz
bus) or 2.1GHz (400Mhz bus). I forget off-hand how deep the P4 pipeline is,
but is something like 24, isnt it? The Athlon is something like 12, or 15.
Either way, the numbers are off, but it still is rather close. The P4 has
L1 & L2 cache running at 3GHz, while the Athlon's is about 66% of that, but
more plentiful. The bus bandwidth of the P4 is going to be either
4.27GB/sec or 6.4GB/sec (533 or 800MHz bus [yet it is really 133 or
166MHz]). Yet the Athlon is using a 3.2GB/sec bus. As for memory, the most
you can get out of the Athlon is the 3.2GB/sec (whether you use P3200 RAM,
any speed dual channel RAM, even PC3200), but with P4 you have a shot at
getting a theoretical of 6.4GB/sec (dual channel PC3200).

All this combined, things sure look favorable for P4. It has so much more
bandwidth in every area, cache, bus, and RAM. Yet, how come with a 900MHz
core clock lead, it is only able to tie the Athlon? It seems like it is
using all the bandwidth and wasting it. If AMD could get the sort of
bandwidth that Intel has, I would imagine that the P4 would need about a
1200MHz or more head start to start being comparable.

For anybody who cares, I do use AMD, so if you want to say I'm promoting AMD
unfairly or whatever, that's wrong, I'm simply showing that Intel isn't
efficient.

 

[KR Williams]

It does seem as though the P4 is just that. A P3 with SSE2, with very long
pipelines (extended further thanks to Prescott) for a hyper-inflated clock
speed that eventually is pretty decent, but only when you get to a
ridiculous level of clock speed, and some of that is due to the quadrupled
bandwidth bus speed combined with the memory speeds (dual channel anyways).
As the P4 increases in clock speed, so does the L1/L2 cache, which can only
help but improve performance further.

Yikes! The architectures are *vastly* different. THe P4 has no
integer multiply (has to send the data to the FPU, across chip)
and has no barrel-shifter. The architectures of the
PPro/PII/PIII and P4 are *vastly* different!

What strikes me is that a P4 @ 3GHz is generally on par with an Athlon
3000+, which depending on the bus speed chosen is either 2.16GHz (333Mhz
bus) or 2.1GHz (400Mhz bus).

Sure, because the micro-architecture is *vastly* different.
IFAIC the P4 is a failure in micro-architecture. Maybe they'll
improve it by shoring up it's weaknesses, but so far it is a dud.

I forget off-hand how deep the P4 pipeline is,
but is something like 24, isnt it? The Athlon is something like 12, or 15.
Either way, the numbers are off, but it still is rather close. The P4 has
L1 & L2 cache running at 3GHz, while the Athlon's is about 66% of that, but
more plentiful. The bus bandwidth of the P4 is going to be either

You're missing a lot of other details here.

4.27GB/sec or 6.4GB/sec (533 or 800MHz bus [yet it is really 133 or
166MHz]). Yet the Athlon is using a 3.2GB/sec bus. As for memory, the most
you can get out of the Athlon is the 3.2GB/sec (whether you use P3200 RAM,
any speed dual channel RAM, even PC3200), but with P4 you have a shot at
getting a theoretical of 6.4GB/sec (dual channel PC3200).

Now, consider latency. Bandwidth isn't everything. Bandwith
only takes money, latency takes physics.

All this combined, things sure look favorable for P4.

Only because you're not looking at the right problem.

It has so much more
bandwidth in every area, cache, bus, and RAM. Yet, how come with a 900MHz
core clock lead, it is only able to tie the Athlon?

See above.

It seems like it is
using all the bandwidth and wasting it. If AMD could get the sort of
bandwidth that Intel has, I would imagine that the P4 would need about a
1200MHz or more head start to start being comparable.

Bandwidth isn't a useful measure, unless you don't have enough.
Latency is *always* a useful measure.

For anybody who cares, I do use AMD, so if you want to say I'm promoting AMD
unfairly or whatever, that's wrong, I'm simply showing that Intel isn't
efficient.

If I were to buy a system for encoding video and *only* that
function, I'd likely buy a P4. For anything else, forget it. As
you've noted Intel has gone down the wrong path.

<rdh> ;-)

 

[GSV Three Minds in a Can]

Bitstring <[email protected]>, from the

If I were to buy a system for encoding video and *only* that
function, I'd likely buy a P4. For anything else, forget it.

Actually it does rather well (2x as good as an Opteron or Athlon64)
running Prime95 LL tests, but only because AMDs SSE2 has some sort of
implementation glitch that means you can't process at the speed you
ought be able to.

see:
http://www.mersenne.org/bench.htm

 

[Robert Redelmeier]

(e-mail address removed) says...

Yikes! The architectures are *vastly* different. THe P4 has no
integer multiply (has to send the data to the FPU, across chip)
and has no barrel-shifter. The architectures of the
PPro/PII/PIII and P4 are *vastly* different!

Exactly what I was trying to say. I see the Pentium4 mostly
as a throwback to the original Pentium (P5 core).

Odlly, the Pentium4 may not perform too badly because compiler
technology lags horribly and alot of apps (MS-Office?) are
still compiled on older compilers that optimize only for two
exec pipelines.

-- Robert