Intel and AMD's 2005 Plans Revealed
Takemedown writes "There's a good article on CTZ that talks about Intel and AMD's plans. Intel, continuing on their 18-month chipset refresh rate, will introduce their Glenwood and Lakeport chipsets for the Smithfield dual core desktop microprocessor in 2005. The chipsets will support SATA II, Matrix RAID and a higher system bus speed for the new Pentium 4 name holder.
As far as Intel's dual core strategies are concerned, they will most likely bring their dual core additions by the very end of Q2 or Q3 this year, so for those waiting for these next generation chips are better off with a due upgrade. Secondly, if you are hoping for a noticeable performance gain in regular computing tasks are in for a disappointment. Dual core microprocessors are for those who like to do multitasking or work on multithreaded applications. For example, if you are gaming and burning a DVD at the same time, dual core chips will come in handy and will definitely give a smooth computing experience."
...chat on AIM and refresh Slashdot fast enough to get a first post!
http://brandonbloom.name
Is it more efficient memory sharing amongst the different cores?
Slashdot: Where people pretend to be twice as smart as they really are by behaving like children.
Sure to please Joe Lieberman AND the MPAA: play GTAA while downloading "Meet the Fockers" !
Only thieves burn dvds, so I see the MPAA stepping top stop this.
A plea to both Intel and AMD. Please make a nonexpensive SILENT cooling system.
Yeah fans are pretty good but let's be honest, they wear down and become noisy.
Water cooling is great but I've already got one aquarium in my room.
One core was bad. Two? Three? Twenty! Passive heat sinks, huge slabs of copper, whatever, just please, I can't hear myself think.
-Teiresias
I liked the photo of the Intel booth, which had the tagline "Upgrade your senses". For the life of me I can't figure out what that means. Are they planning on offering upgrades to give me better vision and sight? Perhaps a socket for the back of my head too? Or maybe their new cpu can now smell me and indicate when I need to shower?
I Am My Own Worst Enemy
Is a dual core actually an in-box dual processor that communicates between cores at extremely high speeds?
Broken Hearts are for Assholes. - Frank Zappa
Processor power has been overrated for quite some time. A lot of people don't realize that other components, especially RAM matter just as much, if not more in most every day tasks than pure CPU power. If I had a choice between 2GHZ and 1GB ram, vs. a 4GHZ and 512mb ram, I would definatly recommend the former. So although this technology will help some people, most people should stay away from it if you are just doing day to day. Does grandma really need dual core processors for sending email and browsing the web anytime soon? Hell, a 500mhz and 256mb is more than enough for a lot of people to write documents and browse the web, but you will never see such a system on Dell website for $120 :).
When did using computers or the internet become an "experience"? They're tools, nothing more.
Trolling is a art,
The real bottleneck for gaming these days is hard drive access. If you are burning a CD while you are playing a game, there is a good chance that the game will need to load something like textures while you are burning the CD (presumably from an ISO on your hard drive). On the other hand, with a 52X CD-R burning a full CD takes less than 3 minutes, so it won't kill your game. Unless you have two hard drives, in which case the above is irrelevant.
Burning a DVD is IO-bound given all the traffic on the PCI bus from the harddrive and to the DVD. Burning a DVD is not CPU-bound, so it doesn't seem like a dual core CPU would actually help that situation.
The reality is most of the server market is their Xeon line and the dual-core Xeons are currently planned for 2006 and maybe even later.
It's called a heatsink.
Many CPU's function fine at a reasonable clockspeed and with a large heatsink.
But if you want top performance you're going to need active cooling. You can't have your cake and eat it too.
For example, if you are gaming and burning a DVD at the same time, dual core chips will come in handy and will definitely give a smooth computing experience.
Why, of course, doesn't everyone burn DVDs and play games at the same time? I usually burn DVDs when I'm playing GTA: San Andreas, so by the time the DVD is done I've forgotten all about it and the tray opening scares the living shit out of me, so I pull out my penknife and stab the DVD to its rightful death! So with this new dual system you're telling me the DVD will be done so quickly that I won't forget about it? Or will the tray slide out more slowly in a smooth and controlled manner as not to provoke me?
"Secondly, if you are hoping for a noticeable performance gain in regular computing tasks are in for a disappointment."
This sentence must've been written in a hurry.
People that play DAoC but don't want to buy two computers will love this. It'll let them run their buffbots and mains without too much of a hassle. /scandalous
Job? I don't have time to get a job! Who will sit around and bitch about being broke and unemployed then?
I can already game and burn a dvd on a single core system. I'm using an Athlon XP 2500+ with a Plextor 8x DVD-RW drive and I've never seen a drop in FPS while playing SOL.EXE, Ever
On a more serious note my old roommate, the SCSI lover, could play Quake 3 while burning a CD because he was burning from SCSI HDD to SCSI CDR while playing the game off a seperate SCSI HDD. He claimed that the only thing making my machine slow while burning a CD was the CPU overhead involved in IDE.
Im dreaming ofa big bndwdth, That can resist the
I hope Intel pulls off multi-core better than they did hyperthreading. The P4 netburst architecture simply weak, and hyperthreading is really just a patch to make it not suck quite so badly. I "upgraded" from a 1.6GHz AthlonXP to a 2.8GHz P4 Dell and was horribly disappointed with task switching performance. Tried throwing more RAM at it. The P4 with 1GB was still slower than the AthlonXP with 768MB. OTOH, I setup a friend's new Dell with the latest PCI express chipset and was really impressed with the speed, so maybe Intel is finally getting it together...
Question is: will the netburst architecture benefit more from dual core than it did from hyperthreading? Its essentially like having an SMP P4 system, so it ought to.
There's no place like 127.0.0.1
Oh will they? Consider what frequency these chips will be running at... You won't be getting dual cores featuring core frequencies along the lines of current top end CPU's anytime too soon. This should tell people that gamers would be much better off sticking to their single core guns... If they want to encode and game at the same time, there computing experience is most definetly going to have to be compromised.
There is no other way about this considering current limitations... As the fab processes are refined and application of technology is perfected, we will see dual cores running at higher frequencies, but there are considerable improvements which will need to be made before dual core can be referred to as a formiddable gaming option for new releases at the top end of the system spectrum. (they might not even be formidable until the unlikely circumstance when gaming authors start coding for multicore platforms on a large scale)
For MANY people with top end single core systems currently, the move to dual cores will not immediately present what would be considered a smooth computing experience - there will be noticeable deficincies in various areas, the severity of which will be determined by the specific way their system is utilized.
Overclockers
Or the fact that IDE doesn't use the bus as efficiently as SCSI, which is why many people put their CD/DVD burner on a different IDE channel to their hard drive.
Via has been offering very - if not the most - stable chipset drivers for Linux for ages. There were many occasions in the past when I specifically chose via chipset brand boards with amd cpus because good experience in the past with Linux. And I never had any bad experience. That doesn't mean I don't have and/or use other chipsets/boards/cpus with Linux on them, I do - but mostly @ work. It's just I never see much sane reason in arguing like I-went-intel-because-of-better-linux-drivers.
I am putting myself to the fullest possible use, which is all I can think that any conscious entity can ever hope to do.
Modern games are multithreaded. Even if the game is not written to be - even if it does not use seperate threads for sound, rendering, NPC AI, and I/O - the rest of the system is running other threads (networking, interrupts, disk I/O) that are competing with the game for the CPU. A multi-CPU system can reduce that competition, allowing the system to service the NIC and hard disk IRQs while truly simultaniously servicing the game engine.
www.eFax.com are spammers
...except they tend to be a little flaky. But you can usually get the flakes off with a little soap and water.
I doubt it. Today's personal computers are already like those 60s muscle cars from Detroit (a 400 horsepower engine bolted into a car with narrow bias-ply tires, drum brakes and a solid axle).
I was burning DVDs a couple of days ago. The system was mildly sluggish. The CPU meter was pegged at about 2% usage. Then I ran an md5sum to verify the whole disk, and the system ground to a crawl. The CPU meter indicated about 10% load. In both cases the sluggishness was caused entirely by I/O latency and/or all of the working set being flushed out of memory to make room for disk buffering. Dual-cores aren't going to do anything for that.
and I would really like to finally upgrade: I'd love to have an SMP box again but I'm really not sure if it's possible at all nowadays, what are my options (at a reasonable price point) for something in the 2xAthlon64/3500+ performance range (I know Athlon64s are not SMP-capable).
The option(s) seem to be Xeon and Opteron, but I'm not quite sure which mobos are best and most supported and/or which one of them is the most cost effective (also including RAM costs). My typical usage is linux (would vmware it in this case), win32 games (would prefer AGP to PCIe) and music (hauptwerk -> I need lots of RAM (2-3gigs) and CPU power).
I don't think I can wait another year for multicore CPUs to come out (already been waiting forever).
-- the cake is a lie
In times of old, an IDE channel would configure itself to the slowest device on the channel.
That is, if you put your UDMA/133 hard drive on the same cable as a CD-ROM that can only do PIO mode, the whole channel runs at PIO mode.
Modern controllers don't have this limitation.
I don't need no instructions to know how to rock!!!!
I'm tired of this. I process video. Lots of it. I need as fast processor as I can get. If possible, it should have lots of RAM, but I still need fast processor(s).
No, for me processor speed (as opposed to GHz) is not overrated.
Robert
Bastard Operator From 193.219.28.162
How did this become a top-level post? I mean, the news part is interesting, but teh editorializing is... not.
/. crowd are aware that two processor cores only help if you're running two threads/processes.
a.) Talking about dual core as if it was not already introduced, and people don't already know what it is.
b.) I'm pretty sure most of the
c.) Who isn't running at least two processes these days? Are there really people still running DOS today?
Thanks.
It is not our abilities that show what we truly are... it is our choices.
InfoWorld had a nice story about the Power5 multi-core CPU (You'll have to download the report) coming out this year. It may outperform the coming dual core AMD chip, both in raw performance and in lower power consumption.
AMD has a write up on their upcoming dual core processor and what it means to performance. Somewhere I believe there are some published numbers for how an AMD dual core CPU running 5 steps below it's single core counterpart can still outperform dual single core processors. (i.e., a 1.4 GHz dual core CPU will outperform a 2.4GHz dual processor machine)
Meanwhile, Intel's dual core demo was doubted doubted when presented at the same time as the above referenced AMD demo. Also, Intel's dual core will not perform significantly better than a dual processor system, or so the analysis of the two processors stated. (I really need to bookmark these things when I read them! Hopefully someone else will provide that reference.)
The cesspool just got a check and balance.
Wow it's like CoolTechZone paid to get these posts. Here is an article written by someone who has a clue:
i =2317&p=2 i =2317&p=12 i =2317&p=13
Intel: http://www.anandtech.com/tradeshows/showdoc.aspx?
AMD: http://www.anandtech.com/tradeshows/showdoc.aspx?
Transmeta: http://www.anandtech.com/tradeshows/showdoc.aspx?
Notice the $700 price point on dual core Athlon 64s (socket 939). Start saving up now.
I dont see how that will beat AMD 64 in games :). Only this metters to me.
Its nice to be important but its more important to be nice
Now if only Mandrake could figure out how to work the USB ports on them.
MDK 10.1 chokes on my K7T266A (3 year old) chipsets USB.
General Relativity: Space-time tells matter where to go; Matter tells space-time what shape to be.
For MANY people with top end single core systems currently, the move to dual cores will not immediately present what would be considered a smooth computing experience.
Agreed, the example given in the post was pretty inappropriate.
However, that's not to say that the advent of dual-core CPUs isn't an exciting. In my case, I've just got a $5k grant to buy a computer, with which I intend to perform magnetohydrodynamical simulations of magnetic stars. I've already decided on a multi-CPU Opteron system, but with current CPU prices I am limited to a dual-processor system. Why? Because such a system can be built using the Opteron 2xx series chips. A quad-processor system would require 8xx series chips, which are far more expensive, on account of having more memory controllers.
In principle, a quad-processor system based on 4xx series Opterons would be ideal; but AMD doesn't make such chips, only the crazily-priced 8xx chips. This is where dual core comes in: projected prices for dual-core 2xx chips are not that much above current single-core levels. Accordingly, it should be possible to build a quad-processor system using 2 dual-core 2xx Opterons, within my 5 grand budget. So I'm excited!
Tubal-Cain smokes the white owl.
As the story on /. discussed, Intel and AMD seem to be going very quietly ahead with their Palladium-class chips - what about the presence of installed DRM on the new class of dual-core chips? If it's there, then you probably won't be accelerating your burning of anything to DVD by using the new chips.
Grandma will need dual-core processors if she wants to check her e-mail and browse with the next version of Windows. And most likely grandma will only ever use Windows because that's what she got from the store.
This is different performance here, though. Apples and apple trees. With monolithic kernels like Linux there's a modest gain with multiple processors. There's significant overhead from switching tasks among them. With microkernels, each component of the kernel can run more independantly in each processor, providing better gains (at least potentially). So holding out for GNU/Hurd (I hear the laughter) and dual-core processors will likely provide huge performance gains.
This is not GHz vs. RAM. This is your computer literally doing 2 things at the same time as opposed to current context switching between tasks. That's a big difference.
Developers: We can use your help.
I hear this all the time. Dual processors won't help most people because they only do one thing at once.
But your system is doing all kinds of things now. Look at the services Windows is running even when you don't want it too. What about screen refreshes? Those are done outside of the application. Shouldn't dual processors show a lot of improvement on Windows with even a single application, even if it's just cutting down on the context switching?
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
When will apples have dual cores?
I little while ago I was involved in some DSP stuff, nothing major, delay lines, oscillators, filters bit of FFT. I nearly went bonkers when my budget box, a Duron 1800 + 768MBytes PC133 RAM +all in one mobo, beat the hell out of a P4 2.4Ghz (not celeron)+ 512 meg of PC2100 RAM + spanky mobo and ATI9600. Go figure. Most FP benchmarks were at LEAST a 1/3 faster on the Duron and some (sin, cos etc) were faster than that. Even were the P4 DID win (SSE mostly) simple things like function call/return would be far slower (30% again) and exception handling is dreadfully slow. Unless you run artificial benchmarks (like those stoopid memory copy benches) then the P4 goes nowhere.
Time flies like an arrow. Fruit flies like a banana.
``if you are gaming and burning a DVD at the same time, dual core chips will come in handy and will definitely give a smooth computing experience.''
Or simply gaming and having a few daemons running at the same time. Remember that task switches are major performance killers on x86. Your game will run smoother if all the hits are taken by the other core.
Please correct me if I got my facts wrong.
Yes, definetly exciting so long as it is taken for what it is... For those with really powerful cooling solutions, the overclocking on these should prove VERY fruitful. I can't wait to hear the first overclocking stories on these beauties.
Overclockers
We are the good kind of Socialist -- the kind that respects privacy. Nice try.:)
Is this a sigs-optional kind of place? 'Cause I am totally down with that if you know what I mean.
The performance scaling will be measured by multitasking and multithreaded application usage rather than single-threaded applications. You can expect to not see a huge performance gain, if any, with regular computing tasks.
Who really has issues with desktop processing, when only doing *one* thing?
George II -- Spreading Freedom and American values, one bomb at a time.
Well, as for clock speeds on AMD's dual core chips, the Inquirer claims to have initial specs on the chips.
2.4GHz and 2.2GHz @ 95W
2.2GHz and 2.0GHz @ 55W
1.6GHz @ 35W
Although most /. readers probably won't care, dual core CPU's are already on the market in the form of the UltraSPARC IV CPU from Sun Microsystems. Sun also happen to be sporting the most ambitious multi-core project going in the form of Niagara, which although initially an 8-core system has apparently been seen running Solaris 9 with 32 independent CPU cores.
In addition to this, the POWER 5 CPU is also available with multiple cores, fully supporting Linux.
Also of note is that the Opteron dual-core CPU's from AMD are apparently going to be pin-compatible with the current Opteron processors (by current,I mean, the latest socket 939 (I think) systems, not the original Opteron 2xx or whatever).
This is really of most use for the data center right now, but as more applications wrap their heads around paralelizing themselves, multi-core CPU's on the desktop will become more popular.
That said, developers really have no excuses for not having blazing fast "dual-core aware" apps... a multi-processor system purchased today provides about as much performance as a dual core system... so it's not like a wild new technology where application developers have to wait for SDK's or test hardware. Multiple cores, HyperThreading CPU's or multiple physical processors are all just additional CPU's from the operating systems perspective, and are developed for using the same tried and true thread libraries (pthreads, etc).
Multi-thread those apps people! There are so many instances, especially when writing GUI apps, where an extra thread or two thrown in the right direction can really improve the user experience.
Of course, a big problem is just how developers learn to program. Everyone learns their "Hello World!", then goes from there... but this is all very linear in approach. Finding good programmers who can think of an application in terms of what many parallel threads should (or shouldn't) be doing isn't easy... but I digress.
bash-3.00$ uname -a
SunOS panda 5.10 Generic sun4u sparc SUNW,Ultra-2
I was burning a DVD last night and took a look at process monitor - total CPU load was ~4% (this was an 8x IDE DVD burner on an AMDXP 3k+). I don't game on that box, but I can't imagine the 4% CPU making much of a difference if I had wanted to.
---- Den ene knappen er powerknapp, den andre er Bender voice knapp "Bite My Shiny Metal Ass"
People ( mainly M$, but Intel too ) have been using this BS in their advertising since 1995. Upgrade to product X and you can play games and burn DVDs at the same time.
... sitting at their Pentium 4 desktop they got for Christmas, playing a cracked version of the latest WWII FPS, downloading another 2 games, 10 mp3s and some porn with edonkey, IRC windows splattered all over the desktop, and ... wait for it ... burning a DVD. Of course Windows won't run seamlessly for the time it takes to burn the DVD, and they will most likely have to chuck it in the bin and try again ... minus the game. But they'll blame the cheap DVDs they bought.
Who actually plays games and burns DVDs at the same time anyway? You'd have to be some sort of moron. It doesn't matter how many processors ( or processor cores ) you have, if the OS can't allocate sufficient resources to your burning task, you'll make a coaster. I can think of *many* games that seem to lock the system for a couple of seconds while changing from one mode to another, switching to the next level, bringing up an info screen, etc. The in-game music will pause for a couple of seconds, and the screen will also occasionally pause. If you're playing an mp3, that will pause too. And this is all on decent hardware, but it's always been like this.
I can see the snotty-nosed brats right now
Man, every time I hear the old 'play games and burn DVDs at the same time' line I just wanna punch someone.
The problem is not really the CPU, it's the drive IO as has been mentioned earlier, eventhough the CPU is pretty idle, there is a good bit information being sent between the hard drive and dvd burner, if you add a recent game to the mix, the hard-drive will have to keep the dvd fed with data to burn, and the game fed with textures, geometry info, sounds etc. that could well overwork the hard-drive and cause problems with either the game or the dvd burning. Chances are the CPU would still be fairly idle during all of this.
Still, a small percentage of the computing world needs the fastest chips possible, and today's bleeding edge, "who needs that much, anyway?" chip is tomorrow's bargain basement chip. It's a matter, as with many things in life, of priority and need.
Why do the solutions have to come from the chip manufacturers? There's plenty of great third-party solutions, just check Quiet PC. I already have one of their power supplies, and just ordered a couple of their SilentDrive enclosures and a low-noise heatsink/fan combo.
Another option is to just order one of their AcoustiCases.
Maybe this isn't that important... but whenever I use MSIE to read slashdot, it's at my college. They actually insist on it, and I actually don't really care as long as my site is pulled up. I figure they'll learn the hard way :).
cheap labor conservatives - they want to keep you hungry enough to be thankful for minimum wage.
That's odd; my previous system was a 1 GHz Duron with a 266A chipset (on an Epox motherboard), and I never had trouble with the USB.
On the other hand, my current 2.4 GHz Pentium 4 system, with Intel motherboard, seems to be having a lot of trouble with the USB ports lately. And USB 2.0 never did work; I get some kernel error message about it saying "very bad".
I've been using standard 2.4.x Linus kernels from kernel.org for years now on both these systems.
Linux drivers?
AMD provided full driver support for their chipsets, and even optimized BLAS libraries (these are scientific computing libraries).
To get this from Intel you have to buy their compiler suite.
How about next time you study up on some facts before you blindly repeat the Intel party line?
Maurice W. Hilarius Voice: (778) 347-9907
Drool over this: http://www.iwill.net/product_2.asp?p_id=36 ZMAXdp
Now that I think of it, it could be my third-party USB2 board (VIA chipset as well).
If you look at alt.os.linux.mandrake, you'll see that 10.1's USB on VIA is an abomination.
General Relativity: Space-time tells matter where to go; Matter tells space-time what shape to be.
I wonder if one could setup a dual-core cpu computer to run for two users. A second graphics card or a dualhead card with a second montior attached, a second keyboard and a second mouse and you just spared a second entire computer. That sounds to me like a system that might work. And while we are at it, what about adding a third one? Would that be a way to spare some money for... lets say a internet cafe or school?
MATRIX RAID!!! The bastards just renamed RAID 10 to make it seem they had a trendy new product. Damn intel!! Wasted 10 seconds of my life searching for something that sounded new becuase I didn't know what it was. Now that I do know what it is I want the marketing trolls at Intel dead.
err, I beg to differ. I don't know what chipset you've had trouble with, but even the laptop chipset of my athlon XP-M gives gentoo no trouble. Almost all chipsets are now supported by linux, at least most of the VIA I've tried, and the kernel lists a big bunch, which are not for Intel processors. I've had linux on 3 computers with all a different motherboard, but all AMD CPUs: Duron 1.3 GHz, Athlon XP 1800+ and Athlon XP-M 2400+. No trouble from linux with those chips.
---- I am certain of only one thing : I know nothing else.
"...if you are hoping for a noticeable performance gain in regular computing tasks are in for a disappointment. Dual core microprocessors are for those who like to do multitasking or work on multithreaded applications."
This is just plain wrong.
First, take a look at the number of tasks running on your system (taskmgr for windows, top for unix systems) On any given Windows box, you are going to have at least a dozen processes running from the moment you logon forward.
Each of those processes is its own thread.
That means on virtually _any_ modern operating system, adding a processor will have a decisive impact on the speed of the system. Even if every one of those processes were single threaded within themselves, you still have multiple threads for the operating system and user applications, and the system distributes those threads across as many processors as it can get its hands on.
More processors = good, even for regular users...
--- Generation X: The first generation to have SIG lines inferior to their parents... ---
....until you try simultaneous dma transfers and the whole board locks up! Check the linux kernel mailing lists.
---
... make lots of third-party devices that solve this problem. Heatpipes are particularly good. Many of the small Shuttle-style cases use them for moving heat silently onto a nice big heatsink and result in a system that's very nearly silent.
I'm not sure you could have a fully-loaded Winchester without at least some type of active cooling...
This fully-loaded winchester does fine with completely passive air cooling. It even says so in the table, scroll down the page and take a look.
What's wrong with yours?
I stole this sig from someone cleverer than me.
-Cheaper RAM for the socket 939. The socket 940 CPUs need registered RAM.
-So far, Cool&Quiet only works with Socket 939. Again, the registered RAM is a problem.
-Cheaper boards, because socket 939 only needs a 4 layer PCB. Socket 940 needs a 6 layer PCB.
C - the footgun of programming languages
I can't say much good about the article - so I will just say thats the inquirer for you.
That information is likely completely fabricated, and will reflect nothing of what will happen. If you look at how chips perform and their current specs, there is simply no way to think that what the inquirer said would actually be possible.
Take this link for example: http://www.xbitlabs.com/articles/cpu/display/athlo n64-90nm_5.html
They note that winchesters are rated at 67 watts but cooling is significantly different due to the smaller die size... Two of these cores would output over 134 watts of heat, and the cooling load with that die size for heat dissipation could prove problematic - much moreso than dissipating that amount of heat on a 130nm process chip.
What we will see are core frequencies being sacrificed to stay within thermal limitations... Its no gaurantee, but I have seen nothing that persuades me to expect to see dual cores with each core running at the speeds that top end CPU's run at.
Overclockers
If you are transcoding DVD files (i.e., converting them from one resolution to another) and gaming at the same time, a 2nd CPU or dual-core chip will help.
Both Gaming and video format/resolution translation are CPU intensive (the later also I/O intensive), and the 2nd CPU will be kept busy as will the 1st.