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.
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.
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...
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.
How is this informative?? The dual core chip Intel is shipping (smithfield) IS one die, with 2 cores. Actually, this is inferior to MCM packages with 2 dies, as it is difficult to get 2 cores side-by-side with equal performance/power. And yield goes down when you have to have a single large die.
Re: sharing I/O bandwidth. Intel has to do this because they don't have a built-in MCH. It has *nothing* to do with "selling chips with 2 normal P4 dies on them".
Re: Amd's offering. AMD doesn't have to change their design because they have a MCH onboard. That's why the number of pins can remain the same. On the flip side, if you change memory type, you'll have to throw away the chip. It's called engineering tradeoffs, and both companies do it.
Arrgh... practically every point in the above post is misleading or wrong, and it get's modded to +5.
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."
BTW, this is why the Opterons have on-chip memory controllers. Then your aggregate memory bandwidth scales with the number of CPUs (assuming your OS is suitably NUMA-aware) and you can sidestep this problem. (More or less. A memory hog processes could start stealing bandwidth from the other CPUs if its working set doesn't all fit in one CPUs memory bank.)
"Arrgh... practically every point in the above post is misleading or wrong, and it get's modded to +5"
1 34740.html
x
Ok, the two dies on one chip was true, or believed to be true when they first demoed:
Source: http://www.xbitlabs.com/news/cpu/display/20040915
I'll concede that point to you - that Intel is now putting 2 cores on a die... however they were never engineered to work that way initially. They only have an 800 MHZ FSB, not 1066 like the newer P4's, so they have even less bandwidth to share. Want a source?? Here:
Source: http://www.anandtech.com/printarticle.aspx?i=2252
As far as my other points go, let's go over them, shall we???
"the new dual core P4s won't be compatible with a majority of Intel boards on the market"
Source: http://www.theinquirer.net/?article=21793
"The two cores use hyper transport to communicate with various system devices"
Source: http://www.amd.com/us-en/0,,3715_11787,00.html
It actually uses a cross-bar to handle the switching as well.
"Now for the best part - anybody with an existing Socket 939 AMD based motherboard will be able to use one. Worst case, you'll have to download a bios update to enable it, but it will work."
Source: http://hardware.gamespot.com/Story-ST-x-1583-x-x-
"AMD designed the K8 core to be dual ready out of the box, so this whole thing about them having an extra year isn't exactly true - they've had much longer than that."
Source: http://www.theinquirer.net/?article=13344
Still think almost my whole post was wrong? About what you said:
"Re: sharing I/O bandwidth. Intel has to do this because they don't have a built-in MCH. It has *nothing* to do with "selling chips with 2 normal P4 dies on them"."
It has EVERYTHING to do with having 2 P4 cores in a single package - look at that anand article I posted above, here is a quote from it:
"The major issue with Intel's approach to dual core designs is that the dual cores must contest with one another for bandwidth across Intel's 64-bit NetBurst FSB. To make matters worse, the x-series line of dual core CPUs are currently only slated for use with an 800MHz FSB, instead of Intel's soon to be announced 1066MHz FSB. The reduction in bandwidth will hurt performance scalability and we continue to wonder why Intel is reluctant to transition more of their CPUs to the 1066MHz FSB, especially the dual core chips that definitely need it.
With only a 64-bit FSB running at 800MHz, a single x40 processor will only have 6.4GB/s of bandwidth to the rest of the system. Now that 6.4GB/s is fine for a single CPU, but an x40 with two cores the bandwidth requirements go up significantly."
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