Intel Demos Core 2 Extreme QX9650 Quad-Core At IDF

MojoKid writes "Intel demonstrated a dual socket gaming rig at IDF this week, based on their Skulltrail platform with the X38 chipset. The interesting thing about this machine wasn't just that it had 45nm quad-core CPUs in its sockets, as well as PCI Express 2.0 capable slots, but also that it was running a pair of NVIDIA graphics cards in SLI. That's right, SLI on an Intel chipset. No word whether or not X38 would officially be supported with SLI just yet. In fact, NVIDIA representatives noted Intel was buying NVIDIA nForce 100 SLI Southbridges just for this one Intel motherboard model."

Comments

but how to pay for it?

[Anonymous Coward]

guess it's time to sell another child so that i can play the next gen games!!

Re:but how to pay for it?

[bbcisdabomb]

That's the most naive thing I have ever heard. Everyone knows that to play next gen games, you'll have to sell three to four children! They're only going for about $150,000 each these days!

SSE4 is overrated

[Silverlancer]

The SSE4 ESA SAD instruction (for an exhaustive SAD motion search) has been touted constantly as the "new big thing" with DivX benchmarks showing 100% speed improvements, etc, etc. This is generally bullshit. The DivX encoder was specifically modified so as to use the exhaustive motion search in its normal encoding, basically contriving the test to work faster with SSE4. Talk to anyone working on an encoder and they'll tell you the same--not only is an exhaustive motion search generally useful, but there are equivalent algorithms, such as successive elimination (SEA) that are actually faster implemented in software than SSE4 is implemented in hardware with mathematically equivalent results. The main developer of x264, for example, has stated that SSE4 offers basically no useful instructions whatsoever.

The chip as a whole, on the other hand, is quite awesome, but I think its important to correct this bit of common misinformation.

Re:SSE4 is overrated

[Silverlancer]

Slight correction, "not only is an exhaustive motion search generally useful" > "not only is an exhaustive motion search not generally useful".

Re:SSE4 is overrated

[Gabest]

This is MADD-ness!

Re:SSE4 is overrated

[Ant P.]

The main developer of x264, for example, has stated that SSE4 offers basically no useful instructions whatsoever. Yeah, but it's not there just for video codecs. Maybe someone'll find a use for it to speed up crypto.

Re:SSE4 is overrated

[Briareos]

This is MADD-ness!

But this ain't even Sparta!!1!2!eleven

np: Kid606 - Pregnant Cheerleader Theme Song (Who Still Kill Sound?)

Re:SSE4 is overrated

[Silverlancer]

SSE4 as a whole, perhaps. The particular instruction that has received so much press that I commented on, definitely not (it is ridiculously specific in its application).

Re:SSE4 is overrated

[samkass]

I assume you're complaining about Intel documents such as this one that show a 1.6x to 3.8x speedup for certain HDTV encoding operations. There are still some likely reasons someone might pick SAD for encoding. One reason might be patent coverage-- the better the algorithm, the more likely it is to be patented these days. Providing a baseline fast algorithm that's part of all future Intel hardware and can be used without patent problems might be nice. Also, just because something can be done "faster in software" doesn't mean it's really faster. If it doesn't use the SIMD pipeline, it's occupying more of the int or fp pipelines and thus may have fewer potential parallelism opportunities and/or stall the pipeline more often. With SAD offloaded onto the SIMD pipeline one could do other things with the other pipelines-- perhaps even a combination of both algorithms running in parallel (assuming sufficient instruction dispatch speed) to get even more speedup.

I think there's a lot of as-yet unrealized potential here, and it will be interesting to see where it leads. It won't be the end-all be-all of encoding, but it will be another arrow in the quiver.

Re:SSE4 is overrated

[Silverlancer]

I'm not talking about the block-matching metric; SAD is perfectly fine and already has an SIMD instruction for it, PSADBW. What's pointless is the exhaustive SAD search in SSE4, which is worse than already-existing and relatively simple free algorithms that allow the lossless elimination of unnecessary block candidates before doing the actual SAD search.

Super duper deca-core X8789FDS extreme

[Daimanta]

Seriously, what is it with these names?

Re:Super duper deca-core X8789FDS extreme

[Chandon Seldon]

How else would you name these things so as to communicate A.) what type of chip is it (entry level, mainstream, or high end) and B.) the model number of the chip and C.) the basic technical information that people want (i.e. "quad core")?

Re:Super duper deca-core X8789FDS extreme

[iminplaya]

It's generally easier to market something if it has a moniker to provide a convenient way to refer to whatever it is you're selling. Naming things can be a very lucrative business. It doesn't what the thing does, if has a catchy name, it will sell. And what's with all those little fans on the side of the case? One big, slow turning, much quieter one would fit nicely.

Re:Super duper deca-core X8789FDS extreme

[Foerstner]

Oh, for the sensible names of my youth, like 80486DX-2.

Re:Super duper deca-core X8789FDS extreme

[Anonymous Coward]

It's not really that complicated. "Core 2" is the architecture. "Extreme" is mostly marketing, but it's usually indicative of some "above and beyond" features ... higher clocks, unlocked multiplier, possibly a larger L2. "Q" means quad-core, "X" means extreme, and 9650 is just a number for comparison between other models in that line (i.e. a 9650 is better than a 9550, if there were such a thing).

It all sprang from the end of the GHz wars ... when they realized they couldn't ramp clock speeds (and make it the primary selling point) forever, and that new architectures would have higher performance but at lower clock speeds.

Re:Super duper deca-core X8789FDS extreme

[confused one]

80486DX2? Youth? Wow, I must be getting old. Z80, 6502, 6809... These are are the uP's of my youth.

Re:Super duper deca-core X8789FDS extreme

[WhatAmIDoingHere]

Because it makes it easier to tell a high end 2.8ghz processor from a "budget" 2.8ghz processor?

Re:Super duper deca-core X8789FDS extreme

[plover]

Punk. I see your Z80 and raise you a 4004.

I was a youth BEFORE the invention of the microprocessor. I did my growing up years on a CDC Cyber 72 mainframe, but we were all pretty excited when the 4004 came out. The 4004 was actually the first microprocessor I ever owned: in a Mattel Electronics Football game. Before that, I had an ENIAC -- which was just six really smart switches I could wire to do all sorts of cool tasks. And when I was really little, I had a Dr. Nym, which was a marble-and-gravity cascading flip-flop game.

Now get off my lawn, you damn kids!

Re:Super duper deca-core X8789FDS extreme

[anethema]

How the hell do you know it is 2.8 ghz without looking it up ?

I really like ye olde days where the speed is in the model number. Or the intel equiv. speed as the case may be.

Re:Super duper deca-core X8789FDS extreme

[Fred_A]

How the hell do you know it is 2.8 ghz without looking it up ? That's why it says "89" in the name, so you'll know it's 2.8GHz. What's the point of making up those helpful names if you don't bother reading them ?
(duh)

Re:Super duper deca-core X8789FDS extreme

[plover]

What, are you still here?

Oops, sorry, it was a GENIAC, not an ENIAC.

They say when you get old, the mind is the second thing to go.

Re:Super duper deca-core X8789FDS extreme

[confused one]

Phew, I feel better now. I'm not THAT old :P The oldest machines I ever worked with were DEC PDP-10/11 or an IBM System 370 at university. Never saw a 4004 irl.

Re:Super duper deca-core X8789FDS extreme

[plover]

I'm not all that old either (45). I just got an early start, learning BASIC on a state-run Honeywell 6000 at age 11.

Re:Super duper deca-core X8789FDS extreme

[Emetophobe]

I actually think Intel's recent chip naming convention is pretty good. It's not great, but it's pretty easy to figure out. Basically, each chip is given a letter (or two in this case) to tell us what type of chip it is. Each chip is also given a number to let us know how fast it is relative to clock speed (the higher the number, the higher the clock speed).

AFAIK, there are 3 letters that Intel uses to label their desktop chips. E means dual core, Q means quad core and X means extreme. The difference with the "X" or extreme chips is that they have an unlocked multiplier, which makes it much easier for people to overclock them.

So, just by looking at the letter(s) of the model number, right away I can tell that the QX9650 is a quad core "extreme" chip. It's also probably clocked fairly high judging by the number. Also, I can tell by the xx50 that this chip supports a 1333mhz FSB. Older chips end in xx00 and use a 1066mhz FSB while chips that support a 1333mhz FSB end in xx50.

So to summarize, if you know what to look for, you can gather a lot of information just by looking at "QX9650". You can tell if it's a dual or quad core, you can tell if the multiplier is unlocked, you can tell if it supports a 1066mhz or 1333mhz FSB and you can get an idea of how high the cpu is clocked.

For detailed information on each Intel Core 2 processor, check out the wikipedia page.

Re:Super duper deca-core X8789FDS extreme

[Emetophobe]

Don't forget D) FSB frequency.

A model that ends in xx00 supports a 1066mhz FSB while a model that ends in xx50 supports a 1333mhz FSB.

This isn't always true, older chips all ended in xx00 and some used an 800mhz FSB and some used a 1066mhz FSB. Also, I believe there are a couple of chips that end in xx20 and xx40 to confuse things a little further. I'm pretty sure all newer chips that support a 1333mhz FSB end in "50" though instead of "00".

Re:Super duper deca-core X8789FDS extreme

[anethema]

Was that funny or am i just stupid. How does 89 mean 2.8 ?

Re:Super duper deca-core X8789FDS extreme

[Amouth]

yet.. sadly i was jsut looking up the jumper settings to set the fsb to 133 on this 1u box cause they where lazy and didn't print them on the board....

some people really don't need nor care about he latest and greatest.. what we have is fast enough for what we need...

i want optimization - not a space heater

Re:Super duper deca-core X8789FDS extreme

[Wicko]

Q = Quad core
X = Xtreme Edition (unlocked multiplier)
9650, I don't know.. But I wonder if thats a typo, as the latest quad core is a 6850, so maybe this is the 6950? I could be wrong.

I can see your point though. I mean they had the 2000 series, the 4000 series, and the 6000 series. What happened to 1000, 3000 and 5000?

Fans

[SpeedyDX]

I've got a rig at home with four case fans. How many does THAT monster have? Six visible on the side + bottom, up to two more infront of the hard drives, and up to two more right at the back. On top of that, you have up to two on the power supply and the two CPU fans AND the two on the video cards. That's SIXTEEN FANS in one rig!! Jesus, the fans on that thing probably have more combined horsepower than a souped up Civic! And it probably SOUNDS like one too!

Re:Fans

[binarybum]

seiouswee, the "V8" on the side of that thing represents a new metric for the internal combustion engine type it would take to generate the power needed to boot-up.

Re:Fans

[ExploHD]

Jesus, the fans on that thing probably have more combined horsepower than a souped up Civic! And it probably SOUNDS like one too!

I have just one word for you: Thundercougarfalconbird

Re:Fans

[ceoyoyo]

Only if you get the optional large diameter exhaust pipes. They add a couple of horsepower you know. Not quite as much as the Type R stickers, but close.

Re:Fans

[Anonymous Coward]

Large diameter exhaust pipes do add horsepower. A lot, in fact. Engine exhaust doesn't get magically sucked out of the motor. It has to be pumped out by the pistons. Larger pipe diameters mean less resistance to being pumped out.

Re:Fans

[Sczi]

Unless it's so fat that the exhaust velocity drops low, backs up gas in the pipe, and actually *creates* backpressure. You could also have so much cam overlap that you need some backpressure to make the air/fuel stay in the cylinder while waiting for the exhaust valve to close. Everything in moderation, friend, especially stickers, wings, and fart cans.

Re:Fans

[DigiShaman]

Larger is not always better. All engines have a sweet spot in regards to excaust flow. Too small of a pipe diameter, and you run into restriction. To large, and you're not tapping into the scavenge effect.

Due to some active-x plugin, I will cut-and-past from the miata.net page.

OK, so here is Backpressure 101.

The purpose of the car's exhaust system is to evacuate gases from the combustion chamber quickly and efficiently. The exhaust gasses do not flow in a smooth stream. Because the gasses are vented at each opening of the exhaust valves there is a pulse of gasses from each cylinder. Just put you hand near the exhaust tip and you will feel the pulses. In a MX-5 engine there are four pulses per cycle (except if it's John Pitt's supercharged V8 then there are eight really big pulses per cycle).

The exhaust gasses produce a positive flow in the exhaust pipe. Backpressure can be likened to resistance to the positive flow of the exhaust stream. Taken to its extreme backpressure can lead to a reversal (albeit momentarily) of the exhaust stream.

Is Bigger Better or is Faster Best?

When contemplating a modified exhaust system there are those who want the biggest diameter pipe that can be had. Their idea must be that fatter pipes are more effective at venting than narrower pipes. This sounds reasonable but it is not quite correct. Sure wider pipes have greater volume and higher flow capacity, but that is just half of the story. Capacity is one consideration but gas velocity is the other factor.

An experienced exhaust designer knows that the best exhaust is one that balances flow capacity with velocity. A given volume/time of gasses will travel faster through a 2" pipe than the same volume of gas passing through a 3" pipe. So when taken to its extremes we can see that a too narrow pipe will create backpressure (restrictions to positive flow) problems and a too wide pipe will cause a very slow flow with no backpressure.

The optimum is where the fastest velocity is achieved with the least constriction possible.

This situation will arise when the pipe is wide enough so that there is the least level of positive backpressure possible whilst achieving the highest exhaust gas velocity.

The faster the exhaust gas pulse moves, the better it can scavenge out all of the spent gasses during valve overlap. The scavenge effect can be visualised by imagining the high-pressure pulse with a trailing low-pressure area behind. The faster the high-pressure pulse moves the stronger the draw on the low-pressure gasses and the gasses behind that. The scavenge action is like (but not exactly) suction on the gasses behind.

The greater the clearance burned fuel from the combustion chamber the less diluted the incoming air/fuel mix is. Scavenging can also aid intake on overlapping valves (where the exhaust and inlet valves are open at the same time) by drawing in the intake. These are good things to happen.

So instead of going for the widest pipe possible we should be looking for the combination of the narrowest pipe that produces the least backpressure possible. In this scenario we achieve the least restriction on positive flow and the highest gas travel speed.

Exhaust pipe diameters are best suited to a particular RPM range. If we used a constant RPM engine this would be easy to specify. But a variable RPM engine will mean that not one size suits all. It is possible to vary the size of exhaust volumes according to rpm but it is very expensive (Ferrari has done it). The optimum gas flows (volume and speed) are required at the RPM range that you want your power band to be located. For a given engine configuration a small pipe diameter will produce higher exhaust velocities at a low RPM (good) but create unacceptably high amounts (bad) of backpressure at high rpm. If you had a car with a low RPM power band (2,000-3,000 RPM) you would want a narrower pipe than if your power band is located at 5,000-7,000 RPM.

Re:Fans

[SueAnnSueAnn]

That configuration thermally speaking is a peace of garbage.
There will be so much turbulence in that case it cannot cool properly.
Furthermore one of the cpu fans blows hot air into the other cpu. Smart guys does it take a girl to show Y'all how to cool a computer without doing the Tim The Tool Taylor lameness.
I am surprised the case isn't ether diamond plate or stainless steel.

One think that Intel would do something a little more modern like peltier assisted liquid cooling for the processors and and one large low RPM fan to replace those four imported peaces of junk.

besides real hardware geeks use 115 VAC fans with trac base controllers that monitor the case air temp and regulate the fan speed from that.

Oh well i guess the engineers at Intel can't build it unless they can bolt it on.

See Ya

Sue

Re:Fans

[Anonymous Coward]

The primary requirement of a riceboy car is a fully sick subwoofer badly mounted in an MDF boxso that when they play their doof-doof music you get a dsszt-dsszt effect instead of a clear bass pulse.

Re:Fans

[petsounds]

Although rice rockets are the modern equivalent, this kind of looks-over-performance started back in the '50s during the custom car craze. The Beach Boys wrote a song about it called "No-Go Showboat":

"Well the engine compartment's filled with all chrome goodies
In my no-go showboat (no-go showboat)
Yeah but everybody takes me even old Ford woodies
In my no-go showboat (no-go showboat)
When it comes to speed, man, I'm just outa luck
I'm even shut down by the ice cream truck
'Cause it's a no-go showboat (no-go showboat)"

Of course, at least back then the posers cared enough to use nice-looking parts. Rice rockets these days just use whatever $2 part looks like it might fit.

Re:Fans

[Anonymous Coward]

well if you say it like that. It sounds to me more like a heating rather than a PC. I have the same at home, well not with Core cpu, it doesn't heat that well, I've got this P4 cpu, the best heating machine on the world!!! :)

Re:Fans

[Fred_A]

Large diameter exhaust pipes do add horsepower. A lot, in fact. Engine exhaust doesn't get magically sucked out of the motor. It has to be pumped out by the pistons. Larger pipe diameters mean less resistance to being pumped out. This is silly, just add exhaust fans to regular exhaust pipes. Some geek you are...

Re:Fans

[bcmm]

I use Gentoo, you insensative clod!

Re:Fans

[bcmm]

Actually, diamond is one of the most thermally conductive materials known and would make a great case, thermally...

Seriously though, I'm with you on the low RPM/large diameter thing. I put one of those in my desktop when I couldn't stand the noise from the stock cooler anymore, and it can keep the CPU below 50C at max load, almost silently. Blows air out and over the GPU and chipset heatsinks too. Pretty good for a cheap cooler, except that it's actually slightly over the weight specification for a 775 cooler.

Re:Fans

[Sparky McGruff]

She said "DiamondPLATE", not diamond. As in the chrome steel with herringbone ridges that's used on trucks. I disagree, however. You can't just do diamondplate--that's too common. It also needs the "Back Off" mudflaps with the picture of Yosemite Sam.

FBDIMMs are a joke for a gameing system + weak SLI

[Joe The Dragon]

The only thing this has over there old v8 is more pci-e lanes also the SLI is only pci-e 1.1 The NVIDIA nForce 100 MCP converts a single x16 PCI Express Gen 1 bus into dual x16 PCI Express Gen 1 buses. This is how SLI is being supported on Skulltrail.

A AMD 4x4 dual quad-core with DDR2 ram and dual x16 pci 2.0 and all slots with pci 2.0 and SLI, also there will also be a ATI chipset for the same system with all pci 2.0 16x-16x or 8x-8x-8x-8x CrossFire + Discrete PCI-E x4 slot. With Support for HTX slots.

all this and the kitchen sink too...

[downix]

What are the chances a real machine will ever ship with these features? I highly doubt. They pulled every stop for a demonstration, and now the beancounters will start knocking features off to try and save a buck. End result, customers will likely never see such a rig in mass production, which is a shame, for it would make me seriously consider Intel again.

Re:all this and the kitchen sink too...

[Anonymous Coward]

Do vendors ever sell the super high end gaming systems?

No, they generally don't. My guess is that Dell, HP and the others will never sell a system like this, but the super gaming dorks who think they need this crap will order all the parts and build their systems themselves. Just like they've always done.

Re:all this and the kitchen sink too...

[lordSaurontheGreat]

It's stunts like this that make me even more convinced that Intel is a slowly sinking ship.

This platform, as stated, will not be available with a feature set like this for about five to ten years, unless you're going to actually pay a price in the neighborhood of $5000. Comparatively, I have a AMD rig I build myself that right now can get about 3/4 the power of that rig which I built for $750. I still can't find anything (save Ageia PhysX software) that'll put a strain on the system (well... SuSE 10.2 and stupid YaST is another exception, but I've never seen rug go fast, ever.)

For interesting tech, ya, Intel is king. But this kind of stuff should be done at universitys. AMD is still king of the Performance Per Dollar, which is where I spend. Friends can build a machine 20% faster than mine. I don't care. They paid $2000-$3000 more. They buy a machine every 5 years. I build one every year. I'm always on the low end of the (sometimes literally) bleeding edge. They're not.

That's the AMD difference to me.

Kudos to Intel, but I'd love to see that put into a system I could afford. Until they can master performance AND price, they're just a three-ring circus, not a product fit for the big boys to play with.

Re:all this and the kitchen sink too...

[Sczi]

They're just pimping a Viper while hoping to sell more Neons.. ssdd.. Price:performance is still competitive, but Intel owns the high end at the moment.

It's funny what you say about the 20% faster, though. In high end tech terms, that 20% is full scale mind blowing dominance. 100fps versus 120fps, heh.. what, that's not worth an extra couple grand to you?

I bet this pc's refrigerator cost more than my whole computer.

Re:all this and the kitchen sink too...

[Trinn]

I wish this was still true in the mobile arena, but Intel is starting to dominate there, more power per watt, and less watts overall, not to mention more per dollar as well (though until it gets outrageous, most mobile users prefer better power-per-watt)

Re:all this and the kitchen sink too...

[downix]

You have a full PCB shop with SMD toolchain?

Remember, the motherboard is custom-built.

Re:all this and the kitchen sink too...

[LWATCDR]

Oh I think they will sell a few of these. They will cost as much as a used car but then gamers will buy anything :)
I wonder if there is a sub-class of audiophile gamers? I could sell them granite cases lined with gold leaf to go along with their balanced power cords and CD
demagnetizers.

Actually there are probably a few workstation users that could actually use one of these. They would just have to put them into cases with out flames or skulls.

Time Again

[Nom du Keyboard]

Time again to throw out last month's hardware and get the new, all the same things as before, but now with Tint Control model.

Re:Time Again

[kalirion]

I'm still sticking with my P3-800, waiting for prices to drop.

Re:Time Again

[Nimey]

Don't bother. If you want to buy a computer, just do it, because there's *always* something newer and better coming.

IMO the best metric for when to replace a computer: if it won't do what you want any longer. That covers both being dead (lightning damage) and being too slow to run the latest game that you really want.

Unless you upgrade regularly, you probably shouldn't bother with considering upgradability of your parts, possibly save the case, power supply, and disk drives. Every few years new processor sockets, new card connectors, new RAM, and sometimes new power-supply standards become common and (like your PIII) you can't upgrade your old kit without throwing out almost everything. I replaced an Athlon XP system in April and was only able to keep the case and p/s from the old parts, and the latter needed a 20-to-24-pin adapter; AGP's obsolete, so's DDR RAM, so's Socket-A, so's PATA. I suppose I could have kept my PATA CD-ROM drive, but it was well-past time to upgrade to a DVD burner.

I don't care what was at IDF

[Anonymous Coward]

And I piss on DivX. Gimme 51 weeks and I'll pick that board up at the ARC for $7.50.

Go Gamers! Go! Daddy needs a new machine.

Re:I don't care what was at IDF

[Nimey]

Better save that $7.50 so you can buy yourself a girlfriend. For an hour.

Re:I don't care what was at IDF

[SmokeyTheBalrog]

Better save that $7.50 so you can buy yourself a girlfriend. For an hour.

All the one's that go for $7.50 for an hour where released 51 years ago.

Yeah, but does it have a coffee-can exhaust?

[Anonymous Coward]

And a spoiler that belongs on a 747?

It can't be a rice rocket without those accessories!

That's not surprising

[Sycraft-fu]

I'm sure ATi is not high on Intel's list of people to be nice to now that AMD owns them. Whatever reason they had for choosing crossfire in the first place has now been reassessed I'm sure. Intel isn't going to do anything stupid like prevent ATi card from running on their boards, but neither are they likely to go out of their way to support anything ATi specific anymore.

Re:That's not surprising

[dwater]

...and I guess the same goes for the nVidia/AMD relationship, except more so, probably.

Re:That's not surprising

[Sczi]

As an amd+nvidia fan, I have been quietly hoping all involved will take the high road. I can see AMD putting more resources to back ati, but I hope amd doesn't actively spurn nvidia. It's funny, but I'm actually a bit afraid to read up on it just in case they are fighting. I guess I'm not above a tinge of fanboyism occasionally.

Re:That's not surprising

[dwater]

I guess I have a similar frame of mind, my last few computers having been nforce and amd cpus (don't care about graphics, since they're servers).

I have just had cause to upgrade my motherboard (MSI K8N-something), and have noticed that nvidia have dropped the ball somewhat, in that there was no upgrade path for me - only a complete replacement of m/b (it was broken), cpu (nothing takes 768pin any more), memory (new cpu, new memory) *and* graphics card (no AGP). Furthermore, nothing budget seems to have 2 IDE + 4 SATA ports any more, only the very high end ones have 6 SATA ports on board requiring some (admittedly cheap) SATA-IDE converter boards on the drives. There were some m/bs specifically for servers, but they cost a premium or weren't available...there's an availability issue in my location (everything seems to be about 6 months behind the US in China, despite almost everything being made here).

I have an MD RAID5 array with 8 drives total, made up of 4 SATA (attached to m/b) and 4 IDE drives (attached to a PCI IDE fakeRAID card). It would have been nice to put the drives all on a card, but they're all some PCI-X thing, and everything seems to be PCIe on the m/b :(

I guess it has lasted too long, though it doesn't seem like it. It's about 3 years old.

Re:That's not surprising

[Fweeky]

Anyone could have told you S754 was a dead-end upgrade path in 2003 when it was launched; it's a low end/mobile socket with no dual channel memory, and as I recall it was known or at least reliably postulated even then that dual core was going to be for the higher end sockets only. I paid the extra for S939 and my system's still pretty decent. It's not nVidia's fault you're still on AGP (low end PCIe cards aren't expensive, and for a server you can probably get away with a freebie PCI card) or that everything's moved to DDR2 (blame AMD and the market in general phasing out DDR).

The dearth of PCI-E IO cards is a bit annoying, though, as is the almost complete lack of higher end PCI sockets on even quite expensive boards; hardly anyone's even supporting 66MHz PCI. I expect we'll see better mid to low end PCIe support as time goes on though.

Re:That's not surprising

[darkwhite]

Or maybe crossfire is just harder to implement.

IIRC crossfire hardware requirements are a superset of those of SLI, namely they require bus support for peer writes.

Re:That's not surprising

[dwater]

Well, yes, I guess it's not (all) nVidia's fault. It did seem to just snow-ball though. At first it was just the motherboard and power supply. That meant that the CPU had to change - no 939, so the memory had to change too, and the graphics card (even if you use a PCI one) since it was AGP, then only the expensive boards had enough IDE/SATA ports.

It just ended up that I need pretty much everything replaced. The only things that don't need replacing are the disk drives (6 IDE and 4 SATA) and the PCI IDE board. So much for building your own PC so that you can only upgrade bits of it at a time...I guess that's just one of the (possible) reasons for building your own though.

It's especially not nVidia's fault since they do actually produce chipsets with the necessary guts to give me what I want. It's really the other guys (MSI/etc) who have chosen not to make them, or the shops here who have chosen not to stock them.

The Age of Crappy Concurrency

[MOBE2001]

If your multicore CPU or concurrent programming language or operating system does not support fine-grain, instruction-level parallelism in a MIMD (multiple instruction, multiple data) environment, it is crap. Sorry.

The Age of Crappy Concurrency

when i was a kid...

[kesuki]

we thought 640k was enough to run games in and 16 colors was good enough for anyone! now we have to have 2-4 graphic cards, and 8 processing cores??? and probabbly 8 gigs of ram!!! dosent anyone think of how many watts these gaming rigs use anymore? i mean wow... pulling 49 amps over the 12 v rail... you might as well sell them with a dc generator and solid copper power rails.

seriously add in liquid cooling and cold cathodes and a 52" HDTV and youre talking over 3 killowatts of power draw... Im glad i play blizzard games, not only to people play them for a decade after theyre made, the initial launches try to have a configuration setting that will lower the bar and let less impressive systems play too.

sure their engines might not be so impressive that youd need quad 100 pixel pipeline cards... that themselves have 2 GB of ram on them.. or a system with 4x processors with 8 gb or ram... but i think the gaming industry has gone too far ever since they realized there was a market for $600 gaming cards..

Re:when i was a kid...

[Kjella]

Well, unless they pull off anything fast either in displays or dazzling new effects that eat framerate for lunch, graphics cards are seriously starting to outpace what to display them on. If you're blowing it up on your HDTV or projector, none of those are going over 1080p and probably won't either, since that's all HDDVD/Blu-Ray/HDTV broadcasts offer. The only 1080p+ displays are a few computer displays, which you must admit limit the market to a very select few enthusiasts.

So what of the graphics cards? Here's from the launch article for the 8800GTX on Anandtech that was 10 months ago:
"A single GeForce 8800 GTX is (...) breathtaking. Being able to run modern day games at 2560x1600 at the highest in-game detail settings completely changes the PC gaming experience."

Even Oblivion, which is a massive hog at high detail runs smoothly at 1920x1200 on a single 8800 GTS. Given time and improvements we'll see soon that performance move to mid-end cards soon, but I don't see the typical desktop getting HDTV+ resolution any time soon. Yes, you can put 2x8800GTX in a box bur you're doing it for the showoff factor. As far as I'm concerned the 8800s negated any need for SLI in the first place.

Re:when i was a kid...

[kesuki]

actually about this technology trickling down to the mid and low end im going to have to take point with... with ati releasing 2 pixel pipeline cards as the low end market things arent getting better on the low end.. and the mid range cards are still as expensive as they were 18 months ago. they have been really careful not to bump up the mid range very much, you still pay over $120 for a 12 pixel pipeline card, and those are using reject 16 pix pipe chips. card vendors really arent trying to go for economy of scale. but theyre trying to maximize their bottom lines.. and as long as they keep charging mucho dinero for any chip with more than 4 pixel pipes its just going to be more of the same in the mid range... not that long back i remember their being $40 graphic cards in best buy, but last time i was in their they sold nothing under $80.

by the time 100 pixel pipeline cards become affordable ill probabbly be an old man... at least the way the vendors are dragging their toes at lowering the cost of performance cards. before the latest generation of ati card the lowest number of pixel pipes they had in a card was 8, this generation they sell defect 4 pipe cards as 2 pipeline cards, and nvidia isnt any better at lowering the cost of decent graphic cards.

Re:when i was a kid...

[zerocool^]

i mean wow... pulling 49 amps over the 12 v rail... you might as well sell them with a dc generator and solid copper power rails.

seriously add in liquid cooling and cold cathodes and a 52" HDTV and youre talking over 3 killowatts of power draw...

Well, yeah, maybe, sort of. Since the AC power comes out of the wall at 120V (and someone jump in and correct me if I'm wrong), the 12v 49a is the downconversion of 4.9a and 120v. 4.9a pulling at the outlet is a lot for a computer, it's true, but I mean, most houses these days are wired with 15a circuits. A 15a circuit will be able to hold three of these 12v rails (so, probably 2 computers once you add in the 3v and I think there's a 5v rail on the atx power connector), or to put it in perspective, slightly less than two modern waffle irons.

4.9a is a lot of power for a computer. It's not a lot of power for any modern power tool or small kitchen appliance. The wow factor isn't that this computer uses that much power; it's that up until now, the rest of the computers haven't used this much power.

~wx

Re:when i was a kid...

[kesuki]

yeah the 3v and 5v rails are used in the latest atx specs... and they are on a 49a 12v rail usually in the 30-40 amp range, and those psus are not sufficient to run dual 4core cpus and dual gpus... there are psus with quad 12v rails at 20 amps a pop for those kinda setups... and theyre usually 600-800 watt psus although you do run acroos 1000-1200 watt psus meant for watercooling. dont ask me how may amps those bad boys provide, as theyre meant to run a watercooled pump that uses way more electricity than any fan cooling system would (and gets the system much cooler, if its got a sufficient radiator/tank which with the intel article kinda setup you would need to air cool an automobile radiator to keep the water from rising above room temp in the system) or use an ocean as your reserve tank...

ive seen normal watercooled servers using a 25 gallon fish tank as reservoir so with all those cores to cool plus the graphic cards, and some even water cool the PSU and ram as well... using the pc to heat a waterbed might make more sence than paying for the electricity to run a waterbed heater ;)

i can see someone now posting pics of their waterbed cooling reservoir.
only problem would be laying down on the water bed, but if you make the pipe into that tall enough gravity will keep the water in...

Re:when i was a kid...

[Kjella]

Well, they have to do *something* to make people buy new cards. Sure it was expensive. But unless my resolution goes up or framerate in new games goes way down, ir's a one-off investment. I've only had two graphics cards go bad on me and my parent's computers over the last 20 years put together, and one was just a noisy fan under warranty, so unless there's some incentive to buy a new card I think it could easily run for 10 years. I think neither nVidia nor ATI would be very profitable at that rate. Maybe it's the other way around, that a high-end video card is becoming a more stable investment so people find it "cheaper" when divided by expected lifetime and still buy. After all for quite many years graphics card were essentially perishable goods which dropped in value like a rotting fruit.

Re:when i was a kid...

[SueAnnSueAnn]

All of this new cool hardware is why GOD made CRT's in the first place She knew we would need fast responding analogue displays.

Sue

Re:when i was a kid...

[darkwhite]

you still pay over $120 for a 12 pixel pipeline card, and those are using reject 16 pix pipe chips. ... not that long back i remember their being $40 graphic cards in best buy, but last time i was in their they sold nothing under $80. by the time 100 pixel pipeline cards become affordable ill probabbly be an old man Huh? I just bought a card with 32 SPs for $100. ATI now sells midrange ($120) cards with 120 SPs. Both sell cards for under $40 (check online sometime) that kick three year old cards' ass. Check your facts.

The midrange market is not doing great in that you actually have to pay proportionally more to get a higher performing card (using the 8800 as the benchmark), but it's nowhere near as bad as you paint it.

About time.

[Anonymous Coward]

Intel, for some reason, chose to support only ATI for Scan Line Interleaving on their chipsets.

Then AMD bought ATI out. Bad news: the only graphics card that runs SLI on Intel chipsets is now owned by their competitor.

More than a year after the purchase annoucement, Intel has finally decided to rectify this on a prototype board?

Re:FBDIMMs are a joke for a gameing system + weak

[Jeff DeMaagd]

A AMD 4x4 dual quad-core with DDR2 ram and dual x16 pci 2.0 and all slots with pci 2.0 and SLI, also there will also be a ATI chipset for the same system with all pci 2.0 16x-16x or 8x-8x-8x-8x CrossFire + Discrete PCI-E x4 slot. With Support for HTX slots.

The funny thing is, as far as I can tell, you really aren't even saying anything. You can spew specs and acronyms all you want, but what is the actual tested performance compared to this Skulltrail rig?

NVIDIA is demonstrating tech for IDF?

[Eli Gottlieb]

HOLY FUCK! WE'RE ALL GOING TO DIE OF GRAPHICS CARDS! THE IDF IS COMING!

For Allah's sake, hide the children and get to the bomb shelters! The IDF is coming!!! RUUUUNNNN!!!!! /me dies of a graphics card with "Never again!" inscribed in the silicon falling from the sky.

Poster and commenter misconceptions...

[Glasswire]

Poster said: Intel demonstrated a dual socket gaming rig at IDF this week, based on their Skulltrail platform with the X38 chipset.
Skultrail is a dual socket chipset (probably a Greencreek follow-on) -which means it CAN'T be a X38 which is a single socket chipset.
What was seen at IDF was TWO systems - one dual socket and one single.
Also... for those who think these won't come to market... The X38 is a planned commercial chipset and what everyone has been calling a V8 is basically a dual quad core DP workstation platform which has been available since last November. The Penryn gen version is just a newer version of the same thing.
Eight Intel cores in one box is old news, what's new is the perf on the Penryn 45nm parts.

Re:Fans -- Compressors!

[Technician]

What's a little fan noise and power consumption for a few fans compared to a triple cascaded refrigerated rig like this overclock demo.

http://www.custompc.co.uk/news/601310/idf-556ghz-penryn-breaks-three-benchmark-records-in-two-minutes.html

That is 5.56 Ghz demonstrated at the IDF. It ran and broke 3 CPU speed records in under 2 minutes. This is extreme! Don't ask how much power the cascaded refrigeration system uses. ;-)

"Worth then proceeded to show off the fruit of his labours by claiming he could break three world benchmark records in just two minutes. This included SuperPi 1M, where he beat Team Japan's previous record, and he then went on to run AquaMark where his score of 273,000 trashed the previous record of 267,000. Finally, he then ran the 32-bit version of CineBench 10, where a score just shy of 20,000 (he didn't reveal the actual score, unfortunately) again clinched a world record for a quad-core CPU."

Re:FBDIMMs are a joke for a gameing system + weak

[Joe The Dragon]

Dual amd quad-core on the 4x4 are not out yet but The ram will cost less and have less lag then a FB-dimm system also there is less heat from the ram.

Re:FBDIMMs are a joke for a gameing system + weak

[dwater]

> The only thing this has over there old v8 is more pci-e lanes also the SLI is only pci-e 1.1

'there old v8'? Where? I don't see any 'old v8'.

Useful, or like chrome on the car?

[davmoo]

I'm not a gamer, so I have to ask...

Is the current state of game software such that it really can take advantage of things like 8 cores? Or is this marketing hype and chest-thumping, but little else?

Re:Useful, or like chrome on the car?

[Carbon016]

From my experiences, only games from about HL2 on support dual-core, quad-core being utilized either badly or not at all. When you talk about Photoshop, CAD, encoding video and so forth, the situation improves.

Re:Useful, or like chrome on the car?

[Anonymous Coward]

I remember seeing a tech demo of a game running on a Core 2 Quad system, with explanations of what each core was doing. But I think the next iteration of Valve's Source engine (shipping with HL2 Episode 2) is the closest thing to a threaded game engine that actually scales with an arbitrary number of cores. According to them, it'll immediately benefit framerates, physics, particle systems and AI complexity. It'll be interesting to see what kind of performance impact it really brings.

Re:Useful, or like chrome on the car?

[JambisJubilee]

We call it "go shine"

Re:Useful, or like chrome on the car?

[illumin8]

From my experiences, only games from about HL2 on support dual-core, quad-core being utilized either badly or not at all. When you talk about Photoshop, CAD, encoding video and so forth, the situation improves.

I think a lot of what is driving this dual-quad-octo-deca-core EXTREME!!!!111!11!one!11!1 madness is that PC gamers who don't know much about hardware hear about how many cores are in a PS3 or Xbox360 and think their PC must have more cores than that in order to be better than a console. They don't realize that console processors are highly specialized things, and not much like a general computing processor.

There is a pretty large high-end market where people will pay upwards of $4-5k for a gaming rig. The look on their face when they realize that 99% of the games on the market only take advantage of a single core? Priceless.

Re:Useful, or like chrome on the car?

[DocSavage64109]

There is a pretty large high-end market where people will pay upwards of $4-5k for a gaming rig. The look on their face when they realize that 99% of the games on the market only take advantage of a single core? Priceless. Instead of multiple cores making my game that much faster (and really, I think the video card is the biggest bottleneck) I am more interested in background tasks causing less drag on the game I'm playing. That is where multiple cores will come in handy. Though to be fair, I don't see much (if any) slowdown in my single-core overclocked amd3700 while gaming and downloading multiple torrents and having various apps like firefox sitting in the background.

Re:Useful, or like chrome on the car?

[Wicko]

I have heard about Crytek (making Crysis) and Valve (Half life series) trying to make better use of the cores, but most games do not. I personally opted for a dual core, while I could have afforded a quad. Mainly chose it over single core due to the fact that there aren't really any single core processors that can keep up the speed for a lower price. Spent about 185 CDN on my E6550. I like that I can run things in background (which I have always been able to do) but I can still alt-tab out of a game, and have no delay in windows whatsoever. Usually things would be sluggish but not anymore. It is also handy when a program craps out and uses 99% of the CPU, but with dual core it just uses 99% of one core. I can then easily go to Task Manager and kill it without the PC hanging. So, to answer your question, its chrome on the car.

Re:About time.

[SleepyHappyDoc]

Ten years ago called. They want their acronym back.

Does it have a Hemi?

[flyingfsck]

A V8 is nice, but without a Hemi, I'll have to pass on this rig...

English, mothafucka!

[Anonymous Coward]

Do you speak it?!

Re:FBDIMMs are a joke for a gameing system + weak

[Vegeta99]

Slashdot Man Law 0x3F: If someone with a lower UID than you asks you to prove yourself, you must cite yourself.

Slashdot Man Law 0x40: If their UID is under 10000, you must also buy them a beer (or in the case of PFY, a Jolt.)

AMD Needs Help It Seems

[jflo]

After reading this article.... well actually, while reading this piece my plans to build an AMD 4x4 just went out the Window. Although I am all about the fair competition, it is sad to see Intel kicking AMD in the a$$ so damn hard.

Re:AMD Needs Help It Seems

[Wicko]

Best idea would be to wait to see REAL benchmarks, by unbiased sites. I went Intel this round, but like you, I love competition (as most consumers should), and I would like to see AMD make a comeback.

LUXURY!

[MikShapi]

When I was a youth, the school had us rebuild a working ENIAC out of used teabags and rusted scrap metal from the schoolyard, then forced us to stay overnight and pedal dynamos to power it so the professor could play PONG using the bulbs.

But you try and tell the young people today that... and they won't believe ya.

Money where yer mouth is

[spineboy]

OK, prove yourself! Let's see some refs.

Re:Money where yer mouth is

[Vegeta99]

Damn. Guess I'll have to be Geekbitch for a while. :(

Re:FBDIMMs are a joke for a gameing system + weak

[Anonymous Coward]

feel free to use less punctuation, you're definitely way too readable there