Slashdot Mirror
Dual Core Intel Processors Sooner Than Expected
Hack Jandy writes "AnandTech reports that Intel's Smithfield processors are going to get here sooner than they originally predicted; most likely within the next few months. Apparently, the Intel roadmaps reveal that the launch dates for next generation desktop chipsets, 2MB L2 Prescotts and Dual Core Smithfield processors (operating at 3.2GHz per core) are almost upon us - way ahead of the original Q4'05 roadmap estimates. Hopefully, that means Intel will actually start shipping the new technology instead of waiting four months after the announcement for retail products."
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.
Slashdot: Where people pretend to be twice as smart as they really are by behaving like children.
This means I can shut my furnace off this winter, instead of waiting until the end of 05.
You see? You see? Your stupid minds! Stupid! Stupid!
As I see it, the smart step to take would be to start with consumer-level 64-bit chips, make them as fast as they can be, and then move on to dual-core. The only way dual-core could be better at this point is if it is given to the server market, where 64-bit Intel processors already exist.
Consumers like me are usually stuck with one-core, one-processor 'boards. It doesn't help with boot times, whether Windows or Linux. I wouldn't mind a 3.2GHz/core dual proc at all, no matter how toasty it gets...
You can hold down the "B" button for continuous firing.
I read about multicore processor in American Scientist a few months but I didn't expect to hear of production units for at least a year.
I don't need a compass to tell me which way the wind shines.
I can see how this is good for gamers, but normal office use? The biggest waiting time I have on my centrino is network. (In a big company, network by Siemens, it can take 15 seconds between O and a complete list of network drives. Go figure.) Servers will opt for the 64 bit thingies, your secretary doesn't need one; is gamers a big enough market share to make money on this shit?
10 ?"Hello World" life was simple then
Intel added the x86-64 instructions to the Xeon line and called it EM64T.
Read up!
http://www.intel.com/technology/64bitextensions/
500GB of disk, 5TB of transfer, $5.95/mo
I ran dual P3s for a while last year. While I loved the responsiveness of the system, I hated the lack of programs avalible to take advantage of SMP.
How is this year going to be different?
Even if you *could* get SMP aware versions of your software, would it be worth it? Lots of problems are harder to solve when you add SMP to the mix.
Gamers will be put off by the fact that games can't take advantage of SMP.
Home users will be put off by the fact that their $500 Dell surfs the world-wide e-mail just fine.
Buisness user may take advantage of this in servers, but there's only so much cooling and power you can provide to a 1-U server.
So, how is dual core going to ever be anything bigger than Itanium, Xeon, or any of the other technologies that fail to meet customer expectations?
I'd rather you do it wrong, than for me to have to do it at all.
I find it interesting that Intel has code named these chips using the same name as one of the world's largest pork processors, Smithfield Foods.
I expect that these chips will be large power hungry pigs.
Let me get this straight..... Intel(or most any other company).... getting something out earlier than expected ... I felt a great disturbance in the force. The earth has stopped moving.
-1 Redundant, but how can they possibly do this? Their heat issues are so out of control that I can't imagine, BTX or not, how this is feasible without liquid cooling...
You don't generally run one application at a time, right? So I don't see the problem.
See which product comes out first:
Intel Dual Core chips
or
ATI X850 XT PE
Anybody recall how many months passed between the Pentium IV trademark registration and the release of Pentium IV processors?
I would have thought Dual core chips would have already been available by Intel already.
People complain a lot about Sun Microsystems, but the Dual Core in Sun's SPARC IV has been out since last April or May I believe.
Doesn't AMD already have dual core cpu's shipping as well? IBM is working on a dual core G5 as well aren't they?
Heck, is this even news?
Shouldn't we be talking about 4 core cpus that are already working in development labs around the world. Sun and IBM both have those... I would bet money that AMD and Intel both have them running as well, and if they don't they better get moving!
Want to change Intel's behaviour? Don't give them any press when they announce "real soon now" stuff, only when they actually ship. But if /. (and other media) print every press release, the press releases will keep coming.
Everybody's a libertarian 'till their neighbour's becomes a crack house.
What's the next marketing scheme? The only way to find out is to closely follow the events. By the time most people grokked DMCA, it was too late.
Also, here is your chance to speak out against any possible ripoffs you can already detect... at least if someone doesn't mod you down :( But then maybe that's because you're stating the obvious :P
For all we know, the reason they are coming so much sooner is because they are simply relabeling their HT cores.
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.
/dev/random
"I wonder if it would be possible to have both a P-M and a P4 (or P4 like) core in a dual-core processor. This way you could get the benefits of both architectures on the same chip (P4 is fast in mp3/divx encoding for example, and P-M is fast in gaming). It would propably require some special scheduling from the OS though..."
I wondered the same thing about the G5 and the G4, like a portable with power when you need it!
You get a lot of value even using non-multithreaded apps, eg make -j2 almost doubles compile speed on largish projects on a dual processor system even though the compiler is not multithreaded.
Until multiprocessor systems are more widespread, its barely worth the effort. Writing multithreaded apps is a royal pain, and the development tools don't help either. For instance std::string in VC6 is not thread-safe - you dont even find these things out until trying to do multithreaded stuff.
http://rareformnewmedia.com/
640k is already way too much!
It's the year of Linux! To celebrate I have x free hotmail accounts to give away
Im a software developer and REALLY hate the movement towards dual-cores. While dual-cores will be great for some things (I tend to write everything using threads where its easy to leverage performance) there are many apps (many of which I have no control over, no source access or the cost of re-writing (legacy apps) to be multi-threaded is too high) which need pure-raw processing power and this means its going to take far longer for that power to be available.
Its a bad move IMO on AMDs and Intels part - personally rather than head to dual cores I'll be looking more and more towards how to get the maximum (i.e. overclock) out of the higher rated single core processors - and this is from someone who normally upgrades every 12-18 months.
That said if the dual-cores overclock well my stance may change....
http://www.redlightrunner.com/lib/redlightrunner/c rowdcontrol.mov
sorry, don't kow how to fix the link
"Yeah, yeah, yeah.... Now where's the latest mac ad - It's been over 24 hours since the last slashdot front page sighting...."
I don't completely understand how dual core processors and dual processor systems work. I'm wondering if there could maybe be a way that Intel, through certain hardware advancements, could have allowed the full power of dual core processors to be used on all applications. I'm thinking not, since this has not been mentioned. Could anyone help explain this to me?
You wasted ten seconds of my time when I read your bullshit pseudo-rant and attempt at niche sarcasm. I hope you die. I have just become stupider for having read it. Fuck you.
after reading the previous post about the new pentium-M chips and this one, I'm a little surprised that no one seems to be complaining about the heat and power problems with the G5 CPU. As it is, my G4 1.5 GHz powerbook heats up to beyond comfortable temperatures (while on my lap) and delivers a sad 2 hours of battery life (w/ screen as dim as it can be). Maybe apple should take a page from the Intel centrino book when designing new G5 powerbooks
Take a look at what happened on Apple's side of the fence in the last couple of years. The G4 was lagging in speed. So they started offering out-of-the-box SMP offerings. This brought SMP into the hands of any mere mortal who could afford one (i.e. no special home-built config. You want the fastest mac? get a PowerMac)
:)
Now, software developers had no choice but to build their apps multithreaded if they wanted to keep their clientele coming. But even more interesting is that the OS became more and more SMP-aware, to the level that many single-threaded apps could profit from this (sound, graphics, interface, etc offloaded to another CPU).
What dual-core CPUs will do is help more software be SMP aware. Developers usually want their apps to perform well. If the MHz stop climbing, they'll have no choice but to optimize their apps. So the OS will be multithreaded, the apps will be multithreaded. Soon enough, computers with a single-CPU will be considered outdated. And thus the chicken-egg problem will be solved
I was just reading that most people here don't like the idea of multi core processors because their games like Quake won't run any better.
Lately I have been doing a lot of work on distributing software to the internal network and RARing files. I would like the option of just RARing and not have my system turn to mud. Having one core running flat out giving me a chance to still do work is a great idea! Besides I'm sure a better balance with all of those 50 processes on my Windows box would be nice.
Likely to ship to OEMs at the end of Q2, about 5 months from now. Volume in Q3.
But these Smithfields will feature poor application performance for the vast majority of applications that only take advantage of one core, with 2.8-3.2GHz cores, and terrible power dissipation of 130W.
This is because they are not true dual CORE parts, but rather, two 1MB L2 Prescott parts side by side on 1 package.
Considering their low power useage, I am surprised that Transmeta has not pushed into multi-cores. Of course, I noticed a powerpc with > 700 mips and using < 1 watt of power.
I prefer the "u" in honour as it seems to be missing these days.
Mmmmm Minesweep/Solitare on SMP, sooner then I thought possible :oP
All I need now is another pair of hands, keyboard and mouse -- maybe that was what USB was for in the first place.
/. is good for you.
More than one processor is "allways" better but only if the OS supports it fully. I should add "and if the application developers would think a little". My age shows - we started multi-threaded in 70's ( multitasking - better than threading IMHO but the basics are same ). What is missing in most OS support is the control of what, where, when and how much the threads are allowed to use one processor, I/O channels, etc.. It makes a huge difference in speed, resource usage and reliablility. Anyway - it will come even to Windows and how it handles resources - waiting some responses to Outlook locks the system independent how many processors there is - I have two. Some other applications do the same - C#, XP and multiple processors doesn't play nicely (yet).
Linux ( AIX, Solaris, etc ) are better on that today (IMHO). And a question - what is so difficult in making multi-threaded applications. To do it well needs some thinking ( thread pools suck badly if not used correctly ) but other than that ??
Using latest nanotechnology research, CPUMax developed the first CPU speed booster that dramatically enhances the CPU speed and reduces heat output. CPUMax is based on the SiXR, a new exclusively developed nanosemiconductor material, resulting from years of laboratory research. CPUMax foil speeds up the movement of electrons in the silicon substrate used by 99% of all modern CPUs and thus provides improved CPU speed. CPUMax is a small (11.4 x 19.2 mm) rectangular sticker which is installed on the CPU packaging. Users just need to attach CPUMax to the CPU or the case of the computer. They claim users will notice a CPU speed improvement after 5 to 10 booting cycles!
With how much wattage the Intel dual cores will eat and using the same tired design I can see Next Gen console cpus beating them up.
Today's CPUs are, in the final analysis, little different than the 386 launched in 1985. Notable exceptions are in details like feature size and operating frequency. Other significant differences are in the pipelining logic, crufted on instruction sets (mmx anyone?) that are rarely called into action, cache and pinouts.
.09 micron process... consider that the 386 had 275,000 transistors- compared to the P4s 42 million. You could fit around 150 386s in the space (on the die) of a single P4.
Now, take a step back and imagine what a classic 386 would look like on a
Now, of course there are many advances to consider over the 386, but fundamentally, that processor logic is capable of handling 99% of 32 bit computing tasks. They may have done so slowly, but there you are.
My thinking is, they could use some of this old logic, buff it up a little to accomodate some modern techniques and carve it all into a single die. Imagine a CPU with 64 simple processors, 4Mb of cache and some controlling logic running at 3-5 Ghz. All this in the space of and at the (manufacturing) cost of a single P4.
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.
What use would it be? Off the top of my head, this would be perfect for real-time monitoring, transaction processing, switching and so forth. There would also be serious advantages in the desktop space as compilers and kernels were built to adapt to the new distribution of resources. Image processing could be handled using the same techniques as SLI cards use to split the tasks up over two or more video cards, and any other large body of data could be simlarly broken up. Compilers would be designed to break a program up not into a paltry 2 or 3 threads, but into dozens. Speed and responsiveness would skyrocket, while fab costs and board speeds remained stable.
This might be the logical outcome of the current drift towards multiple CPUs per die, and it could also unite and surpass the schools of CISC vs RISC, as strategies from both would benefit the endeavor.
I believe Id took advantage of dual G4 CPUs in Quake 3. From what I recall one CPU was assigned to AI and audio while the other handled graphics and such.
As AI gets more realistic, it needs more cycles. I think dual core CPUs have their place.
Also note, at 12 MHz, 128 386's could do an amazing 1.5 GHz clocks in total, not counting all the overhead for getting memory to flow between 128 different processors not even designed for dual-processing.
the INMOS stuff was more along the lines of discrete processors(with built in RAM controllers- another idea dredged up from history and recently applied to the x86s) and that you can easilly string along into clusters.
What i'm talking about is maximixing the versatility of a single die (through wide distribution of simple tasks across the logic).
The inherent threading of OCCAM is interesting though. It would be quit useful for the chip I'm suggesting.
I find the overrated and troll modifiers to be amusing. I guess Slashdot is like everywhere else, and contentious opinions are just as unwanted.
Need a Python, C++, Unix, Linux develop
this will make people running distributed computing like SETI or Folding@Home drool all over the keyboard.
Seem to be rather soon to me, some weeks ago some news sites told that Intel had "some problems" with heat in multicore processors, and now there aren't? I think it's just promotional and nothing more, just a way to make Intel fans wait longer instead jumping to AMD dual core 64 bits cpus to be released in the second half of this year.
By the way, most of the software available today is single-threaded and just a few "pro" apps can take advantage of two processors on a system. Are people really thinking that buying a dual-core cpu will make their system fly or something? It won't! Buying a SSE3 enabled CPU doesn't mean a thing if the software doesn't use those instructions!
People are thinking in 64bit dual cores, but developers aren't. just that.
"Only two things are infinite, the universe and human stupidity, and I'm not sure about the former" - Albert Einstein.
I'm not sure what kind of programs did you use...
I do some development in bioinformatics, and it seems to be pretty good case: most applications are divided into different processes (SQL db, WWW server or X server are examples), so you use about 2-4 threads most of the time... when you are short on CPU ;-).
(Indeed most applications with more sophisticated user interface can be treated as 2-way.)
Development tools like make or JVM are also to be multithreaded. (But in case of make you need to add an option.)
PS I personally look forward to dual-core laptops! As far as I can tell, they could give twice horsepower for half as much energy... because energy usage grows quadratically with gigahertzs.
I edit up a movie and choose- burn this sucker to DVD.. anywhere from 4-12 hours later, using the computer for nothing more intensive than webbrowsing and email, I have a DVD..
now I could plain doom3 while I wait..
every day http://en.wikipedia.org/wiki/Special:Random
Stupid opinions are unwanted too.
So, show me either an instance of Intel admitting they are now playing follow-the-leader, or an instance where they are actually leading. Is there any reason at all to pay the price premium they charge for their hardware?
Need a Python, C++, Unix, Linux develop
RAWR, no discussion of dual-core CPUs is complete w/out a mention of Herb Sutter's The Free Lunch Is Over: A Fundamental Turn Toward Concurrency in Software!
[o]_O
consumes 10 W / GHz. While it is a more watts than the powerpc, it is is still a great deal less than the intel/amd world, but compatable with them. That is why the interest in seeing them dual core it. 2GHZ and ~20 Watts.
I prefer the "u" in honour as it seems to be missing these days.
do you have the ADD, or is it just some manner of reading comprehension problem that prevents you from understanding my initial post?
Adding transistors to reduce 'the adverse affects(sic) of pipeline stalls' has nothing to do with chip speed. Feature size and materials are the predominant factors in scaling clock frequency. Those other features are just hoo-haw wizbang addons that boost the performance of the chip by augmenting the quality of data flow. not the speed of data flow- the quality.
aside from the major revamp with the pentium pro, there really haven't been any major changes to the core logic since the 386. maybe you should do some reading up on this stuff before trying to spar with a professional.
The real issue with all of the features added to the x86 line over the years is working to keep the "386" in the heart of the proc fed with data. so you can take a huge chunk o' data and play musical chairs with the pieces, as they do now, or multiple tiny chunks sent to 2 or more units as they are now implementing (ahead of schedule, even), or as I am suggesting.
Apparently Dell has already made a few machines and they are in quiet circulation. Expected release date is May-June
http://shit.slashdot.org/article.pl?sid=05/01/29/1 61217
Will AMD respond by moving up the "release" (in very limited quantities) of their dual-core CPUs? Will the race to dual-core cause Intel to release a chip that's not ready, like the 1.13 GHz Pentium III?
TO START
PRESS ANY KEY
Where's the 'ANY' key? I see Esk, Kitarl, and Pig-Up...
Everyone bitches and says that software apps do not take advantage of dual-cores so whats the point?
Evolution is the point.
What was the point of the first TV station? No one had televisions to watch it!
Why create SATA drives? Noone's motherboard supported SATA!
Someone had to take the first step. When dual-cores become standard, people will start writing software to use them. At the rate software is growing we will need dual-cores to do anything in under 5 minutes. How long does it take your OpenOffice to start up? How long would it take on your system 5 years ago?
according to intel rhetoric, the benifit of having dual cores is the ability to run two cpu intensive tasks at an optimal speed, as anyone who has tried to burn a dvd movie whilst surfing would appreciate. so following that logic, i dont think that dual core will really benifit ANY ONE app, but rather speed up the use of multiple apps being used simultaneously.
-distantbody
EMPEROR GROVENTINE: Now witness the power of this FULLY OPERATIONAL BATTLE STATION! Fire at will, commander!
Will AMD forces destroy the shield generator in time? Will Linus Waterwalker give in to the dark side? Will Darth Gates find a better remedy for his chronic asthma? Tune in next week for the next exciting episode!...
This is my reply. http://www.aaronpentzer.com/ -Aaron Pentzer
at least a quarter of voters still believed that Iraq had WMDs and ties to Al-Queda.
I know you Americans are ignorant and believe what your Democrat media and Hollywood tells you, but that dumb?
So 75% were unaware of the Iraqi WMDs and the Baathist support for al-Qaida, Hizbollah, et c? Wow.
Nice to see that they were able to push this crap out the door ahead of schedule once they realized that AMD was whipping their asses in an area where they should have been the leader.
Unfortunatly for Intel, winter is going to be over soon (at least in the northern hemisphere) and I don't think the southern hemisphere market is that big (Australia, South Africa and South America). Besides, with general trend of global warming smithfields are truely going to be margional processors without demand.
... he wants you to fund his 25 processors on a single chip project.
/ /c olorforth.com/25x.html
Referenced from http://colorforth.com/
but only visible via the way-back machine:
http://web.archive.org/web/20020806132234/http:
With that out of the way, I think what you propose sounds great. It'll take programmers another decade to adjust to the new model, but I think it would reveal advantages we haven't even thought of yet.
"The workaround is to 'bind' a device to a specific processor with a tool called the affinity tool that has been around since NT4, and can be downloaded at microsoft.
As the readme in the affinity package states:
"This Interrupt-Affinity Filter (IntFiltr) allows a user to change the
CPU-affinity of the interrupts in a system.
Using this utility, you can direct any device's interrupts to a specific
processor or set or processors (as opposed to always sending interrupts to
all the CPUs in the system). Note that different devices _can_ have
different interrupt-affinity settings. This utility will work on any
machine, regardless of what processor or interrupt controller or HAL is
used. "
And the HowWorks tells something about the effect of the tool
"As a result, lower drivers (which use entries in this resource list when
setting up their ISRs) will get their ISRs installed only on the set of
processors that the user has specified (via the IntFiltr configuration
tool). "
Wich means that a low-level driver will always get its information (or 'data') from one processor; thus avoiding the loss of cache coherancy."
Read the test here.
I am currently wanting to go to ITT tech so I won't have to spend my life fixing spyware infected pc's for lousy pay.Any suggestions on a career choice that won't get outsourced to india before i graduate?I like working on the hardware and software sides of the fence,I'm good with 98-xp but haven't got to do much with *nix as my isp won't run on it.Any help and I'll be so grateful.The only pc guru is the owner of the local pc shop and he lost $14000 last year and calls me for the problem installs.Thanks /.
ACs don't waste your time replying, your posts are never seen by me.
Picture **THIS** my friend:
the advertising schema for the dual, then tri, then quad processors could follow those damn razor blade commercials!:
Slashshotted? Feb. 31st, 2007 (c):
''Intel has recently come out with the Pentium II Mach 4 Core Processor. The new wave in disposable CPU's, the Mach four features not one, not two, not three, not five, but FOUR incredibly dull processing cores used to reap your winrar/gcc/wintools/botnet/adware/windows processes!
"We're very proud of the Pentium II Mach 4 Core Processor", says Intel CEO Linda Gates. "Back in what we here at Intel now refer to as the dark ages of Single Core Barbarianism, the consumer had to actually process trojans on a single CPU. Bearskins and knives anyone?! Ha HA... But now, with the Mach 4, uh, mimble murble..."
She then trailed off...''
You can see it at
Ace's Hardware
My advise to you is get a degree in something other than CS....learn to become a great programmer on your own...yes it can be done....check the CS curriclum hell even audit some of the classes if you want. The point is programmer jobs are starting to look more and more like plumbers and electricians. A lot of programming is now contract work. American programmers simply cannot compete with Indian programmers when it comes to making low bids. I program almost eveyday, yet I am a computational chemist. For me it is the best of both worlds...interesting subject with hard problems to solve and I get to write a lot of code.
what?