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."

SSE4 is overrated

[Silverlancer (786390)]

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 (786390)]

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

Re:

[Gabest (852807)]

This is MADD-ness!

Re:

[Briareos (21163)]

This is MADD-ness!

But this ain't even Sparta [softpedia.com]!!1!2!eleven

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

Re:

[Ant P. (974313)]

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:

[Silverlancer (786390)]

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 (174571)]

I assume you're complaining about Intel documents such as this one [intel.com] 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:

[Silverlancer (786390)]

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 (1140543)]

Seriously, what is it with these names?

Re:

[Chandon Seldon (43083)]

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

[Foerstner (931398)]

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

Re:

[confused one (671304)]

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

[plover (150551)]

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!

LUXURY!

[MikShapi (681808)]

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.

Re:

[plover (150551)]

What, are you still here?

Oops, sorry, it was a GENIAC [wikipedia.org], not an ENIAC [wikipedia.org].

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

Re:

[WhatAmIDoingHere (742870)]

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

Re:

[Fred_A (10934)]

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)

Fans

[SpeedyDX (1014595)]

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 (468664)]

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

[ceoyoyo (59147)]

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:

[Fred_A (10934)]

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:

[bcmm (768152)]

I use Gentoo, you insensative clod!

Re:Fans -- Compressors!

[Technician (215283)]

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 [custompc.co.uk]

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 brea

Re:

[bcmm (768152)]

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 coo

FBDIMMs are a joke for a gameing system + weak SLI

[Joe The Dragon (967727)]

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.

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

[Jeff DeMaagd (2015)]

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?

Re:

[Joe The Dragon (967727)]

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:

[Vegeta99 (219501)]

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.)

Money where yer mouth is

[spineboy (22918)]

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

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

[dwater (72834)]

> 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'.

all this and the kitchen sink too...

[downix (84795)]

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:

[by 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.

Time Again

[Nom du Keyboard (633989)]

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.

That's not surprising

[Sycraft-fu (314770)]

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:

[dwater (72834)]

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

Re:

[dwater (72834)]

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 ID

Re:

[Fweeky (41046)]

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 everyt

Re:

[darkwhite (139802)]

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.

when i was a kid...

[kesuki (321456)]

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:

[Kjella (173770)]

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? H

Re:when i was a kid...

[kesuki (321456)]

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:

[Kjella (173770)]

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 i

Re:

[darkwhite (139802)]

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.

Re:

[zerocool^ (112121)]

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 hous

Re:

[kesuki (321456)]

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

Poster and commenter misconceptions...

[Glasswire (302197)]

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.

Useful, or like chrome on the car?

[davmoo (63521)]

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:

[Carbon016 (1129067)]

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

Does it have a Hemi?

[flyingfsck (986395)]

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

Re:

[SleepyHappyDoc (813919)]

Ten years ago called. They want their acronym back.