Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Intel Reveals Next-Gen CPUs

Zonk posted more than 8 years ago | from the low-power-means-more-flavour dept.

Intel 515

EconolineCrush writes "Intel has revealed its next generation CPU architecture at the Intel Developer Forum. The new architecture will be shared by 'Conroe' desktop, 'Merom' mobile, and 'Woodcrest' server processors, all of which were demoed by Intel CEO Paul Otellini. Rather than chasing clock speeds, Intel is focusing on lowering power consumption with its new architecture. Otellini claimed that Conroe will offer five times the performance per watt of the company's current desktop chips. He also ran the entire keynote presentation on a Merom laptop, and demoed Conroe on a system running Linux."

cancel ×

515 comments

Sorry! There are no comments related to the filter you selected.

Power concerns (5, Insightful)

bigwavejas (678602) | more than 8 years ago | (#13381612)

With Laptop sales "Surging" and technology growing exponentially, isn't it time to look at the batteries? You hear a lot about faster video cards/ CPUs and memory, but almost nothing about Next-Gen batteries. Battery technology hasn't really evolved at the same rate as other computer components, has it? I personally feel the bottleneck resides in the batteries and for the industry to progress (on a whole), they're going to have to take a look at all aspects.

Re:Power concerns (5, Insightful)

Epistax (544591) | more than 8 years ago | (#13381651)

I agree however I believe at least 50% of our battery life extension will come from developing ways to use less stored energy instead of storing more.

Re:Power concerns (4, Funny)

FLAGGR (800770) | more than 8 years ago | (#13381668)

A better battery doesn't get any more polygon's out in Quake 4.

Re:Power concerns (3, Interesting)

Harbinjer (260165) | more than 8 years ago | (#13381798)

Yes, but you with the size of games today, you won't have enough time to actually load Level 3 before your battery runs out.

I bet hard disks and Cd-roms are sucking down a lot of power today compared to teh CPU. The new solid-state storage ideas look cool in helping with that.

Re:Power concerns (2, Insightful)

FLAGGR (800770) | more than 8 years ago | (#13381837)

I wasn't saying that battery life isn't important, it's just that people don't shell out as much money for it because they are more concerned with power in most cases, since most people don't go very long without having access to an electrical outlet.

Re:Power concerns (3, Informative)

Anonymous Coward | more than 8 years ago | (#13381879)


Nope: current Intel CPU is 100+ Watts, a hard drive is like 15 Watts.

Are you kidding? (4, Funny)

ShaniaTwain (197446) | more than 8 years ago | (#13381681)

We now have batteries powered by urine! [theregister.co.uk]

Who hasn't wanted to pee on their new laptop? Marks your territory and provides hours of power!

what else could you want?

Re:Are you kidding? (1, Funny)

Anonymous Coward | more than 8 years ago | (#13381717)

NOW we know what the hell this picture was about!

http://www.comiccaptions.com/images/dogpee.jpg [comiccaptions.com]

instant power!!

There's something sorta YEECH about that. (4, Funny)

crovira (10242) | more than 8 years ago | (#13381788)

While I admit there's been times I WANTED to get back at my laptop for being so slow, the smell factor stopped me. Okay that and the cost, not to mention that I could get zapped in a very private place!

Urea don't small like roses, just sniff my cat box after the cat's used it. Yurk! (Actually, just be in the room after he goes. Bleah!)

Re:Power concerns (1)

jasongetsdown (890117) | more than 8 years ago | (#13381709)

but a processor that draws less juice will run longer on a current gen battery. If you can't make longer running batteries then you have to build more conservative components.

Re:Power concerns (2, Interesting)

Anonymous Coward | more than 8 years ago | (#13381710)

That's been a common thread in mobile technology for a long time. It's a lot more difficult to optimise the same chemicals to store more energy in a smaller container than it has been to build smaller and smaller computing components.

As a matter of fact - reading around a little bit will show that basically mobile device design is driven around the battery. We could go much smaller, much faster, and generally far niftier with our devices if we didn't have to strap a car battery to it.

Addressed in the article... (2, Informative)

Anonymous Coward | more than 8 years ago | (#13381722)

Somehow I don't think you RTFA.

Thanks to the death of NetBurst, Conroe will feature a 5x increase in performance per watt. Here's to the death of the power-hungry Intel processor.

and

Woodcrest and Merom will both improve performance per watt by a factor of 3 over their predecessors.

They're improving the processor as opposed to the batteries...

On electrical cost savings alone, PC users will save $1 billion per year for every 100M computers.

Pretty amazing. Although I'd like to see real #s to back up that claim.

Re:Addressed in the article... (2, Interesting)

bigwavejas (678602) | more than 8 years ago | (#13381762)

I beg to differ, I believe they're both directly related to one another. Less power hungry components and better performing batteries.

Incidentally, I did RTFA...

Sometimes the thought process goes well beyond what's in black in white.

Re:Addressed in the article... (1)

MindStalker (22827) | more than 8 years ago | (#13381773)

On electrical cost savings alone, PC users will save $1 billion per year for every 100M computers.

1 billion / 100M = 10

So your cost saving is $10 a year. Not hard to achieve. Don't be fooled by fancy large numbers.

Suicide Concerns (Re:Power concerns) (-1, Flamebait)

Anonymous Coward | more than 8 years ago | (#13381730)

How many slaves (H-1Bs or Americans) were tortured and possibly killed by Intel management in order to produce these stunning new processors?

The rumor mill says that 5 Intel employees committed suicide during the development of the Pentium 4. How much blood was shed for Intel's Conroe?

Inquiring minds of health officials and ambulance chasers want to know. Get the facts at FACE Intel [faceintel.org] .

Re:Suicide Concerns (Re:Power concerns) (0)

Anonymous Coward | more than 8 years ago | (#13381804)

lol what?

FACE Intel (0)

Anonymous Coward | more than 8 years ago | (#13381843)

Here is the correct link: FACE Intel [faceintel.com] .

Re:Power concerns (4, Informative)

LWATCDR (28044) | more than 8 years ago | (#13381731)

Because batteries are more mature than electronics.
Honestly there just is not that much room for improvement unless someone makes a huge break through.
If you think about the requirements for a battery they are pretty harsh.
1. Relatively none toxic
2. Relatively none explosive,
3. Last a long time.
4. Cheap.

Re:Power concerns (1)

Billy the Impaler (886238) | more than 8 years ago | (#13381739)

Laptops really are taking off, but as I observe, most laptops are NOT used as primarily protable devices. They usually sit on a desk doing the same job as their larger, more power hungry brethren. They just take up lass space and are ocnsidered more chic by the non-nerd masses. Sure they get used on batteries occasionally, but most people will plug their computers into the wall if at all possible.

Re:Power concerns (0)

Anonymous Coward | more than 8 years ago | (#13381899)

"but most people will plug their computers into the wall if at all possible."

The whole reason they plug their laptops into the wall is because their batteries aren't capable of keeping their laptops running too long.

Re:Power concerns (0)

Anonymous Coward | more than 8 years ago | (#13381753)

There are other ways to get longer battery life, namely by making the major drains on power (cpu, hd, screen) more efficient.

Improving the efficiency of the cpu, for instance, gives longer battery life, but *also* results in lower energy bills (which improved batteries alone would not offer) and fewer scorched laps, which is better for the environment, your pocketbook and other things you probably keep near your pockets.

Re:Power concerns (1)

alkaloids (739233) | more than 8 years ago | (#13381768)

the battery development problem is a frontier that is being worked on very frantically in such research areas as the people who want to bring you electric cars, as well as the fuel-cell development folks. the fuel cell/battery researchers are trying to solve the exact same problems as far as i can find out: easily moving electrons around in solution without protons (or other ions, such as Li+) going along for the ride. so rest assured, someone is trying to make you a better battery.

Re:Power concerns (1, Insightful)

Anonymous Coward | more than 8 years ago | (#13381790)

Well, the lower power usage of these chips they're talking about goes some way to deal with the battery bottleneck. Remember that battery technology is always improving - it didn't just stop, it's actually nearing the threshold of what it can physically do. Hence Intel's stance on power-saving; if they want to make laptops go faster, then they're going to have to figure out a better way of using the power they've got.

Batteries are also a fairly basic way of making power. Technologies like fuel cells may go some way to solving the problem and nuclear batteries would be wonderful, but will never be sold to the public.

For now though, Intel have to do more with what they've got, so instead of throwing more power in for an inefficient CPU and using brute force, they have to rethink, which is good all round; less energy = less waste = less cost = better use of resources.

Re:Power concerns (4, Insightful)

realmolo (574068) | more than 8 years ago | (#13381824)

It's hard to improve batteries. You might as well ask "how come we don't have gasoline that gives us 100 mile per gallon in an average vehicle"?

Because there are physical limits to how much energy you can store in given materials. You can't "design around" these limits. All you can do is try and come up with better materials/better combinations of materials. And we've already tried every combination that is practical.

Which is why fuel-cell powered notebooks are interesting. But who knows if those will ever actually get produced.

Different Physics (5, Interesting)

sterno (16320) | more than 8 years ago | (#13381857)

The problem is that the physics for how to increase the number of transistors on a chunk of silicon is very well understood and the physics of how to make better batteries is not.

To double the number of transistors on a processor is primarily a matter of lithography, that is etchich smaller and smaller lines into an existing wafer. Same materials, more or less, and same technique, more or less. With batteries, it's far more hit and miss.

The technology and fabrication process to make a lead-acid battery is vastly different than NiCd. NiMh is somewhat similar to NiCd, but then Lithium Ion is rather different and requires a lot more technology to make it work. Then you've got fuel cells as a possibility, and that's vastly different from anything I just described.

There's a lot of effort being put into battery research because everybody understands what a fundamental limitiation it is to everybody's dreams of pervasive wireless. It's rather ironic to describe these internet coffee shops as having "wireless" when you still have to have A/C power to do anything. The problem is that it does not have the clear and obvious path that CPU's have had.

I expect that fuel cells will eventually be the way to go. Still there's a certain inconvenience in them. If I want to charge my laptop batteries, i just plug in my laptop. If I've got a fuel cell, do I have to buy numerous cells? Do I have to fill them up with methanol, etc? It doesn't seem like there's a panacea for portable power (and other p words) anytime soon.

Good (5, Interesting)

alecks (473298) | more than 8 years ago | (#13381613)

Rather than chasing clock speeds, Intel is focusing on lowering power consumption with its new architecture.
Exactly what we've all been waiting for. Is Intel Good(tm) now?

YES... (1, Insightful)

Anonymous Coward | more than 8 years ago | (#13381686)

Speaking as someone who has only purchased Opteron systems for the last 2 years, I welcome this. When these chips start shipping, I will re-evaluate our policy at that time and if Intel delivers what they're claiming, I suspect we'll be back to Intel chips, depending on how AMD responds to this.

But this is VERY GOOD. It sounds like a return back to real competition.

Re:Good (5, Insightful)

GamblerZG (866389) | more than 8 years ago | (#13381697)

Is Intel Good(tm) now?
No, they just reached the limits of silicon technology. Increasing performance any further would require eather designing "smarter" (rather than faster) processor or using multiple cores.

Anyway, the trend is good indeed. Finally, people will start thinking about performance on the level of software.

Re:Good (4, Funny)

davmoo (63521) | more than 8 years ago | (#13381732)

You must be new here, and obviously do not know the rules. Let me help you.

AMD is always good, no matter what they do.
Intel is always bad, no matter what they do.
Apple is always good, no matter what they do.
Microsoft is always bad, no matter what they do.
Steve Jobs is always right and the sun shines out his rectum, even when he's wrong.
Bill Gates is wrong and is the spawn of the Devil, even when he's right.

These rules apply even in cases where one entity does something, and then the other entity does the exact same thing two weeks later.

And finally, my reply and any like it will always be moded -1 'troll' because the majority of readers here do not want to admit they are this biased.

Re:Good (4, Insightful)

Dorsai42 (738671) | more than 8 years ago | (#13381810)

You left out the most important rule:

You cannot rely on anything you read here.

Re:Good (2, Insightful)

needacoolnickname (716083) | more than 8 years ago | (#13381869)

You forgot Google. Can't forget Google.

OF course (0, Flamebait)

cmdrTacyo (899875) | more than 8 years ago | (#13381618)

Another close to first post
I'm the /.er who can boast the most roast
To the next gen cpus I have a toast
On my porsche I will coast
Nicca's hate me hackers envy me
I'm the internets version of raps notorious BIG
So thuggin like tupac
Selling crack on ebay and smack

Hello (-1, Offtopic)

Anonymous Coward | more than 8 years ago | (#13381619)

Hello

Now we know... (3, Insightful)

wvitXpert (769356) | more than 8 years ago | (#13381628)

So this is what Steve was talking about.

But notice, they didn't have any OS X machines... (2, Interesting)

crovira (10242) | more than 8 years ago | (#13381723)

I feel good about the choice that Steve made but I don't think he capitalized on the announcement.

Here's hoping that the new architecture is not just a M$, Linux thing.

I'd really like to have a low-power multi-core 64 bit chip blazing away in my next iMac.

Re:But notice, they didn't have any OS X machines. (1)

CausticPuppy (82139) | more than 8 years ago | (#13381786)

I'd really like to have a low-power multi-core 64 bit chip blazing away in my next iMac.

Intel probably can't even talk about it due to Apple NDA's. Rest assured that the Intel-based mac notebooks will use this technology.

Re:But notice, they didn't have any OS X machines. (1)

qaq (908831) | more than 8 years ago | (#13381860)

why would intel be using apple at IDC?

Re:But notice, they didn't have any OS X machines. (1)

riversky (732353) | more than 8 years ago | (#13381803)

I agree, an associate of mine at the keynote said not a peep about Apple. Hmmm I wonder if it was becuase Steve wouldn't allow it because it might give a hint to when certain machines would be released....I don't know, we will see what the Mac OS X on Intel does....Could be a good thing.

Re:But notice, they didn't have any OS X machines. (1)

Gogo Dodo (129808) | more than 8 years ago | (#13381865)

Probably because Steve doesn't want to be upstaged anybody. He will want to show off any new hardware. It would have been interesting if Steve had a presentation at IDF, but that's not likely to happen.

I'm sure that there a few of these processors running in Apple's labs.

Re:Now we know... (1)

wpmegee (325603) | more than 8 years ago | (#13381795)

Cooler, quieter, more efficient, and faster clock-for-clock than any other x86 chip on the market including the Athlon64, Pentium M, and Pentium 4. At least 30% faster per Ghz than the Pentium M, which is in turn >30% faster per Ghz than the P4. So that 3Ghz Conroe will be approximately equal to a dual-core 4.6Ghz Pentium 4 and put out 65W of heat/power.

Better cache handling, faster bus, 4-issue wide core. 35W TDP for Mobiles, 65W desktops, 85W for servers. Sounds like the best of all worlds to me.

Check out this Inq article:
http://www.theinquirer.net/?article=25623 [theinquirer.net]

Re:Now we know... (1)

wpmegee (325603) | more than 8 years ago | (#13381867)

I can't multiply today, should be 4.8ghz in the last sentence of the first paragraph.

woot! (5, Funny)

Anonymous Coward | more than 8 years ago | (#13381632)

Awesome. Now I'll be able to run 4 times as many CPUs with my 1000w PSU.

Re:woot! (1, Funny)

OmniVector (569062) | more than 8 years ago | (#13381740)

In a beowulf cluster?

Now that Apple has joined the Intel bandwagon ... (-1, Troll)

Anonymous Coward | more than 8 years ago | (#13381638)

I am sooooo rooting for AMD.

Go Advanced Micro !!!

No hardware DRM !!!!

Places (5, Interesting)

kevin_conaway (585204) | more than 8 years ago | (#13381653)

Ok, Conroe [sjra.net] appears to be a lake in Texas, Merom [webshots.com] is a bluff near the Wabash river in Indiana...where/what was the inspiration for Woodcrest?

Re:Places (0)

Anonymous Coward | more than 8 years ago | (#13381702)

The designer's mother's uncle's birthplace.

Re:Places (5, Funny)

Trip Ericson (864747) | more than 8 years ago | (#13381704)

where/what was the inspiration for Woodcrest? Well, a crest is like a high point or a "peak," and wood is... Oh dear.

Re:Places (0)

Anonymous Coward | more than 8 years ago | (#13381817)

Conroe is a city an hour north of Houston which has a fairly large lake near it, named after the city. :)

Re:Places (2, Funny)

Burdell (228580) | more than 8 years ago | (#13381848)

Woodcrest is a street a block over from my parents' house in Huntsville, AL, but I don't think any Intel folks live there.

Re:Places (0)

Anonymous Coward | more than 8 years ago | (#13381851)

Conroe [google.com] is an entire city in Texas, about 50 miles north of Houston.

Re:Places (0)

Anonymous Coward | more than 8 years ago | (#13381915)

And Conroe is just a few miles south of Huntsville, the death capitol of Texas (making it the death capitol of the United States). I wonder if that implies anything?

Re:Places (0)

Anonymous Coward | more than 8 years ago | (#13381918)

I live in Woodcrest - It's a development in Cherry Hill, NJ. About 15 minutes outside of Philadelphia, PA.

we still care about performance too (4, Interesting)

iggymanz (596061) | more than 8 years ago | (#13381654)

So instead of clock speed how about execution speed of standard benchmarks on a reference machine? Or would that show how much they suck per dollar next to AMD?

More detais: (5, Informative)

Anonymous Coward | more than 8 years ago | (#13381656)

Enough touch and go, I see (2, Insightful)

milktoastman (572643) | more than 8 years ago | (#13381658)

They've taken a little cooler and stopped chasing their speed dragon to make a more solid, well-organized, and efficient architecture. Once they've established this 'way point' of stability, then they can get back on the zip zoom bus. I'd like to stand in on the silicon vista, if I were tiny, and see how much less litter they've got hooked up down there. Copper plate thatches, cat scratches, now Intel has the cool down rock and roll.

Neuronal Grids (0)

andrew1222 (906582) | more than 8 years ago | (#13381660)

Although probably not their intention, Intel is paving the way for high-density grids of "neuronal" multi-processors (that's a word, right?).

Might be OT: So neurons are super low power, extremely highly connected, relatively simple logic gates.

What happens when you have low power, highly connected and relatively complex logic processors connected in a grid? Does the processor complexity reduce the effectiveness of the interconnectivity?

Re:Neuronal Grids (0, Offtopic)

gardyloo (512791) | more than 8 years ago | (#13381764)

So neurons are super low power, extremely highly connected, relatively simple logic gates.

    I could be off-base here, but I think the thinking (heh) is that neurons are NOT relatively simple logic gates (which I suppose I'd characterize as being *like* your common NAND, OR, NOT operators, etc.). In particular, neurons are famously non binary; there are a lot more stimuli which go into making a neuron fire than just two inputs. Too, one can get radically different firing patterns out of neurons than just ON or OFF. This, coupled with the high interconnectivity of the brain, means massive complexity.

Re:Neuronal Grids (1)

andrew1222 (906582) | more than 8 years ago | (#13381881)

neurons are NOT relatively simple logic gates

i agree neurons are not simple from a computational standpoint. Certainly neurons' forte is to get a fuzzy (analog) result out of a super large amount of input.

i guess what i was trying to do was to compare the high connectivity simple logic (analog, neurons) to high connectivity complex logic (CPU instruction set).

Actually... (4, Informative)

EconolineCrush (659729) | more than 8 years ago | (#13381665)

This post originally linked The Tech Report's coverage [techreport.com] . Not sure why the mod changed the link.

TR also has additional details [techreport.com] on the architecture itself.

Re:Actually... (1)

dema (103780) | more than 8 years ago | (#13381708)

Not sure why the mod changed the link.

More pretty pictures. This is slashdot, I don't want to have to read anything (:

10x less power? (0)

Anonymous Coward | more than 8 years ago | (#13381667)

5x more power per watt...
will they be half as fast as my 'all your watt are belong to us' prescott?? ;P

Re:10x less power? (0, Offtopic)

milktoastman (572643) | more than 8 years ago | (#13381744)

Preston is the better name for the hog, but corporate lackeys didn't have that dream because of a high pile of snow just inside the hall entryway. Seems unbelievable, yes, but I saw the uncensored memo. They had a machine do it, and weren't careful about the commands--meaning, of course, they didn't get what they bargained for and a mount was formed in their path. No kitties got left out, however.

Re:10x less power? (0)

Anonymous Coward | more than 8 years ago | (#13381791)

oops that's 5x more performance per watt...
still... my prescott will cook breakfast if you throw eggs on the thing... that's gotta be worth something :P

Yes, but will they be AMD64 compatible? (0, Funny)

Anonymous Coward | more than 8 years ago | (#13381669)

That is the most important question. I'd hate to buy one of these also rans and find out that it is no where near as powerful as the industry leader.

The real question is... (1)

rob_squared (821479) | more than 8 years ago | (#13381671)

...does it still have an insane number of pipelines?

And I bet you were expecting me to ask if it runs linux.

Re:The real question is... (0)

Anonymous Coward | more than 8 years ago | (#13381901)

yo dumbass. it is not the number of pipelines that was insane but the number of "stages" in the pipeline. and no it does not have the same insane number of stages, it has been reduced to 14.

Yes, that's nice, but... (3, Funny)

BandwidthHog (257320) | more than 8 years ago | (#13381692)

Does it run Lin--, err, Mac OS X?

Re:Yes, that's nice, but... (1)

javaxman (705658) | more than 8 years ago | (#13381878)

Does it run Lin--, err, Mac OS X?

Modded funny, but this roadmap, including the fact that

Woodcrest, Conroe and Merom. All of these CPUs will be built on a 65nm process and will be 64-bit enabled.
compared with what IBM and FreeScale were doing with the PPC ( not a heck of a lot ), show us exactly why Apple decided to move towards Intel. The whole Intel-provides-entire-chipsets-complete-with-DRM thing is just icing on the cake for Apple. 64-bit high-performance low-power chips with real, ongoing R&D and a guarantee of performance parity with the rest of the PC world... it's pretty clear how Apple's two-year switch to Intel corresponds to the release schedule Intel has committed to:
The new processors will be available in the 2H of 2006

instruction set? (4, Interesting)

John_Sauter (595980) | more than 8 years ago | (#13381694)

Does anybody know what instruction set these three new processors implement? The article states that these are 64-bit CPUs, but doesn't say whether they feature the AMD64 or the Itanium instruction set.
        John Sauter (J_Sauter@Empire.Net)

Re:instruction set? (1)

Harbinjer (260165) | more than 8 years ago | (#13381757)

Its probably AMD64...err EM64T or whatever they called it. I'm sure its software compatible with today's Intel processors.

Re:instruction set? (1)

bflong (107195) | more than 8 years ago | (#13381800)

All I can say is that Intel would have to be increadibly braindead to even think about trying to get people to switch to the Itanium instruction set after the embarresment of the AMD64 fiasco. They must be using the AMD64 instruction set. In fact, since they have a slide that shows Windows XP 64bit compatibility, I'm going to say that I will eat one of my iguanna's (not my best one though) if they are using the Itanic instruction set and not AMD64.

Re:instruction set? (1)

John_Sauter (595980) | more than 8 years ago | (#13381906)

All I can say is that Intel would have to be increadibly braindead to even think about trying to get people to switch to the Itanium instruction set after the embarresment of the AMD64 fiasco. They must be using the AMD64 instruction set. In fact, since they have a slide that shows Windows XP 64bit compatibility, I'm going to say that I will eat one of my iguanna's (not my best one though) if they are using the Itanic instruction set and not AMD64.
Keep in mind that Microsoft Windows does support Itanium [microsoft.com] .
        John Sauter (J_Sauter@Empire.Net)

Re:instruction set? (5, Informative)

Anonymous Coward | more than 8 years ago | (#13381913)

... it clearly states that it combines the 64bit and netburst from the P4. M$ already told intel to fcuk off when it came to itanium 64bit. Hence EM64T that they have now which is compatible with AMD's implementation.

"combining the lessons learned from the Pentium 4's NetBurst and Pentium M's Banias architectures. To put it bluntly, the next-generation microprocessor architecture borrows the FSB and 64-bit capabilities of NetBurst and combines it with the power saving features of the Pentium M platform."

What about performance (1, Interesting)

Harbinjer (260165) | more than 8 years ago | (#13381696)

So its the revamped P3 once again. I'm glad they optimized it for power instead of marketing, but will it scale to higher clockspeeds? Will it be able to reach 3 Ghz in the next 2 years?

Re:What about performance (2, Informative)

FadedTimes (581715) | more than 8 years ago | (#13381799)

higher clock speeds isn't the only way to get more performance.

At 14 stages, the main pipeline will be a little bit longer than current Pentium M processors. The cores will be a wider, more parallel design capable of issuing, executing, and retiring four instructions at once. (Current x86 processors are generally three-issue.) The CPU will, of course, feature out-of-order instruction execution and will also have deeper buffers than current Intel processors. These design changes should give the new architecture significantly more performance per clock, and somewhat consequently, higher performance per watt.

Re:What about performance (2, Funny)

LnxAddct (679316) | more than 8 years ago | (#13381856)

I believe upoon release it will be 4.6 Ghz.
Regards,
Steve

Is this the right direction? (5, Interesting)

loose_cannon_gamer (857933) | more than 8 years ago | (#13381699)

Don't get me wrong, I don't care for my house being heated by computer heat the way it is now by my small LAN. But...

Fundamentally, most markets of any age undergo specialization, niches form, and those most fitted to the niches, do best. But having a unified architecture between server / laptop / desktop flies in the face of that; it either claims there is no niche market anywhere, or that there is a "killer chip" which fits all niches better than anything else.

Now, I can guess what Intel would choose of those options, but is there something about the chip industry that makes it immune to this specialization idea? What am I missing?

0.5W (2, Insightful)

blamanj (253811) | more than 8 years ago | (#13381716)

The reduction in power will enable a new class of devices to be created at the 0.5W marker - the Handtop.

Also known as the video iPod, perhaps?

Is this the end of HT? (5, Interesting)

BikeRacer (810473) | more than 8 years ago | (#13381726)

The screenshots make it look like Intel isn't including HT with this next gen core. Is that because it's likely the pipeline is shorter? I thought it would be uber-cool to have a dual-core CPU with HT for some awesome synthetic 4-core action. But, I guess the real question is: Should I care about HT anymore?

Re:Is this the end of HT? (0)

Anonymous Coward | more than 8 years ago | (#13381858)

yes you should, because its insecure and generally homosexual.

Re:Is this the end of HT? (0)

Anonymous Coward | more than 8 years ago | (#13381883)

The Pentium D EE 840 is designed exactly as you described. It has two Prescott cores in a single package, for a total of 4 logical processors. It works extremely well for heavy multitaskers or multithreaded apps.

So in other words? (1)

coopaq (601975) | more than 8 years ago | (#13381728)

Otellini claimed that Conroe will offer five times the performance per watt of the company's current desktop chips.

We've been able to lower the power consumption by 5 times, but really cannot make a "faster" processor?

So now laptops will have a super longer battery life and that's good.

Maybe you'll need less fans and thats good.

But what I really want is double the performance every 18 months like the old days.

NOISY FANS BE DAMNED!

Transmeta was there first (4, Insightful)

Vengeance (46019) | more than 8 years ago | (#13381743)

It's been YEARS since Transmeta began preaching performance/watt, and it looks like right now, when Transmeta has some big contracts (with Sony, Microsoft, Fujitsu, etc) beginning to pay off, Intel finally figures it out.

Of course, Transmeta's already GOT the technology to cut leakage by tremendous amounts... Given that they are no longer a direct competitor of Intel's, it would make some sense if Intel simply licensed Transmeta's LongRun2 tech. But what do I know? I'm always foolishly choosing the better technology instead of the better marketing.

Arm was there earlier (1)

nurb432 (527695) | more than 8 years ago | (#13381907)

ARM processors were power friendly before transmeta even appeared....

But yes, they went about it differently.

err.. but what does it actually look like? (0)

Anonymous Coward | more than 8 years ago | (#13381752)

Am I the only one not seeing much of what will be inside the new chips and just a load of intel propaganda?

The question is, have the stolen intergrated controllers yet?

Gee, who are they aiming at? (1)

ChipMonk (711367) | more than 8 years ago | (#13381755)

You don't suppose the Conroe processor is a slam at the Crusoe's near-has-been status, do you?

Re:Gee, who are they aiming at? (1)

Vengeance (46019) | more than 8 years ago | (#13381859)

Crusoe is obsolete and near end-of-life.

Efficeon is the more recent generation of Transmeta processor.

Better than EITHER of those, though, is their LongRun2 technology which can help any chip (particularly at 90nm) to use less power.

So much for Moore's Law (5, Insightful)

SiliconEntity (448450) | more than 8 years ago | (#13381779)

So much for Moore's Law. So much for the supposedly inexorable march of technology. So much for that nonsense about increasing CPU performance, you all didn't really want 4 GHz anyway, did you?

People have been predicting the demise of Moore's Law for years. It's funny that it's happened and nobody seems to notice.

Now that Moog's dead, so is Moore's Law (1)

WillAffleckUW (858324) | more than 8 years ago | (#13381809)

So much for Moore's Law. So much for the supposedly inexorable march of technology. So much for that nonsense about increasing CPU performance, you all didn't really want 4 GHz anyway, did you?

No, I want faster wireless and hardline cable/DSL speeds like I can get on Internet2, with really fat fast pipes.

Who cares about processor speed? Just stop melting my candy bars if I leave them on the case - cut the power consumption and save a few barrels of oil.

Re:So much for Moore's Law (2, Informative)

Anonymous Coward | more than 8 years ago | (#13381852)

Moore's Law does not make a statement about performance. It makes a statement about the number of transistors in a certain area.

http://www.webopedia.com/TERM/M/Moores_Law.html [webopedia.com]

Re:So much for Moore's Law (1)

Just Some Guy (3352) | more than 8 years ago | (#13381884)

So much for that nonsense about increasing CPU performance

I didn't see anything about dropping performance, just cycles. What are you alluding to?

Moore's Law is about components per sq. cm. (1)

crovira (10242) | more than 8 years ago | (#13381893)

Hz doesn't enter into it. (well not directly except that light speed is constant and as long as they don't increase then die size the component have to get faster if only because the electrons have the approximately same distance to go from one side of the die to the other.)

CPU Rating (2, Funny)

Neoprofin (871029) | more than 8 years ago | (#13381792)

But if Intel stops going for higher clockspeeds how am I supposed to know how impressive an AMD 3200+ is? I need my completely reliant rating system intact! I guess the FX chips have already destroyed my ability to rate things simply.

Take that you money-grubbing energy companies! (0)

Anonymous Coward | more than 8 years ago | (#13381794)

Only North Koreans need 850-watt desktop CPUs!

So there!

Oh wait, only North Koreans need 850-milliwatt desktop CPUs. Yeah, that's it.

mod +5 funny -15 stupid

power saving servers (4, Insightful)

ndansmith (582590) | more than 8 years ago | (#13381806)

I am glad to see that Intel is addressing power consumption with the server chip Woodcrest. After all, desktops and laptops are small potatoes compared to servers when it comes to power usage. For corporations with large server implementations, I could see this saving a lot of power (=$). Good move for Intel; lower power bills are good leverage for new technology purchases -- many of us used that same argument to upgrade from CRTs to LCDs. It is nice to finally have something to be excited about from Intel again.

Power Consumption (4, Insightful)

Botia (855350) | more than 8 years ago | (#13381838)

This is something Intel needs to do to stay in the CPU market. Their NetBurst architecture has allowed AMD to capture the hearts of the enthusiests as it is a better processor. (Note: the mass market has many other factors besides which processor is best in determining sales.)

While I currently favor AMD's processors, The Pentium M is a magnificant piece of hardware. With Intel basing their future processors on the Pentium M they are going to give AMD a run for their money. This will force AMD to drop their prices to a more reasonable level.

The one thing Intel is doing that IMHO is wrong is changing the definition of performance from clock speed to performance/watt. This tells us nothing of the performance of the processor or the power required to run it. Instead we should have two basic measurements for all processors: performace and power consumption. Most people are able to do simple calculations such as division on their own or with a calculator. The is no need to hide the actual performance from the end users.

From TechReport with actually useful info (5, Informative)

Kaa (21510) | more than 8 years ago | (#13381850)

Instead of Anand's pictures of PowerPoint slides, here's some actual info from TechReport:

"IDF -- On the heels of Intel's announcement of a single, common CPU architecture intended to drive its mobile, desktop, and server platforms, the company has divulged additional details of that microarchitecture. This dual-core CPU design will, as we've reported, support an array of Intel technologies, including 64-bit EM64T compatibility, virtualization, enhanced security, and active management capabilities. Intel says the new chips will deliver big improvements in performance per watt, especially compared to its Netburst-based offerings.

At 14 stages, the main pipeline will be a little bit longer than current Pentium M processors. The cores will be a wider, more parallel design capable of issuing, executing, and retiring four instructions at once. (Current x86 processors are generally three-issue.) The CPU will, of course, feature out-of-order instruction execution and will also have deeper buffers than current Intel processors. These design changes should give the new architecture significantly more performance per clock, and somewhat consequently, higher performance per watt.

Unlike Intel's current dual-core CPU designs, which don't really share resources or communicate with one another except over the front-side bus, this new design looks to be a much more intentionally multicore design. The on-die L2 cache will be shared between the two cores, and Intel says the relative bandwidth per core will be higher than its current chips. L2 cache size is widely scalable to different sizes for different products. The L1 caches will remain separate and tied to a specific core, but the CPU will be able to transfer data directly from one core's L1 cache to another. Naturally, these CPUs will thus have two cores on a single die.

The first implementation of the architecture will not include Hyper-Threading, but Intel (somewhat cryptically) says to expect additional threads over time. I don't believe that means HT capability will be built into silicon but not initially made active, because Intel expressly cited transistor budget as a reason for excluding HT.

On the memory front, the new architecture is slated to have the ever-present "improved pre-fetch" of data into cache, and it will also include what Intel calls "memory disambiguation." That sounds an awful lot like a NUMA arrangement similar to what's found on AMD's Opteron, but I don't believe it is. This feature seems to be related to a speculative load capability instead..

The server version of the new Intel architecture, code-named Woodcrest, will feature two cores. Intel is also talking about Whitefield, which has as much as twice the L2 cache of Woodcrest and four execution cores.

The company has decided against assigning a codename to this new, common processor microarchitecture, curiously enough. As we've noted, the first CPUs based on this design will be available in the second half of 2006 and built using Intel's 65nm fabrication process. "

Name game... (1, Interesting)

TrevorB (57780) | more than 8 years ago | (#13381863)

'Conroe', 'Merom', and 'Woodcrest'. Hmmfph!

Enough with the name game, where's my Moore's Law mandated doubling of CPU speed every 18 months!

And flying cars, dammit they're due too. I want my flying car running on my 12Ghz "Zoomy" processor.

Lower power = more cores... (2, Insightful)

MosesJones (55544) | more than 8 years ago | (#13381912)


With everyone chasing multi-core rather than clock-rate this isn't really a suprise. If you want to run 4 cores on one die you clearly need to reduce the power consumption of each of those cores over what is done today.

It clearly helps with laptops, which of course will be multi-core themselves in a year or so.

What an odd day it will be when I start ordering either a "2-way" or "4-way" laptop.

Bigger than IE? (5, Interesting)

otis wildflower (4889) | more than 8 years ago | (#13381924)

I have to wonder if Intel basically ditching the last 5 years of CPU development in favor of their Israeli skunkworks ranks at or above the famous Microsoft IE U-turn?

I mean, Intel sold millions and spent billions on Netbu(r|)st, and hit the wall far before the 5+ghz figures bandied about back in the day. This is basically ctrl-alt-del on a large part of their roadmap, though I'm sure they'll still be selling 'traditional' P4s for awhile.
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>