Slashdot Mirror
Preview of Intel's Dual-Core Extreme Edition
ThinSkin writes "Intel let ExtremeTech.com sneak behind the curtain of its anticipated Dual-Core Pentium Extreme Edition processor for a full performance preview with benchmarks. Bundled with essentially two Prescott cores on one die, the Extreme Edition 840 processor clocks at 3.2GHz and contains a beefed-up power management system to keep the CPUs running cool during use. Expect Intel's dual-core line to hit the streets sometime this quarter. No word on pricing yet." Update: 04/04 17:26 GMT by T : Timmus points out FiringSquad's preview, too, writing "The benchmark results are mixed, with a few applications taking advantage of the new CPU, and some that don't." And Kez writes in reference to this article to say: "Our article on HEXUS.net, covering the P4 EE in detail, states the price as £650 (that's what we're looking at in the UK anyway, not sure about the U.S.)."
On SlashMark? Namely, how many seconds does it take to compile the Linux kernel? :P
unixkb.com -- articles on practical Unix issues.
"Yeah, by today's standards it's EXTREMELY slow!"
"Only dual core, ha ha ha ha hah!"
I guess they can't very well call it 840i, as they've already used that for a chipset, but maybe Intel should stick to names ending with -ium and -on instead of something which timelessly proclaims some chunk of doped silicon as superior.
Next up from Intel, the Ultra-Spifftronic-Wowee-Zappo Triple Core, with extra schmaltz!
A feeling of having made the same mistake before: Deja Foobar
... something else we can use to make breakfast with!
We recently returned from a road trip to discover a very large box waiting for us.
If the processors that big how the heck will I fit it on my motherboard?!
Running cool during use? It seems to me they'll need the power management to keep it from melting itself, judging from the heat output of just one of those beasts...
we just call it what it is, a two-die module. This is not true dual core but two cores slapped into one chip package... Sure you'll only be using one socket but thats about the only different. Architectually, you will need to look at AMD's offerings for true dual-core.
If one of the cores generates a floating-point error, the other core can be used to correct the problem by adding both errors together to derive a slightly larger error.
Intel is just playing catch-up now to AMD. With AMD's 64-bit architecture being chosen by the market over Intel's shoddy architecture, Intel is ahead only in name-recognition. As the article says, AMD has been working on their dual-core offering for a year longer than Intel. AMD is a year ahead in development. Their offering is likely to be much more robust than Intel's with that extra year.
But, who knows? Intel seems to be shipping first. And we all know, Real Artists Ship.
I think it's great that you are developing new products.
However, because of your poor form of not making documentation or firmware freely available, I will instead be sending my personal dollars, and (significantly larger) work budget, to AMD.
vodka, straight up, thank you!
Why do intel marketers think that if they name it "extreme edition" it will sell more?
If I wanted to build a Windows system for gaming, would I have to buy Windows XP Pro for multiprocessor support...or is this dual core configuration invisible to the OS, meaning I could get away with XP Home for $100 less.
Bill Clinton: Pimp we can believe in. - The Shirt!!!
I think Intel's decision to leave out extensions developed by AMD are going to kill to processor fairly quickly. Granted they bought the rights to them from AMD, but their must be some royalty type deal here, because Intel is only including a handful of them. That will make their processor increasingly incompatable with the already accepted AMD architecture. Why is Intel so grudging to admit they are behind? They are going to kill themselves with that attitude. A couple more processor iterations and failures like this, and I expect Intel to make moves to get out of the desktop processor market altogether.
People are actually asking how much it's going to cost?
The Answer is simple
An arm, a leg and your left testicle* - it's Intel afterall
--------
*or ovary if you're a woman
If you cannot keep politics out of your moderation remove yourself from the Mod Lottery.. NOW!
It looks like gamers won't be all that interested in this offering. Even once games support mutli-threading, this wont end up boosting their framerate much. Instead this will raise the lower framerate and give them smoother gameplay. While this is a great improvement unfortunately most gamers seem only interested in their max fps and not the minimum. However for workstations this will be great, lower cost than dual procescors means graphics design companies and advertising agencies can get their job done quicker and more efficiently.
So in other words... unless you have extreme cooling this thing will never run at full speed for long. Because when it does, it will quickly heat up and this power management will throttle the clock speed and core voltage. Apps may start up a little faster, but long-term consumers of CPU cycles (e.g media encoding, some games, etc) won't see much improvement. But I'm sure lots of clueless consumers will go for this new eXtreme CPU. Can't wait to see what bullshit analogy Intel will come up with for the TV ads...
Why do we have dual cores? Everybody's admitted they are going to be prohibitively expensive, so is it just for show? Let's see some AFFORDABLE dual cores before we start heralding them as the future of processors.
Does that mean I'll be able to fry two eggs at once ?
Each core runs at 3.2Ghz, RTFA ;), or read this one:
X JsX3Jldmlld19JRD0xMDg1
http://www.hexus.net/content/reviews/review.php?d
Going to be about £650 in the UK according to HEXUS.
Does it have a hemi?
GET FREE APPLE STUFF!
Now the spyware on all my users's machines will have a processor all to themselves. That means the users will have the second processor to run Word, excel, et al...
That means they'll leave me alone and quit bitching about slow machines for a while! Woohoo! Oh, and will help that winword.exe that keeps crashing and staying backgrounded. Woot!
(Yes, I know the spyware will take over both proc's. Let me dream)
Do not meddle in the affairs of sysadmins, for they are subtle, and quick to anger.
Excuse me if this sounds unusually stupid at Slashdot, but they will in other words release 3.2 GHz dual core models initially? Won't they then have developed a new technology just to hit problematic clock frequency spoken of at ~4 GHz almost immediately? I was always thinking of something like two 1.6 GHz cores possibly with some tricks to achieve similar speeds as a current 3.2 GHz P4... Am I missing something here or is this just an unusually short term solution?
Beware: In C++, your friends can see your privates!
I wonder how it will compare to a dual core G5 chip from Apple.... whenever they get it out, which with all this dual core news from Intel, I would think it would be soon.
WWDC perhaps?
It's more like a short term flop in my eyes. With this Dual core bearly beating a slightly fast clocked single core procesor in only a small handful of tests coupled with it's extremely high cost, it's dead before it even hits the streets. People are not going to spend 2 or 3 times the amount of cash for that kind of performance. It's just not going to happen.
I agree that the expectation is double the core, double the power. This test processor is dismal in that regard. I guess we will all have to wait until AMD releases their product results, so that Intel can see how it's supposed to be done.
No, in that they provide two entirely distinct functions in the computer. With out dragging on too much, take the simple example of upgrades. I, myself, have upgraded my GPU twice since my last processor upgrade - not including the new graphics card I bought along with it orginally. Do you expect me to buy a new CPU every time I want improved graphics performance?
There may be a niche market for this, handheld devices and the likes, but not for the general computing market.
-dave
http://millionnumbers.com/ - own the number of your dreams
The review is useless without comparing their test box to an Opteron dually. Since the details regarding how AMD is going to implement dual core is well known, they could take an existing AMD dually, and hobble it with a slower hypertransport setting which would give a pretty accurate simulation.
This lack of comparison indirectly tells me that AMD's dual core solution is going to wipe the floor with Intel's, even more so than the current AMD performance advantage over Intel on single core procs.
I wonder how big a gun Intel put to their head. I also wonder how much AMD is pissed off at being "scooped", when they've been working at this for a much longer time.
jh
Is the way they benchmark it.
Listen, for office productivity and "how fast can I open spreadsheets", nobody SHOULD need more than one CPU.
The rendering tests were a little disappointing (I seem to recall a bigger gap in the AMD benchmarks), but really the point of dual CPU's is, as anyone who has used one knows, responsiveness.
Yeah rendering times dropping to 60% of normal is nice, but let me tell you, where a normal single CPU system would sit there gurgling and choking on its own vomit because some dirty little application decides it MUST use up all the CPU time, dual CPU systems just go "eh, whatever, hes being a jerk, I can help you over here."
It is SO nice to use a dual CPU system in daily routine useage (which for me is QUITE varied) just for the increase in responsiveness alone.
"The saddest words of mice and men, are not those which were, but should have been."
You are correct. A "two die module" would have two separate pieces of silicon, interconnected through one of several techniques.
But this is /., where you're supposed to cheer for
AMD and mock everything Intel ever does.
Just remember this, and you can get lots of 'Informative'
mod points, even if you don't understand even the
most basic terms of chip manufacturing. At
least that's what I can figure by looking at what
gets modded up around here.
even the Extreme Edition dual core CPU only has an 800MHz effective FSB, not 1066MHz
It doesn't make much sense to put two processors on the same bus, and then lower the bus speed. And, as the benchmarks showed, single-threaded applications ran slower on the dual-core processor than on the regular P4
I understand "dual core" has a certain market appeal - much like faster clock speeds. Never mind the fact that bus bandwidth and hard drive speed have a greater overall effect on system performance.
Those who want dual cores would be better off buying a computer that was designed to support multiple cpu's - for example, a UNIX workstation. It doesn't matter how many cores you put on a chip if your memory bus can't feed them:
- An P4 can theoretically execute 2 instructions every clock cycle.
- Make that 4 instructions/clock for a dual core.
- Each instruction averages 4 bytes of data access. Since we'll consider the instructions to be cached, we'll ignore the memory access for them, for now. So we're up to 16 bytes of throughput per clock cycle.
- At 3200 MHz, times 16 bytes/clock, we're up to 51,200 MB/s theoretical throughput.
- Yet, the 800 MHz FSB (which transfers 8 bytes/cycle) can only do 6400 MB/s throughput.
Granted, 6.4 GB/s is very fast - But even a single core P4 can saturate the memory bus. What point is there in adding another core (aside from marketing hoopla), when the bus can't run fast enough to support it!It seems to me that Intel added the power management features to the chip because they knew that the second core was going to be idle most of the time.
The society for a thought-free internet welcomes you.
more sense?
Seriously, what's the point?
Nothing wrong with dual CPU servers, heck, I've got two Linux dual-CPU boxen sitting at home, but in terms of ROI, it would make far more sense getting better bandwidth or just giving the machine more RAM or better disk access, than it would wasting all that money on the CPUs.
-- Tigger warning: This post may contain tiggers! --
If the application only has one active segment of code in memory...it doesn't matter how many processors there are, if there's only one unit to actually execute.
Multithreaded applications spawn off multiple segments of executable code in memory to do different things...a network scanner that operates in a multithreaded model might spin off a thread for every few hundred connections, so it can handle more in parallel.
"Multithreaded" applications are built to parallelize easily, as each thread can hit a different physical CPU. Single-threaded applications will also benefit from multiple CPUs/cores, but less directly: a single-threaded app would have less resource contention on a multiple CPU system, vs a single CPU system.
The OS scheduler is the deciding factor for what-goes-where and there's some hefty math involved for a lot of it...most of that, however, is handled automatically and transparently (although you can "force" affinity to CPUs if you're so inclined.)
ON a quantum compiler, it's both compiled (with avery combination of options) and not compiled already :)
hawk
Eventually, that won't be an issue. Procs will run so fast and have such good power management that the only time you'll worry about cooling is the very second you tell the computer to do something. Then, in a huge explosion of activity that lasts a few microseconds, your computer will do everything you wanted it to and silmulaniously eject a molten wad of copper that used to be your heatsink. If you have liquid cooling, your head will explode.