Slashdot Mirror
Intel Launches Power-Efficient Penryn Processors
Bergkamp10 writes "Over the weekend Intel launched its long-awaited new 'Penryn' line of power-efficient microprocessors, designed to deliver better graphics and application performance as well as virtualization capabilities.
The processors are the first to use high-k metal-gate transistors, which makes them faster and less leaky compared with earlier processors that have silicon gates. The processor is lead free and by next year Intel is planning to produce chips that are halogen free, making them more environmentally friendly.
Penryn processors jump to higher clock rates and feature cache and design improvements that boost the processors' performance compared with earlier 65-nm processors, which should attract the interest of business workstation users and gamers looking for improved system and media performance."
While Penryn is a small increase in performance, it is not a big change in the architecture. Instead of upgrading to Penryn, customers can expect Nehalem, the next major revision in the Intel architecture, was responsible for the release in 2008.
At the Intel Developer Forum in San Francisco in September Intel showed, and said it would be a better yield per watt and better system performance through its Quick Path Interconnect system architecture. Nehalem chips will also provide a memory controller integrated and improved communication between system components.
It's sad that the industry is still sticking to the x86 instruction set. It should've been replaced a long time ago with a pure RISC instruction set especially now with the quest for less power-hungry chips. The Power/PowerPC architecture was good but because they didn't have enough demand, the price was high and development low. A few failures (compare to Netburst) and their customers (amongst them Apple) went running to the competitors.
We're still running PowerPC here because they're low-power and do certain mathematics very well (I'm not the science guy). Hopefully Apple will switch back to PowerPC or so now that they are fully "Universal" and IBM has some promising chips lined up.
Custom electronics and digital signage for your business: www.evcircuits.com
Don't know whether it's my adblock or what, but I don't see any story at that link. Here's an alternative link & story: http://www.computerworld.com/action/article.do?command=viewArticleBasic&articleId=9046362&intsrc=news_ts_head
... And it's not just this generation. Intel will just crank this thing faster and faster, and it will be a challenge for AMD to respond."
Intel's 45nm Penryn desktop expected to pack a big wallop
Sharon Gaudin
November 12, 2007 (Computerworld) Intel Corp.'s new 45-nanometer chip for the desktop, part of the newly released Penryn family, should give gamers, researchers and serious multitaskers a significant performance boost, according to analysts.
And that is not good news for rival Advanced Micro Devices Inc., which recently started shipping its quad-core Barcelona processor -- built using a 65nm manufacturing process. AMD isn't expected to move to 45nm technology until the second half of 2008.
The release of Intel's Core 2 Extreme quad-core processor came as part of a larger release of Penryn processors, including 15 server dual-core and quad-core 45nm Hi-k Intel Xeon processors. To make the move from 65nm to 45nm processors, Intel designed a new transistor, stemming leakage and improving energy efficiency. With 820 million of these newly designed transistors in just one chip, Intel is calling it one of its biggest advancements.
On the desktop side, all of this should add up to a major performance boost.
Dean Freeman, an analyst at Gartner Inc., said he expects Penryn will be 20% to 50% faster than Intel's previous chip releases in general purpose applications and 10% to 40% faster in technical applications, multimedia and games. For example, someone using Microsoft Excel or PowerPoint should see a 20% to 50% boost, while an Adobe Photoshop user should see a 10% to 40% increase.
"It's going to mean a faster desktop. It's a more powerful tool, operating applications faster," said Freeman. "Basically, it means that for those of us who are concerned about the speed at which applications work on our desktop, the good news is that it will work faster."
Boyd Davis, a general manager at Intel, said a larger L2 cache and support for new SSE4 media instructions are part of the chip's performance boost.
And while no one will be expectantly lining up around the block for the new chips, Charles King, an analyst at Pund-IT Inc. in Hayward, Calif., said that Penryn is a "step up" from previous Intel designs and should appeal to the high-end gamers and workstation customers.
"The Penryn architecture blends notably high performance with significant steps forward in power efficiency," he added. "It's a bit like a new sports car that hits a higher top speed than previous models, while simultaneously delivering better gas mileage."
Dan Olds, an analyst at Gabriel Consulting Group Inc., said the Penryn desktop won't just appeal to the gaming community. Power users with more than 10 applications open at once, video editors and researchers are going to be eager for a performance boost.
Olds added that with this "big step forward" for desktop performance, he's not sure what AMD has to respond with.
"AMD has their work cut out for them," he said. "[Penryn] will be hands-down the fastest desktop chips in existence
Intel last month opened a new $3 billion manufacturing facility in Chandler, Ariz., kicking off mass production of its new 45nm microprocessors. Freeman has previously noted that the opening of the new Arizona facility, named Fab 32, is expected to boost production of 45nm wafers from 5,000 a month in the pilot program at an Oregon facility to 25,000 to 30,000 wafers a month. Davis added that two other new 45nm fabrication sites -- one in Israel and one in New Mexico -- are expected to go online, boosting 45nm production over Intel's 65nm production
...faster and less leaky... What a coincidence! Precisely the traits that I look for when switching condom brands!I'm sure they mean eliminating halogenated organic compound or something similar Otherwise I think eliminating halogens from chips themselves is just a drop in the ocean. A deep, halogen salt enriched ocean.
The world is made by those who show up for the job.
Intel engineers should not be allowed to name the new chip lines after their D&D characters.
Virginia is for lovers. EVE is for griefers.
Why is there so much emphasis on size (as in 45nm) for these things? Does making it smaller make it inherently faster or more efficient? Why? I've looked around (well, I looked at wikipedia anyway) and it's still not clear what advantage the smaller size has.
Free the Quark 3 from asymptotic confinement! Bring your charm! Don't get down! All colours and flavours welcome!
The link to Computerworld is just a title and no article. Penryn must have left the writers speechless...
I believe that x86 already has many of the benefits of RISC chips incorporated into them. Way back in 1995 http://en.wikipedia.org/wiki/X86#Chronology.Intel added to the Pentium Pro a RISC core. From the Wiki article, "During execution, current x86 processors employ a few extra decoding steps to split most instructions into smaller pieces, micro-ops, which are readily executed by a micro-architecture that could be (simplistically) described as a RISC-machine without the usual load/store limitations."
As for PowerPC Macs, I doubt it. The switch to Intel is what made most new Mac users switch because there was no longer a risk of not being able to run the one Windoze program they might need. If Mac ever went to a non-mainstream CPU again it would be a big big mistake.
but not so good for Transmeta who have power saving chips long before Intel invent them.
I've followed the stories about these machines since the hype about their "V8" setups, and even now they miss the important info: Who is going to ship systems with these in them, how much and how soon? Oh, and Intel should be bitchslapped for not making a multiprocessor motherboard that takes the Socket T (LGA775).
These days:
One of the real problems with x86-32 was the low number of registers, which resulted in many stack spills. x86-64 added 8 more general purpose registers, and the situation is much better (that's why most people see a 10-20% speedup when migrating to x86-64 - more registers). Sure, it'd be better if we had 32 registers ... but again, with 16 registers life is decent.
The Raven
When TFA is not informative, seek the source. Enjoy.
The game.
biopowered.co.uk - catalytically cracking triglycerides for home automotive use since 2008. Just say no to big oil!
While I realize that GPUs may be doing more calculations that CPUs (I'm not a Programmer), the power consumption of many graphics cards/GPUs at idle is getting ridiculous (some are 100 to 200 watts), never mind what is needed during gaming. On the one hand, I would buy an on-board accelerator or a cheap PCI-x with the knowledge it won't need additional power to the board, but for the odd games that I play, I need more GPU power. Game consoles' -as a whole like the X360- consumes about 200 Watts @ max draw. This is for the whole system - may PC video cards draw this for the video card alone!
On the subject of these new chips, I'm quite interested in building a new desktop with a Penryn - been a long time since I upgraded. I'm particularly interested in the Xeon chips because previous designs from Intel included fanless/passive coolers. If this continues on the Penryn, I'll definitely buy one. I'm all for a quieter desktop.
The NexGen Nx586 was actually the first x86 chip to have a risc core... It came out in 1994.
Intel's own spec sheet shows the best of these (and only a single one at that) with a TDP of 65W.
Call me a pessimist, but my two main systems peak at less than that at the wall, and I have yet to find them too slow for any given task (though I admittedly don't do much "twitch" gaming).
Might this be followed by a price drop in their current offerings? I'm about to buy a new C2D, so I'd wait if it meant a significant savings.
"Ask not what your country can do for you." --John F. Kennedy
Just how much Hafnium is there in the world, and has Intel cornered the supply before AMD could get their hands on any of if?
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
What I want to know is, when are they going to finally make the oceans halogen-free?
I'm more interested in what high efficiency chips like this could do for my server room. I have two huge air conditioners to cool a 10'x20' data center. They simply can no longer keep up with the heat coming from the servers. I could install newer, better, bigger air conditioners but that seems to be attacking the wrong end of the problem. VM, 2.5" sata raid, and SAN have all helped somewhat, but the biggest heat problem is still the processors.
http://www.CelloFourteGroupie.net
What the FUCK is a silicon gate people? This type of tech journalism really grinds my gears. Should we go back to the basics? A standard CMOS transistor is basically a stack comprised of a silicon substrate, an insulator, and a polysilicon gate. The new thing that Intel is doing is replacing the insulator with a high-K hafnium based material instead of the silicon dioxide that's been used for the past 40 years. And the polysilicon is being replaced by metal. The metal is needed due to the work function discrepancy between polysilicon and the high-K insulator. But cheese and rice people, calling the old style gate a silicon gate does a great disservice to the people who have spent the better part of their lives perfecting the silicon dioxide and polysilicon.
Is Penryn the core name or the CPU series name? Does this mean the end of the Pentium brand that we have all come to know and love and hate and love again?
You can close your eyes to reality but not to memories.
This is a bit like saying that a truck with a rocket plane inside has 'many of the features of a rocket plane.' The point of RISC is to manage the complexity of the processor, minimise the amount of unnecessary work, and shift load onto software wherever that has zero or negative performance impact. By, effectively, adding an on-the-fly compiler in hardware, the Intel engineers have not done this, even if they have streamlined the back-end execution engine using tricks published in the RISC literature.
But Intel's traditional expertise is in memory and process—and since caches now dwarf execution units, well, there's no need to worry about doing it 'right' anymore! And sadly, I almost mean that.
The situation is common in computing. The engineering design of familiar systems such as C++ or the Web itself is nothing short of incoherent: layer upon layer of patches and transformative interfaces where a little planning and a more minimalist approach would reduce both resource consumption and programmer effort all around. But performance and efficiency are nowhere near as important to industry as back-compatibility and, well, marketing; and the overheads are concealed by providing capacity that honestly grows much faster than the task at hand.
Well, bear some things in mind:
1. At one point in time there was a substantial difference between RISC and CISC architectures. CPUs had tiny budgets of transistors (almost homeopathic, by today's standards), and there was a real design decision where you put those transistors. You could have more registers (RISC) or a more complex decoder (CISC), but not both. (And that already gives you an idea about the kinds of transistor budgets I'm talking about, if having 16 or 32 registers instead of 1 to 8 actually made a difference.)
Both sides had their advantages, btw. If it were that bleeding obvious that RISC = teh winner and CISC = teh loser, a lot of history would be different.
The difference narrowed a lot over time, though, so neither is purely CISC or RISC any more (except marketting bullshit or fanboy wars.) Neither the original RISC idea nor the CISC one scaled past a point, so now we have largely the same weird hybrid in both camps.
E.g., the Altivec instruction set on PowerPC is the exact opposite of what the original RISC idea was. The very idea of RISC was never to implement in hardware what a compiler would do for you in software. So the very idea of having whole procedures and loops coded in the CPU instead of in software would have seemed the bloody opposite of all that RISC is about, back in the day.
At any rate, what both are today is what previously used to be called a microcoded architecture. It's sorta like having a CPU inside a CPU. The smaller one inside works on much simpler operations, but an instruction of the "outer" CPU translates into several of those micro-operations. Which in turn are pipelined, reordered in flight, etc, to have them execute faster.
What both sides are doing nowadays for marketting reasons is basically calling the inner architecture "RISC", because marketing really likes that term, and the lemmings have been already conditioned to get excited when they hear "RISC". Really, PowerPC's architecture is only "RISC" on account of basically "yeah, but deep down inside it's still sorta RISC like"... and ironically the x86's can make the exact same claim too.
At any rate, whether you want to call that RISC or not, once you look inside it, both the PowerPC and the Pentiums/Athlons have nearly identical architectures and modules. Sure, the implementation details differ, and some have advantages over other implementations (the Netburst ones had too long pipes, while a G4 had a tiny pipe, so the G4 did have better IPC), but essentially they both are based on the exact same architecture. Neither is more RISC than the other. We can lay that RISC-vs-CISC war to rest.
2. That said, the x86 still was somewhat hampered by the lack of more general purpose registers. Although the compilers and the CPU itself did optimize heavily around the problem, they didn't always do the optimal job.
That has changed in the 64 bit version, though. AMD went and doubled the number of registers for programs running in 64 bit mode, and Intel had to use the same set of instructions so they have that too nowadays.
The performance penalty of that architecture basically became a lot lower than it was in the days of G4 vs Pentium 4 flame wars.
A polar bear is a cartesian bear after a coordinate transform.
anyone care to calculate the ratio of lead and halogens in intels world output to lead acid car batterys or american's swimming pools ?
talk about BS
(swimming pools use large amounts of that well known halogen, chlorine)
An often overlooked benefit of the way that modern IA32 processors achieve high performance through translating the CISC x86 instructions into microcode instructions is that the chip designers are free to change the internal microcode architecture for every CPU in order to implement new optimizations or to tune the microcode language for the particular chip's strengths. If we were all coding (or if our compilers were coding for us) in this RISCy microcode, then we, or the compiler, would have to do the optimizations that the CPU can do in its translation to microcode. I agree that the Power architecture is pretty cool, but I'm tired of hearing people bash the Intel x86 architecture for its "obsolete" nature. As long as it is the fastest and best thing I can buy for a reasonable amount of money, it's my top choice.
Dr Superlove 300ml. I use my powers for awesome
The problem is not the halogen atoms themselves, but the chemical reactivity a carbon atom gets when it's bonded to a halogen atom. That is, an organic compound that contains carbon-chlorine bonds is obnoxious not because of the chlorine atoms, but because the chlorine atoms "activate" the carbon atoms to which they're bonded (more precisely they make it far easier for nucleophilic and radical reactions to happen at the carbon atom) so that the carbon atom can do chemistry inside you (or inside some other animal) that you really don't want to happen, e.g. mutating your DNA. This is why chlorinated organic compounds (e.g. PCBs, perc, carbon tet) tend to be tightly regulated.
The halogens themselves (Cl_2 et cetera) and the halogen-oxygen compounds you find in swimming pools (e.g. hypochlorite anions) are merely noxiously caustic, like acid. At high enough concentrations they might scar your lungs and skin, or kill you, but they won't seep into your tissues and do insidious chemistry that gives you cancer or lupus, and they're quite harmless at low concentrations (e.g. what you find in your pool, or in seawater).
If this is how it ends for AMD, this is how it goes.
AMD is fighting a losing battle. Intel defined the current market and AMD cannot beat them at their own game. They are condemned to always play second fiddle unless they can find a way to redefine the market. They can only do so by reassessing the current state of the art in multicore CPU architecture and computer programming and correct what is wrong with it. And there is a lot that is wrong with it. I call it The Age of Crappy Concurrency. Check it out.
Now that the industry is transitioning to massive parallelism, AMD has the chance of a lifetime to change the computing landscape in its favor and leave Intel and everybody else in the dust.
RISC architecture is going to change everything!
Didn't know Intel was into the dietary supplement business. Anyone know where I can pick up a bag of these?
This sig isn't original enough, it's time to come up with something witty...
Once upon a time (1970's), everybody used metal for their FET gates. Those aluminum gates are where we got the names MOSFET (Metal-Oxide-Silicon Field Effect Transistor) and CMOS (Complementary MOSFET). In the 1980's, pretty much every fab gave up metal gates for the polysilicon that has been used since, amidst various enhancements in polysilicon deposition technology, self aligned gates, etc.
Now, the trend seems to be to return to the metal gates of yesteryear and ditch the oxide (the 'O' in MOSFET) for high-k dielectrics (not high-k metals, as the summary seems to say)...
That's all well and good, but I have one question... when will we get around to updating the term "CMOS"?
>> Standing on head makes smile of frown, but rest of face also upside down.
You are forgetting one of the most important factors in business. Time to market. A fantastic product that's been optimized as much as possible is wonderful, but it won't matter if someone else already has a similar product and controls the marketplace (See how hard AMD has to work to take market share from Intel, or Apple from Microsoft.) Once someone has the market (and the mind share) it's very hard to win it back. So businesses concentrate on getting their product to market as quickly as possible. Yes, that means that products like the Penryn may not be as efficient as possible, but if they are good enough and in the marketplace soon enough, then that is enough to make the company money. Also keep in mind, as I understand it, the back end of the Intel processors may be changing greatly ever few years if the engineers find a better way to speed up their processors. So the underlying micro-code may only have a few years to be worked on before it is replaced with something new. That will greatly limit the amount of time the engineers have to optimize the code, and limit the amount of time and money the company wants to put in to such efforts.
I'm just wondering which will end first - Moores law, or the number of river names left in Washington. For those of you who don't know, all of Intels chip names are named after rivers in Washington state.
..........FULL STOP.
....but every time I look at a motherboard for a intel processor I think of this quote.
"People can have the Model T in any color...so long as it's black." -- Henry Ford
If some manufacturer could sell a 1GHz CPU for $5, it would blow away everything else on that price/performance chart but would not run most modern applications. There are only a half-dozen of the high-end desktop processors anyone should even consider purchasing for a new PC. Intel and AMD both have processors in that category, and apparently AMD is ahead in the price/performance metric. In all of the purely performance-based reviews however, Intel has held most of the top spots.
You're correct that the x86 instruction set is still cruft, and a pure RISC CPU is theoretically more efficient. However, the real world disadvantage of x86 support is minimal. With each die shrink, the x86 to micro-op translator occupies less die space proportionally, and the advantages of the installed hardware and software base gives x86 CPUs a huge lead in economies of scale.
I know we're both just putting different spins on the same facts, but in the end, practical considerations outweigh engineering purity. x86 is even competing against ARM in the embedded space now, not just in higher powered UMPCs, but also routers too like this one with a 486 class CPU.
x86 CPU's have always been microcoded. Even the original x86. The latest Core CPUs are actually closer to 1-1 mapping between microcode and x86 code than ever before :)
The thing about calling P6 a RISC CPU was that it was a marketing win back in '95 when RISC was all the rage.
I don't disagree, but I think "the situation" is common in design and engineering of all kinds. The flexible nature of IT may result in more and faster-growing cruft, but continuity in the face of technological change (which is where cruft comes from) is important for any business endeavor. Backwards compatibility always trumps everything, despite the cruft it creates, whether you're talking about CPU architectures, internet protocols, user interface paradigms, keyboard layouts, biofuels, mechanical fasteners, building materials, transportation infrastructure, human languages, etc.
Even if you could scrap the entire existing IT infrastructure and start from scratch, in 30 years time it would be just as crufty as it is now.
Intel will begin to make their own rivers. But they will also be based on the 45 nm process and be damn hard to see.
What I'd like to see in a 45-nm process is an ARM architecture based SoC (System on a Chip).
now we need to go OSS in diesel cars
Certainly the situation is much subtler than that. If time to market were the overriding concern, then complex systems like x86, C++, Windows and the Web would not be in use, since their excessive complexity makes them expensive both to develop and to develop for. Instead, I suspect that their complexity and long effort-to-market is part of the barrier to entry for newer, more sophisticated, better engineered and simpler systems; only the great behemoth developers have the resources to get to the market in a timely fashion, or perhaps even at all, past this mountain of complexity.
To put it bluntly, more complex designs are harder to copy, and thus to the advantage of entrenched players, even at the cost of product quality and time to market.
// MD_Update(&m,buf,j);
Do you think? I think we currently pay a factor of four or more in cruft, and it won't go away by itself. So our choices for 30 years from now, assuming things go as they have been going, are a factor of 16 or a factor of 64 slowdown, depending on whether we make an effort in this generation or not... not that we will.
My key interest is that I can play the games I want to play when I want to play them, but when I've got my system on doing file sharing, or sitting idle, I don't want to be raising my electric bill.
It still strikes me that Intel chips suck more power on idle, cost more, and run hotter when they run at capacity. So, since I don't do high-end processing, I don't need one. And my SQL servers benefit more from better bandwidth to the processor that high processing power.
So far, I have yet to see anything from Intel that will make me want to buy from them. And every time I hear another Intel jingle on the TV, I resent them even more.
(I also refuse to get a PS3, for the same energy concerns, plus Sony is so damn arrogant.)
Linux - because it doesn't leave that Steve Ballmer aftertaste.
RISC was not developed to improve the lives of programmers, it was developed improve the lives of CPU designers.
... "originally inspired by the discovery that many of the features that were included in traditional CPU designs to facilitate coding were being ignored by the programs that were running on them".
Wikipedia: "in order to enable easier implementation, greater instruction level parallelism, and more efficient compilers"
The "RISC Design Philosophy" section begins: "In the late 1970s researchers at IBM (and similar projects elsewhere) demonstrated that the majority of these "orthogonal" addressing modes were ignored by most programs. This was a side effect of the increasing use of compilers to generate the programs, as opposed to writing them in assembly language."
If you think RISC is for CPU designers and not compiler users/writers, you've got serious revisionist history issues that I'm not going to touch.
The biggest change to transistor fabrication since the creation of the silicon transistor. This is a previously unavailable technology for making integrated circuits that is substantially different than was used before. Isn't there a word in the English language that describes this?
Education is a better safeguard of liberty than a standing army.
Edward Everett (1794 - 1865)
Actually, one of the reasons that Apple jumped off of the PowerPC platform was BECAUSE of their power inefficiency.
No, actually, Apple went off in a huff because Pontiac got the first G6s.
My other car is a 1984 Nark Avenger.
Most apps I run would run on a 1GHz CPU (actually, until September, my main workstation was a 1.2GHz *laptop*). CPU Speed is seldom an absolute requirement. Having enough RAM (in the Gigs) is nice.
The only app that I see requiring a fast proc is video editing. It would still crawl on a slow one, but it is painful.