Slashdot Mirror
Intel Readying Dual-Core Desktop Chip
sunisha.shah4eva writes "CoolTechZone is reporting that Intel is planning on introducing a dual-core Dothan chip for desktop computers. According to the article, Intel has plans to turn the performance table around with AMD. From the article: 'Finally, it looks like Intel has learned from its mistake and secretly prepping a surprise for the rest of the industry. According to the information we received, Intel is currently working on a desktop, dual-core Dothan microprocessor with SSE3 instruction set that Intel plans to launch sometime in the future. Whether the launch will take place this year or in 2006 is currently unknown.'"
Anyone know the power consumption/heat output of these things?
...just in time for the Apple switch to Intel products?
I'm still kind of miffed about that but if they run new dual-core chips it might not be so bad.
CAn'T CompreHend SARcaSm?
I'll say it again, I LOVE competition. Ever since AMD became a threat to Intel, we've seen outrageous processor wars and benchmarking tribunals. I can buy a P4 3 gig processor for about $150 now.
Most likely, Intel will take that performance throne with their "secret". They have a way of doing that (like HT); but, we'll see something better come from AMD. And so the cycle continues...and we all benefit!
IGB: More fun than eating oatmeal!
From reading this article, SSE3 doesn't look like too much of an improvement. More registers are always good, I suppose. Compile-time "hinting" might be kind of interesting to do some optimization research into.
I do like that they are readying a dual-core chip; Intel's chips have always been really hot, particularly in an SMP rig.
but will it run OS X?
---- Take the Space Quiz!
Many dothans died to bring you this information...
Once I get this in my MAC - well you just watch out linux users!!!
I remember reading that Intel's "dual core" chips aren't true dual core at all, but simply two CPU's put into one package. AMD's dual cores actually have two cores in the same die.
I don't think so. It's no secret, it's known to all who care to investigate a bit. Their roadmaps point to it, and have in some form or other for the last 4 years. This is just hype that is being spread... what next, the MACs will have them exclusively?
---
Programming is like sex... Make one mistake and support it the rest of your life.
I am posting this message in order to pre-empt and prevent any lame beowulf cluster cliches. Thank you, that is all.
I didn't RTFA, but perhaps these will go right into Apple's new designs?
Finally, it looks like Intel has learned from its mistake and secretly prepping a surprise for the rest of the industry.
Many Dothans died to get Intel that information.
...what ever happened to Google? ;)
libertarianswag.com
"that Intel plans to launch sometime in the future"
This just in: AMD has plans to launch their dual core desktop chip sometime in the past, thus beating Intel to the punch yet again.
The global economy is a great thing until you feel it locally.
More Megahurtz
Powerbook Dothan next year (annonced on a tuesday for sure). Already feeling much sn'happier.
Do they have any other choice for timeframes?
Maybe they'll release it in the past just to screw with us!
and that isn't good enough ... why?
... that sort of makes the Intel 'duel core' sound better.
'two cpus' vs 'a cpu that thinks it is two'
Wasn't that Gimili's older brother?
Thalasar
Shhh let the little hardware sites think they got a scoop to feel good about themselves. I mean just from the blurb, secretly prepping for a future release. Heavens! a new chip coming in the future?? Who would have thought it?
I'm currently running a Dothan on my desktop (ASUS CT-479 + P4P800-VM), it makes it very clear that Netburst has been dead for some time now. Intel has been milking a dead but very expensive cow, and will continue to do so for as long as they can.
That was an article with no information!
Of course Intel is going to put a dual core Pentium M on the desktop. And of course it will be dual core. Of course it will be sometime this year or next.
Where is the NEW information. I could have made this up with NO inside info.
Intel? Making a high performance chip?
;)
Alright then, who wants to bet these are for Apple?
best 2 out of 3?
"Waste not one watt!" - CZ
Sounds like a good idea to me since I have already ruled out current Intel dual core designs because of their outrageous power consumption. AMD Athlon 64's are much better in this department except they are awfully expensive right now. A more economical dual core Dothan design would definitely be something I would be interested in.
And if you all thought you had seen the end of the cow fwds, here is a
revelation- another one. The last line rings so true...
INFOSYSism
You have a thousand poor cows. You put them on a nice campus, and send them one at a time to the US for milking.
WIPROism
GE has a cow. You take 49% of the milk.
DELLism
Intel has a Goat. Samsung has a Camel. Buy milk from both and sell it as Cow's milk.
IBMism
You have old stubborn cows. You sell them as pet dogs to unsuspecting small businessmen.
MICROSOFTism
You have a cow. Force the world to buy milk from you. Spend a million dollars to feed poorer cows.
SUNism
You have a bull. It doesn't give milk. You hate Microsoft.
ORACLEism
You have a cow. You don't know which side to milk, so you sell tools to help milk cows.
SAPism
You don't have a cow. You sell milking solutions for cows implimented by milking consultants.
APPLEism
You have a cow. You sell iMilk.
SONYism
You have a cow. You spend 50 million dollars to develop the world's thinnest milk.
HPism
You don't know if what you have is a cow. You sell complete milking solutions through Authorized Resellers only.
GEism
You have a donkey. People think you have a 100-year old cow. If someone finds out, that's his imagination at work.
RELIANCEism
You don't yet have a cow. You sell empty cans to people for Rs. 501, because Dhirubhai wanted everyone to have milk.
CITIBANKism
Welcome to citibank. If you have a cow, press one.
If you have a bull, press two... stay on the line if you would like our customer care officer to milk it for you...
TATAism
You have a very old cow. You re-brand it as TATA Indicow.
Where's my free iPod!? Until then, I'll settle for a kiss...
- Apple switched to Intel for the explicit purpose of benefitting from advances like this
- Apple will most likely be using a slightly different architechture than wintel(mobo, bios, firmware, etc), so not every hot new Intel chip will make it into an Apple system.
- Apple will still be offering a limited selection of systems, so they will have to pick and choose what makes it into thier product line
The first systems are more than a year away (not counting the dev system) so everybody take a deep breath.That's what I want.
:(, various Windows flavors, all running on the same box at the same time. Sweet.
... oh, and a super-sized power supply and liquid-metal cooling system to make it all work.
Multiprocessor too. Gotta have more than one CPU.
MacOS, various Linuxes, various non-Apple BSDs, and because I have to
Hmm, what else do I need, a few dozen GB HD per OS, a GB or two of RAM per OS, a core per OS, 10GHz networking, high-end sound and video,
Knowledge is how to play a game, intelligence is how to win, wisdom is knowing what game to play.
I bet Intel's people wish that all software could be recompiled on installation, to target the specific tweaks they put into a certain chip model. Instead of waiting for the OS or app vendor to recompile for an optimized binary distribution, which rarely happens. Of course, that depends on open source...
--
make install -not war
Communication efficiency and information sharing between the two cores.
On AMD Dual Cores, there is a specific bus for communication between cores and with the memory module, while in Intel types they have to use the main bus.
So intel choice for Netburst dual core lowers the total efficiency (since the cores have to share with the rest of the system, situation akin to regular dual processors) while AMD dual cores have a special bus which is even faster than the regular main bus, lowering latency and increasing communication capacities between the cores, on top of making them compatible with regular mobos.
But one has to remember that the choice Intel made for Netburst's dual core was more than likely done in a hurry, to release DC faster than AMD.
They'll probably design a much more specific processor for their Dothan dual cores.
"The way we can tell it's C# instead of Haskell is because it's nine lines instead of two." -- wadler
Well... uhh, no. The Pentium D is an ugly hackjob, they are technically dual core but don't really have any design features that actually take advantage of that fact. This is why they are readying a *NEW* dual core chip.
I didn't think this was actually news, info about Dothan being released in mid/late 2006 has been floating around for a while now.
News flash, Intel to release new product at some point in the future with existing technology. Should be 'Cool', may kill AMD. -Rick
"Most people in the U.S. wouldn't know they live in a tyrannical state if it walked up and grabbed their junk." - MyFirs
They are currently working on their dual-search-engine core "secret" and will be available late this summer ...
Google is like, so 2 months ago
;)
like omg, Intel is in
apple computers now
Last time i looked the P4 in my desktop at my feet now has dual core..
---- Booth was a patriot ----
Y'know, this better behave and not require a cooler assembly that could liquefy nitrogen. I want performance on my desk, not a space heater. So I'm a little leery of anything from Intel right at the moment.
What we need are chips that get along with each other in an SMP configuration perfectly, don't cost a lot to make quad boards, and whose boards also don't cost a lot and can be rack mounted. Then we can have a household cluster and remote terminal in a nice cool place like the basement instead of putting hulking tower cases everywhere sucking up cat hair and dust into the cooling system, sitting by the desk waiting for a teen to kick it and fark the hard drive during a write operation, etc.
Instead I'll probably see quad core single processors where each core hyperthreads at some absurd new level, confuses Windows altogether, makes Linux cry and and needs to have a case with a volume greater than one cubic yard to avoid melting it due to proximity to the heat pile.
Never mind that if you have one core dead and the other not, you can't simply replace it by itself. It's like welding your transmission and engine to each other and the frame of your car. Just replace everything at once if there's a problem. Hey, let's stick all the other chipset functions and sell a giant monolithic chip that does everything. If it fails, you can keep pumping power to it, mount it horizontally, and cook tea on it; call it Open Hotplate or Intellicooker.
More wait and see...
If my grammar and spelling are off, I am [distracted/tired/careless] (take your pick)
Because intel's cores have to communicate with each other through the FSB, which is slower and also eats into your other bandwidth. AMD's dual cores have a special connector IN the chip that accomplishes this MUCH faster than the FSB. All intel did was take two chip and package them together, they still communicate in the same way that any normal dual chip system does. AMD's don't.
Smithfield is two cores on one die.
The difference is both cores access the system bus directly, there's no on chip core to core communications as there is with AMD's solution. That shouldn't surprise anyone though, SMP by deffinition is done in the same mannor, each chip sharing the system bus. Intel doesn't have the same abstraction between the core and the system AMD has.
Intel has shown plans for two seperate dies on a package (I forget the name, a version of Pressler maybe it was), but that should only help Intel, if one Smithfield core is bad, they throw both away (or more maybe sell them as single core prescotts, but we'll see), independant cores makes it easier to discard only the bad dies.
Whoops - wrong link. Here's the correct nonbinary link (though the other one is somewhat related).
More
No such thing as a G5 powerbook..
And now, there never will be, due to the dimwitted Steve Jobs..
---- Booth was a patriot ----
Ok, so intels presumed "high performance" chips that are going to come out. Are they like the 3ghz+ pentium4s that perform like 2.0ghz AMDs? Mhz for Mhz ??
It seems that the processor manufacturers have been slowing down in the race to get more and more Ghz out of thier chips. I think AMD will respond with a triple-core processor, and we will see a new race to put more and more cores into the chips.
Technoli
Wow, news for nerds? This isn't news, it's been known for months.
d -run-at-2-5-GHz-056.shtml
Just search for Intel Yonah. Jeez.
http://news.softpedia.com/news/Intel-s-Yonah-coul
http://lkml.org/lkml/2005/8/20/95
Well, for one, they don't work together as well as the AMD. With the Intel, any communiction between the cores has to be done through the FSB, where as with AMD, its done internal to the processor. That is huge. The on-die memory controller on the AMD just makes the chip much more advanced than anything Intel has.
Here is a link with some info on the architecture.One big advantage AMD has is that as you add cores, the performance hit you take over contention for memory is very low. For example, look at these benchmarks: Opteron vs Xeon
The Operton in a 4-way configuration makes a mockery of the Inetl Xeon and its running 800Mhz slower and with much less power consumption. People updating from dual opteron to quad by going multicore are going to get a lot more bang for their buck, specially since they don't need to buy a new motherboard.
If Apple gained rights to some technology when Motorola and IBM didn't deliver, perhaps they could bring Altivec to Intel?
Well, as an Apple user let me say this Intel dual core thing, it looks, ah, mighty good. Go.... Intel? Yes. Go Intel!
Man this is going to be a rough transition.
"There is more worth loving than we have strength to love." - Brian Jay Stanley
See what I just did? I got around your preemption. Karma, come to me...
Without getting into the details on why Intel doesn't have silicon-on-insulator (IBM wants to "trade" instead of license...), one would think that AMD would have been a *much* better choice for Apple.
How about Silicon on Saphire (SoS)? SoS (assuming SoS!=SoI) is usually considered too expensive except for harsh environments and places where you really need it. However, since saphire can now be artifically created, it may have come down in price enough for them to integrate it into the assembly line.
Fly me to the moon Let me sing among those stars Let me see what spring is like On jupiter and mars
Just trying to help. Don't shoot the messenger!
Top of the line single core PIV are at 130W, and dual cores are above 150W... Well confusing Windows is not a tough task, as soon as you start having more than a single processor/core it's more or less done.
Confusing an unix system, on the other hand, is a bit tougher...
"The way we can tell it's C# instead of Haskell is because it's nine lines instead of two." -- wadler
You can buy them now: http://www.anandtech.com/news/shownews.aspx?i=2437 3
HJ
...of cliches...
CAn'T CompreHend SARcaSm?
stuff that might happen.
We have been thermal testing these for a couple weeks now. They are smokin hot! They've got big 'ole heatsinks. I dunno about performance but they suck a lot of power, a helluva lot more than AMD's dual core opterons. The new 65nm opterons are awesome on power effieciency.
I hear and I forget. I see and I remember. I do and I understand. -Confucius
Sure the consumers don't know the diffrence and just keep buying intel but the people in purchasing must be saying.
Hey Intel if they find out how shitty these things are, well they're gonna be pissed!
It's increadible how long intel has gone without a serious update.
This however is just an attempt to Jam up AMD, a new processor architecture THAT IS JUST AN EXISTING ARCHITECTURE GLUED TOGETHER and RELEASED IN A YEAR!
Total Garbage.
See above post. ;-)
10GHz networking
I think you mean 10 Gbit networking. That aside, I think what you want is an OC-192. That clocks in at around 9.955 Gbps. That close enough for ya?
Fly me to the moon Let me sing among those stars Let me see what spring is like On jupiter and mars
AMD's production costs will be even better in comparison to intel.
Repeal the DMCA!
Don't you think maybe the D/C P4 was just a fix to compete with AMD while intel developed a REAL dual core sol'n? Do you think Intel is dumb enought to make that mistake twice?
1. In Soviet Korea, only old computers have dual-core desktop chip in YOU!
2. ???
3. Profit!
Signature.
"...secretly prepping a surprise for the rest of the industry"
uh, hate to burst your bubble, but I got this nagging suspicion that somebody from AMD reads slashdot.
"What does slashdotting mean?"
"You've never heard of slashdot?"
"I know it makes websites not work."
Tom's Hardware has some interesting benchmarks with a Dothan in a desktop system with a halfway decent memory system.
- 21.html
http://www.tomshardware.com/cpu/20050525/pentium4
Intel: "When I left you I was but the learner, now I am the master."
AMD: "Only a master of MHz Darth."
Well, yes I do (think D/C P4 was made in a hurry) and no I don't (think that they'll keep doing that kind of retarded shit).
But since I'm not actually 100% sure of that, I used conditional statements in my previous post, to show what I think without stating that it's an absolute truth (since it isn't).
"The way we can tell it's C# instead of Haskell is because it's nine lines instead of two." -- wadler
I believe the first desktop systems from Apple will be based on Intel's Conroe processor.
The Conroe will probably be the first to use Intel's NetBurst successor and is planned for late 2006.
http://www.dvhardware.net/article5251.html
Funny that, I can already buy dual-core chips at Newegg. As a side note, dual core P4's are about one half to one third as expensive as dual core Opterons. In fact, dual core P4's start at a mere $311, whereas opterons start at $900+. Looks like AMD has some re-pricing to do.
Why would Intel do that? If Intel won't give up on Itanic, the processor that could..n't make it into enough server rooms to break even on its development, then why, why oh why would they drop a platform that's got such great market saturation????
Not only will providing Pentium 4's for existing desktops produce some income for a couple of years to go, the Xeon line is still *dependent* on it. In environmentally controlled rooms, these machines can produce all the heat they want and nobody's gonna give a damn. Couple that with more thermal work, bigger caches (hah, no surprise), and a few reworkings of internal components, and the Netburst Arch can live on, finally driving the wedge between their Desktop and Midrange Server class machines, like they've been trying to do for YEARS with the Xeon branding.
[AMD did this easily with Opteron vs Athlon 64. (Sledge/Clawhammer).]
Now if they'd just hurry up with their damned productions instead of sitting on their arseloads of technologies.. I guess that's the problem when you control all of the aspects of production; too hard to get the wheels greased and in motion.
"Victory means exit strategy, and it's important for the President to explain to us what the exit strategy is." G.W.Bush
Damn! You almost got me that time!
Apple bought into the AIM deal (Apple, IBM, Motorola) for producing the PowerPC, they let it slip for a few years but the G5 was supposed to remedy all of that. Nowe we know that the G5's problems were too great and to stay competitive they had to do something, even something as rash as a complete platform migration.
So don't be too harsh on Apple, they tried.
Damien
" I often wonder hwo they can fit 1.4GB of info on a singel 700MB CD without compiling from the source code."
Compression, mostly. Also a lot of the information is being generated after install... the registry and such. Some files are installed multiple times.
Seriously, a 50% compression rate isn't startling.
"Aside from some experiences I've had moving between Intel and AMD with the same install (very interesting blue screens)."
That's because you actually have drivers for all sorts of things you didn't know you had. GART drivers, USB host controllers... The Windows install process mostly detects these right, but the operating system isn't particularly good at redecting them if you switch. There isn't much incentive, anyway. Microsoft doesn't *want* you to be able to take an installed copy of windows and run it on a different motherboard without issues. That would enable easier piracy, so it's not a feature.
I'm guessing you didn't even read my post?
I'm gonna say this for one, last, time. The Pentium-M is the Next Logical Evolution in the P6 archetectural line. This iteration brought micro-op fusion (more RISCy behavior), more cache room, smaller chips (reduced size, which in turn reduced the power demands), and a faster bus speed. For all purposes. With better versions and designs of SpeedStep, Intel *designed* it to bring the mobile revoltion to the forefront.
The only problem is, their savior for the Server machine (Itanium), failed to catch on. So they regeared their systems, and we have the hideous P4 we all hate. A few years later, the Pentium M is now perfectly able to take over the role of desktop processor, and all is happy.
Go back and read my post again if you're still confused.
"Victory means exit strategy, and it's important for the President to explain to us what the exit strategy is." G.W.Bush
I once saw a cow poo on another cow, which was quite weird, but also very funny!
--Unknown start of unknown TV show(BBC)
...has yet to release a statement about their new processor range, but many believe it to support a range of hard-drive-to-google-search-engine instructions, for easier indexing.
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
A curious fact about Apple's choice of Intel over AMD, as I learned over on the Ars Technica forums -- AMD's CEO, Hector de Ruiz, was formerly the director of semiconductor products at Motorola.
I think this is one big reason why Steve Jobs and Apple could not / did not consider AMD -- they notoriously burned their bridges with Motorola/FreeScale over the G4's lackluster performance and slow development. Thus, Jobs and de Ruiz probably don't have a particularly good relationship.
This Intel roadmap:a i01l.gif ...shows "Jonah", a dual core laptop chip.
http://pc.watch.impress.co.jp/docs/2004/0227/kaig
I saw an elephant drops it's dump on my little cousin in the vegetable market - my cousin was 4 years old and standing in the wrong place at the wrong time. It was quite funny really... I wish they had digital camera's back then :-(
Where's my free iPod!? Until then, I'll settle for a kiss...
Actually, for anyone who cared about such things (chip geeks), the popular consensus WAS that PPC's WERE better than anything in the x86 camp. That is, during the G4 era. The instruction set was much saner (even Intel fans will complain about the bass-ackwards quirky x86 instruction set), it pushed more numbers with far less power, AltiVec showed a ton of promise (if you were willing to either wait for a good compiler or use the vector unit by hand).
With the introduction of the G5 and the failure on the promise to break through the 3GHz barrier without incurring much larger power requirements, the situation probably began to change, but us Apple Believers, admittedly, chose to ignore this slowly-dawning information. Just like those stubborn Windoze users who only surf the web and check email, and reinstall Windoze every year and spend 2 hours a week disinfecting and have pieces of apps lying around on their hard drive that failed to successfully "uninstall" (a concept foreign to OS X users), and STILL believe that their choice is cheaper and/or more effective than getting even a used Mac for the job. Their time must not be worth a damn thing. I know, because I tried to convince just such a non-technical person to buy a used Mac (since I put equal time on Macs and PC's and knew what was best for this person), but they insisted on a crappy PC laptop, and then had the nerve to call me over for free tech support... Objectivity is hard to come by all around.
Maybe we liked having a different processor because it was a different TAKE on things. It was outside the box. And certainly, every last one of us understood that it added COMPETITION to the market. Competition is good for everyone. Something else you Wintel fans seem to not care about or understand, as you freely throw your money at an industry with a leader who is a convicted monopolist. You should be kissing AMD's ass that they lit a fire under Intel's butt, because around the year 2000, it certainly did look like PPC was going to hand Intel's ass to it. (And of course, if Microsoft didn't consider open source a "threat", it would have zero incentive to change, either. Why improve when you can market instead and charge as much as the [exorbitant fee just under what would force people to buy elsewhere because it's the only game in town]?
I can't believe I even devoted this much thought to your jerkitude.
Yes, you can buy what are called dual core P4s for a third the price of an actual dual-core Opteron, but that's because you get what you are paying for.
Opterons have their own high-speed dedicated bus for core to core communication. Dual core P4s are really two separate P4s on a single chip and use the regular bus for communications (along with memory, i/o, etc.).
The dual core P4 you mentioned is operationally no better than dual P4s (single core).
Saying the P3 was green lighted before the P4 is pretty stupid statement.
Have you ever been to a turkish prison?
Will these chips include soul sucking DRM?
When I read things like this it reminds me of the classic Microsoft, "ours will be better" BS they crank out to make consumers believe it is wise to wait to buy their newest line extension.
I also don't believe Intel is going to "give" something to Apple just to keep them as a customer. Would a company that has gotten to be the size of Intel give an important technology to one customer (Apple) when they can make far more money selling it to all customers?
http://www.maxineudall.com/2010/02/should-economists-be-sued-for-malpractice.html
I guess that's the whole idea of this new Intel design. They have finally learned that people don't want to have a powerful room heater under their desk just to type an email to their friend, while watching DVDs on a desktop is lame with all the fan noise necessary to keep the CPU operating.
Intel may have finally learned that this may be the reason why people buy laptops (without EVER taking them outside their home) or that cute little mac mini. Most people consistently don't care about actual performance any more as long as the computer does what they want it to do (insert favourite joke about viruses and spyware here).
By putting mobile pentiums on the desktop they allow PC makers to design something slick (think mac mini) while still selling state of the art silicon (= make more money than they do with low end chips). I hope it works out like that!
Nobody is surprised Intel is making a dual core Pentium M with SSE3. This is old news called Yanoha.
What is big is that Intel will finally support the platform on the desktop. That means offering an Intel branded motherboard and Pentium M chips clocked for the desktop thermal envelope. It also means much better prices on boxed Pentium M processors.
Pentium M chips can already be overclocked 50% and in fact need to be if you want them to compete with real desktop processors. For many people overclocking is simply not an option. Even at 50% overclock the chips are barely warm meaning Pentium M has the potential to make a huge leap in performance with some minor tweaking.
Also motherboard support is nonexistent at best. Motherboards for Pentium M are outrageously priced (~$250) and come from unreliable manufacturers. No IT department is going to fill the office with AOpen hacks, they want Intel brand mobo in their white boxes. Finally, the chips themselves are also outrageously priced and barely a deal after overclocking. Most boxed chips are more for development applications so this is to be expected. Bringing Pentium M to the consumer desktop market will thankfully drive prices down closer to Pentium 4 prices.
On a side note, Pentium M has yet to make the transition to 64-bit. With Microsoft moving forward on Windows x64 and Apple moving OS X to Intel's mobile chips first, Intel needs Pentium M 64-bit support NOW. Apple can't go on supporting 4-way fat binaries with 32/64 PPC and 32/64 x86.
all this fanfare about the new Dual Core processors has made for a media field day about performance and benchmark figures... but not one story has appeared (as far as I know) in any manstream manner documenting the fact that this generation of intel processors will have DRM embedded DIRECTLY IN THE CHIP FUNCTIONS.
you can have your fancy new hardware, chances are i'll be running P4s or this generation of AMDs long into the future, most likely in large parallel arrays bought as surplus. You DON'T F*CK WITH MY RIGHTS, tech industry. Sadly, i feel i'm in the minority on that principle... and the thousands upon thousands of sheeple who blindly purchase this new harware will render my boycott meaningless.
I miss idiotic
Isn't this the very definition of FUD?
Wintel to Appletel to Suntel ;)
will it be 64 bit?
Rerelease XP for PPC / 970! Microsoft can say: *We* haven't abandoned you. I'm sure they still do the builds internally.
Best Buy can have you arrested
I always wondered why someone didn't cobble together a FreeBSD "make buildworld" installer that would install some rudimentary base system, reboot, and then begin a cvsup and then buildworld process which would produce the final finished result, including building any desired ports from source as well.
There's a limit as to how much you might gain from this, I suppose, as well as the compiler's ability to support or keep up with all the latest and greatest tweaks for some new CPU. Plus it would be really, really time consuming and installs take too long as it is (generally, not FreeBSD specifically).
HT is not a joke if your encoding movies 24/7 on a PC and desire a snappy PC in the process. Sure, HT is only a 20% increase in performance if the application is written to take advantage of it. But the fact it makes WinXP runs so much smoother and without hick-ups when slamming my CPU is well worth the HT feature alone.
Life is not for the lazy.
They named it after that lame little town in Alabama near to Fort Rucker where I was stationed from 1968 to 1970?
Talk about obscure code names!
Richard Steven Hack - This sig is TOO GODDAMN SHORT TO DO ANYTHING USEFUL WITH! MORONS!
The design team (P-M design team) looked at the Pentium 4's architecture and quickly concluded that it wouldn't be appropriate for a mobile microprocessor.
the P-M came out way after the P-4.
I hope ol' Stevie announces the new Mac's name soon.
It won't be a 'power' anything Mac since they're no longer using the PowerPC chip.
iMac's already on my desktop and that uses a G5.
IntelMac's just too long to type.
Hmm... X(86)Mac... YEAH.. XMac! XMac'd fit and it would fit in with all the XServe stuff.
Let's hope they go 64 bit wide real soon. I'd hate to be buying down in chip set.
Though a dual core dual chip desk top box would probabky be real sweet...
MSBPodcast.com The opinions expressed here are my own. If you don't like 'em... Think up your own stuff.
Intel has been planning a dual-core, Pentium-M processor since they nixed the "Pentium 5" last year. Maybe they will introduce this quicker than originally expected, but that is pure speculation.
That's the current problem with Intel. They have lots of nice things (HT, NX-bit, VT, dual cores, 1066MHz frontside bus, large caches, etc.), but it's hard to find one chip with all the good stuff at once.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
>the popular consensus WAS that PPC's WERE better than anything in the x86 camp. That is, during the G4 era.
And, as usual, popular concensus turns out to be wrong.
The x86 still dominates any other processor available today in raw speed, though not on throughput. If you want to program in assembly, it's easier for a beginner to pickup risc because of its regularity, but I highly doubt most that the people complianing about the ISA actually used it and were just complaining that it seemed to them to be unelegant, and today it's pretty much a non-issue, as evidenced by the fact that special instructions like SSE2 are automatically used by compilers, making it unnecessary and actually more harmful sometimes to code assembly due to the way modern CPUs schedule instructions.
>it pushed more numbers with far less power
I'll give you that it required less power per flop, but check the results about to see how the mythical power of the g4 was all apple hype.
>AltiVec showed a ton of promise
According to wiki, Altivec has been around since the late-1990s, while SSE2, comparable in power to it, debuted in 2001. Any chance that Altivec would improve performance would've happened, and IBM and Motorola even had a falling out over whether to include it, according to the register.
The PPC has not been comparable in performance to anything offered by x86 for years. It added no competition to the market. I bid it good riddence so Apple might actually do some innovation that is actually about usability, instead of blatent lies about performance.
As for petty whining about Microsoft having a monopoly - guess what, Windows and x86 have succeeded where Apple failed because they understood what the market, and engineered it to be good enough, as opposed to being control freaks about the purity of their products.
The road to hell is paved with good intentions.
>To this day, a Dual 2.5GHz G5 still pounds a 3+GHz P4/AMD whatev into the ground
See here
Top 20 2-way SPEC systems
Top 20 SPECint_rate2000
2 2600 Opteron 40.5 36.1
6 3200 Pentium 4 Xeon 34.3 32.9
10 2200 PowerPC 970 21.5 20.2
Top 20 SPECfp_rate2000
2600 Opteron 45.8 42.3
3600 Pentium 4 Xeon 28.6 28.2
2200 PowerPC 970 20 19.2
Extrapolating linearly results for a 2.5GHz, x86 is still about 1.5x to 1.75x on ints, and 1.4x to 2x on floats. From this I must conclude that you are as the subject says, or that "pounds into the ground" has aquired the slang usage meaning "is pwnd".
For some reason, IBM PPC processors seem to have aquired Jobs' RDF, from the G5 to Cell.
The road to hell is paved with good intentions.
Is Intel going to drop a bomb?
Not likely, since they're giving the developers Pentium 4 development systems and demoing it all on P4 based systems. To jump to a completely unnanounced ISA
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
And Apple is going to find that being on the Intel treadmill of new processor version releases is really going to wear them down. Instead of announcing new, faster Macs once or twice a year, everyone will expect the new Macs to already be in the stores the day Intel announces their latest and greatest. Wonder if Jobs thought about that?
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
I for one, welcome our new Intel dual-lord overcores.
Yes, but they were talking about the dual core P4.
t he+next+notebook+chip/2100-1006_3-5729925.html?par t=rss&tag=5729925&subj=news
according to this artical: http://news.com.com/Intel+spills+beans+on+Yonah,+
the dual core Pentium M will be different.
"For one thing, it will contain two cores, instead of the single core on current notebook chips. The two separate cores will also share a 2MB cache. Current dual-core desktop chips from Advanced Micro Devices and Intel come with similar sized caches, but each core accesses only 1MB of cache memory dedicated to it. Sharing the cache will significantly boost performance. (The chips communicate with the cache through a single bus embedded in the chip.)"
It's the only way Apple would protect their market - "ensuring" only "trusted computers" could access content.
Without that, moving to Intel would be a death move because it removes Apple's hardware uniqueness and enables clones to run OS X. But not if DRM is invovled, it won't...
Just to hammer home some agreement with another reply, here's a quote from Ryan Gordon I found from another /. story: "SSE3 is way more flexible and feature-rich than Altivec. I don't care what the haters say, that's the truth. In terms of vectorization, SSE will be a better instruction set. There are lots of places were you get the feeling that Altivec should be a good optimization, but you can't find a way to coerce it to do what you want without a lot of effort (and frequently, without making the program _slower_). SSE has wider application. It just does, even without names like "Velocity Engine"."
You could EMULATE a beowulf cluster with these!
The core to core communication on the Smithfields is FSB like, but it doesn't actually leave the chip. The impression that one would get from reading posts around here is that, core0 requests an access from something in core1, the request goes out to the Northbridge and then back in to core1.
From my understanding, it uses a FSB interface and makes requests as if it were a multiproc system, but it's smart enough to know that it's not leaving the chip. This is info I got from talking to people who worked on it.
Thought I should clarify a little.
On AMD Dual Cores, there is a specific bus for communication between cores and with the memory module, while in Intel types they have to use the main bus.
So intel choice for Netburst dual core lowers the total efficiency (since the cores have to share with the rest of the system, situation akin to regular dual processors) while AMD dual cores have a special bus which is even faster than the regular main bus, lowering latency and increasing communication capacities between the cores
A recent CNET News article describes Yonah's (dual-core Dothan) 2MB cache being shared between the two cores, rather than having 512KB - 1MB cache dedicated to each core (like Pentium D and Athlon 64 X2). If you believe the Intel rep's hype, the improved communication between the cores and shared 2MB cache should boost performance "something crazy" over caches dedicated to each core. We'll see.
TO START
PRESS ANY KEY
Where's the 'ANY' key? I see Esk, Kitarl, and Pig-Up...
does it have drm? if so I'm not buying it
then as far as I am concerned it will not exist. Anyone who thinks correctly will not waste a dime on anything Intel produces so long as it includes ANY hardware DRM shit in it.
In Bushworld, they struggle to keep church and state separate in Iraq as they increasingly merge the two in America.
Step backwards? or irrelevant? You decide...
Why would anyone engrave "Elbereth"?
Engineers that do things right would 1. Integrate 64 bit with 32 bit to foster the transition to 64 bit 2. Increase processing power per GHz rather than pump GHz as a marketing move that shoots you in the foot when you hit the 4GHz barrier 3. Implement dual core on die rather than sapping performance by duct-taping 2 old CPUs into the same package and losing big time on bus speed. AMD has done all of the above right, a year ahead of Intel; Intel has done it all wrong. All they can do is release half-assed dual core a few days ahead of AMD and claim they invented it, while rapidly backpedaling to copy the above 3 critical moves AMD made a year ahead of them, and spewing out press released to whoring magazines and hack writers about how they'll have the hot chips REAL SOON NOW. Nice to see the soft shoe shuffle marketing clowns that got Intel into this mess have to break a sweat and tap dance for the next year or two.
Funny mods no longer increase karma, so you fail.
..or at least Newegg seems to think they already have them in stock
Are these not the processors you're looking for? Are they going to be argued as server-class?