Slashdot Mirror
Intel to Dump Pentium 4 in Favor of Pentium M
Opinion writes "According to The Register, Intel is to dump its Pentium 4 plans in favour of the new Pentium M architecture. The scrapped Tejas and Jayhawk processors represented Intel's next-gen 90nm P4 CPUs, due to arrive in 2005."
This seems like a really smart idea. Dont go an get the Ultra-Gigaherz-Processor but a descend, processor that consumes only a low amount of power -> Longer batterylife for laptops -> Silent PCs -> Longer lifetime of the processor (?)
Spelling mistakes: My is english spoken not tongue of mother.
This really shouldn't be a suprise to -anyone- who's been paying attention to what's been going on.
:)
Prescott is disturbingly hot, and the next-gen chips had no real hope of being much cooler. At most 10-15%, which wouldn't have gotten near their MHz goals.
P-M, on the other hand, is a damned good chip in its own right, has better IPC, and is a better CPU, all around, than the P4 line.
Now, what does this mean for those of us in the enterprise space? Are we -really- going to have to wait until 2006 for a new chip iteration from Intel? If that's the case (and I -really- doubt it), AMD would have a disturbingly large (and long) opening in which to pitch its wares...Intel would definately lose marker share in the server arena at that point.
So, multi-core P-M chips for the desktop next year-ish. So we're stuck with the hotplate known as Prescott until then. Guess I'll be sticking with AMD for a while yet
Dothan is in due course expected form the basis for 'Jonah', Intel's first two-core Pentium M, due to ship during H2 2005, possibly at 65nm. To date, Jonah has been scheduled to be succeeded by 'Merom' and 'Conroe', two chips based on the same architecture, during H1 2006. While Merom is to be pitched at notebooks, Conroe - crucially - is a desktop chip.
Dothan: Meaning: two wells. A famous pasture-ground where Joseph found his brethren watching their flocks. Here, at the suggestion of Judah, they sold him to the Ishmaelite merchants (Gen. 37:17). It is mentioned on monuments in B.C. 1600.
Jonah (We all know who Jonah was and/or you need to back to sunday school....)
Merom (WebBible Encyclopedia) - christianAnswers.Net. Merom. Meaning: height. a lake in Northern Palestine through which the Jordan flows
Looks like Intel got some religion....
"All great things are simple & expressed in a single word: freedom, justice, honor, duty, mercy, hope." --Churchill
Have they been able to ramp up the speeds for this architecture? None of the articles that I've read even speculate on what speeds these would be introduced at. I know Intel was planning on releasing a 2.0GHz Pentium M in the near future, but what about for desktops?
Side note: "Whitefield" a new processor in the Xeon line based somewhat aroudn the Pentium M, was created in India.
Casual Games/Downloads
We've been on 32bit chips for quite some time..
:(
Is 32bits enough? Is that why 64bit chips don't
seem to be catching on? or does the fact that
AMD and Intel seem to have fairly different
workings to their interface (AMD's seems fairly
simple, I haven't looked at Intel's).
Slightly related,
It seems both Intel and AMD stopped shipping free
copies of their Architecture Manuals.
It has been known for quite some time that the Pentium-M processors would outperform desktop chips even when clocked at a higher frequency.
Seems that Intel finally wised up and is exploiting the technology in the Pentium-M Chips to lower its development costs even though that isnt explicitly stated in the article.
Yes, I did RTFA.
What makes you think that? Why wouldn't you want to put a Pentium-M into a desktop machine?
-- *My* journal is more interesting than *yours*...
In the article, they mentioned 2- and 4-core chips coming out in 2005 and 2006. How long will it take the unix and windows operating systems to take full advantage of all the cores? Are they already there? Does software running on these systems need to be specially written and/or compiled in order to take advantage of the multiple cores or will they mostly serve to handle multitasking?
Let's go Hurricanes!!! 2006 Stanley Cup Champions!!!
If Intel is moving to low power multicores chips what will this mean in terms of os licenses that limit the number of cpus which can be used at any one time such as MS? Will the likes of MS relax the licensing terms so that this type of technology will take off or will they use it as an excuse to make more money and kill off demand for multicore cpus? I wonder if Intel has discussed this with MS?
Don't forget, when the Pentium first came out it was refered to unoffically as the 586, and the PII was refered to in the press as the 686, so even if intel had to change their naming scheme (they couldn't copyright a number like 80586, so they had to pick a name for it) people still thought of those chips under the old terms for quite some time. Now, of course, with the product line so divergent into different sub-classifications, it really doesnt make sense to map to the old numbering scheme.
I spoke to an Intel guy recently, they have moore's law covered for about the next ten years. If you're prepared to pay. Basically they can produce insanely fast processors, they just can't mass produce them. I suspect this is the case with AMD and IBM as well, it's just a case of getting the fab costs down.
From what I've read the Pentium M is nothing more than a souped up P6 core [slightly longer pipeline, 1MB power optimized cache and SSE/SSE2 iirc].
So really it's the PIII v2.0.
Last I checked though the Athlon XP [and Barton] still whoop the PIII's ass and probably the Pentium M at equal clockrates [let's not forget that 2.2Ghz AMD Bartons exist...].
So my guess is if they do ditch the P4 it won't be directly to the Pentium M but instead a design based off it [but with a higher IPC than the P-M] cuz otherwise they'll get screwed in the processor speed wars and that would look awful stupid.
Tom
Someday, I'll have a real sig.
Desktops have been in trouble for a while. A new CPU comes out with an 8% higher clockspeed, and then it uses 15% more power. Obviously there was a limit to how long that could continue, especially as those diddly performance increases weren't providing tangible benefits (compare an 8% clockspeed increase with switching to a dual core processor, for example). And at the same time the desktop market has been being heavily outpaced by laptops and mobile devices.
This means the end of desktop CPUs in laptops.
Decent battery life in a cheap laptop? Nah, they'll cut down on the batteries instead.
It's never too late to have a happy childhood.
The long pipeline approach was sustainable for a while, but with their newer processes (like the 90nm process used for the Prescotts) the heat costs of having the longer pipelines have proven too high. Their long pipeline design worked quite well for the Pentium 4's - give them enough cache, and they perform spectacularly, but the even longer pipelines required to keep cranking the clock speeds up, as with Prescott, are starting to be quite detrimental to the design. The Prescott architecture may be able to run at much higher clock speeds than the previous Northwood P4's, but they do so at the cost of requiring an even larger cache, and a much improved branch predictor. Had the improved branch predictor and increased cache simply been implemented on an existing Northwood core, and if Intel manufactured the chip on their 90nm process, it's quite likely that they'd have an even better performing chip than what Prescotts are capable of at higher clock speeds. That's all conjecture though - Intel didn't go that way, they let their marketing people decide on what the Prescott was going to be, and are now paying for it.
80186 was not a failure. I just was not used in PC's. Once upon a time, there was no real difference in the embedded field between the desktop processor and the processor used in say a traffic light. The 80186 was used in lots of embedded solutions. Checkout Wikipedia
Gorkman
Still, process shrinks in the past have yielded easy speed increases, but not this time around. Intel's move seems to confirm that there might be trouble ahead.
It looks like the folks at IBM also have concerns:
"Somewhere between 130-nm and 90-nm the whole system fell apart. Things stopped working and nobody seemed to notice."
Is there a technical reason you want a specific brand of processor?
To me, the CPU brand is becoming much less important. The supporting chipset (features and quality), memory expansion, and system maker tend to sway me much more these days.
A firewall can not protect you from yourself. Turn off what you do not need. Do not use the firewall to do your work.
This should have been visible from a mile away. A month or so ago there was an article (on The Register I think) about Intel abandoning it's Mhz marketing in favor of a simple number system (for example, 5xx series for one processor line, 7xx series for another processor line). It was obvious to me at the time this was because they would be dumping the current P-4 and going with the P-M. Why else would you remove Mhz from the equation?
The 80186 still isn't dead - you can still buy them. I have a 186 single board computer sitting in a box on my desk that I assembled and programmed last year for a microprocessors course. The chips are still sold by DigiKey and the other usual suspects. I have a copy of the 186 datasheet here that actually says "updated June 2002" on it. Old hardware never dies...
I'd like to know who the grandparent poster thinks is paying for all this diamond research.
If I recall, most of it is taking place in small research companies funded by capital from corporations like Intel, who then would have a percentage stake in the technology if and when it comes around.
There's also plenty of interneal research and doctoral work funded by grants from IBM, Intel, etc.0
Hey freaks: now you're ju
Intel has already announced that it will also be releasing a variant of the x86-64 technology that was developed by AMD. You can see their announcement here. While technology analysts see that there are indeed differences, it is approached fundamentally in the same manner that AMD used - making compiler development for the "extended" 64-bit Intel processors easier.
This does not mean Intel is simply give up on the Itanium. They have more than a decade worth of R&D dollars into the processor. I don't believe they will actively pursue integrated the two 64-bit processors under one flag, either, because it would be easier to keep one facility churning out Itaniums and all their other facilities to make modified P4/PM chips with 64-bit extensions.
This is a matter of market preference. The market prefers a single processor (right now). I remember seeing supporting statistics but I can't find those at the moment. It was better than 90%. R&D is currently focusing on making single processors more efficient (Intel's hyperthreading is a good example). All these improvements will eventually trickle down to the small SMP sector Intel supports.
Also, Intel wishes to keep its Xeon and Xeon MP line strong. To do so would be to limit the offerings of SMP capable chips and chipsets to focus the multiprocessor market for higher profitability.
Intel is beginning to realize this, but this does not change the fact that there are many people that will still choose Intel over AMD just based on name alone. I run into these types on a regular basis.
Ayup
that say this is a great idea. I'm personally not so sure. They havent got the core beyond 1.7 ghz. Why? This is a P6 core cpu! Thats right, pentium pro, pentium 2, pentium 3, etc. They added some features, new stepping and thats it.
This has also been mentioned, but what I'm saying is, I have NO idea how they will get any kind of clockspeed out of this thing. It's been tooth and nail to try to get it to run where it is even. They can drop the process size to get more speed out of it, but that only takes you so far. You will have to lenghten the pipeline eventually which carries with it all the problems of the P4.
I just honestly cant see them taking the P6 core any further. I'm suprised they can even do what they do with it.
I also doubt they will drop the Pentium 4 core while they still have a lead on the athlons performance wise. P4 is a core they spent a LOT of time and money developing. I doubt they will just drop it.
Also, in the article, they say that intel will be tearing up their roadmaps and they SPECULATE Pentium-M will be the replacement. Might be a modified Pentium 4, or maybe a Pentium4-PentiumM mix.
Just my 2c.
It's easier to fight for one's principles than to live up to them.
It's not that we can't technically go on with Moore's Law, it's just that maybe it's not worth it.
rm -rf /home/leia
What the heck are you talking about? Wattage is a word, and it means "power". I'm an electrician. We use the term "wattage" rather than "power" because the latter is too ambiguous. A watt is a unit of measurement, so asking "what's the wattage on that bulb" will get you an answer in watts. Asking "what's the power on that bulb" will get you either puzzled stares or an answer in watts. It is always preferential to speak about quatities using their units of measure. That means amps, volts, and watts. "Power" is not a unit in ANY system.
If a job's not worth doing, it's not worth doing right.
Windows 95 and 98 are actually version 4.something, which you can see with the 'ver' command in a DOS shell. Bloated and disappointing, you said?
Escher was the first MC and Giger invented the HR department.
Actually, the reason it took THIS friggin long to come to this decision was the resistance on the part of Intel in the US to fully accept the design of this chip by Intel in Israel. Apparently, there was quite a bit of "not invented here" mindset on the part of the US Intel folks, even though it was still Intel that created the Pentium M... just in Israel.
I can't find any info regarding this online at the moment, but I did get this information from a reliable source. Anyone else read this?
Portable versions of Firefox, GIMP, LibreOffice, etc
See here, it was one of the few PCs that used the 80186.
Mea navis aericumbens anguillis abundat
Either that or a very extensive marketing campaign for the Pentium M. The Pentium M is easily confused with chips like the Pentium 4 M. I have a laptop with a 1.6 GHz Pentium M (not full Centrino since it has an IBM a/b wireless card). An IBM project manager for the T-series Thinkpads compared it to a 2.0-2.4 GHz Pentium 4. Given that it also gets 4+ hours of battery life (year old battery with 80% original capacity) while using wireless network, the system is definitely better than a P4 based system. It's also more expensive, which makes marketing it harder.
I don't think we can count on quiet, low-power desktops though. I bet Intel will just ramp up the Pentium-M until it's a hot as the P4 (but by then it will be faster than todays P4 due to higher IPC).
I'm guessing you must be Jewish or something? What a nice contradictory post:
The Pentium-M is a modded Pentium-3.
Quite right. It's a Pentium 3, but with SSE2, the Pentium 4's bus, more cache and improved branch prediction. "Dothan" adds a couple of extra features on top of that.
Pentium-M was designed in Israel
Yes, but only insofar as Intel Israel was handed the P6 core and told "keep up to date, please". Moreover, the physical design (i.e. the main reason it runs cool and at a relatively high clockspeed for its complexity) was done in the US.