Intel To Redesign PC With "Grantsdale" Chip

MarkRH writes "Over at ExtremeTech, we tracked down some Intel roadmaps that discuss "Grantsdale", Intel's most important chipset in nearly a decade. Grantsdale brings PCI Express to the PC, so get ready to toss out your motherboard, AGP graphics card, and maybe a host of other components, too. Also check out our articles on the "Tejas" microprocessor, Intel's first CPU to forego pins (check out the waffle iron socket!), as well as the real reason Banias saves so much power."

Comments

Not necessary

[(1337) God]

We've all switched to Macs!

Re:Not necessary

[Anonymous Coward]

Microsoft is doing a great job boosting the Macintosh. There is no way I will install software with product activation, so when win2k gets too obsolete, I'll have to switch to a mac. Linux still isn't an option on the desktop, I used it for 2 years and switched back to windows. I want to use my computer, not spend half a day configuring for any change.

Re:Not necessary

[Anonymous Coward]

Extremely well said.

Re:Not necessary

[Anonymous Coward]

Parent poster is a known moron. Please mod down. Don't believe me? Check out his journal. Or watch how fast his freaks list is growing. He's setting a new record.

Re:Not necessary

[Anonymous Coward]

With Intel and AMD delivering faster and more powerful processors at a rate which makes your head swim, the consequences are plain as day. Apple is hurting, its spindly financial footing sinking ever deeper into that fiscal bog of no return. Frankly, many prominent industry analysts have crunched the numbers, concluding that Apple's outlook is bleak indeed.

In Apple's latest numbers released in January for its fiscal first quarter of 2003, revenue fell from a year earlier and all of the company's major computer lines saw diminished numbers. PowerMac sales were down 20%, while iBook sales fell 8%.

At the same time Apple's sales were falling, PC sales rose, though just slightly, according to figures from IDC released last month.

The last time Apple was in this state, it brought back co-founder Steve Jobs to fix its issues. He fostered the development of the iMac and secured a US$150-million investment from Microsoft. But there aren't any new iMacs in Apple's future and Microsoft, bolstered by its victory over the U.S. Department of Justice, is clearly not going to help the beleaguered computer maker this time.

So what have you got left? Apple is a company that controls around 3% of the computer market, has recently undergone a restructuring and is slowly fading into nothingness. Software makers don't even have Mac users on their radar and it's not like Apple can bring Mr. Jobs back to right the ship this time -- he's already there.

Stick a fork in 'em -- this Apple is cooked.

Re:Not necessary

[alext]

Now you mention it, I sense that this problem (EULA and restrictions in post W2KSP2) is becoming common enough to justify its own support structure - forum, lobby etc.

Anyone know of one?

Re:Not necessary

[malloci]

funny, my computer at work has linux running on it (of course, so does my one at home :), and the only things that I really configured were the network settings and the window manager theme on gnome...

Re:Not necessary

[MessyO]

I have never purchased an apple an I never will. I need raw power, versatility, and heck I play games, so an Apple is useless to me. It's used for design because it loks nice and has capabilities to run photoshop smoothly. If you are a developer and you want to create high-poly models in programs like 3DStudio max, or if like me you need a machine that can compile huge programs regularly into a game, then test the game then you need a PC. Heck, I use MS Visual C++.NET so there's no option. Workstations are PC's, dual processor maybe, but rarely an Apple of any kind. Good old PC's, if you want to upgrade it's simple, with IMacs and the like, you need to buy a new Apple. Apple are getting left behind, much like Intel in my opinion, I have always used intel chips and chipsets but I think I may be switching to AMD for their Hammer processors, 64 bits is going to make a ridiculous difference to what I do. I don't know why intel aren't doing anything to battle this, their latest idea being Hyper-Threading on the new chips over 3GHZ. Oli.

Re:Not necessary

[MidnightBrewer]

iMac != workstation. The workstation lineup that Apple offers is as versatile as that of any PC manufacturer, including upgrade paths through many standard PC architectures (PCI, AGP, Firewire, USB, and yes, the processors.) A Mac workstation can last a good three years (I made one last six) with upgrades.

I've worked in television production for five years, primarily on the Mac. I use LightWave 3D, Photoshop, and AfterEffects as my primary tools. Television deadlines are notoriously gruesome, and the Mac has never let me down. I've also used PCs where necessary, and keep coming back to the Mac as my platform of choice. Max for games, LightWave and Maya for television and film. Since I do the latter and not the former, I'm set.

I grant that the current Mac processor drought has me on the edge of my seat, waiting for Apple to announce a solution. However, I also know that processor architecturs have always leap-frogged each other, and I think this is no different. The next iteration will most likely be 64-bit, making it as significant an advance as the introduction of the first RISC-based PowerPC was. And knowing Apple, it will work right the first time (mostly; nothing's perfect.)

Not only have you never purchased a Mac, it would seem a little homework is in order, too. I hope this helps a little.

Re:Not necessary

[Junks Jerzey]

Good old PC's, if you want to upgrade it's simple

Upgrading a video card is usually simple, even though sometimes you need a certain level of motherboard for some cards. Upgrading the processor, is rarely easy. Intel changes so much so quickly that the upgradability of PCs is, and has been for some time, a myth.

64 bits is going to make a ridiculous difference to what I do.

Only if you're planning on having more than 4 gigabytes of memory. In almost all other cases, a 64-bit processor will be slower. It's amazing how few people catch on to this.

Re:Not necessary

[Anonymous Coward]

Thanks for your input AC!

For using the word "beleagured" to describe Apple in your uninsightful, short-sighted diatribe, I'd like to offer you a job as senior technical journalist for our publication, "1337 M4$T3RZ 0F 73H 73CH J0UNR4L1ZM." Please send a resume with an 8x10 headshot (of your anus) to our HR department, and we will schedule an appointment.

FO SHIZZLE MY NIZZLE, LET'S DO THIS THANG, HEEEEEEY.

Following PCI Express...

[Anonymous Coward]

Will be the new improved AGP Express!

I hope APPLE uses this chip!

[Anonymous Coward]

...so their Macintoshes have a fighting chance of being faster than Windows machines. They're about 1/2 the speed now. It's sad.

Re:I hope APPLE uses this chip!

[Anonymous Coward]

I agree. Apple needs to do SOMETHING to get back on track. Being an early adopter for a new Intel chip would be a step in the right direction.

Re:I hope APPLE uses this chip!

[Anonymous Coward]

yeah! grantsdale is a chipset for controlling pci, ram access etc.

wow! let's add this into an apple! then what will we have.

uhhh. G4s at the same speed, using a different chipset.

Did you RTFA?

Re:I hope APPLE uses this chip!

[Anonymous Coward]

As long as Steve Jobs is at the helm of Apple, the situation is hopeless. He is a control freak whose main goal in life is keeping the Mac pickaninnies confined to his plantation, interoperability and industry standards be damned.

Hey

[papasui]

Now you can finally play Doom 3.

Re:Hey

[davebarz]

Nope. No, you still can't.

Re:Hey

[AftanGustur]

Now you can finally play Doom 3

The funny thing is that this joke will still be funny for years to come ..

What about Hypertransport?

[Anonymous Coward]

Anyone for Hypertransport?

Re:What about Hypertransport?

[Clay Pigeon -TPF-VS-]

I am. The HT consortium needs to get its act together to offer some viable competition to PCI express in terms of cards and peripherals. HT is free to use while mobo and card makers will have to pay liscencing fees for pci express, driving up component prices and possibly adding to tech market stagnation (assuming the tech market doesnt turn around by h2 04, god forbid).

Re:first post!

[coday]

oh well

PCI Express effect on graphics cards

[writertype]

It's going to be really interesting, I think, to see what this does for the holiday selling season. Since it's out there now that Grantsdale is going to have such a dramatic effect on PC architecture, what is this going to do for sales of graphics cards? Of sound cards?

It looks like PCI will be supported in some way, but it's almost up to a motherboard manufacturer to come forward and say, "OK, we're only going to support one PCI slot, so figure out what you want to keep, now."

My guess is that Nvidia's NV35 will be released later this year (fall?) on AGP8X, but that it will REALLY run well on PCI Express. So--wait, or buy? An old question, but with far more significance.

Re:PCI Express effect on graphics cards

[Max Romantschuk]

It's going to be really interesting, I think, to see what this does for the holiday selling season. Since it's out there now that Grantsdale is going to have such a dramatic effect on PC architecture, what is this going to do for sales of graphics cards? Of sound cards?

I doubt this holiday season will be any big break for PCI Express. Remember when PCI was introduced? Roughly around the time of the first Pentiums. You can still buy motherboards with ISA slots...

It looks like PCI will be supported in some way, but it's almost up to a motherboard manufacturer to come forward and say, "OK, we're only going to support one PCI slot, so figure out what you want to keep, now."

The same applies here, the transition won't happen over night. There is lots of stuff which runs just fine on the bandwidth that PCI has to offer. You will have to decide what to keep, but I'd say that years from now.

Re:PCI Express effect on graphics cards

[naktekh]

Nvidia's been releasing the NV30 cards (Geforce Ti4200 and MX series) as AGP8x modules.

The problem is that the bandwidth that is offered by the AGP bus tends to be a PCI-AGP bridge, rather than a true AGP graphics card, so what you essentially have is a PCI card running at a slightly faster dedicated bus speed.

If PCI Express can truly deliver, I'll be impressed... but Intel's known for making decisions that are not necessarily widely implemented in the long run (remember Rambus?). I'm taking a wait and see approach with this one.

Re:PCI Express effect on graphics cards

[buffer-overflowed]

And sometimes you need an ISA slot. It's rare, but recently I've had occassion to really, really need one (in fact several...).

Sure they're slow, ancient, legacy (appologize for the redundancy there) but sometimes you just really need an older piece of hardware or a board you can solder and design yourself without an EE degree.

The same will be true of PCI. There are more PCI cards out there than ISA, so PCI-Express should really be backwards compatible, capable of both modes. Or at least have a few slots on it that are mutual, then faze it out over a few years.

Why don't major vendors get the fact that some of us like our legacy stuff and don't want to move just because we "have" to?

Re:PCI Express effect on graphics cards

[Zork the Almighty]

Why don't major vendors get the fact that some of us like our legacy stuff and don't want to move just because we "have" to?

Oh I'm sure they do, it's just they make more money this way.

Re:PCI Express effect on graphics cards

[S_hane]

> Why don't major vendors get the fact that some of us like our legacy stuff and don't want to move just because we "have" to?

Why don't consumers get the fact that their hardware would be faster, cleaner, easier to use, and downright sexier if legacy stuff didn't have to be supported?

Take Intel CPUs. They're a kludge. A terrible, messy, evil kludge. And they're a kludge because they have to support legacy applications that ran on the 8086.

Intel, of course, is making exactly the same mistake by attempting to emulate x86 modes on the Itaniums.

If you really, really want to use legacy stuff, then go and get a PCI to ISA Bridge or something. But don't try and force ISA compatibility into PCI-Express, because that's just going to make things slower (and messier) for everyone else.

-Shane

Re:PCI Express effect on graphics cards

[Clay Pigeon -TPF-VS-]

Um the Ti 4200 8x is a NV28 chip. The controversial GeForce FX 5800 and 5800 Ultra use the NV30 chip.

Re:PCI Express effect on graphics cards

[Matimus]

I don't know about you, but with the frequency that I upgrade, I doubt that it will have much of affect on what I purchase this year, or next. Its not often that I buy a whole new computer, I just buy one part at a time. This just means that some time in the future I will probably be looking into buying a Whole new computer.

On another note though, if technology is going to get much faster, we are definitly going to need to make changes like this, in the next 10 - 20 years we will probably see lots of changes like this. I doubt that it is anything to worry about, if anything we should get excited.

Re:PCI Express effect on graphics cards

[MtViewGuy]

I think we can be confident that both ATI and nVidia know about the PCI Express spec and both companies will introduce graphics card design based on ATI's R350/R400 GPU's and nVidia NV3X GPU's by the fall of 2004.

Re:PCI Express effect on graphics cards

[Hobophile]

Responding in arbitrary order:

Intel, of course, is making exactly the same mistake by attempting to emulate x86 modes on the Itaniums.

Because of its abysmal performance, Intel has abandoned this approach and now uses a Celeron coprocessor to handle x86 software execution.

Take Intel CPUs. They're a kludge. A terrible, messy, evil kludge. And they're a kludge because they have to support legacy applications that ran on the 8086.

Even though this is quite a popular sentiment on /., the reality is that consumers and businesses don't want their computers to be some sort of Platonic ideal of a perfect machine. They just want the damn things to work reliably, chock full of "evil kludges" or not.

So the attitude you're propagating, that older is bad and anything supporting something older is therefore also bad, is pretty much not a viable approach to the economic realities at work here. You seem to think that sweeping revisions and corrections that throw out the work of previous generations are justified, but really all they would do is anger users and create chaos. It might be faster, cleaner, easier to use, and sexier, but it also be much less useful simply because there wouldn't be any software that ran on it.

And you can argue that it's the principle of the matter, and that we shouldn't compromise our ideals just because they are unworkable in the market. But keep in mind that computers are a tool, not a religion, however tempting it may be to categorize them as such, and it's a bit silly to attach an ideology and a morality ("evil kludges" indeed!) to tools.

Re:PCI Express effect on graphics cards

[TechnoWeenie]

Dang, and I just got rid of my last ISA card in my last upgrade, a couple months ago. Now I gotta start all over again.

Re:PCI Express effect on graphics cards

[ShavenYak]

You seem to think that sweeping revisions and corrections that throw out the work of previous generations are justified, but really all they would do is anger users and create chaos.

Yep, I know so many Mac users that just hate the PowerPC and want to go back to the old 68k CPUs. And OS/X is a big failure for the same reason.

Hint: do it right, and 90% of the consumers won't even know about the sweeping revisions.

Re:PCI Express effect on graphics cards

[maraist]

Actually, if you read the article, PCI and ISA can still be supported. ISA is supported on current PCI boards through a host-to-host-bridge. Likewise, the new architecture can support PCI, and there's no reason to think ISA couldn't be supported.

The issue is that such a bridge costs money and space. The majority of people purchasing new computers (with no intent on upgrading HW) will want the cheapest, most-compact solution. This is the problem that faces video card retailers. They'll ahve to carry two lines of video cards (3 if they seriously still sell PCI versions), and they'll have to conflict amongst themselves as they market different HW. Especially in the months leading up to the roll out.

No word on whether AMD boards have any chance of supporting the new BUS. If not, then AGP cards will persist for some time.

Re:PCI Express effect on graphics cards

[Anonymous Coward]

Who the hell modded that to flamebait?

Re:PCI Express effect on graphics cards

[PCBman!]

Chances are good they'd support it through a an I/O chip (which would be pretty cool to tie PCI Express to their Hypertransport bus--1 chip switching data for say 6 PCI Express devices tied directly to the CPU Ram Controller which uses another HyperT pipe to manage the AGP slot). It's what I'd expect anyway.

Re:PCI Express effect on graphics cards

[jayslambast]

Because of its abysmal performance, Intel has abandoned this approach and now uses a Celeron coprocessor to handle x86 software execution. I think you're mistaken. Itanium and Itanium2 have dedicated logic to run x86 code. They don't emulate x86 code, they actually run it. The logic is not pentium nor celeron based. The amount of engineering time to add a celeron coprocessor to a processor the size of an Itanium, or to modify a chipset to include a celeron, would be not be costeffective, nor be a sound engineering decision. btw, everything else in your comment is well thoughtout.

Re:PCI Express effect on graphics cards

[ncc74656]

Yep, I know so many Mac users that just hate the PowerPC and want to go back to the old 68k CPUs. And OS/X is a big failure for the same reason.

It's easier to pull off that kind of change when it's just one company that's involved. I also don't doubt that Steve Jobs' infamous Reality Distortion Field (R) played a part in each transition.

Re:PCI Express effect on graphics cards

[Hobophile]

I think you're mistaken. Itanium and Itanium2 have dedicated logic to run x86 code. They don't emulate x86 code, they actually run it.

I think you're right. I have no idea where I got the notion that the Itanium 2 had a Celeron more or less integrated to handle x86 software. It did seem ridiculous to claim a full-blown Celeron was on the actual chip, so I fudged something in there about it being a coprocessor.

But I guess my main point was, as you say, the Itanium actually runs x86 code rather than emulating it. x86 support is hardware based, though by all accounts I can find, the performance still sucks, and seems to be comparable to early Celeron chips at this point.

Re:PCI Express effect on graphics cards

[Hobophile]

Nowhere did I say that advancements in technology or transitions to more advanced hardware were impossible or undesirable. I am only saying that supporting legacy stuff is not "evil" and it's actually in pretty much everyone's best interest.

Hint: do it right, and 90% of the consumers won't even know about the sweeping revisions.

I agree, and I'd venture to say this is another way of arguing my point: it's OK to change things, as long as you don't change them so much that all previous investment in the technology is worthless.

But it's clear we're referring to different kinds of "sweeping revisions." The parent of my comment asserted:

"hardware would be faster, cleaner, easier to use, and downright sexier if legacy stuff didn't have to be supported."

Cutting off support for legacy hardware/software is what I was referring to. To my knowledge OSX can still run many Mac Classic apps. Would you like it if Apple said, "you know all that software you bought for your system? None of it will work now. Buy OSX enabled versions instead. Oh and the vendor may not have an OSX version yet. Kindly wait a few years for it to be ported. Thanks."

What if you went out and bought a new PC motherboard, and discovered that none of your old PCI cards would work, that they'd changed the audio connectors to SPDIF inputs/outputs and that only USB keyboards and mice could be used?

Sure, it might mean that overall the system was "cleaner" or "sexier" and perhaps even performed better. And yes, USB is an improvement over PS/2. But if all you had were analog speakers and PS/2 keyboards and mice and regular PCI cards, you might be a little irritated to find that equipment that had served you well and still worked fine was no longer useable. At that point you might be tempted to say, "no thanks, I don't want the hypothetical performance increase or the theoretical purity of this new architecture, I'd rather be able to use my existing stuff."

This is a reality that new technologies simply can't ignore. People vastly prefer steady improvements to revolutionary redesigns, especially if each redesign means they have to spend money buying things they already had.

Re:PCI Express effect on graphics cards

[Anonymous Coward]

Why don't major vendors get the fact that some of us like our legacy stuff and don't want to move just because we "have" to?

Because they are vendors. And not getting the fact, is what makes them major vendors.

Re:PCI Express effect on graphics cards

[Zeinfeld]

Grantsdale is going to have such a dramatic effect on PC architecture, what is this going to do for sales of graphics cards? Of sound cards?

Nothing, sound is now considered to be part of the basic PC motherboard package, as is USB, firewire, the PS/2 rodent and keyboard connectors and at least one ethernet connection.

Unless a motherboard is aimed at the server segment alone, sound and graphics are going to be part of the basic package by the time the grantsdale motherboards come on stream. Sound is going to mean stereo and 5.1 dolby digital. Graphics is going to mean the legacy analog 15 pin plug and a DVI plug as basic with TV-out and TV-in being common.

I don't think that many people are going to be asking 'how can I plug my PCI card into my PCI-Express motherboard'. Most features you had to buy a PCI card for in the past are already available on the motherboard.

I think that folk on slashdot are missing the fact that the principal movement going on here is that the PC is becomming a home appliance rather than office equipment. Unless you are writing video games or such there is no reason why you should need an expansion slot today in an office PC.

The biggest single limitation in the current PC design is the mechanical form factor, in particular the way that the design places expansion boards at right angles to the motherboard so the basic PC ends up being at least 5" thick with 7" or more being more common. That is deadly if what you are trying to do is to provide a sleek unit that will sit underneath the VCR and receiver in a HiFi / Home video tower.

To create a slimline PC today you have to do one of two things, either you put in a riser board and crank the PCI slots at right angles or you do without expansion slots altogether. The riser board solution is pretty icky, its basically limited to 2 cards worth and you have a fragile mechanical connection.

A much better solution would be to get rid of the PCI expansion slot part of the motherboard entirely. make a cut out in the motherboard the way a large PCATX board has a cut out for the power supply. Then connect the expansion cards in via an edce connector the way that PCMCIA cards do. That way you get the convenience of PCMCIA without the power constraints imposed by limited cooling.

Re:PCI Express effect on graphics cards

[Ataeagina]

flamebait? Yeah, it's not like it's the God's honest truth or anything...

Re:PCI Express effect on graphics cards

[geekee]

If a lot of people want motherboards that support legacy PCI, when PCIexpress is around, someone will build a motherboard that supports it. It's simple economics. PCs aren't like Macs, where there's only one hardware supplier.

Re:PCI Express effect on graphics cards

[Anonymous Coward]

These solutions always have costs. IE: PCI->ISA requires a converter, which raises the height of the ISA card, which means it doesn't fit quite right in a case, etc. Besides that if I don't need a PCI slot, why should I need to pay for the "superior" technology and then pay for the converter to the technology I need?

Re:PCI Express effect on graphics cards

[buffer-overflowed]

You forget my friend, that most of these chipset/mainboard specs are defined by the CPU vendor. Of which currently there are only 2 major players, and soon there will probably be only one.

Market forces don't really factor in to PC's if you think about it. The frameworks of yesterday could still work, they would just require more development time to get all the whizbang features into the smaller memory space and cpu pipe. If those features are even needed. Windows is what has pushed CPU's and CPU's are what has pushed Windows into being what it is today.

PC economics is odd, apart from that, it's not like economics is a science. I mean come on, they can't even predict the stock market tommorrow, even weathermen are better than that.

Re:PCI Express effect on graphics cards

[elitotaco]

To my knowledge OSX can still run many Mac Classic apps. Would you like it if Apple said, "you know all that software you bought for your system? None of it will work now. Buy OSX enabled versions instead.

Using OSX right now, I can say that while OSX does support Mac Classic apps, it doesn't support it completely. You have to have OS9 installed in order to use the Classic environment. Anyhow, the only real use I've found, and other people that I know have found, for the Classic environment is for programming and developing. Other than that, the new OSX programmes I have to buy are definitely worth it, if only my mac was faster...

Re:PCI Express effect on graphics cards

[sjames]

Agreed. That's why we usually have years long transitional phases where both old and new interfaces are supported. Nearly any time the old is completely thrown away for the new, there is consumer resistance.

So, for example, PS/2 will go away one day, but not today. Meanwhile, USB ports are everywhere (nearly unused until recently) and USB devices for things otjher than Mac are starting to become common.

It's been unusually long for USB since it was essentially pushed out there is spite of having no consumer demand at all when it started.

Re:PCI Express effect on graphics cards

[naktekh]

OK, my mistake, I stand corrected on that.

I think most manufacturers will stick with the AGP bus until PCI Express becomes a proven viable alternative.

Either that, or find a way to significantly increase the bandwidth of the AGP bus.

Re:PCI Express effect on graphics cards

[Anonymous Coward]

Stupid Scroll Mouse! The flamebait moderation was unintentional. I'd give you some karma if I could.

Re:PCI Express effect on graphics cards

[Anonymous Coward]

In fact, it was supposed to be interesting or insightful....dammit....well, by posting to this note I rolled back your moderation anyways....too bad its probably too late...

Big deal

[Jason1729]

so get ready to toss out your motherboard

Since when can you upgrade to a new generation CPU and not have to replace the motherboard?

Jason
ProfQuotes

Re:Big deal

[Anonymous Coward]

Bah! You kids these days have it easy. Back in my day, if we wanted new components, we had to wire vacuum tubes together by hand... AND WE LIKED IT!

Re:Big deal

[Anonymous Coward]

Since AMD chose socket A, d00d.

Re:Big deal

[hxnwix]

since the first overdrive in 1992

Re:Big deal

[kfg]

I have to toss out the motherboard pretty much every time I buy a cpu, which makes the "quick change" feature of this unit rather moot.

If they're going to hold the basic architecture steady for at least a few years this is going to be quite handy, but if each iteration is going to require a general upgrade to properly utilize the new speed and features anyway. . .big deal.

The motherboard manufacturers like to see a steady upgrade cycle too you know and it almost always comes down to "gut the case" and hope a few cards are still usable.

KFG

Re:Big deal

[buffer-overflowed]

Excellent point, but since when do you have to upgrade everything at once?

I mean come on, I can't think of a processor upgrade yet that forced me to actually replace an entire system (graphics card, peripherals, etc.). This system is more like buying a PS3 over a PS1 than your typical computer upgrade. I'll swap a mainboard out, no problem.

Surely you can admit that?

Re:Big deal

[Anonymous Coward]

I recently went from a K6-2 to an XP. I had to replace the CPU/MB/Memory practically as a single unit. Now I'm left with a xpert@play video card that, a 36 gig HD, 4x CD-RW...it really brings down the system.

Re:Big deal

[Anonymous Coward]

You could put a P266 in your socket 5 mb when you upgraded from a P100?

Re:Big deal

[Walterk]

Luxury.

Re:Big deal

[pi radians]

I take it you have never owned an upgraded Macintosh. Almost every PowerMac can be upgraded to at least a G3 (but most can go up to a G4) without changing the motherboard.

Heh, and people say that Macs can't be upgraded. Sheesh.

Re:Big deal

[MarcQuadra]

Since you bought an Athlon three years ago, or a PowerMac G3 at the same time.

Re:Big deal

[MidnightBrewer]

Did it with an 8500/120. By the time I sold it, it had a G3/250 and was USB-equipped. This was also with Apple's possibly worst-designed case ever (but the best components); you had to remove the processor and unmount the motherboard to add RAM. ;)

Re:Big deal

[jafac]

Gee, I put a G4 in my G3 Mac without upgrading the motherboard. Sure, bus bandwidth was kinda tight, but hey, it's a G4 now!

Oh, sorry, I guess you can't really do that on the intel side, can you? too bad. so sad.

Re:Big deal

[Anonymous Coward]

"so get ready to toss out your motherboard"

"Since when can you upgrade to a new
generation CPU and not have to replace the
motherboard?"

Yeah, but usually you don't need to leave all the cards plugged into it.

Re:Big deal

[Anonymous Coward]

haha, that's funny. guess we know why macs run like shit now.

This means..

[Anonymous Coward]

>so get ready to toss out your motherboard, AGP graphics card, and maybe a host of other components, too

And PC also?

Slide rule rules! ;-)

Re:This means..

[kfg]

Got two lovely aluminum Pickett's right here. One full size in a leather holster, and one pocket sized. . .in a leather holster. Now *that's* geek chic.

Someone wandered off with my K&E bamboo rule though. The bastard.

The batteries never wear out. You can use them by candlight in a power outage. You can fully douse them with water. They even keep working when your space capsule blows a gasket and you to figure out how to get home with the air you've got left.

Plus they keep on your toes with regards to the concept of of significant digits.

Quake runs a bit slow though.

KFG

Why NewCard?

[KiahZero]

I don't understand why revamped PC-cards are being pushed for desktop computing. I can understand increasing the bus speed on PCI cards (faster real-time TV encoding... yay!), but why does this need to happen in cards the size of two quarters?

Is the goal to make it so that users with two PCs can carry peripherals from one computer to the other? I would also hope that there will be legacy ports. I'm not planning on buying a new chip for a while, but I really don't feel like having to buy brand new hardware when I do. I'll have to buy a new video card (no AGP port), but they could at least put a few standard PCI ports on the mobo so I could slap in my more expensive expansion cards.

Re:Why NewCard?

[bellings]

but they could at least put a few standard PCI ports on the mobo so I could slap in my more expensive expansion cards.

If you have expensive expansion cards, you'll be able to find PCI motherboards for a long, long, long time.

Unless, of course, you think that a $150 sound card is "expensive." Then, you're fucked.

Re:Why NewCard?

[Apple Acolyte]

KiahZero opined: I don't understand why revamped PC-cards are being pushed for desktop computing.

The parent makes it seem as if PCI Express only defines the standard for new generation PC Cards. It doesn't simply do that; otherwise it would be nearly worthless as the next generation successor to PCI. Take a look at relevant quotes from the PCI-SIG:

The "Mini PCI Express Electromechanical specification, an alternate for the existing Mini PCI form factor specification, is being completed for membership review and is expected to be finalized for publication in the first quarter of 2003."

"IBM is excited about the PCI Express architecture because of its compatibility with the past and its high-bandwidth options for the future," said Peter Hortensius, Vice President of Development, IBM Personal Computing Division. "IBM embraces open industry standards and provides innovation on top of them, and PCI Express presents outstanding opportunities for solving real customer problems."

Mini-PCI Express, then, is a spec in its infancy that is designed to replace the previous generation PC Card. It should make future laptops far more expandable, which is a great thing. And PCI Express is one of multiple candidates for desktop expansion. Yet, it seems that PCI Express is going to be backward compatible with important specs, and that it seemingly has industry support. I just wanted to make sure everyone understands the PCI card isn't going to be replaced by the PC Card.

Re:Why NewCard?

[Anonymous Coward]

I did not know that, thank you for informing me.

Re:Why NewCard?

[Slowping]

So what's the deal between PCI Express and Infiniband?

Re:Why NewCard?

[Greger47]

Mini PCI express isn't the same thing as NewCard. Go read Slashdot.

"Grantsdale"? Jesus H. Christ

[Anonymous Coward]

If chips company would stop spending half of their research budgets on stupidly grandiose names, maybe we'd be getting somewhere.

Re:"Grantsdale"? Jesus H. Christ

[Anonymous Coward]

I would call my new CPU "Barry"

the chipset, I believe I would call "Rhonda"

Re:"Grantsdale"? Jesus H. Christ

[Anonymous Coward]

I believe Intel uses the names of nearby Rivers and Lakes for all their product code names, though they may have different naming schemes for different products. Also, AMD has their own system for naming new products; witness Barton, Thunderbird, etc

I think they should just stick with the product namese, that would be way cool. Of course, that would get confusing pretty quickly. Is this processor a Klamath, or a Coppermine? Is this chipset a Granite Bay, or a Springdale?

Re:"Grantsdale"? Jesus H. Christ

[JebusIsLord]

I personally like Redhat's naming scheme, where each name has something to do with the one before and after it... shoot i can't find the link explaining the connections.. anyone?

Re:"Grantsdale"? Jesus H. Christ

[Anonymous Coward]

The link explaining the connections.

--Friendly neighbourhood AC.

Re:"Grantsdale"? Jesus H. Christ

[Clockwurk]

Atari had something like that in the ill-fated Jaguar console, it had co-processors named "Tom" and "Jerry"

Re:"Grantsdale"? Jesus H. Christ

[Anonymous Coward]

And the Amiga with Fat Agnus, Denise, Gary and.. um. there were a lot more. Anyone remember?

Re:"Grantsdale"? Jesus H. Christ

[Jugalator]

Paula. :-)

Hmm, perhaps even more?

Wait...

http://www.amiga-society.de/ahwbook/achips.html

There you go. ;-) Wow... I never heard of some of these.

hmmm

[jms258]

i'll be very interested to see amd's answer to this.

Re:hmmm

[Anonymous Coward]

And I'll be very interested to see you SHUT THE HELL UP

Re:hmmm

[cheezedawg]

Um, considering PCI Express is an industry standard, it probably will be a chipset with PCI Express. Of course AMD has already developed Hypertransport to use in some places where PCI Express would fit also.

Re:hmmm

[kwashiorkor]

Well, their answer to Grantsdale's "whopping" 4GB of memory will be: "uh... your penis is so tiny".

* small that? that's my karma going up in flames *

Mmmm Chip Waffles

[Anonymous Coward]

Arghahghaghaaa

Most Important?

[silvakow]

Intel's most important chipset in nearly a decade

Of course, because this will be the first chipset to fail in the marketplace because computers are already fast enough for businesses, and gamers already have overkill. The first market failure is always an important landmark.

Re:Most Important?

[josh crawley]

>>Intel's most important chipset in nearly a decade

>Of course, because this will be the first chipset to fail in the marketplace
>because computers are already fast enough for businesses, and gamers already have
>overkill. The first market failure is always an important landmark.

If anything, I'd like to see an addon vector processor for high speed math. G4
motherboards have them under an Altivec core instruction set. I would also want
the ability to directly program (in chip asm) to do misc functions.

Personally, they can take this waffle-chip and shove it. If anything, I'd want
an architechure where EVERYTHING's on a very high speed, very high bandwidth
quad-plane bus with basic controllable logic. You put drive cards on it,gfx
cards, sound cards, network cards, memory on it, cpu's on it.. anything. It
would be the backbone of the system where anything would go. You could build a
simple scan/bootstrap code to find what devices do what. It could be a simple
hex line of simple "whatis information". To those who say this isnt possible, I
believe the Altair 8800 used this similar architechure. You want a
"beowulf"system, add 1 drive controller, and rest cpu controllers. BAM! You now
have insta-BeoBox. You could also add DIFFERENT CPU architechures with this
system, given they coincide to your bus setup (including the altivec and x86like
one I want).

Re:Most Important?

[be-fan]

If anything, I'd like to see an addon vector processor for high speed math. G4
motherboards have them under an Altivec core instruction set.
>>>>>>>>
It's not a component of the motherboard, but of the CPU. And Intel CPU's *do* have vector units, just like AltiVec. These units (SSE units) probably aren't as powerful as the G4's AltiVec units, but both are essentially limited by bus bandwidth, of which the P4 has 3x as much.

I would also want
the ability to directly program (in chip asm) to do misc functions.
>>>>>>>
They do. It's called a "function call." If you're worried about the extra-overhead, don't be. Features like the Trace Cache in the P4 remove a whole lot of the decode overhead associated with x86 CPUs.

If anything, I'd want
an architechure where EVERYTHING's on a very high speed, very high bandwidth
quad-plane bus
>>>>>>
And I want to be the Queen of England.

with basic controllable logic.
>>>>>>>>>
No such thing as "basic" control logic anymore. Read the tome that is the Infiniband specs and weep.

To those who say this isnt possible, I
believe the Altair 8800 used this similar architechure
>>>>>>
Life was easier back then. Today, we're hitting a whole bunch of limits, both engineering and physical. We can't engineer a bus that fast to those tolerences and have it work in existing environments. Not enough precision, too much environmental interference, etc.

Re:Most Important?

[Mac Degger]

While you're at it, add in a fractal chip (either to the cpu or the video card) so we can have cooler and more realistic smoke/plants/heightmaps/ground/dirt/trees/uh, actually, anything that you can come across in nature...

Re:Most Important?

[Anonymous Coward]

My god.. you're a fucking moron. Almost everything you said was either wrong, gibberish, or unintelligible.

Banias is the real deal...

[craenor]

If you are thinking about making a Portable PC Purchase and are looking for either a performance or "road warrior" system...just wait a bit.

The ones I've been playing with at work just absolutely rock. You can clearly see the difference that 1mb L2 cache makes...and combined with systems that already have decent battery life you won't have to worry about whether or not you'll be able to finish the Braveheart DVD on battery power.

Craenor

Intel's first CPU to forego pins...

[tommy]

I beg to differ. My 10MHz Intel 286 had no pins. It looked like this.

Re:Intel's first CPU to forego pins...

[Anonymous Coward]

That is a seriously impressive looking chip!

Re:Intel's first CPU to forego pins...

[shepd]

Those chips were manufactured by AMD, though. So technically, intel design, but AMD chip...

I used to keep one in my wallet for good luck. :-)

Re:Intel's first CPU to forego pins...

[Jordy]

That is known as CLCC packaging. It was used for a couple versions of the Intel 80186 (made by AMD), Siemens 80286, Intel 80286 (made by AMD) and AMD 80286.

In addition, slot-based packaging (SEP, Slot-A, etc.) all used gold fingers just like PCI cards.

Re:Intel's first CPU to forego pins...

[spiderbiten]

Hey, I got a couple of those things. make nice looking paper weights. When set along side my 6502 processors out of my C64's and my Intel 385 processor, they work pretty well for making sure my system fan doesn't blow my papers full of ip's away:)

Re:Intel's first CPU to forego pins...

[LucVdB]

What did you do, embed them in concrete?

Re:Intel's first CPU to forego pins...

[Anonymous Coward]

The Slotted CPU's still had pins, which were soldered to the cpu card thingy.

Re:Intel's first CPU to forego pins...

[Jeff DeMaagd]

Interesting. Were they soldered to the board or was there some sort of removability in mind?

Re:Intel's first CPU to forego pins...

[tommy]

It's been awhile, but IIRC, there was a piece on a hinge that laid down on top of the CPU and clamped to something on the side opposite the hinge. Imagine a ZIF socket with no lever, just the heatsink holding the processor in place. It worked pretty much like that.

Re:Intel's first CPU to forego pins...

[tommy]

Also, that picture is of the bottom of the proc. May be obvious, but you know... due diligence and all...

Re:Intel's first CPU to forego pins...

[Jeff DeMaagd]

Interesting. I did assume that the traces were the bottom side of the chip. This really isn't too different from the ball grid array where you don't have leads sticking out of the package like most current CPUs. Right now, ball grid arrays are generally soldered to the board.

It sounds to me like it is one of their efforts to maximize signal integrity, particularly when they go to such high bus speeds.

Re:Intel's first CPU to forego pins...

[spiderbiten]

Nopes, didn't embed 'em in concrete. Just have an abundance of them. I have a lot of old computer hardware setting around.

Re:Linux

[Anonymous Coward]

hehe yeh and that >> support new architecture in 2034 >> might be the same timewhen apple crack the ghz!!

Forced Obsolecense?

[Low2000]

I'm all for improving hardware but... Why would this be done other then to foce people to buy new hardware? Is the current PCI spec so bad?

I just see this happening.

Hey. So you want a new sound card? Great! What? You only have regular PCI? I'm sorry we only have it in PCI Express. No worries. We offer this brand new Intel board and chip and ram that will solve your problem. Only $1,200!

What am I missing? I hope I'm missing somthing =/

Re:Forced Obsolecense?

[Anonymous Coward]

So, what's your point?

Or are you not American? This happens in every other industry, why be shocked when it happens here.

Re:Forced Obsolecense?

[Anonymous Coward]

Basically, there is no need for more speed from systems, I agree with your point there. I suspect this is a case of moving forwards for the sake of moving forwards. There are very few REAL applications that require anywhere near 3Ghz. Currently, even top line servers are rarely over the 1.xGhz mark, going in favour of more CPUs, something that can be done more easily and less wastefully with current chipsets. Compatibility is also kept.

Honestly, a PC with eight $20 CPUs would end up far more responsive and just as useful for every task than one with one single several-hundred-dollar chip

Re:Forced Obsolecense?

[Anonymous Coward]

Maybe if all you do is troll around websites you can manage with a Pentium and Netscape 3, people who do real work always need something better.

Re:Forced Obsolecense?

[kfg]

Exactly. That's why I retired the 4mhz 8088 Compaq transportable that handled the core functions of my business a couple years ago.

Well, no, actually, now that I think of it I retired it because I couldn't find spare parts. It still did "real work" just fine.

Go figure.

Not that I don't like the box I replaced it with. That one runs *games* much better.

KFG

Re:Forced Obsolecense?

[Anonymous Coward]

Why even go to PCI for sound?

I'm using a SB16 in ISA. I never found any use for the new wavetables. 3D sound looks promising though...

Re:Forced Obsolecense?

[Anonymous Coward]

I guess you must either be fairly young (16) or must be fairly new to the internals of computers.

Not to long ago, PC motherboards used something called the ISA interface. It originated from IBM XTs and was 8bit. Then they added an extention to it so it could be a 16bit bus as well. This added some additional pins onto the end of the connector BUT was backward compatible with 8bit cards but not forward compatible (you could use an 8bit card in a 16bit slot but not the reverse). Then since that wasn't fast enough, something called the VLB (Vesa Local Bus) was added. It was intended for video cards. It added an extention but was not connected to the 16bit ISA portion but was at the other end of the card. This extention added 32bits. Other things besides video cards came out for VLB including IDE and SCSI controllers. Then they added PCI, which made it so you couldn't use any of your old ISA or VLB cards anymore. Most motherboard manufactures had at least one 16bit ISA slot though, up until maybe a year or so ago. I don't think any new motherboards still have a ISA slot. Well anyway, then the PCI bus wasn't fast enough for graphics, so they optimized PCI for graphics cards and called it AGP (and changed the connector). PCI does have 64bit and 66Mhz capabilities, though you wont really find it on most motherboards until you go to some SMP or "server" motherboards.

Now they're going to change some stuff again, because the software is hitting its limits until the hardware can go faster. This is NOTHING new. This is what always happens with computers. See thats why you see those stupid jokes about computers going obsolete the second after you bought them.

You're not missing anything, its just how it goes with computers. Software is hitting the limits with its hardware and the hardware companies need to stay in business so they comp up with new things. Sometimes those new things cause big changes, sometimes they dont. This is NOTHING new. See thats why you see those stupid jokes about computers going obsolete the second after you bought them.

Re:Forced Obsolecense?

[Anonymous Coward]

What is wrong with people on Slashdot? Man. Hey, here's something interesting - ten years ago motherboards came with these low bus-speed slots called "ISA" slots. They were too slow for pushing the data around that needed to be pushed around, so someone came up with "EISA" slots, and slowly but surely they replaced ISA slots without anyone really noticing. Then video card manufacturers decided they wanted a faster slot and "Local Bus" came along. A few years later we had "PCI" slots in all our computers. Then "AGP" came along. All the while consumers merrily going about their business. Today motherboards only come with "PCI" slots and usually also an "AGP" slot. Noone is particularly missing ISA slots. What's the big deal? It's not like from one day to the next the only components you will be able to buy are these "PCIE" slots. There will still be plenty of PCI and AGP peripherals, there will still be motherboards with multiple slots. Honestly... who cares? If you're a slow upgrader it'll only be a couple hundred by the time you want a new PC, and believe me, by then you'll want that extra bandwidth for one reason or another.

Re:Forced Obsolecense?

[Low2000]

No.. not 16. Not far off though (18)
Still, thats not the point. I just figured that an inprovement on PCI was not really needed concidering application. I never read about it not being fast enough. I'm sure a quick trip to google would let me view the throughput of the spec but it has to be pretty fast to keep up with current tech. USB 2.0 controllers? USB 2.0 is what, 480 Megabits? I'm sure its a necisary evil. Ultimetly we will need to move on and I'm sure there will be boards that offer both.

How much faster then PCI is PCI express anyway?

Re:Forced Obsolecense?

[be-fan]

Have you ever tried compiling something in Linux. Even on a 2GHz P4, KDE takes 8 hours to do a full build. Renders still take a couple of hours. Even some simple video encoding can take several minutes. Before making overly general comments like "there is no need for more speed from systems" try actually *doing* something with your system.

Also, there is no such thing as a $20 CPU. The only reason you can buy them on PriceWatch for $20 is because they're subsidized by sales of the $400 CPUs. And a PC with eight $20 CPUs would be dead slow. Most code is not that parallizable, and any interconnect that can handle 8 CPUs is going to be a whole lot more than a few hundred dollars.

Re:Forced Obsolecense?

[be-fan]

PCI is (in theory) 133 MB/sec. PCI express is from 250MB/sec (2 channel) to 16GB/sec (32 channel). Also, PCI Express is designed to more than replace PCI, it's also designed to replace AGP. Lastly, there are several things bottlenecking on PCI these days. Gigabit ethernet (which Apple ships by default), HDDs that can burst > 80 MB/sec, RAID arrays, IEEE 1394b (400MB/sec!), etc.

Re:Forced Obsolecense?

[Mac Degger]

Huh? I read the article, and it said 2 GB/channel, with a max of 32 channels...wouldn't that make the max 64 GB/s ?

Also, saying that PCI-E will also replace AGP is misleading...AGP is nothing more than a slight variation on PCI to start with...so if you replace PCI, you automatically replace AGP, I'd say.

Re:Forced Obsolecense?

[TheRaven64]

IEEE 1394b (400MB/sec!)

Uh, no. IEEE 1394 runs at 400Mb/s (50MB/s), IEEE 1394b runs at 800Mb/s (100MB/s). While this come close to saturting a 32-bit, 33MHz PCI bus, it doesn't dent a 64-bit or 66MHz PCI bus, of the type commonly found in servers, and Macs (The PowerMacs I've looked in had 2 64-bit PCI slots).

Re:Forced Obsolecense?

[Alcohol Fueled]

"What am I missing? I hope I'm missing somthing =/"

You are missing something. The E in something. :P

Re:Forced Obsolecense?

[DavidBrown]

I can see this with video cards, but sound cards? When was the last time anyone bothered to upgrade their sound card? You have a point, but this is not going to be an issue very often. 99%+ of the users out there, even the ones who tinker with their systems, never even think about upgrading their sound card. Most don't even upgrade their speakers.

Re:Forced Obsolecense?

[Hoser McMoose]

The reason to go for PCI is because ISA is shit! The ISA bus is quite possibly the worst bus ever designed, it was a terrible design 20+ years ago when it first came out and it didn't improve any with age. All modern systems now throw ISA onto the end of the PCI bus through a host-to-host bridge, but since ISA was designed so poorly, using an ISA device ends up using quite a bit more PCI bus bandwidth than the same device thrown on a PCI card. And after all that, you're still stuck with a device that can't share IRQs (due to the fact that interrupts on ISA are done in what is probably the worst possible way to do interrupts on a bus), can't be automatically configured with any sort of reliability (ISA Plug 'n Pray was extrodinarily unreliable in my experience).

Finally though, you can get WAY better sound quality out of a current sound card. Ok, this has absolutely nothing to do with the ISA vs. PCI vs. PCI Express deal, it's simply that the sound quality out of the SB16 isn't all that hot. I used to have one and thought that it sounded just fine. That is, until I bought an SBLive! to replace it and immediately noticed a world of difference in sound quality (on rather low-quality spearkers none the less!).

Anyway, long story short, I don't see any big reason to rush out and replace all PCI cards with PCI Express ones as soon as it comes out. But PLEASE, someone take the ISA bus out back and put it out of it's misery old-yeller style!

Re:Forced Obsolecense?

[be-fan]

2 gigaBITS per channel, 32 *dual* channels. That's 128 gigabits/sec, which is 16 gigabytes per second. However, initial implementations will have up to 16 dual channels, in the case of the AGP replacement. And when I said that PCI-E will replace AGP, I meant that there would be no more seperate graphics bus like there is now. In order to do that, PCi-E will have to have at least as much bandwidth as AGP did.

Re:Forced Obsolecense?

[sconeu]

Then there's Fibre Channel (Currently at 2Gb/s FDX, and slated for 10Gb/s), and 1000BaseT ethernet....

Servers need/want this stuff yesterday!

Re:Forced Obsolecense?

[CdOg62]

If you are doing "real work" that requires massive amounts of computing power then you need to re-think your tactics...

Re:Forced Obsolecense?

[CdOg62]

I agree with you be-fan. It seems that people think that if more processors used all problems are solved. The fact is most operating systems and software are not robust enough to parallelize tasks effectively. Even if the software is parallelizable you hardly ever achieve a linear increase in speed...

Re:Forced Obsolecense?

[Mac Degger]

Ah....

Oh well, bits, bytes, what's the difference? ;)

Re:Forced Obsolecense?

[JaxGator75]

Some of us get integrated sound and have never had to buy a sound card (and no, i'm not 16, I just inherited a sound card years ago and it worked until AC97 became standard on new mobos)

Re:Forced Obsolecense?

[be-fan]

Firewire 1394b includes the 3.2 gigabit/sec mode.

Braveheart?

[Anonymous Coward]

Aye, Laddy.
Me finds that ye olde porne plays better too.
Thank ye, Intel!

transemta crusoe?

[TerraFrost]

it'll be interesting to see how the "Tejas" processor compares to the Transmeta Crusoe - currently, the least power intensive x86 compatable cpu out there...

also... if you're currious about PCI Express, this link seems to be pretty... informative:
http://www.intel.com/technology/pciexpress/

and is anyone else disappointed that the new "Grantsdale" chipset isn't supporting rambus ram!? i know i am :(

Re:transemta crusoe?

[istartedi]

Crusoe is their old chip. I think you want to compare it with Astro, coming out RSN.

Re:transemta crusoe?

[Wesley Felter]

Did you mean Banias? I think it will compare quite well with Transmeta. Tejas will be a high-end, high-power desktop processor.

Re:transemta crusoe?

[Hoser McMoose]

Err, I think you must be confusing the "Tejas" and the "Banias" chip from Intel! The "Tejas" is going to be a desktop processor following in the Pentium 4 line. It will offer SIGNIFICANTLY higher performance than any Transmeta chip now or in the next 5+ years. However it will also consume a lot of power. Intel's current P4's are using nearly 100W of power at the high-end, and while the Prescott and Tejas will lower power consumption per-GHz, they will probably end up requiring even more power.

The "Banias", on the other hand, is Intel's low-powered notebook processor that will compete with Transmeta's line-up. As for how it will compare, it looks like it will use more power but offer WAY higher performance. The ULV 900MHz Banias chip is listed as consuming a maximum of 7W, which is very comperable to the maximum power of a 900MHz Crusoe TM5800. However, clock for clock, the PIII is usually twice as fast as the Crusoe, and the Banias will be faster still. Even Transmeta's next-generation of processors don't look like they'll offer much competition here. At best it looks like they might manage 70-80% of the clock-for-clock performance of the Banias.

I'm actually slightly dissapointed in the Banias specs though. From the first stories I heard about it, it sounded like all these chips would have a maximum power consumption in the 10-15W range, with the ULV chips consuming even less power. However, the 1.6GHz Banias has a maximum power consumption of almost 25W! To put things in perspective, only 5 or 6 years ago, 25-30W was considered to be a lot of power for a DESKTOP chip!

PCI slots

[DrMrLordX]

On a side note, if they do design Grantsdale well, who cares about your legacy PCI slot? Stuff like sound cards, NICs, modems, etc should all be integrated with the motherboard ala nForce 2. Or, at least, the option for such a configuration should exist. I, for one, know that the only PCI card I have right now that I actually use is a horribly dated Ensoniq AudioPCI. Integrated sound solutions, even now, kick its ass. Oh, wait, and my modem. wheee. 56k powah

Anyway, old PCI stuff should be easily replaced by integrated components on the motherboard. One available legacy PCI slot would likely accomodate the rare exceptions.

Support your slashdot trolls! View at -1, and mod up all troll, offtopic, and flamebait posts. Thank you.

Re:PCI slots

[Clay Pigeon -TPF-VS-]

Who modded this poor bastard down? He actually has a good point.

What about ISA?

[whitelabrat]

And Floppies too!

Oh Yeah!

[Waffle Iron]

check out the waffle iron socket!

I'm stoked. I'm going to pull in some serious coin on this deal.

Every socket designer dreams about being chosen to do a major Intel processor. It doesn't get any bigger than this, baby!

Re:Oh Yeah!

[Anonymous Coward]

I hope AMD would follow this mechanical design so that we can all make waffles on the hot stove^W CPU.

GeForce/Quadro FX and ATI R400 obsolete already?.

[mcbridematt]

If Intel stays on it's current plans, the only markets for the GeForce and Quadro FX as well as the ATI R400 (refreshed 9700) will be the AMD market. But then, if new Intel CPU's can't use them, such cards may only have a limited production run before being taken off until PCI Express versions come out.

Bloody tricks!

[HoneyBunchesOfGoats]

From the second page of the article on Banias:

EBL encompasses four features: a non-synchronous vertical refresh control for displays, which will save between 200 and 800 milliwatts; an optimized LCD inverter design, expected to cut an additional 550 mW to 880mW; device performance state monitoring, which will reduce overall power by an additional 900 mW; and a device power profile utility tool, designed to monitor the power of all devices in the system.

So basically, their "über-cool" power-saving processor isn't what's really saving power, but a bunch of other little tricks in the rest of the system. All they did with the processor was take a PIII-M, ramp up the frequency, and slap on a bigger cache.

Not that I hold this against them or anything; if in the end it increases battery life, that's a Good Thing. I just wish they wouldn't hype up their new processor as being so great, when really there isn't much more improvement over the PIII.

Re:Bloody tricks!

[Walterk]

It's all about the bloody tricks in systems. UN*X is a combination of bloody tricks. It gets interesting to see how a cmobination of tiny little tricks cause major systems improvement (like paging, and on demand page loading).

When you have to work with what you have, tricks are best to squeeze every last drop out of that, but then performance really matters you need to redesign from the ground up, which intel has been failing to do since the PPro(?).

Re:Bloody tricks!

[dr.badass]

They're not putting the hype behind the processor so much as the platform, especially with respect to battery life. The new chip is faster/more efficient, etc; but you're probably not going to find many of them outside of the whole "Centrino" platform, not only because of the technical advantages, but because Intel is offering OEMs some huge marketing dollars if they use the whole package. I think it's a win for the consumer.

Nice

[pheared]

I can't wait until I have no choice but to buy some hardware that's not compatible with anything I might possibly already own. What's even cooler is that I get to do my part and add my obsoleted hardware to our local dump.

P.S.: It would be nice to get the computing companies to do a bit more in the way of reuse. I don't think it's a good idea to use until there's no more, and then just move on to a new resource.

</rant>

Re:Nice

[cheezedawg]

So are you suggesting that the industry should ignore the increasing system bandwidth needs (gigabit ethernet, USB2, 1394, Infiniband, SATA, etc) just so you can use your old hardware for longer?

And your hardware will be compatible for years to come. Legacy interfaces linger for a LOOOONG time.

Re: Nice

[Black Parrot]

> What's even cooler is that I get to do my part and add my obsoleted hardware to our local dump.

Yeah, I'm looking forward to digital TV too!

Re:Nice

[Anonymous Coward]

Solution? Don't upgrade. If you are happy to keep your old hardware - keep it! Noone's forcing you to upgrade.

About those macs

[Anonymous Coward]

So that means you'll have all of the above around 2020?

PCI Express FAQ

[Anonymous Coward]

PCI Express FAQ here.

Quick summary: Formerly known as 3GIO, Software compatibility. Point-to-point instead of bus. 1 to 32 bits wide @ 2Gbps per bit = 16 GB/sec max (vs. 1-4 GB/sec for regular PCI; this is about AGP16X)

Re:PCI Express FAQ

[Anonymous Coward]

Warning: parent poster is a known Karma Whore. Do not mod up!

Re:PCI Express FAQ

[mabinogi]

Um.....how exactly does an Anonymous Coward become a karma whore?

Wait, what?

[exley]

"The improved battery life derived from the ability of the Centrino platform to complete the assigned tasks more quickly than the Pentium III-M, Chandrasekher said"

With 1 MB of heat dissipatin' cache (assuming it's on-die) and higher clock speeds, I think things are a little more complicated than "oh, it does things faster." What all have they done to get energy consumption and heat dissipation under control?

trivia: "Tejas" means "Friend"...

[marhar]

... and is the word from which Texas is derived.

Re:trivia: "Tejas" means "Friend"...

[Anonymous Coward]

Texas?? Friendly???!!!

Re:trivia: "Tejas" means "Friend"...

[Anonymous Coward]

In Sanskrit the word "Tejas" means brilliance/fire. I guess this is the association that the guys at Intel want you to make.

Re:trivia: "Tejas" means "Friend"...

[m1chael]

as in "dont run we are your teji" ?

Re:trivia: "Tejas" means "Friend"...

[Rayder]

In what language ? In spanish from where "tejas" comes, does not means Friend, friend is "amigo" and tejas can be translated to "slates" or "tile". It's the slate of pizarre or the tile of clay used for roofing or covering houses.

Re:trivia: "Tejas" means "Friend"...

[-tji]

Google comes up with this link that says Texas was derived from the Hasinai Indian word "tejas", which means friend.

Re:trivia: "Tejas" means "Friend"...

[Anonymous Coward]

Also, it is pronounced: Tay-hahs

Joy of joys

[buffer-overflowed]

Even more stuff that as someone who uses computers primarily for work, I don't need.

Sure it looks good, yea, I'm all exited about a "new era of computing," but it breaks backwards compatibility with all of my old stuff and I bet it still can't outperform the mainframe I program on now in terms of raw MIPS.

Why did we ever move to PC's from thin clients in the first place? We have consoles for gaming, windows for PC gaming, and *nix for serious work (try doing something else under say Solaris, and posting to slashdot doesn't count.) now. Why all of the redundancy? Aren't we in an economic downturn? The bus speeds and improvements are nice, don't get me wrong... but in a PC? It removes the PCI bottleneck problem, but I don't see where it removes the HDD bottleneck in terms of raw speed.

All in all i'd say it's a nifty gadget.

When we get holographic/full immersion, give me a call. I'd love to see what my brain can output in raw source without needing to actually type.

--I'm just continuing my tradition of posting drunk, pay me no head. Don't post to slashdot under wine.

Re:Joy of joys

[be-fan]

Grognard. It's not 1992 anymore and PC's aren't lumbering beasts.

Thin clients: How are people going to use this at home? Over their 28.8 dialup connection? With the work I do, I can peg pretty much anything you throw at me. You think they want user's like me on shared systems? You think I want other users slowing me down?

PC architecture: A modern PC has more resources than most RISC workstations that are 5x the price. Ever since the P4 came out, PC memory bandwidth (one of it's traditional weak points) has skyrocketed. By the end of the year, it will be up at 6.4 GB/sec, which is an impressive number even for an SGI or Sun machine.

Bottlenecks: What do you do where the HDD is the bottleneck? After an hour of use or so, my Linux system pretty much runs out of RAM. On workstation tasks, the HDD is often not the benchmark. It's not the benchmark for the 3D rendering I do, the scientific sims, the gaming, the programming, pretty much everything. In fact, I thought it was going to really suck moving to a P4 laptop, because of the slow 4200 RPM hard drive. Ever since I put 640MB of RAM in there, I don't noticed any slowdown at all.

Re:Joy of joys

[Dynedain]

Why did we ever move to PC's from thin clients in the first place?

Trust me...you don't want to be working on the same mainframe as me when I'm editing/rendering huge 3D animations :)

Re:Joy of joys

[Kopretinka]

did you mean "it removes the PCI barrelneck but doesn't remove the HDD bottleneck"? 8-)

Re:Joy of joys

[Walterk]

It'd be fun using a floppy at 2GB/sec = 2147483648B/sec, a floppy contains 1440000B, so reading a complete floppy would be possible in (1440000/2147483648=) 0.0006705522secs. I wonder how fast floppies would need to rotate for that.

Re:Joy of joys

[MtViewGuy]

I think PC architecture is going to undergo some drastic speed improvements over the next 24 months--and that's not including the CPU.

Between faster chipsets, big increases in memory bandwidth (PC3200 DDR-SDRAM is only the beginning), and Serial ATA, you'll see overall faster computers anyway.

Re:Joy of joys

[Morologous]

The entire point of a mainframe is that you and I can both do our processor intensive work without interfering with each other's execution. If I were on the same mainframe as you when you were rendering graphics, chances are, I wouldn't even notice you.

What I'm getting at here is, you can't bog down the mainframe the same way you bog down your workstation -- the mainframe controls your resources in such a way that you'll only bog yourself down, not the whole system.

Re:Joy of joys

[jejones]

[PCI Express] removes the PCI bottleneck problem, but I don't see where it removes the HDD bottleneck in terms of raw speed.

I thought that was what serial ATA is supposed to do.

Re:Joy of joys

[ergo98]

Why did we ever move to PC's from thin clients in the first place?

Because it was the right thing to do.

We have consoles for gaming, windows for PC gaming, and *nix for serious work (try doing something else under say Solaris, and posting to slashdot doesn't count.) now. Why all of the redundancy? Aren't we in an economic downturn?

Really, eh? And what's with all these different car models and types? Who needs Hondas, GMs, Chryslers, and Fords; Minivans, compacts, pickups and transports? We need one unified universal transport solution! Who needs competitive forces bringing the best solution from each vendor. I propose that we all drive transport trucks because that can encapsulate any need (ala a mainframe).

The bus speeds and improvements are nice, don't get me wrong... but in a PC? It removes the PCI bottleneck problem, but I don't see where it removes the HDD bottleneck in terms of raw speed.

The HDD bottleneck? When do you have a HDD bottleneck? While this misnomer is often repeated, repetition doesn't indicate a foundation of truth. My machine, XP, boots in about 15 seconds, and shortly after all my apps are running it barely ever touches the harddrive at all (a standard 7200RPM IDE), running virtually everything in the copious RAM. Even for things like video compression my CPU is currently the limiting factor, and of course where the harddrive is the limiting factor feel free to buy a high performance solution: You can set yourself up a 6 disk RAID 10 15,000RPM array today to eliminate all of your hard drive needs.

I really don't get how you scored 5 for this: This is an absolutely standard "bah humbug!" type of post that follows up absolutely any story regarding new hardware/technology.

Re:Joy of joys

[Zathrus]

breaks backwards compatibility with all of my old stuff

Whine whine whine. Have you looked at a modern system? Unless you have specialized needs you probably have one card - the video card. Everything else - sound, USB, firewire, network, HD, other I/O - is on the motherboard. The most common add-ons are a TV encoder/decoder (although increasingly becoming part of the video card) or a SCSI controller - which will certainly be available for PCI-X (and you'd want to move anyway to get the additional bandwidth).

Oh, you have a specialized card available only on <insert ancient standard here>? Guess what - specialized means costs more. Get over it. And I bet you'll still pay less than anything else on the market.

I bet it still can't outperform the mainframe I program on now in terms of raw MIPS

I bet you're wrong. A top line PC often outperforms everything else on MIPS per CPU basis. The issue is that the bus sucks and it can't do anywhere near as many transactions or I/Os as a high-end workstation (Sun, MIPS, etc), much less a mainframe.

Of course, PCI-X helps address this bus issue - it doesn't solve it, but it'll go a long way toward improving the problem. And will narrow the gap between PC and mini/mainframe performance even further.

Why did we ever move to PC's from thin clients in the first place?

Besides, not every problem needs the throughput of a mainframe or even a Sun class box. Why spend several hundred thousand or a couple million on a box when you can get the job done with a $1000 PC? What was that you were babbling on about regarding an economic downturn?

Re:Joy of joys

[Sarcazmo]

SATA, higher areal densities (Maxtor has 320GB+ drives planned for release very soon) or 10,000 RPM SATA drives will pretty much eliminate the bottleneck at the hard disk.

Modern ATA drives are already pushing 25-50 MB/Sec, doubling the capacity also doubles this sustained rate. Within a year we will likely see single drives that are able to max out the initial 150MB/Sec SATA spec.

I think we should be more concerned that most people are still on 100Mbit LANs. Duplicating a single 200GB hard disk over 100Mbit LAN takes ages. Gigabit is still pretty expensive, compared to how extremely cheap 100Mbit is. An example, we checked into adding a 8 port copper Gbit card to our Cisco at work, and I think the figure was something like $5000. We have a few fiber Gbit slots, but just the GBIC for those costs around $400 a port.

I just have the feeling that by the time Gbit becomes cheap enough for the masses (i.e. someone is heard saying "we might as well go Gbit, it's not much more expensive"), it will already be obselete.

Not to mention that there are a whole lot of crappy Gbit NICs that can do no where near Gbit speeds.

Re:Joy of joys

[ArsonSmith]

Are you saying 640MB of RAM should be enough for anybody?

j/k

Re:Joy of joys

[Stween]

The HDD bottleneck? When do you have a HDD bottleneck? While this misnomer is often repeated, repetition doesn't indicate a foundation of truth. My machine, XP, boots in about 15 seconds, and shortly after all my apps are running it barely ever touches the harddrive at all (a standard 7200RPM IDE), running virtually everything in the copious RAM. Even for things like video compression my CPU is currently the limiting factor, and of course where the harddrive is the limiting factor feel free to buy a high performance solution: You can set yourself up a 6 disk RAID 10 15,000RPM array today to eliminate all of your hard drive needs.

You make the common mistake of assuming that if the hard drive is fast enough for you, it's fast enough for the processor.

The hard drive really is a major bottleneck on any modern computing system - it can take hundreds of milliseconds to retrieve a piece of data and have it transfered all the way into memory, where the processor operates in terms of nanoseconds. The thread waiting on the data is left waiting for thousands of cycles, where it could be getting on with some work.

Sure, various levels of caching inside the processor, on the motherboard, and on the hard drive itself help alleviate the problem, but don't clear the problem entirely, and none of these mechanisms can predict to within a reasonable degree of accuracy what data the user will request off the disk next.

In "average" day to day use (lets say email, word processing, web surfing), the CPU spends a crazy amount of time idle, and for much of the time where the user is actually interacting with the system, is waiting for data to be retrieved either from disk (or, even worse, a network).

You might be happy with the speed of your hard drive, but your processor isn't.

Re:Joy of joys

[ergo98]

The hard drive really is a major bottleneck on any modern computing system - it can take hundreds of milliseconds to retrieve a piece of data and have it transfered all the way into memory, where the processor operates in terms of nanoseconds. The thread waiting on the data is left waiting for thousands of cycles, where it could be getting on with some work.

Only really poor programs actually sit around waiting for the data to come back from the hard drive: Instead most good applications nowadays operate on a non-blocking IO (in Windows jargon it is "Overlapped IO") where an application informs the OS that it'd like a piece of data and it then proceeds to do whatever it was doing, eventually getting around to using that data. I say this having written several compression and encryption applications that did exactly that: I would only wait for the very first block, and from then on would initiate the next block read, start processing the current block, and by the time I was ready for it the next block was there. In the grand scheme of things "loading a word document" or what have you is trivial in the overall context of system speed (i.e. that 60ms loading a file that is then used for two hours is somewhat inconsequential).

Re:Joy of joys

[Stween]

I would only wait for the very first block, and from then on would initiate the next block read, start processing the current block, and by the time I was ready for it the next block was there.

Chances are that by reading the first block on disk that the surrounding data on that track was read into a buffer inside the drive anyway, so by requesting subsequent blocks you've already knocked (at least) a few hundred milliseconds off the access time.

Yes, there are lots of ways of speeding up an inherently slow system, but none of them are 100% reliable. The point I was trying to make was that the hard drive is a very, very, _very_ slow device as far as the CPU is concerned, and there isn't much that can alter this.

Whole new bus?

[bluesoul88]

I just hope it ain't the short bus. I hate getting on that friggin' thing, and I don't do well with ramps on a friggin' bus.

Offtopic...

[bluesoul88]

...whore.

ATI is currently Intel's only validation partner

[Anonymous Coward]

Don't expect any PCI Express cards from Nvidia this year.

Cost implications ?

[bushboy]

It would be great to have an idea of the cost implications of the new chipset - the fact that you'll need a new motherboard, CPU and graphics card means this setup isn't going to be for the masses right away.
The price to upgrade could easily reach $1200 US for early adopters.

I don't see much of a problem with the PCI slots as the majority of current modern systems have a lot of components onboard already, such as LAN, Sound, Video etc.
I guess the safe bet is they'll include 2xPCI slots which should be enough for most peoples purposes.

Total incompatibility?

[antispamist]

That new tech. had better be damn fast! Good luck getting ppl to do widespread replacements. I would prefer to see some slow replacements through dual compatibility. Like USB 2.0, they could have just said to hell with it but they were smart. Eh, either way...long as it's fast.

Re:But how many PCI slots will there be?

[writertype]

That's the question. If you read the article, there's going to be four PCI Express x1 slots.

OK...so does that mean those are going to take the place of the PCI slots that will normally be found within a motherboard? PCI will be supported--but how many slots will we have to work with?

At First Glance

[mestoph]

This may seem a bad idea for intel to aim for this now. Especially with current market releases of other hardware in formats these technologys do "not support" (Nvidia/ATi gfx cards, 1 gig lan cards and also soundcards). But this news can be taken in two ways. Firstly its actually trying to force us forward to better hardware and not stick with current day limited technologys, which is a damn good thing. Or it can be viewed at trying to hurt AMD. Afterall if it got support from nvidia/ati/cisco/creative/3com etc to provide "futuretech" cards it would certainly force AMD to rethink the Athlon-64 supporting chipsets. As to be honest we need to have some kind of standard. As to cost of upgrading, it wouldn't really bother me. I spend $2000 a year anyhow. But then again i'm AMDcore really and not intel. One last thing to consider is that staying with a 4gig limit on ram, it means they are not intending to go 64bit either, so i wonder whats the point in doing a half job. I personally currently have 1.5gig of ram and i still want more (640k blah).

I just love the idea...

[cyril3]

that some innocent tries to google tejass by accident and ends up listening to the butthole surfers.

Grantsdale?

[Anonymous Coward]

Feh. Anybody who's seen intel's roadmap (as I have) knows the Grantsdale chip is just a stepping stone.

Personally, I'm waiting for the Higgenbotham chips in early 2005. After that, the Ranmatheau chips. In earlier 2007, expect amazing performance from the Cleodranvier chipset.

2008 brings us the amazing 10-GHz Hefnestranthellhaller chipset, and 2009 unveils Intel's most impressive chip: the Quackenbush.

But the true surprise comes in 2010, when the world experiences the amazing speed of the Gentrecktagazunt.

Truly wonderous times ahead.

Re:Grantsdale?

[Anonymous Coward]

Do you have any sources for this? I have looked for about TWO hours and can not find any relevant information on this. Do you work for Intel or are privy to inside information?

Re:Grantsdale?

[evocate]

Moderation +5
100% Funniest post of the year (so far).

Re:Grantsdale?

[HiThere]

Even if it's a reference to their real plans, you shouldn't take it seriously. Projections that far ahead don't mean much.

But even if he saw the real plans, I think the post is a joke. (And one that is pointed, funny, and accurate.)

Re:Grantsdale?

[IronicCheese]

It's a crying shame that we'll have to wait so long for the pollyanna-anastasia-plutzenbomer-krauzenmeier-hoff enfeffer-one-re-eerie-ickery-ann-fillsy-fallsy-nic hloas-john-queevy-quavey-dickery-davey-eenie-meeni e-miney-moe-my-momma-says-youre-are-the-very-last- one-to-be-it chipset.

I've seen the plans. The chip is round. You know. For kids.

Re:Grantsdale?

[Art Tatum]

I'm holding out for the Johann Gambolputty de von Ausfern -schplenden -schlitter -crasscrenbon -fried -digger -dangle -dungle -burstein -von -knacker -thrasher -apple -banger -horowitz -ticolensic -grander -knotty -spelltinkle -grandlich -grumblemeyer -spelterwasser -kürstlich -himbleeisen -bahnwagen -gutenabend -bitte -eine -nürnburger -bratwustle -gerspurten -mit -zweimache -luber -hundsfut -gumberaber -shönendanker -kalbsfleisch -mittler -raucher von Hautkopft of Ulm, due out in 2057.

More CPU's dont mean faster

[MatthewNewberg]

One Fast CPU is always going to have an advantage over multiple slower CPUs. It takes a lot of bookkeeping in the background to assign different tasks to different CPUs. Not to mention programs need to be written multi-threaded to take advantage of another processor.

Re:More CPU's dont mean faster

[shepd]

He said:

"Honestly, a PC with eight $20 CPUs would end up far more responsive and just as useful for every task than one with one single several-hundred-dollar chip"

More responsive and faster don't mean the same thing. Encode some video in windows and set the codec to realtime and notice the speed increase, but also notice that it takes 10 minutes to open up a new explorer window.

With more processors running separate tasks, responsiveness is bound to increase. Sometimes responsiveness is most important, for example, when you're typing in a shell, you'd rather ls take an extra 2 seconds than having to wait 2 seconds between each keystroke appearing.

Re:More CPU's dont mean faster

[oliverthered]

You are talking out of your...... well
2 slower cpu's run cooler than one fast one.
2 slower CPU's are cheaper. (production yeilds are higher)
2 slower CPU's have twice as much cache.
2 slower CPU's have less latency (think 1 cpu waiting the other actually doing something, instead of 1 cpu waiting)
All applications should be written multi-threaded, for when my 1000 CPU's are slower than your 1 CPU. And how many times have you booted into DOS and run a single application. I have 40 processes running at the moment.

On the bookkeeping, there isn't too much overhead between 1CPU and 2CPU's since you still have to do most of the bookkeeping for a single CPU system(unless your running dos!).
System architecture is one of the main overheads, if chipsets had better support for multiple CPU's then that overhead would vanish (infact the single CPU system would also have a performance boost).

Your thinking Mythical Man Moth, well the Mythical Man Moth argument doesn't hold up when there's more work and information than can be handled by one person.

Re:More CPU's dont mean faster

[g4dget]

It takes a lot of bookkeeping in the background to assign different tasks to different CPUs. Not to mention programs need to be written multi-threaded to take advantage of another processor.

There are lots of ways of using multiple processors for computations; threads is only one of them, and probably among the most cumbersome.

One Fast CPU is always going to have an advantage over multiple slower CPUs.

If that were true, the fastest computers would be like the supercomputers of the past. But multi-processor designs and compute clusters have pretty much killed the supercomputers of the past.

Re:More CPU's dont mean faster

[HiThere]

There a certainly tradeoffs, but it's not a true statement.

It's worth paying for a more complex design, etc., to get a faster unitary CPU instead of two slower ones, for the bookkeeping reasons that you point out, but not worth paying an unlimited amount more. OTOH, simple parallelization schemes have their limits also.

My view of where we are headed is:
1) CPUs will advance to some optimum level of power.
2) Clusters of CPUs will increase the power of the individuals.
3) Clusters will be linked along a fast bus, with one CPU out of each cluster attached to the bus. (This cpu is effectively a member of two separate clusters, but one of the clusters does practically nothing but manage communications.
4) A node at one end of the bus will be linked into an orthogonal bus, which will contain similar nodes...

Now this is just a design for a maximally compute intensive processor. At each step you must pay additional overhead, so you would be better off it the problem could be addressed by a system one level simpler. But if you can't...

At this point we come up against the issue of "but how do you USE it!?" This system will probably not be effective until compilers, or possibly interpreters or VMs can automatically partition problems and assign the pieces to various chunks. This will probably require a message-passing operating system. (Not too unreasonable. I think that Linux could be adapted into one.) But, e.g., when a job wants to open a file, it wouldn't need to know where the disk was, it would just send out a message asking for the file. This is like the separation between files and devices, so the basic layers are already in the design. File permissions would need to include lock status, though, or else file access would need to be managed by a dedicated cpu (which could do it in about the current manner). Etc.

There's lots of details that will need to be thrashed out, and the design isn't going to happen this year, or the next. (Probably.)

At some point, all higher levels would get turned over to a TCP/IP like connection set, slightly redesigned to optimize it for use within one connected computer system. (Probably just a matter of adding some additional protocols for internal use that are more efficient over the known network configuration, and are less concerned with security, but which will only talk internally. [And which have their own limits, so that a virus can't spread unchecked.])

I see all external communication occuring over standard TCP/IP, and possibly even using only a subset of the standard protocols. (N.B.: I'm talking about limiting protocols, not ports. Think of it as a sanitation measure. You want the system to be able to evaluate incoming communications, and react sensibly. If someone tells it "Drop dead!", it should decide not to obey the literal, or even the figurative, interpretation, but rather to consider that this is an expression of frustration. And this should be true even if the remote user is "root". Some commands should require local access.)

N.B.: I talked as if this were a strictly hierarchical system, and, to a large extent it would be. But it should take advantage of sideways links also. This would be largely for error recovery, as the high speed communications would be hierarchical. But it should enable reconfiguration and recovery (and diagnosis) in case of hardware errors. (Think of the cell system for underground agents.)

Re:More CPU's dont mean faster

[oconnorcjo]

One Fast CPU is always going to have an advantage over multiple slower CPUs. It takes a lot of bookkeeping in the background to assign different tasks to different CPUs. Not to mention programs need to be written multi-threaded to take advantage of another processor.

Sure One fast CPU will often outperform a slow smp system when running ONE program (that is not multithreaded) but most people don't run just one program and the cpu's can run different programs on different cpu's. It may still be slower do xyz but xyz can be run in the background while you play doom 3 in the forground without the two tasks slowing each other down on an smp system.

Try compiling a program in the background, while playing mp3 songs, playing chess against the computer (while waiting for programs to compile) and having a few other misclaneous stuff running in the background with a one cpu system. The system starts to feel and sound CHOPPY no matter how fast the CPU.

On a slower SMP system, the compiles may take a little longer, and the chess program may not have the same depth search but the system will run SMOOTHER.

first to forgoe pins?

[mesach]

there were pins on the slot1's?

Re:first to forgoe pins?

[Zathrus]

there were pins on the slot1's?

Yes.

What, you didn't see the processor on the center of that board? With the pins soldered to the board?

Even so, the statment is incorrect, since there have been previous CPUs that were pinless - such as some revisions of the 80286.

A CPU this complex without pins is a pretty nifty thing though.

Re:first to forgoe pins?

[Anonymous Coward]

Actually Intel tried this with the 286 and failed miserably.

I think I still have a ceramic 286/4 without leads lying around here somewhere. Installing cpu into the socket was a nightmare and contact stability between the two was horrible even with full gold lands and socket contacts!

Good luck on that many pins working as advertised for more than a few months at a time!

Hy guess is the contact cleaner makers will clean up literally on this chip to our regret.

Who cares?

[Anonymous Coward]

First of all PCI-express will come in second half of the NEXT year.

Second, PCI-Express x 16 just double AGP8X bandwidth. We can expect same "dramatic" (1-2%) performance increase as we saw with AGP8X and AGP4X. It will take many years until this kind of performance is really needed. Since high-end video cards will have 512MB of very fast (~40GB/s) local memory in H2-2004, 4GB/s bandwidth offered by PCI-Express won't make much difference compared to 2GB/s AGP solution.

PCI-Express add-on cards won't be popular anytime soon. Since:
1) PCI replacement (PCI-Express x 1) offers just 250MB/s of bandwidth, thats isn't a lot more than current 133MB/s offered by PCI.

2) >90% of users won't need any external cards in H2-2004. Currently we have following stuff integrated on the chipset/motherboard:
-two 100Mbps NICs
-Sound with better quality than original Audigy
-Firewire/USB2 etc

In 2004 we will also have:
- NICs will be updated to 1Gbps
- Wireless LAN
- DSL modem

3) In the server market PCI-Express won't be popular since it isn't compatible with PCI. Currently servers use PCI-X (1GB/s) and it will be replaced with PCI-X 2.0 (2GB/s). This is enough bandwidth for many SCSI-raids and Gigabit NICs.

Re:Who cares?

[poot_rootbeer]

Yes, PCI Express will only be an incremental improvement over the latest AGP spec. But there are other devices on the peripheral bus that need to move a lot of data around.

Your processor runs at an internal clockspeed of what, 1.5GHz? And your PCI bus? IIRC, it maxes out out a paltry 66MHz. The peripheral bus is already a bottleneck, today.

I don't care how much they can integrate onto the mainboard, it's still going over the same bus -- the only difference is that the connections are etched onto the board instead of having card slots.

Furthermore, bundling peripherals onto a mainboard is exactly as bad as bundling web browsers and such into an operating system: it's harder to choose solutions from other vendors even if they're better suited to your needs, you're paying for features you may never use or need, there's no incentive for the hardware company NOT to cut corners and put the cheapest shite on there that they can find.

The beauty of the x86 PC architecture, if any, is the extreme modularity. I hope that this feature of the design doesn't get eroded away by increasing levels of device integration, and a stronger, faster PCI spec can help a lot towards retaining openness and modularity.

Re:Who cares?

[cgori]

The key point is that PCI is a bus -- PCI Express is point-to-point. This is roughly analogous to a hubs versus switches discussion in Ethernet network design. In the point-to-point system every channel/device has its own dedicated connection -- the electrical signalling requirements are vastly simpler for such a device.

PCI Express is similar to what AMD does with LDT (HyperTransport), and what will allow them to have highly scalable MPs with Opteron/Athlon64. The LDT hubs can just be scaled up for larger systems. Contrast this with the Intel (ia32 -- Itanium is totally different) method, it pretty much craps out at 4-way SMP (yeah, there are 8-way x86 boxes but they are total hacks, basically dual 4-way boxes highly integrated). In general, point-to-point is where it's at for all future system designs that need to generate any kind of performance.

Last, building peripherals in chipsets is not bad at all from a cost perspective -- the total system cost will almost assuredly go down. Highly-integrated chipsets are gonna make your motherboard dirt-cheap in the long run. All Intel is doing is gluing together lots of discrete components into one "kitchen sink" chipset. Trust me, it's less expensive to hook that stuff up on-die than on-board (in 0.18/0.13u and below, the incremental die area is near-free, plus you pay for only one IC package instead of multiple, have less impact from assembly fallout, etc). If one of these parts isn't high-perf enough for you, it should be trivial to drop-in a card to replace it. That is flexibility.

ExtremeTech article

[dm(Hannu)]

PCI Express Technical Introduction on ExtremeTech.

Sure!

[TechMangler]

I'll just toss my $200+ Radeon out on the trashheap!
Do I hear echos of MCA here?

Re:Sure!

[pboulang]

umm, since it will probably be about two years before you would be buying such a system, what's the problem? Did you not expect to get a new video card by then anyways?

My God!!

[ksemlerK]

This is almost assanine how fast technolgy is going. My motherboard is a DFI 586ITOX Rev. G, and I have 2 PCI slots (1 being shared), and 6 ISA slots. The only way I even have a modem for my system is because I fished it out of the trash behind a computer store that was throwing out all old equipment. I would like to upgrade, but I need to have at least 2 ISA slots, and modern motherboards do not have any. I find this rather inconvenient. Also, finding a motherboard that supports SDRAM is getting very difficult too. I have been looking for a decent P4 motherboard with 2 ISA slots and 4 SD RAM slots, but I do not think this is going to happen anytime soon. I have 768MB in SDRAM, and I am not about to throw any of it away just because of new "improved" technolgy. Where are all the old PIII and PII boards these days. And the processors? It is like trying to find gold at the dumpster now.

Re:My God!!

[Anonymous Coward]

Wait another year or six months. All computers eventually end up in the dumpster.

Sort of like humans.

Re:My God!!

[ksemlerK]

That's true. I will just have to go dumpster diving some more. Oh yeah, your sig goes good with what you said. It is so true!

Re:My God!!

[Anonymous Coward]

You wont find any new motherboards with an SDR SDRAM slot, maybe one or two but I highly doubt it.

If you're going to buy a new motherboard and processor, why not just bite the bullet and buy the PCI/AGP new equivalents of your ISA cards. Unless you have some very special needs (controller for some piece of specialty hardware, etc...), why hold onto your ISA cards so dearly?

You can buy a cheap but OK sound card for under $20 (anything with a CMI8738). You can buy a GeForce4 420MX for under $70 and if you really try you can get a GF3 Ti200 for like $40. Anything else that you need your ISA slot for, must really be dragging down your system performance.

Hell I bet an Athlon XP2000 with 256MB of PC2400 memory will be well over noticably faster than your current machine.
You could find a motherboard, XP2000, and 256MB of PC2400 for about $225 I bet. Then throw in a sound card witha CMI8738 and a GF4 MX420 and you could have a really nice system for under $400 -- shop around and you could probably do it for $350 minus s/h.

Re:My God!!

[JaxGator75]

I've found several mobos on ebay (both new and refurbs/used) that support PC100/PC133 or both DDR and SDRAM. It's not fast or easy, but they are cheap (thanks to DDR being the $#!+ and all)

Re:Why NewCard?-New case designs?

[Anonymous Coward]

Actually I would like to see what all this new technology does for case design. Our cases are the same boring boxes because of the fact that the internals are also big and bulky, or just plain awkward. Snazzy comes to the PC.

Has anyone upgraded from Athlon to Athlon XP?

[Anonymous Coward]

Yeah, except most of the time you still end up needing a new board for new voltage requirements or whatnot. Has anyone actually upgraded from, say, an Athlon to an Athlon XP without getting a new board?

Re:Has anyone upgraded from Athlon to Athlon XP?

[wackybrit]

That's what's stopping me upgrading.

I bought an Athlon Thunderbird 1Ghz (socket A) as soon as they came out, and the motherboard I got can't deal with the XP range at all. Infact, I think it can only cope with up to 1.33Ghz TBird, not even the 1.4.

What's worse is that I need to totally change all my RAM as well :) So.. I gotta buy a lot just to upgrade to XP.

Re:Has anyone upgraded from Athlon to Athlon XP?

[shellbeach]

I made the same error years ago when I upgraded to my current system (a Celeron 400 MHz, overclocked to 500 MHz) - I bought a "better" motherboard (a BX) to allow an eventual upgrade to a Pentium III 800 or something ...

Now that I'm considering getting a new system, I realise that (a) if I ever want to upgrade it, it will require a new MB, new graphics card and probably new RAM, and (b) since I barely need to upgrade my current system, I probably won't *ever* upgrade until my harddisk dies and my motherboard doesn't support the smallest size currently available (which is the case at the moment!)

But anyway ... All I wanted to point out is that you may not have to upgrade your RAM - I know ECS for one makes boards (eg the K7S5A) that take both SDRAM and DDR, and they support at least an Athlon XP 2200. Just a thought ...

Re:Has anyone upgraded from Athlon to Athlon XP?

[ShavenYak]

The motherboard that my 750MHz Duron was on would support the AthlonXP with a BIOS upgrade, but I wound up getting a new motherboard so I could have DDR memory and more USB ports.

Actually thinking about it, every time I've upgraded CPUs, I've gotten a new motherboard - even though it wasn't really necessary every time. There's always either something else the new boards support that I "gotta have", or my mother's computer is getting old and she wants my old board.

By the time I start to feel like my XP1600 is slow, I won't want to just buy a 3000 and slap it on this board, even if I can. I'll want a new board with DDR2, Serial ATA, and FireWire. CPU upgradability is overrated, IMHO.

Re:Has anyone upgraded from Athlon to Athlon XP?

[wackybrit]

Yeah, but I'm find 256Mb a bit of a drag now anyways. Besides, I imagine using PC133 with an Athlon XP 2200 would be like running a Ferrari on biodiesel :)

So, when you gonna make the big jump to the Pentium III 800Mhz?

Re:Has anyone upgraded from Athlon to Athlon XP?

[JaxGator75]

I have to agree. My 2 or 3 PCs are on a continual SLOOOW upgrade path where the stragglers fall off the back-end and into a friend or family-members PC to make it better. It's a symbiotic relationship as they need me to upgrade their old-n-busted as time passes and it affords me an excuse to go out and get new-hotness. When a MAJOR over-haul is required, I'll usually look into what is coming around the corner and try to get yesterday's State-of-the-Art that I feel is most-likely in step with coming changes. You win some (chose DDR over RAMBUS) and you lose some (T-Bird board wasn't AthlonXP compatible) If money is not the determining factor, I'll upgrade my Mobo with my CPU (always nice to recycle RAM, tho, when possible)

Great, another socket change

[Anonymous Coward]

Does anyone remember Intels BX-chipset? It was released in 1998 when 400MHz was the fastest CPU. Many motherboards using it work with 1.4GHz CPUs.

With P4-era, Intels attidue has changed completely. Now we have:
Socket 423 - released in Novemeber 2000
Socket 478 - released in August 2001
Socket 755 - will be released in Fall 2004
+ many Intels chipsets released in the last year don't support hyperthreading.

Any Intel motherboard which is available now, will become obsolete in about a year. I hope that AMD Hammers platform will have a longer timespan.

Socket-5 upgrades

[JCholewa]

> You could put a P266 in your socket
> 5 mb when you upgraded from a P100?

You might not have been able to do that, but the Centaur (the cpu design team that nowadays makes VIA's C3 chips) 240MHz WinChip could make that jump, if I recall correctly.

I am not certain if the WinChip 2 or 2A could work on Socket 5. They were basically just WinChips with 3DNow! tacked on, but they might have been out of spec for Socket 5, ever so slightly.

Oh, and there were probably "upgrade" chips, which were newer processors with adaptor thingies between the cpu and the socket.

-JC

ISA is not dead

[The Tyro]

I have several ISA devices that I still use...

One's a modem (a REAL modem that I can configure with jumpers, that works under linux... don't even get me started on winmodems)

I also have a WINRADIO (or LINRADIO under linux); Those come as ISA cards if you get the internal version...

Yes, I know it's a dinosaur hardware interface, but I still find it useful... and I'll bet I'm not the only one. Hardware may find itself deprecated and unsupported (Apple's Newton, anyone?), but still useful.

Re:ISA is not dead

[Anonymous Coward]

Yeah, but hey moron - nobody is building ISA into motherboards anymore!

6 month driver releases?

[rainwalker]

From the article, ..."Granite Peak" initiative, which limits the number of driver revisions to one every six months, making the launch of each new chipset even more significant.

So, what exactly does this mean? If I have a problem with Intel's drivers that, say, prevents my machine from booting (not that THAT has ever happened) I have to wait 6 months for the next revision? I don't understand what driver revision schedules have to do with product release cycles.

Also from the article: "...[people buying] the latest GeForce card near the end of this year, when six months later it won't work [fit] inside a new PC?"

This is a non-issue for most people, I think. Those people who buy new video cards every six months (you know who you are) aren't really going to balk at replacing motherboard, CPU, and video card all at the same time, if it yields a 25% performance improvement (or more). At the other end of the scale are people who upgrade video cards by buying a new Dell (or whatever), for whom this is also not an issue. Those of us in the middle just won't buy a new motherboard/CPU until we can afford to replace the whole shebang anyway. Once we do, we will most likely build a whole new machine.

Anyway, it's not like nVidia and ATI are going to stop making AGP cards; I'm sure that both connections will be supported. If you look around, you can still get PCI versions of most cards on the market (shudder).

Re:6 month driver releases?

[SmittyTheBold]

Don't forget that since you can't have multiple AGP cards in a machine, there is a darn good reason to have PCI cards around. Multi-head display adapters alleviate the problem some, but it's still nice to be able to have, say, four displays on one PC.

Re:6 month driver releases?

[sjames]

So, what exactly does this mean? If I have a problem with Intel's drivers that, say, prevents my machine from booting (not that THAT has ever happened) I have to wait 6 months for the next revision? I don't understand what driver revision schedules have to do with product release cycles.

Hopefully, it means the first version will be produced by some methother than the currently popular: dd if=/dev/urandom count=102396 of=driver

It might also be nice if it didn't take a daily chart to know which subminor release version of CPU was compatible with a given motherboard.

Gut the case?

[DrCode]

Since my MB and case are AT's, I have to replace the case as well. The one constant in all my upgrading is the floppy drive; it originally came with my 486.

Re:Gut the case?

[PetiePooo]

I replaced my floppy drives with LS-120 Superdrives several years ago. The latest PC I built doesn't even have that; just a CD-RW and a NIC. I'd rather the MB makers eliminate the floppy interface than the PCI.. Does anything still come with a floppy? I haven't seen a new one in ages.

Vat ees thees "fla-pee" you speek off?

Re:Gut the case?

[sconeu]

Piker. My 5.25" floppy came with my 10MHz 286. It's the only original part I have left, and allows me to maintain the fiction that I'm still "upgrading the original computer".

Yet Another Rip-Off

[Anonymous Coward]

Grantsdale brings PCI Express to the PC, so get ready to toss out your motherboard, AGP graphics card, and maybe a host of other components, too.

If Intel think I'm going to chuck everything out just because one single component needs upgrading, they can go screw themselves. I'm fed up with being bled dry.

Re:GeForce/Quadro FX and ATI R400 obsolete already

[Anonymous Coward]

I'm not completely sure on this, but I'm guessing you could add a PCI-X bus to an AMD. Its the northbridge that connects to the main busses in a computer.

Also, I wouldn't doubt that AMD knows this and probably will be able to fully support PCI-X.

I know they (AMD) do have their alternate to it, just like Motorolla does, but they cant and wont limit themselves like that.

What's the point?

[Galahad2]

I guess I don't understand what PCI Express does. If it's just more bandwidth, how could it make any difference? There's no game that saturates even AGP4x; why would you need something even faster than 8x? 8x will be sufficient for games a generation newer than Doom 3, I'd bet; why should we get excited about a standard that won't affect anyone for five years?

Re:What's the point?

[vofka]

Sure, one GFX card may not saturate the Bus, but what about more than one?

Imagine having a board with several PCI Express slots - put a Good Graphics Card in, say, each of 3 slots, and multihead your games :)

Also, if I understand it correctly, PCI Express is an upgrade to / replacement for PCI. Sure, it allows high-bandwidth comm to a Graphics Adapter, but also to SCSI/IDE Controllers, NIC's, Video Capture Hardware etc, etc.

Re:What's the point?

[Anonymous Coward]

The point's to initiate another upgrade cycle among consumers and thus pave the way for TCPA compliant hardware. That's the point, I'd say...

Wish I were wrong, though.

Re:GeForce/Quadro FX and ATI R400 obsolete already

[Anonymous Coward]

Since Intel has played their rambus card I have avoided their stuff, no loss for me....

What's going to happen to USB ports?

[Thagg]

The article mentions that Intel may do away with the USB ports in the Grantsdale systems, that PCI express may get rid of USB entirely -- but if it does have USB it will have at least 8 ports.

OK, that's pretty weird. But why would they get rid of a popular, reasonably high-performance, and cheap interface like USB? Is Firewire 800 going to take it's place? SATA? Is everything going to be wireless?

thad

Re:What's going to happen to USB ports?

[Anonymous Coward]

Im not really sure what they mean but an interpretation could be that they are going to get rid of USB 1.1 for good and only support USB 2.???

I can't see Intel dumping USB totaly...

Re:What's going to happen to USB ports?

[JaxGator75]

I understood it to mean that they will ONLY have USB 2.0 and no longer 1.1 This should not be a problem as you can plug a 1.1 device into a USB 2.0 slot and just get slower speed. Then again, I could be wrong... It struck me as odd too, and this is the best I could come up with...

Extensible market awaits!

[AnonymousCowheard]

PCI-X is being received incorrectly. Many people look at it as another hardware interface, yet are lacking the guidlines of this technology. PCI-X is a raw IO medium that will allow technology to scale efficiently on various platforms. Not to mention, PCI-X's initial design is to allow hot-swaping of PCI-X compliant hardware. With the skill of various engineers, legacy ISA/PCI/AGP implementations of products will be re-implemented upon systems using temporarily-necessary hardware abstraction and "bridge" technology to allow the most ethical cost of acceptance of PCI-X enabled system BUS.

The lack of extensible technology is the main reason of the acceptance of the Accelerated Graphics Port (AGP) and addresses the need of maximum system up-time and stability for most efficient administration of hardware and software.

Yes, I am speaking out of my a$$, but the Karma feels so gooooood!

Re:Extensible market awaits!

[Anonymous Coward]

That was the best load of crap I've read in ages! Please sir, blow more smoke up my ass! And where can I preorder?

Re:Extensible market awaits!

[Anonymous Coward]

Wrong !!! PCI-X != PCI express.

PCI-X is a compaq initiative that is backwards compatible to PCI2.X as we all knows it.

PCI-Express is an Intel initative that uses a serial bus.

pft. i'm still using ISA.

[themusicgod1]

there are many many people who would love the hardware you use right now. Mabye it won't be state of the art any more...who cares? imagine all the stuff that you are using it for - - at last us below-the-poverty-line may be able to do those things too... I'm pretty damn happy using djgpp, IE 3.0, 1-2-3, and a whole whack of programs instead of having to use DOSSHELL, EDIT, and and the like... don't just toss your old computer parts, if there is anything to salvage, salvage it and give it to groups such as Sasktel Pioneers, or whoever it is that locally distributes computers to those who can't get them when they are straight out of the box... just as people 10 years from now will be tossing computers that can't do real-time, surrealistic fractal VR ... there is no excuse to throw any computer out, unless there is something seriously wrong with it. stupidity is not an excuse, either.

hell SETI needs processing power, even...

PCI express - what's the benefit?

[Anonymous Coward]

Article:

However, the chipset will most likely be known for its PCI Express capability, which was formed because the PCI bus and the Accelerated Graphics Port were running out of steam. PCI Express uses a series of point-to-point channels to communicate information, in either x1, x2, x4, x8, x12, x16, or x32 dual channels, with 2.0 Gbits/sec of available bandwidth per channel.

But regular 32bit PCI @ 66MHz has (32x66=) 2.1 Gbits/sec ... doesn't it?

Or is the dedicated channel the innovation? (is that what Serial-ATA's about?)

in India "Tejas" is ...

[Anonymous Coward]

Tejas means lustre, shining, burning .. usually associated with sun ... of the 15 official languages in india, it means in the same in the 2 that i know viz marathi and hindi (national language)

But there are other important PC updates left out

[master_p]

Sure, I need faster speed (Doom III comes to mind; and a whole load of cinema-quality games-imagine Half Life II for example, or Duke Nukem For Ever), but there are some other things that bother me:

1) the PC BIOS!!! for how long should we tolerate the shitty 16-bit PC BIOSes ? I mean, in the days of PCI-X and 800MHz memory buses, the PC's BIOS is still 16-bit and operating systems need to perform wild tricks to boot.

2) the partioning scheme. Only 4 partitions!!!! this is an artifact from the days of the original PC.

Ok, not so important but irritating nevertheless.

What's Obsolete?

[maizena]

No matter how long you wait, the day after you buy/upgrade your PC it will be already obsolete.

We shall not forget that, as any other enterprise, Intel's business is to make MONEY. Cutting edge technology is just a plus...

It's in their best interest to push forward the their latest family of products. This is how Intel works and obsolescence is carefully planed by them.

It's up to us, as consumers, to set the pace and not get swept by the low-tech fears. An upgrade is really only necessary when your PC performance gets in the way of you doing your usual tasks.

Therefore, we must keep in our minds that obsolescence is dictated by our needs, not by theirs.

Re:What's Obsolete?

[Anonymous Coward]

It's up to us, as consumers, to set the pace and not get swept by the low-tech fears. An upgrade is really only necessary when your PC performance gets in the way of you doing your usual tasks.

That's fine, until you find out that your neighbor has more processing power and I/O bandwidth than you. That's when you wonder: maybe his penis is bigger too.

I question the wisdom of naming this chip

[Jamesie]

Mr Grantsdale!

When this chipset comes out...

[fok]

My motherboard, processor, videobord, SDRAM, etc will be *long* gone, as they are already 1yr old.It will be a good time to change it all an get some extra-extra-extra performance ;D

your old stuff

[Ratchet]

There's an PCI-X to AGP bridge that vendors can take advantage of to offer AGP ports on PCI-Express motherboards, so you'll likely be able to hang on to that new $500 vidcard you just bought (not that you'll be seeing PCIX anytime soon mind you). Your "old" PCI devices should still work as well.

Who exactly is in the PR/Graphic/Ad Design Dept at

[adzoox]

Who exactly is in the PR/Graphic/Ad Design Dept at Intel? I think the only markettable ideas Intel has ever come out with were the names Pentium and little tone at the end of commercials. The names they come out with are very rarely tongue rolling or memorable. Same goes for their commercials. I mean, one campaign has Homer Simpson getting his brain replaced by a Pentium. The next campaign has aliens using it. The first tells me that stupid people use the Pentium, the second tells me that only aliens think a Pentium is cool,

Not being Apple bias, but you have to hand it to Apple Computer's PR/Design/Ad/Graphic Design Departments. They even get press for what they name variations of the operating system. It's not goofy either. Jaguar and all the promotional material has spawned the entire design industry into using animal prints, especially Jaguar.

However?

[AyeRoxor!]

"Tejas uses a 775-contact pinless Land Grid Array (LGA) that far exceeds the 478 pins used on the Pentium 4, and Prescott. However, the additional pins were required for the additional I/O and power requirements of Tejas, the documents say."

Ohh, for I/O and power ! I thought they would be used for..... umm... Well, that's about all they can be used for. Why does that sentence begin with "However"?

Re:However?

[Repugnant_Shit]

Not to mention "the additional pins" - I thought it was pinless.

Re:However?

[tomstdenis]

There are clock, reset, bus control, state control, interupts, etc. pins as well.

But yeah, the majority of the pins will probably amount to a 256-bit data bus and a few hundred 1v power inputs :-)

Tom

Re:However?

[AyeRoxor!]

"There are clock, reset, bus control, state control, interupts, etc. pins as well."

Aren't those all data transmission pins, otherwise known as input/output pins, aka IO pins?

IP and lock-in aspects

[dpilot]

As others have said, so what if a new motherboard is needed - they're obsolete about as fast as a CPU chip, anyway. Another post indicates that PCI eXpress is a reasonably open standard.

But the IP/lock-in aspects still bother me. Intel behaved like a spanked puppy for a few years after their Rambus fiasco, but lately they seem to be back at those games, again.

They've taken steps to ensure that Banias/Centrino only sells with their chipset. It's only a logo program, but it probably carries a heavy enough advertising kickback behind it to have the force of law.
The Itanium is *the most proprietary* CPU on the planet, or at least a contender for the crown. No second sources, no cross-licensing on any of the IP.

So in this light, anyone want to bet that Tejas is not tied to Grantsdale?

Assuming it is, the net effects are questionable. It appears that Intel is driving compatibility away from the CPU pins, and out to the motherboard plug interface. I seriously doubt they have the capability to push it any further than that. In the long run, this probably opens the market niche for AMD and Via C3, because it's closing the market for low-cost chipset providers to service Intel CPUs.

Re:But there are other important PC updates left o

[ponos]

> 2) the partioning scheme. Only 4 partitions!!!! this is an artifact from the days of the original PC.

You can definitely have more than 4 partitions. I think
2 primary plus 8 logical is the maximum (total of 10).
It would be nice to have an arbitrary number of partitions
but this is not very important in my opinion.

Regarding the BIOS, I have to say that I like it the way it
is. Complex things fail and BIOS should be 99.999% error
free. I don't see the need for a themeable GUI-Bios with
transparent windows. If it works, don't break it.

P.

Not so worried about Braveheart...

[PurplePhase]

as I would be impressed if it could finish playing Farscape, The Complete Season 1 on battery power.

*That* would be an accomplishment. Or how about backing up the portable's HD by burning a library of DVD*XX's? All on battery power.

Not that I've tried either with any current laptops.

8-PP

This is an uninformed post. Move along. If this was an informed post flames would start shooting out of your ears.

How completely ...

[bob670]

boring. Yet another round of upgrades from Intel. The first poster was right, this is why Mac will gain marketshare this year. Intel and Microsoft will unleash another round of upgrades that promise to change the way we work and play. Then Apple will continue releasing new products that do change the way we work and play, all the while the Wintel fanboys will continue to proclaim Apple is dead. Just once I'd like to see Wintel do something really new instead of revisions. Oh boy, longhorn on 4gHz, yippy!!!

Re:How completely ...

[Anonymous Coward]

And when Apple adopts the PCI express standard, sometime after Wintel, you'll no doubt sing songs about Apple's "innovation."

Re:How completely ...

[Anonymous Coward]

Amen to that!

sig

[Anonymous Coward]

I disagree w/ 1 thing U said, I can't take ANYTHING U said seriously = I think skunks stink; so everything stinks

No, it equals:

You step out of the crowd with a perfume to show us all but it stinks;
presumably you'd only present us your sweetest smell ergo all your perfumes stink.

*snaps fingers*

[Anonymous Coward]

Oh, so THAT explains why my mother-in-law redid her entire living room in this really lame fake leopard print! It must be the mac she uses at work!

Hey, at least I got a free non-leopard-print couch out of it.

Other tidbits in the FAQ

[PurplePhase]

Q20: Does the PCI Express Architecture compete against HyperTransport?
A20: No. The PCI-SIG views HyperTransport and PCI Express Architecture as complementary, not competing, technologies.

Q19: What impact will the PCI Express Architecture have on 1394b, USB 2.0, InfiniBand, Fibre Channel, SCSI, Ethernet, and/or other popular I/O technologies?
A19: ... OEMs and IHVs will determine which of these technologies are bridged to the PCI Express Architecture.

A16 says PCI-X's first generation is already twice AGP 8x, which makes me wonder what's the 2nd generation going to be? And how long do they expect this one to last. More specifically, will PCI-X finally jump to the next levels when AGP/video cards need it to?

Also, 32 X 2Gbps = 64Gbps = 8GBps, so it's 8GBps dual channelled, but that's still a max of 8GBps one-way communications, right? Granted, if both points are talking to the other at the max they will reach 16GBps, but I'm not use to thinking of intra-PC situations like that.

8-PP

Poser.

[Thud457]

Vacuum tubes?!!

Jesus H. Christ, man! All we had were steel balls and tracks! And we got 0.00000032 fps in the original Doom.

You noobs!

[Anonymous Coward]

Stella rules all your sorry asses!

Re:But there are other important PC updates left o

[Anonymous Coward]

In the eyes of Microsoft it's tree more than you would ever need...

First to forego pins?

[BoneFlower]

Nope. I distinctly recall the Intel 80186 in an old wang I had once that had no pins, just a bunch of contacts.

Re:First to forego pins?

[Anonymous Coward]

Huh huh huh....you said Wang.

Re:First to forego pins?

[Anonymous Coward]

I distinctly recall the Intel 80186 in an old wang I had once that had no pins, just a bunch of contacts.

We don't want to hear about your old wang. Or its contacts.

Especially not about the pins that may or may not have been in it.

Re:First to forego pins?

[sconeu]

Yep. My old 286 was a PLCC. No pins, just contacts on the side.

Proprietary bus?

[IGnatius T Foobar]

Throw away your video card? Throw away your other slotted peripherals? Replace them with something that uses an Intel-proprietary bus?

Didn't IBM try this a decade and a half ago? Intel needs to read up on something called Micro Channel and learn why it didn't work for IBM, and it won't work for them either.

Intel needs to tread carefully. They may be Chipzilla today, but something like this could be the turning point, like Micro Channel was for IBM, where they turned the screws a little too tight and the customers fled to something more open.

Re:Proprietary bus?

[in_ur_face]

Intel was a main contributor to the PCI bus... you dont call that Intel-propritary do you? The PCI express SIG has many members; Intel is just one of them...

Re:Why NewCard?-New case designs?

[Zugok]

yeah I want a PC in the shape of a stegasaurus so I can slot my PCI cards like spines and have power and HDD LEDs for the eyes.

This is dumb

[Anonymous Coward]

The ultimate in CPU packaging will be RF, that is, one high bandwidth interconnect using a very dense modulation scheme like 1024 QAM. The bus of the motherboard will be Infiniband.
The CPU will look like old style ceramic power triodes, with a built-in bonded heat sink. There will be two low inductance connections for power, and a hard line SMA connector for everything else.

Mo Hype!

[zerofoo]

My Pentium III-M 600-MHz notebook in performance-optimized mode doesn't have the kick to play a DVD

I've played DVDs on Pentium II 300 MHz laptops without difficutly....what's this guys problem?

Worse still, Brookwood said, was when he takes his notebook to the local java joint. "I just want to sit there for a couple of hours"

A couple of hours? Don't you have anything better to do? Go get a job.

whopping" 316 minutes of battery life using a Centrino notebook"

I'll belive it when I see it. The two biggest draws of power in a notebook are the LCD backlight and the hard-drive. "Centrino" doesn't change either of those.

Don't believe the hype.

-ted

Uhhhh...

[OrbNobz]

Intel's "Tejas" processor will do away with pins entirely, making swapping out a new processor quite literally a snap.

I'm sorry, "processor" and "literally a snap" do not belong in the same sentence.

- OrbNobz
"I'm gonna sing the Doom song..." - Gir

Re:But there are other important PC updates left o

[mr. wibbleton]

1) the PC BIOS!!! for how long should we tolerate the shitty 16-bit PC BIOSes ? I mean, in the days of PCI-X and 800MHz memory buses, the PC's BIOS is still 16-bit and operating systems need to perform wild tricks to boot.

Intel EFI, addresses this issue. Certianly from evalution IA-32 systems I've seen "pure" EFI systems should be able to post in under a second if the EFI built in boot manager is turned off.

2) the partioning scheme. Only 4 partitions!!!! this is an artifact from the days of the original PC.

Intel EFI also solves this issue. Effictively unlimited number of partitions are allowed on a EFI GPT (General Partition Table)

Is PCI Express really needed?

[Cutie Pi]

How is PCI Express going to be deployed? Will it be like the PCI bus, where you initially had motherboards with both ISA and PCI slots? The number of ISA slots gradually declined as they were replaced by PCI slots until POOF, no more ISA slots.

However, PCI was a desparately needed technology then. The ISA bus too slow for almost everything except modems. Sound cards, video cards, network cards, SCSI and IDE cards--they all needed more than than 10MB/s total bandwidth (theoretical) of the ISA bus.

But now... is it really necessary to completely displace the PCI slots to make room for PCI Express? Especially for the average user. With the exception of video, what other cards really need PCI Express? The IDE will probably be interated with the motherboard. Modems, soundcards, and network cards (exception: 1000 base T) all work fine at PCI speeds. And SCSI isn't something average users have.

I am just curious, as I am kind of ignorant on the matter.

First with no Pins? NOT!

[Anonymous Coward]

I have a 8086 at home with no pins. Just contact points. I didn't understand why all CPU's didn't do the same thing......

no pins

[chunkwhite86]

This "waffle iron" design which lacks pins is old news to the DEC/Compaq/HP Alpha processor team. They have been using this packaging for almost a year now in production systems.

How could PCI Express possibly be a benefit?

[default luser]

Did I read that right? 250MB/s?

PCI spec is 133MB/s, which is hardly a marked improvement. 16-bit ISA, by contrast, was barely 16MB/s.

If I am to believe the theoretical numbers for AGP, then PCI Express as a graphics bus makes even less sense:

AGP 1x = 264MB/s ( 66.6 mHz, 64-bit )
AGP 2x = 528MB/s ( 66.6 mHz rise and fall, 64-bit )
AGP 4x ~ 1GB/s ( 66.6 mHz - 4 strobe, 64-bit )
AGP 8x ... you get the picture.

What in the hell do we need a PCI replacement for that has zero potential for handling enormous video bandwidth as well as or better than AGP?

What in hell do we need a PCI replacement for that doesn't even utilize the PCI-X or 64-bit, 66MHz PCI already being pushed for servers? Not to mention that fact that any device that can push the bandwidth of PCI is already available in one of the above formats, who wants to build yet another model for PCI Express?

Honestly, if you need to find emerging technologies, just look to the server path. Intel has always been about trickle-down, this move doesn't make any sense.

Re:How could PCI Express possibly be a benefit?

[Wesley Felter]

PCI Express x1 is 250MB/s, but it also comes in x4, x8, and x16 speeds. Intel is planning to use PCI Express x16 for graphics cards; you do the math. Also, each slot has dedicated bandwidth.

Re:How could PCI Express possibly be a benefit?

[illumin8]

I think you misinterpreted the numbers. PCI-X is a point-to-point, rather than bus technology. A connection is 1 to 32 bits wide @ 2Gbps per bit.

So if you're using a measly 2 bit connection sure you might only get 250 MB a second, but if you read the article you'll see that Intel is planning on using a 16-bit wide connection for the graphics card. This would give you 32Gbps, or roughly the same as AGP 8X. There is potential to go much faster by using a 32-bit PCI-X connection. In comparison, the other PCI-X slots on the motherboard for peripherals will be much slower, probably only using 2 bits.

I fully expect server boards to have multiple 32-bit PCI-X slots for maximum I/O throughput. In addition, we will probably see new technologies for clustering that utilize a PCI-X expansion card as a high speed server-to-server bus.

Re:How could PCI Express possibly be a benefit?

[Wesley Felter]

PCI-X is not the same thing as PCI Express, BTW. (I sense major confusion in the future.)

Bye Bye Floppys

[DavidBrown]

Dell is supposed to be dropping floppys as standard issue soon.

Big whoop...

[bkrrrrr]

Who needs a new board - my HP Vectra XU/200 is still running strong! Oh wait...winders users have to buy a new computer every two years to keep up with M$ bloatware. BWWAAAHHAHAHAHHAHAHHAHHAHAH!!!!

First improvement in 6 years

[heroine]

It's amazing that CPU's haven't increased performance on a clock for clock basis since 1997. Imagine if modern CPU's really ran 3000 times faster than a 6502.

Re:First improvement in 6 years

[Anonymous Coward]

Imagine if modern CPU's really ran 3000 times faster than a 6502.

It would ruin the prestige of my almost-completed three-thousand-node 6502 superbeowulfcomputer! I had to buy a lot of VIC20s and Apple II+s to build this thing, and it's going to piss me off if you can start getting the same thing in a single chip from Intel.

I like this

[Anonymous Coward]

I like how all these great advances in hardware parallel the Longhorn rollout. Face it you religious lunatics, the brightest minds run this industry.

"We have to continue to obsolete..." - William Gates (Taken from the Road Adhead).

Read Gates' books, he is a genius. Did anyone else notice that as soon as he went back to software development and software project management the Windows suddenly became better?

Don't follow the Linux Jihad! Believe in progress and innovation instead.

Over-Invented

[zafod]

Does anyone here remember what the phrase "Over-Invented" looks like?

90% of PC users aren't _ever_ going to use the power of these new architectures. Heavy-duty gamers, yes. Scientists, yes. CG creators, yes. But for the most part, it looks like the PC is going the way of the Web; over-invention. And most of it's probably just to keep a generation over over-paid lardbottom Dilberts and Marketing boneheads employed at Intel and AMD, as they've pushed the physical chip technology about as fast as it can go.

Hey, I think a 3.06 Ghz CPU is SO much better than a 2.0, don't you?

Now, if they could all just step back a bit and concentrate on another word: STANDARDS....

There is a standard

[Anonymous Coward]

There is a standard. It's called Microsoft. It's called Internet Explorer. Don't expect everyone to be open and free, especially in a capitalist society. If you don't like it, crash the bank system and take up arms, and fight in the name of GNU.

I wonder about Palladium

[Chewster]

Sorry to bring this up, but there was no mention of the Palladium stuff. I understood Microsoft was pushing AMD and Intel to build their DRM stuff into their next-gen chipsets. There was no mention of it (that I saw, anyway).

I'm just wondering if this DRM stuff will magically appear in some future chipset and the response from the manufacturer will be: "What?? We didn't tell you that was in there?? Our bad."

I want to know the first chipsets it'll be in, so I can buy from the last of the old stuff...

And VB.Net will make this perform like ...

[tjstork]

You need all this big horsepower because of all the stupid VB.Net programmers that think code optimization is clever use of m_ and indenting for code they cut and paste.

ISA isn't dead

[sjames]

ISA isn't dead, it's just in hiding. The thing is, many devices such as serial ports just don't need (and can't really use) a PCI bus. That includes the builtin serial ports on most motherboards.

So, plain old ISA was revamped into LPC (Low Pin Count) which takes good old ISA and wraps it inside a simple hardware driven serializing protocol.

In a modern chipset, the southbridge supports a LPC interface. In turn, the BIOS flash chip and superio (combined serial, parallel, floppy, GPIO, occasionally sensors, etc, etc chip) are connected by LPC. The CMOS and clock may be in the southbridge or in the superio depending on the chipset. Sometimes both have those one or the other is disabled either by a strap or in BIOS. Boards that want to have an ISA slot can also include a bridge that translates between LPC and real ISA.

The same sort of thing happens at all levels these days. Some chipsets do the same sort of thing to PCI as well. The PCI slots connect to a PCI bridge that wraps it up in a serialized protocol to communicate to the northbridge.

It appears that AMD is going that one better and wrapping memory and FSB up in hypertransport.

In all of these cases, the primary benefit is reduced package pin count, and less traces to route through a shrinking motherboard.

Re:Forced Obsolescence?

[DancingSword]

Ah, but there are 2 kinds of performance, see:

Magic Bullet performance, and

No Weak Points performance.

In Magic Bullet performance, you do one thing, really really well, and ignore any potential problems ( single CPU motherboards are in this category ), but ...

... in No Weak Points performance, you instead make sure that no matter what .. the system continues responding, functioning, reducing whatever obstacle/work/opposition it's there to deal-with.

Single Ultrafast CPU, is so very fast that rarely does some wonky process saturate the CPU, .. BUT .. if one does, you're experiencing a DoS from your-own system, because there isn't another CPU ( not saturated ) that is/would-be paying any attention to you...

The believing-mode ( think-of-the-money, or just-believe-in-this, or ignore-what-alternatives-may-be, or propaganda, etc. ) is a human rendition of Magic Bullet Mode...

Ah, but there is also No Weak Points mode, eh?

in No Weak Points mode, there are 2(+) CPUs, sharing the work, so that some process would have to saturate both of 'em ( drastically less likely ), simultaneously, to DoS the system.

In other words, it's much more likely to be responsive .. every second it's running, though it mayn't be as quick at finishing something as the single-CPU version would, when it wasn't experiencing saturation... ( partly due to slower chips, partly due to non-shareable tasks or non-threaded processes ).

The Japanese developments called 'Go' ( the game ), and 'Ninpo' ( formerly nin-jutsu ), and the ( unknown nationality ) programming environment/language Pliant all embody the No Weak Points mode of surviving ongoingly ( whereas, our planet's fossil-record is littered with the remnants of races who, magic-bullet-style, evolved-themselves 'off a cliff', as it were, due to specialization or dependency ).

Magic Bullet mode is good for when things are peachy, and the system ( one's-self, being a possible 'system' ) is 'in its element', but...

No Weak Points mode is better at ensuring enduring survival.

Continuity plans, that include having backups, and having alternate sites, and cross-training, and developing understanding of 'what's going on' ( outside one's specialty ) and not putting all one's family/execs in one plane, etc. are showing No Weak Points mode...

Consider the meaning-of ( and justification-for ) 'diversification', and see if it doesn't contrast directly with 'consolidation'...

( and remember! civilized minds cannot hold balance between two concepts, for even a second, so ... where was I? )

As for nothing needing so strong a CPU, though, .. I gather all RSYNC servers need very strong CPU because the RSYNC system doesn't cache the individual-block checksums, so the machine has to calculate 'em all every time the given file is requested...
... and compression, movie-viewing, etc. are all requiring strong CPU, too

Looks like something to delay the 64 bit processor

[Anonymous Coward]

Looks like they want to stall on the 64 bit processors for another 2 years with this.

Last Post!

[alpg]

Anyone who has attended a USENIX conference in a fancy hotel can tell you
that a sentence like "You're one of those computer people, aren't you?"
is roughly equivalent to "Look, another amazingly mobile form of slime
mold!" in the mouth of a hotel cocktail waitress.
-- Elizabeth Zwicky

- this post brought to you by the Automated Last Post Generator...