Slashdot Mirror
Intel Ships Dual-Core Chips
Torrey Clark writes "Intel seems to be the first to ship a batch of dual core x86 64-bit processors to OEMs.
Intel's first dual-core chip is the Intel Pentium Processor Extreme Edition 840. The new processor runs at 3.2 GHz, backs Intel's Hyper-Threading and is supported by the company's 955X Express chipsets, formerly code-named Glenwood.
Dell also announced that it would be one of the first PC makers to ship Intel's new dual core Pentium Extreme." Reader wyckedone adds "AMD is set to ship their dual core Opteron processor, designed for servers, next week."
I want to see dual-core Pentium-Ms.
At the rate that power consumption and heat dissipation are increasing on these chips, I consider Pentium-Ms to be the only processor worth using.
If AMD is shipping in about a week, then one wonders if it's worth paying the Intel price for dual core chips when you can just wait a week and get twice as much for the same price ...
Mind you, it depends on the heat specs.
-- Tigger warning: This post may contain tiggers! --
I thought that AMD is slated to ship their dual core chip first? Is this Intel rushing something to maket?
Agile Artisans
Just last week we were all ment to assume that Dell (oops, I mean Intel) wasn't ready to ship dual core until Q1 of next year...
Now all of a sudden -- out of nowhere -- they launch a surprise attack and shipped the cores early, even before AMD's announced launch date. Sounds like some VERY hefty competition for AMD. They had been claiming all along that they would be the first with dual cores an it was even used as an "excuse" for Dell to talk about starting to sell AMD chips specifically because of this feature.
AMD had better look out! Their stock price will probably take a plunge due to this surprise announcement.
Your ignorance is infinitely greater than you realize.
It will be interesting to see how much difference there is consumer wise between the AMD and the Intel version, not only in performance, but in sales.
Foxed Design
There's a bunch of interesting information about AMD's dual core offerings over at AnandTech. Very insightful read.
From the article. "If dual core Opterons do indeed have two memory controllers, the pincount of dual core Opterons will go up significantly - it will also make them incompatible with current sockets. AMD is all about maintaining socket compatibility so it is quite possible that they could only leave half of the memory controllers enabled, in order to offer Socket-940 dual core Opterons. AMD isn't being very specific in terms of implementation details, but these are just some of the options."
about manufacturers charging per-core licenses for their software. For more info, read this.
..a toast!
Escher was the first MC and Giger invented the HR department.
The P-PEE?
At a hedge fund that I used to work for, traders joked that Intel keeps AMD in business just to keep the FTC off its backs. Whenever AMD gained any advantage, Intel just squashed them.
No one expected Intel to beat AMD in dual cores this quickly and be able to release 64bit x86 process at this rate. This is a huge monopoly even more so to some degree than Microsoft.
Maybe I should invest in the heatsink business. I see a huge future in it thanks to Intel and AMD's dual core plans...
While the idea of dual core cpus is really cool, and will take over shortly due in part to the fact that we need something to do with all those extra transistors, I wonder why the focus of the industry is on chip multi-processors (CMP).
.
While CMP processors can give us rougly the same performance of a standard SMP system (somewhat faster due to interprocessor communication and shared memory, but also slower due to a larger memory bottleneck) I don't think that a CMP system would compete with a simultaneous multi-threading (SMT) solution.
While Intel's response to SMT (hyperthreading) has some benifits the performance of it is rather lackluster. The reason has more to do with their particular implementation. If you've read about the initial observations on SMT an 8-way SMT processor was shown to outperform a 4-way CMP processor. Now, I must note that the 8-way smt processor had more functional units then the cores in the 4-way CMP processor, but the overall area of the 8-way SMT processor would be much much smaller (far less structures need to be duplicated for SMT as opposed to CMP). For more information on this check out some of the papers at http://www.cs.washington.edu/research/smt/
What I don't understand is the insistance of the industry to use CMP first. From everything I've read, an 8-way SMT processor should take up less die space then a two way CMP processor. Even assuming that the 8 way processor contains more functional units. It kind of makes sense that a CMP processor is faster when there aren't enough threads to fully utilize a SMT processor (say only 2 or 3 threads that want full cpu usage). I guess SMT is a big chance in the model of programming and application development (I'm currently running research on the subject which is why I'm so interested in it). Is the reason to embrace CMPs simply because there's less new technology to add (they "just" have to interconnect two cores as opposed to adding the extra logic for SMT).
Does anyone else have any other opinions regarding this matter, or any idea why no one seems to be fully embracing SMT's potential?
I tried to look through the article, but couldn't find it... does this mean that you will have 4 "virtual cores" on one single chip now?
:)
I remembered a slashdot from a while back about licensing for multiple processor setups, but would this quadruple the cost even though it's a single chip!
Though, it will be neat to see 4 CPU usage graphs in XP's task manager.
Yes, but my question is "Will it be AMD-compatible?" ^_^
Intel ships the chips no one is buying. How real is that?
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Sun, HP and IBM have allready got machines ready, just waiting for launch.
p teron_dualcore/
http://www.channelregister.co.uk/2005/04/08/amd_o
"If everybody is thinking alike, somebody isn't thinking" - Gen. George S. Patton
I see lots of conversation comparing this generation of processor to space heaters, wisecracks about Longhorn minimum systems (that actual article was about the predicted "average", not minimum). Not much about actual multi-cores. They're an interesting direction to go.
The current direction of single core CPUs is basically running into the most they can do with XUs, MPUs, caches, etc. Sure, you can decrease the pipeline depth below the 18FO4 that the PentiumIV supposedly has, and that can help you with serial data paths, and that makes simple XUs, MPUs, etc. faster, but the branch mispredict is still horrendous -- perhaps too high for a general purpose processor found in our PCs. The more complicated logic is possible to do, but there's only so much you can do with the data and sub-Angstrom logic.
Beyond the geek factor, multiple cores on a single die attack the same problems as putting SMP did in the first place (plus a few race conditions that otherwise may have been very rare), allowing much less manpower to design a processor that is still much faster in the end. A single threaded application will seem slower, and that will place more burden on the developers to see the light of multiple threads. Instead of allowing an XU to munge through and deal with a single thread at a time, which may be a misuse of incredible resource (like a thread that said "go to grocery store" and the XU was a race car), multiple die have correspondingly multiple XUs each with their own resources, so hard tasks can be spread across multiple cores, or simple ones can get executed in parallel with others (like a thread can take a Kia to the grocery store while another Kia goes to the Post Office). Of course, problems that cannot be divided into multiple threads do not see the advantage of multiple cores, but other tasks remain responsive without requiring a monster task to context switch.
I've read about multiple cores that share a single L2 outperforming multiple cores with dedicated L2s in specific tasks, basically one core essentially acts like a pre-fetch core under a workload and the second core can reap the benefits.
I would rather have faster processors than multiple cores, as it is not enough is multi-threaded. Even the highest end 3D apps, their render engines are SMP capable, but all geometry translation/deformation is not. That would be one core right? Unless multiple cores could show up as one single core/proc in the OS..
Has anyone stopped to look at modern software while thinking about Dual-Core?
Both Intel and AMD have decided upon dual-core as the future of desktop computing. There will be no more massive Mhz increases... instead the focus is now on parallel computing.... But, seriously, how many CPU intensive applications outside of the server arena take advantage of SMP?
As someone who has ran dual-cpu workstations for years, I can personally attest to the fact that 99% of CPU heavy tasks do not make use of SMP.
Think about it... That copy of Doom3 or Half-Life 2 that you just bought, that runs like shit on even top-of-the-line hardware, isn't going to run any better on Dual-Core, because these games are not designed to run multiple threads simultaneously. Neither do most archival programs (WinAce, WinRar, WinZip, SevenZip, etc etc). Nor do many of your encoding tools (though FlaskMPEG and GoGo-No-Coda are noteworthy exceptions).
As a geek, I can attest that the *nix arena isn't much better. Just because the source is open and available does NOT mean that the author(s) ever considered coding CPU intensive tasks for multiple processors. And "porting" tasks from single threaded to multiple threads is NOT a simple task. This is one of the reasons that there are Computer Science degrees -- writing good SMP code isn't something you learn at technical schools (or even half the full Universities out there).
Don't get me wrong... as someone who has ran SMP boxes for the past 10 years, I'm really excited about Dual-Core. But don't expect it to be worth a whole lot for the immediate future... as no one outside the server arena really codes for SMP.
aanndd iitt sseemmss ttoo rruunn rreeaallyy ffaasstt!! FFiirreeffooxx sseemmss ttoo rreessppoonndd rreeaallyy wweellll.... lloovvee dduuaall ccoorreess..
Intel is leading in chip sales because their processors are Extreme
I would like to see a more multi-threaded approach to game programming in general, and not all the benefits would necessarily be about performance.
One thing that has bugged me a long time about a lot of games (this has particular relevence to multi-player games, but also single player games to some extent) is the 'game loading' screen. Or rather, the fact that during the 'loading' screen I lose all control of, and ability to interact, with the program.
It has always seemed to me, that it should be possible, with a sufficiently clever multi-threaded approach, to create a game engine where I could, for example, keep chatting with other players while the level/zone/map that I'm transitioning to is being loaded.
Or maybe I really want to just abort the level load and quit the game, because something important in Real Life has just started occuring and I want to just kill the game and move on. With most games, you have to wait until it is done loading before you can then quit out of the game.
In other words, even ignoring performance benefits for a moment, if a game engine is correctly multi-threaded, I could continue to have 'command and control', and chat, functionality while the game engine, in another thread, is loading models and textures.
One has to wonder if this is going to provide Intel with a competitive edge against Sony's Cell processor in the gaming front...
Very true. I don't really consider AMD to be "late", although both AMD and Intel are late to the dual core. Also, AMD is just focusing on the more profitable server market, I don't blame them if they are getting an extra $700 per chip.
I saw a screenshot yesterday of a 8 way dual core Opteron box showing 16 graphs.
Cant say where though.
"If everybody is thinking alike, somebody isn't thinking" - Gen. George S. Patton
As already mentioned games already do make use of the GPU and the CPU so we're fairly used to some mutliprocessor concerns.
To say that most PC games are GPU bound however is a mistake - most games I've come across (and worked on as a games core technology/graphics programmer) are CPU bound - often in the rendering pipeline trying to feed that GPU.
Anyhow games are already becoming dual-core aware. Most if not all multiplayer games make use of threads for there network code - go dual core (or hyperthreading) and you get a performance win. Again most sound systems are multi threaded often with a streaming/decompression thread, again a win on multi core. These days streaming of all manner of data is becoming more important (our game worlds are getting huge) and so again we will be (are) making use of dual core there too.
I personally have spent a fair amount of time performance enhancing our last couple of games (mostly for HT but the same applies to true dual core) to make sure we get the best win we can. For example on dual core machines our games do procedural texture effects on the second core that you just don't get on a single core machine and still get a 20% odd win over single core. I'm sure most software houses take this as seriously as us and do the same. It's very prudent for us to do so - the writings been on the wall about multi processors being the future of top end performance for a while now.
At the end of the day though us games developers have little choice but to embrace multi core architectures and get the best performance we can. We always build software that pushes the hardware to the full extent of it's known limits because that's the nature of the competition.
Just think what the next generation of consoles is going to do for the games programmers general knowledge of concurrent programming techniques. If we're not using all of the cores on our next gen XBox or PS3 then our competition will be and our games will suck in comparison.
Does anyone know how HT and dual cores will work? Will it appear as 4 processors (2*2) or still at only 2, but with better performance? HT is one of my favorite processor improvements of late, things just seem to run smoother with it.
I did read TFA, but didn't see this.
"What do you despise? By this are you truly known." --Princess Irulan, Manual of Muad'Dib
/)
Having two non-identical CPUs in the same package, or in the same machine, isn't that useful. Typically, the "wierd" ones sit idle unless whatever application that specifically uses them is running. The operating system usually has no idea what to do with the "wierd" processor, so it gets managed as a peripheral, which doesn't work very well.
There were some wierd Mac variations in the 1980s with a second CPU on a plug-in board. They could run Photoshop faster, but otherwise were useless.
There are really only two multi-CPU architectures that are generally useful: shared-memory symmetrical multiprocessors, and networked clusters with no shared memory. Many other architectures have been tried - partially shared memory machines, shared-memory machines where some CPUs lacked some features like floating point, hypercubes, single-instruction-multiple-datastream machines, and dataflow processors. None has achieved lasting success.
About the only unusual architecture ever sold in volume is the Playstation 2, with two vector processors. Even there, the vector processors are mostly used as a GPU. (Although one major game physics engine actually runs in the PS2 vector processors, an impressive achievement.)
Programming for wierd architectures is hard, requires much tool development, and results in programs tied to specific hardware. So it doesn't happen much. That's why the wierd architectures fail. They're never that much faster, and by the time the software works, the hardware market is somewhere else.
For me, system responsiveness is my number one performance gripe. I hate to spend a lot of time waiting for the system to respond to mouse clicks, but I couldn't care less if it takes 70 seconds or 50 seconds to encode an mp3. As far as most ordinary users are concerned, multicore's effects upon UI responsiveness is more than worth it.
The toad can't burp - and for some reason can't fart either, so it swells up and eventually explodes. --Anonymous Coward
I think the focus for most programmers (and game programmers included) is to go multi-threaded since both AMD and Intel are really pushing this solution for speeding up programs.
There is also a movement to make Multi Threading easier with things such as Open MP http://www.openmp.org/ . It looks like the future will be good for SMP applications.
mnewberg.com
Intel began to ship dual core processors on April 11th; I submitted an article about it, but it was rejected.
In any case, I guess I'll have to home-build a computer with those Intel dual core processors soon.
Debugging? Klingons do not debug. Bugs are good for building character in the user.
I'm not particularly fond of Intel. My father used to beat me as a child with an Intel processor.
You can also put 4 dual core processors in a normal 4 socket motherboard to make a 8-way computer. AMD has tons of information on this stuffhttp://www.amd.com/us-en/Corporate/VirtualPre ssRoom/0,,51_104_543~94936,00.html
mnewberg.com
This has been studied, but you get more like 8 cores, not 64. Look up the DEC Piranha or Sun Niagara.
Compilers would be designed to break a program up not into a paltry 2 or 3 threads, but into dozens.
Assuming that was possible, which it isn't.
The most brilliant marketing spin evar. You have a warehouse full of chips that don't do floating point correctly. What do you do?
Design a motherboard that disables floating point and ramp up the marketing on the "486SX", a chip that "is cheaper because it doesn't have features most users never care about."
Profit!
Raise your children as if you were teaching them to raise your grandchildren, because you are.
Okay, sorry about the dumb ass question here, but I can't seem to find an answer:
Are AMD's and/or Intel's processors supposed to work in existing motherboards (err at least with SOME benefit...) or does upgrading to a dual core machine mean getting a new mobo?
"Derp de derp."
I wonder why Apple doesn't seem interested in dual cores though. ... Apple doesn't seem to want to have anything to do with it...
Says who?
Dual core way before Intel and AMD. So I guess that means that my SparcStation 10 with two dual-core MBus modules 0wnz0rs everyone who claims to be an "early adopter" when they buy dual-core Intel/AMD chips.
So what if the clock speed is only 55MHz for the SS10? :)
It's cheaper. Everything boils down to that.
The model-T wasn't designed for todays 10 lane, 75 MPH highways; that doesn't mean a personal automobile can't take advantage of them.
Its like this one software testing boss that wanted an excuse to fire me from my gig at Microsoft when I became moderatly disabled, so he told me that if I didn't find 10 bugs in the next week he would have to let me go. That wednesday at lunchtime, he fired me because I had only found 5 bugs by that point.
(I ended up getting a job in another department, so it's not MS in general)
give it time, dinosaurs take some evolution to start laying chicken eggs.
I've got a dual-core dual Slot 1 Pentium II 400MHz server that I use for running a brace of hard drives of a file server that I'd like to upgrade to a bit faster machine, but I don't want a computer that doubles as a space heater since this is going to be 24x7. I was thinking about buying an Opteron HE, but really would rather have something with a 2 cpus. The thing about the single Opteron is there seem to be a big lack of single Opteron MB's around, epecially those with a fast-wide PCI bus.
It seems what I really want - 2 cpus low power PCI-X 2 slots in an ZTX form factor just doesn't exist. If anyone has a suggestion?
We can barely code for two processors let alone beasts like the TMS320C62. Ignoring this for a second, what kind of memory are you proposing to feed all of these processors?
There are places where we have 'surpassed' von Neumann architecture. Surprise surprise its surpassed for things such as imaging applications. FPGA and ASICs beat Pentiums/Athlons in imaging applications hands down. For much less cost at that.
The idea behind physics processers is that they are designed to perform the types of calculations needed for physics simulations quickly, just as graphics coprocessors are designed to do matrix math quickly.
"Orthodoxy means not thinking--not needing to think. Orthodoxy is unconsciousness." --Eric Blair
Hetrogenous processors can be good things. However, you need to stipulate that they both use the same ISA. Then, it's just a matter of changing the OS scheduler to schedule the heavier process on the more powerful processor, and the lighter process on the weaker processor. No reason for anyone above the OS programmer to care. The benefit is that you can use less die space, and often achieve the same result. Or you can run your MP3 player on the smaller processor and shut off power to the larger processor. A hetrogenous processor can reduce power consumption on a modern processor substantially.
Anyone working on dual-core GPUs? I'd think with the graphics demand + the small amount of real estate on the card, it would be a worthwhile pursuit. Easier to implement than SLI, plus you could still SLI and get 4 GPUs.
Once again everyone on /. is going to debate about what is meant by "dual-core".
This chip could be used in clusters like nobody's business. An array of 128 of these processors could simultaneously handle 8,192 active threads.
True. But the problem with clusters and multiprocessing in general is that, if the application requires a lot of interprocess communication (e.g., a highly connected neural network), performance suffers. The whole thing boils down to the von Neuman bottleneck. Until somebody comes up with a type of cheap memory that allows unlimited parallel access, we will continue to be hampered. When parallel memory arrives on the scene, processor speed will not matter much for most situations: just have a whole bunch of cheap processors access a single huge memory space and voila!
IMO, cheap non-von Neumann memory technology should be the main holy grail of fast computing, not CPU technology.
Of course ASICs beat general-purpose processors. GPUs beat CPUs at pushing polygons. They're hand-tuned to a task, useful for only one purpose.
Ewige Blumenkraft.
I cannot recall ever hearing Intel sound so desperate. First they ship pre-release samples to a handful of friendly reviewers and then they announce that they have 'shipped' the product, apparently to beat AMD's planned announcement on April 21 but the sum total of the evidence for the alleged 'shipment' seems to be a claim that they have shipped the product to Intel-friendly Dell. No one seems to actually have it to sell anywhere and even Dell just says they will be shipping 'soon.' In better days, Intel used to send a new product around to reviewers under NDA a few days before an actual release. The NDA would expire on the day of the product announcement and then you would actually be able to buy it at the time it was 'released.' How times have changed for Intel...and for AMD.
Better yet, multi ARM cores... ARM are RISC and the instruction set is a bit more powerful. ... but oh wait... ARM already did that... ;-) They have 4-way ARM cores that are fairly low power/size [compared to an x86].
But if you wanted to stay in the realm of x86... I'd go for 486 approach. single-scalar pipelined. Not that much larger than a 386 but decently faster. Tact on a pipelined FPU and cache et voila, cheap core.
Tom
Someday, I'll have a real sig.
Before everyone gets excited about Intel's dual core - you should review some of the benchmarks at tomshardware or anandtech. The speed improvements are not that great. In fact performance in a gaming environment is not as good as their high end single core chips.
Intel is currently pandering to the gamer/workstation market. Given the Dell XPS announcement - clearly a target is the gamer. Is it really though? Would any self respecting gamer buy a Dell as their "l33t boXor"? Would they not already know that the nVidia + ATI + AMD64 platform represents the pinnacle of performance in the gamer world? Probably. I'm not sure that dell is going to see the boost to their XPS line that they'd like from the addition of this chip. Intel does get points for getting their earlier but it's not nearly the lead that AMD took a year ago with the deployment of the AMD64 3X00+ desktop processors. The bottom line however is that if you are planning to buy a new machine and actually do a little research you'll find that the Intel chips are not as fast dual core or not - as the AMD chips.
As far as workstation performance goes - the chip seems to hold it's own with some decent performance gains. The real issue with this chip and the architecture as a whole is memory bandwidth. For truly intensive processing tasks, video, audio, data processing, computationally intensive tasks, a fast memory bus makes a world of difference. Intel doesn't seem to have the architecture to support these types of task as well as it should. However, this may be the only area that AMD doesn't have covered well primarily due to the cost of their dual core offering. If you are looking for a workstation that can be programmed to handle multiple threads the Intel offering might be for you.
And then there is AMD - totally ignoring the desktop market. Instead they are going after the high end server market. Why? Itanic is dead - and there is a need, and a void for high density, but "cheap" machines. The dual core AMD provides high performance, low heat and competitive performance especially in situations where high memory bandwidth is needed. It also scales 2x further than the competing Xeon servers (The 8XX series could be called the 16XX series). Since the launch of the Opteron two years ago AMD has established the proper channels to deliver these chips to customers. Sun and HP both offer servers with these chips and will also be offering the dual core chips as well.
Pricing - which I think is most telling. AMD's products are priced at the high-end. They are the leader in 64 bit computing (Intels 64-bit approach is architecturally inferior). They will provide organizations who need this technology an upgrade path to the 64-bit world if they are not already in it. AMD chips scale better than the competing Intel technologies. Thus AMD will continue to consolidate their lead in the high end server market. Also, AMD appears confident that their customers will pay for their high end CPUs. In the workstation/gamer market Intel is trying to stoke adoption through lower prices. In some ways this is a contradiction - low priced chip in a high end segment. I'd argue it's the wrong strategy for stemming their loss of market share to AMD. Why go with an Intel dual core when you can get a dual Opteron? They are faster after all.
Though it comes down to the fact that Intel and AMD are after different things. The Opteron platform is a high-end platform. It's clear that AMD is making it a priority. A sound strategy, as Intel's blunder with the Itanium is still continuing to cause a slip in market share. Second is the AMD64 platform which offers great performance at a reasonable price. No doubt, when dual core hits the AMD64 their will be a bit of a premium to pay - it is a sound architecture which is just starting to hit it's stride. Conversely, Intel is trying to stem the bleeding on their desktop lines - clearly they see the high end gaming and workstation segment suffering. How desperate does a company need to be to tack on "Extreme Edition"
Believe it or not, most profitable businesses didn't get to the point that they are by BLINDLY supporting one supplier.
Sun is comming out with an 8 core sparc processor early 2006. That think is going to have some horsepower in it.
Man, that must have taken you too long to write that. Don't you have anything better...oh, nevermind.
Right now, of the 48 processes currently running on my work machine, only 9 are single-threaded.
Regardless of this, as other replies have noted, SMP means intensive multitasking is that much smoother.
Never mind that computers generate even more heat when they're actually being used. And that almost half the time it's "not being used" is time I'm still sitting in front of it thinking about what to do next.
Karma: It's all a bunch of tree-huggin' hippy crap!
wow.. look at these two guys go at it,
http://slashdot.org/~gangofwolves
http://slashdot.org/~redswinglinestapler
They've plastered this story with pre-packaged comments and taken a massive bite into the karma stack. Nice going guys!
Heh, scroll up and all you'll see are those two names.
Have the marketroids not figured out how annoying that moniker is getting? Or do the masses still think it's chic?
Lost at C:>. Found at C.
Having said that it is so much easier to buy one chip than to try and link up 6 or so computers.
Hmmm... decisions, decisions...
Mens et Manus
Plagiarist.
2) This guy started an account yesterday and is pumping out comments like mad that clueless moderaters might consider insightful to pump up karma. Ignore him.
The Xeon parts to come are SIP, but it looks like the EE is a single die. Though, with no on-chip interconnect, it seems a distinction without a difference. EETimes.com - Potholes seen in latest Intel road map
Free login required. Messy to reach the article if not already logged in. The login dumps you at the the main page, not the page you wanted. Click on the link again after logging in.
1. Design software
2. License software per cpu
3. Wait for multicore cpu's
4. ???
5. Profit !!!!
-- "It's not stalking if you're married!" My Wife.
This comment is just a rip off of another older comment ( http://it.slashdot.org/comments.pl?sid=137696&cid= 11515177 )
Haven't checked for others, but I really wouldn't doubt if he's ripped off others.
If I can't smoke and swear I'm fucked.
So a game job requires uni degrees, but they dont use SMP? What are the unis teaching? java/.net? how is that usefull for games.
Now surely some/most games would use more than 1 thread, ie even if audio was on a second thread. It also is sometimes easier to program using multiple threads doing their own thing, rather than try to fit the whole game logic in one giant while() statement.
Liberty freedom are no1, not dicks in suits.
Yeah, this guy is just stealing other peoples comments and reposting them...
with the current karma system, I have no idea why someone would want to do this, unless he just wanted to see how long he could get away with it for.
If I can't smoke and swear I'm fucked.
According to The Inqurier here Intel's new EE model was scheduled for next month until shortly after it was leaked AMD was releasing dual Opterons this month in NY.
The Intel chip is in my opinion a proof of concept and will have the availability of the original P4EEs. Its also a pointless model, games aren't multi-threaded. AMD however is releasing a CPU aimed at the major multi-threaded market, high-end workstations and servers.
I'm considering purchasing one of these to replace my aging Wintendo box. But one concern comes to mind:
Essentially, how will Windows XP be licensed? Last I remember Windows XP Home supports only 1 processor and XP Pro supports 2. Processors with Hyperthreading already look like 2 processors to the OS - won't this thing look like 4 processors (2 real + 2 hyperthreaded virtuals) and break the XP licensing model? Or does XP not count the hyperthreaded processors as real? (I thought it did...)
-Jack Ash
Read the two part review of Intel's new dual core chip at www.anandtech.com. Maybe you'll put away your typical slashdot pessimism away.
... but Everyone runs a few programs at once.
... but the testers could easily flip back and forth between many different programs, each doing hard tasks, without the computer stalling or the programs going totally non-responsive, and overall more being accomplished in the same time.
... Constantly having to flip back and forth, fire up one, close another, grab a coffee while I wait.
Yes, very few programs are ready for multithreading now
They did a great multi-tasking test to compare the usability of the new dual core chip at 3.2ghz versus intel's 3.73ghz single core chip. And pointed out that Windows XP is in fact multithreaded and can benefit well on its own from a dual core chip.
Of course the single threaded programs ran about the same as usual
The 'real-world' usage tests showed a huge benefit to having dual core, with much smoother operations, far better than hyperthreading alone.
Poor non-HT AMD user's like myself dream of being able to multitask that much without waiting forever when switching between active programs.
I have no doubt that I literally could save an hour or two per day of wasted time at my job if I had a dual core processor. Two large autocad files, an ArcGIS dataset, text editors and more
George Bush + Linux = "I will not let information get in the way of the fight against Windows"
For what it's worth, the parent is a blatant ripoff from this post from January:
= 11516655
http://it.slashdot.org/comments.pl?sid=137696&cid
Asside from your tollingness, there are problems, and there are significant advantages to what you are suggesting. Let's go through some of them:
.09 micron technology, not only is there no way to reliably detect manufacuring flaws, but virtually every chip manufactured on the technology will have these flaws (sure, the big companies have big sophistimacated electron microscopes to see, but that's expensive, and running one of these over every chip would get out of hand fast). With a core the size of a Pentium 4, these errors are almost guarenteed to happen in a few choice transistors that really don't do much (MMX, SSE(1-3), possibily one of the ALUs), simply out of probability. On a core the size of a 386, virtually every transistor taken down will kill that core. So even on a chip with 150 386-like cores, you're only looking at even 100 of them running perfectly.
First of all, with a chip the size of the 386, you can almost see the components, and manufacturing flaws are really easy to detect. With a chip manufactured on
Next, memory archetechure. You're going to need several busses to connect memory to this thing; if you arranged the processors in a cellular fashion on chip, 8 to 16 at a time hugging on to one independent memory controller, you're going to have 10-20 links to deal with, each link consisting of around a hundred pins for the actual processor itself. You're looking at very easily a 2000 pin out chip.
Next, archetecure capability. Each processor had one Integer unit, an NO onboard FPU unit. This makes the processors great at doing nothing.
And now, let's talk about the current environment. The Cell Processor (joint venture from Sony and IBM and a few others) is a processor with a Power-4-like core, with a bunch of float units tacked on to the end of it, making it extremely parallel to execute a series of operations on a lot of redundant data. They call it a "stream processor" for this reason, as it would most likely be used to process "streams" of data; a bunch of signals coming in, pixels to go out to a buffer, etc. The current dual-core projects are making it to a point where they're replicating current industry leading chips, and smashing them together on a single core. Eventually, I believe these companies will see that while this is intellegent, they need to refine the idea; stick 4 ALU/4 FPU, an SSE unit with an MMX translator front end (saves silicon), and a bunch of load store units, running them all in SMT. While this is really pretty much what is going on now (two Pentium 4's almost contain all of that), there is a lot of redundant silicon that won't ever be touched, which is wasting valuable CPU space, and producing more heat.
If we were to take your idea and run with it, I'd suggest taking a bunch of Pentium Pros (like 8 maybe), and sticking them on one die with a Pentium 4. The Pentium 4 can pick up and run any SSE/MMX code, and the 8 PPros can go to town on any huge amount of FPU/APU code. Couple this with a shared L2 cache (probably would want 2 L2's actually; one shared between all 8 PPros using the technology they're using currently with the Pentium M to turn off sections when they're not needed, and one for the Pentium 4 as MMX/SSE code will hit the L2 a hell of a lot more often), and you've got yourself one mean, number crunching machine.
One last note: Who's to say this very technology isn't already in existance? Have you ever read Digital Fortress by Dan Brown? In the book he speaks of a machine capable of cryptographically breaking all current encryption systems with a high level of simplicity. If you were to have maybe 512 of these (100) way processors, you'd easily have 51200 chips at your command to run a distributed key check algorithm over. I'm pretty sure a machine with this power (although consuming the power of a small city, and needing a cooling system like Niagra Falls, not to mention costing nearly/more than a billion dollars on getting the CPU manufacturers in Taiwan to make these chips, having people de
"Victory means exit strategy, and it's important for the President to explain to us what the exit strategy is." G.W.Bush
Dell "said it would begin shipping its Dimension brand of PCs with the new chips relatively soon with prices starting at around $3,000."
So why would you pay 3000 bucks for two throttled CPUs on one die, if you could get a dual PROCESSOR system for the same price? I mean, the second heat sink is not going to raise the price of the system to another level... and you can go with proven technology.
Actually, I would only consider a dual AMD64 system worthwile. With NUMA support improving in Linux, this should be a lot faster than 2 P4 cores competing for the same memory, already suffering from high latency.
...I've never had a single problem with a recent VIA chipset.
Granted, back in the day they were a steaming P.O.S. but my last two machines (the first of which was assembled ~3 years ago) have had no problems at all.
My current machine has the KT800 pro chipset and I haven't had 1 single BSOD in the 4 months I've had it - even when using unnoficial drivers (I use the kX Project sb-live driver as it gives me low-latency asio for use in cubase).
The real problem was their driver bug with the old 4-in-1's but the hyperion range sorted that out nicely.
I am NaN
They are. This "news item" is so full of pro-Intel baloney it has to be a paid placement. AMD started shipping their dual core Opterons to OEMs a couple months ago. HP will have a dual-core Opteron server available for immediate delivery on AMD's release date of April 21. Intel wanted really badly to be first with dual core processor release,
A couple of weeks ago the official date for amd dual-core chips was for Q3 or so, they moved it to 21 April a couple of weeks ago. AMD is playing the same game than Intel.
Doubling the number of cores on a single chip doubles the transistor count. Increasing the clock speed does not.
I am TheRaven on Soylent News
Just last week we were all ment to assume that Dell (oops, I mean Intel) wasn't ready to ship dual core until Q1 of next year...
Intel announced that they'd ship their cual core chips more than a month ago. It you're suprised, you're the only one
More or less. For first-generation dual-core chips this is about the only benefit. For one with a shared cache, you can see more efficient use made of the cache since two threads (executing on different cores) accessing the same data can access it from the same bit of cache, increasing the effective cache available. On dual single-core systems, each chip would keep a copy of the data in cache, which would be invalidated whenever another CPU modified it.
I am TheRaven on Soylent News
I read somewhere that Intel's dual core Pentium Extreme Edition would require water cooling. I don't see why anyone would want this chip right now. It's like sitting on an extremely expensive time bomb waiting to burn up. I'm sure it will bump up the price of the computer a grand or more and not provide any real benefit to the user. Until software catches up, the main place we will benefit from multi-core processors are servers and high-end workstations where the software is multi-threaded and designed to support multiple processors already. AMD's got Intel beat on this one.
Suns latest SPARCs have been very disappointing, although Fujitsu's line still shows some promise.
I am TheRaven on Soylent News
My general purpose chip is made by FreeScale, and the vector processor is made by ATi. Perhaps you have a similar configuration?
I am TheRaven on Soylent News
How much of DSMT will be compiler-bound and how much can be pushed onto hardware without redesigning and remodelling, say, GCC?
(I say compiler-bound because making an automated process to optimise bits of a software program to run together is a logical analysis that can either be done at compile time or on the processor chip. I admit to being a layman, though.)
Surely getting the GCC to include optimisations for parallelism is an essential part of its future in software production? Isn't there a high likelihood of DSMT providing significant performance enhancements that it would be a patented invention and consequently (reasonably) unique to a particular processor manufacturer's implementation of the architecture to which it is applied?
(Do I have the wrong end of the stick?)
And if you're not in a position to Just Say No, then you already have big problems, regardless of how many processors you use.
As copyright owner of this comment, I authorize everyone to defeat any technological measure which limits access to it.
WWhile I agree with you that Intel certainly has wandered from the road to success in the marketplace recently, I do have to disagree with your statement,
"AMD - totally ignoring the desktop market."
I don't see that. All of AMD high end processors are nicely positioned to transition into the desktop market as software for these cores comes into existence. Their strategy distinctly places them in the drivers seat when it comes to the desktop market, and in a fashion that had ought to scare the pants off from the Intel engineering group. AMD has pulled an Intel on Intel.
I do also agree with you on another point though. Intel's new dual core is a miserable show of capability in my book. Why would anyone want to pay more than twice the price for the same performance as an existing single core processor? If anything, Intel seems to be making a case that dual cores are not cost effective and can't compete with the existing single core technology, which shows no signs of slowing down in it's progress. Intel's implementation is sloppy, poorly thought out and extremely inefficient. Why bother? I think they are afraid and felt they had to show something, despite the blatant shortcomings.
Buyer beware. These new intel dual cores are not what they seem. Read the reviews and tests and see for yourself.
They've already obliged our British friends with the P(R)IVEE
So we've got the POOPEE, the P-PEE, and the P(R)IVEE and we wonder why no one wants to analyze core dumps anymore.
--- I wish I could hear the soundtrack to my life. That way I'd know when to duck.
This is true.
I'm employed as a DSP/FPGA programmer. I'm currently working with a chip (ADI Blackfin) that can encode realtime MPEG2 audio/video at a blazing fast 300MHz, while dissipating half a watt of heat. And the chip costs ~$10 USD! Yet I remember the big thing on Tom's Hardware a few years back when a close-to-$1K, ~1GHz P3 or Athlon pushing 30-40 watts of heat finally could do realtime MPEG2.
(and this DSP chip does plenty more than MPEG encoding. It even runs Linux.)
The x86 architecture is old and just "too flexible" - It's not fundamentally designed for many of the things that we do with today's computers. Things like audio/2D-video processing are suited for DSP architectures, and 3D graphics are suitable for vector processors. The x86 architecture can thrash away with add/shl/cmp/call instructions and get these things done - but only when it's running brutally fast with huge caches and putting off gobs of heat in the process.
You can only play that game so long - eventually, the fundamental architectures of computers will have to change and things will have to become more specialized for the things they do. Personally, I'm anxious to see things like DSP cores and maybe even small reconfigurable FPGA cores integrated into CPUs...
I've been thinking about upgrading my pc, and want to go either dual-core or dual processor. The dual Opteron (not dual core, but the ones that have been out for a while) looks pretty attractive. But, with this dual core thingy, should I wait? Should I just get 1 dual core chip instead? Say I have $1000 to use on 1/2 cpus, ram, and a motherboard. Assume that I use very few (if any) multi-threaded apps, but have many apps running concurrently.
"Would it kill you to put down the toilet seat?" -- Maya Angelou
You forgot to turn off local echo on your terminal there, buddy.
Be relentless!
DSMT is completely done in hardware because of the dynamic behavior of most commonly used programs. Only the CPU at runtime can accuratley model the dynamic behavior, so the compile does nothing. Sure programs with parallelism in them originaly will do better, but by having the hardware to the thread generation more of the dynamic behavior can be captured (dure to dynamic data) and every program can benifit. It does require a complete redesign of the CPU, but the benifits could be tremendous.
Space for rent, inquire within
With AMD's dual-core processor launching today I can finally state that for the record, I've been working with OEMs on AMD's dual-core chip-based solutions for months now. AMD sent dual-core chips to its OEMs long before April 12. Go by RAMBUS memory if you believe everything Intel tells you.
Did anyone bother to ask the customers what they want?