Intel May Show Ivy Bridge CPUs at Computex

[exfileme]

Intel's upcoming Ivy Bridge platform may show its face come May 30.

Intel May Show Ivy Bridge CPUs at Computex : Read more

 

[iam2thecrowe]

c'mon AMD, if you dont release bulldozer soon, it will be too late for you.

 

[jimmysmitty]

Even with BD it might not pan well for AMD. I have hopes for BD but have a feeling that on a core per core, clock per clock level, Sandy Bridge will be faster and therfore Ivy Bridge will be too.

As for efficiency, I doubt AMDs first generation HK/MG and early 32nm process will be more efficient than Gulftown let alone Sandy Bridge. And Intels 22nm looks to be amazingly efficient.

Add in the fact that Ivy Bridge will drop into current LGA1155 mobos and its hard to say where AMD will be with BD since BD will only work on AM3+.

 

[eklipz330]

omg 22nm already? i honestly thought that transistor shrinks were going to slow down like hell after 32nm.... but WOW!!!

and for those who don't know, the longest molecule strand known to man is 22nm long!! i forget where i read it though. but it was on the internet, so you know it was the truth

 

[Bigmac80]

So Ivy Bridge will work on 1155 platforms?

 

[kcorp2003]

I was planning my next build around the New Micro architecture (Haswell) in 2012-13 but given the situation (BF3 namely) i might just go with Ivy bridge. If AMD get their act together with Bulldozer and their HD7000 series on the 28nm chip for Q4 2011, then its AMD build all the way. But thats wishful thinking I am seeing more of a Ivy bridge + HD7000s in my future build.

 

[kcorp2003]

http://www.cdrinfo.com/images/uploaded/Intel_Technology_Outlook_Sept2009.jpg

4nm by 2022.

 

[HansVonOhain]

[citation][nom]kcorp2003[/nom]4nm by 2022.[/citation]

You fail. By the time you reach those sizes, the interconnect paths are going to be limited by electron traveling. Those are the complications of Quantum Computing. By that time, there is going to be a new medium built instead of silicon wafer.

 

[Guest]

@jimmysmitty

now if i recall correctly Brazo (fusion) was originally planned for 32nm but due to fab issues had to use 40 odd nm, AMD instead of growing the die size decided to optimize the chip instead and was able to achieve comparable performance without growing the die size at all, that tells me that fusion (in the brazo guise) has significant headroom for when it does go 32nm

yes current gen AMD chips are behind the curve on performance but there is a significant amount of real estate that becomes available when they go to 32nm, just filling that out with transistor count will get you some performance boost, but with an optimized new architecture there is potential for some real good performance gains to be had, not saying they will deliver just saying logically it's plausible

 

[jprahman]

AMD certainly has their work cut out for them. Bulldozer's release in a few months will be AMDs rollout of their 32nm fabricated chips, and now Intel is already going to be releasing 22nm chips ~6-9 months later. Intel's massive R&D budget is showing up quite clearly.

[citation][nom]kcorp2003[/nom]4nm by 2022.[/citation]
Not going to happen. After you pass a certain component size quantum tunneling get so bad that further process shrinks are nearly impossible. Basically quantum tunneling means that electrons pass through the insulating dielectric materials and large leakage currents result, much higher than what we currently see. If I recall correctly 16nm is the smallest process that can be achieved with conventional silicon technology. Further miniaturization and clock speed increases will require the use of new materials like graphene.

 

[kilo_17]

@iam2thecrowe
Exactly. AMD better hurry up, Intel's getting farther ahead of them.

 

[Bigmac80]

AMD is in trouble knowing that the 1155 platforms are already cheap.

 

[jprahman]

Because the chipset is faulty. lol

 

[dan55]

[citation][nom]mayankleoboy1[/nom]the ivy bridge will cannibalize the sales of sandy bridge. but the consumer wins![/citation]

Not really. Ivy Bridge is pretty new tech, and will be considerably more expensive. It'll probably be like the i7-900 series were initially, with prices on the higher side. And, they are only going to be extremely high end procs too, as Intel has said that Ivy Bridge will be 6 and 8 core processors. Cheaper than 980x, but probably still not any where close to the amazing prices of current Sandy Bridge.

 

[aaron88_7]

[citation][nom]mayankleoboy1[/nom]the ivy bridge will cannibalize the sales of sandy bridge. but the consumer wins![/citation]
What makes you think Ivy bridge will be anywhere below the ass-raping price range? Intel isn't going to be price competitive with their own line of chips, I'd be surprised to see any Ivy bridge chips fall under the $500 range, at most maybe one or 2 of their slower clocked non-k versions.

The only competition will be from AMD's Bulldozer if it can compete performance wise. If it can't keep up then it doesn't matter what price AMD charges, many people will stick with Intel for their speed despite the cost. In other words, if Bulldozer doesn't perform well, the consumer looses.

 

[joytech22]

AMD's already in a world of trouble with their late release dates, I'm currently the sad owner of a dying CPU manufacturer's CPU..

The only way AMD's going to catch up is if they re-invent the cpu in terms of performance, and it's not looking good.

 

[notsleep]

i dunno. to me you can get an amd hexa core for $199.99 (1090T) versus intel hexa core for $999.99 (980X) today. 45 nm versus 32 nm (13 nm diff) isn't such a big jump like 65 nm to 45 nm (20 nm diff).

now going from 45 nm to ivy's 22nm (23 nm diff) is well worth it to me. no sandy bridges prices on newegg atm to compare i guess due to intel recall being in effect.

i really hope amd comes through with bulldozer. it really is their last straw. after that, intel will sell cpus for $1000 without competition if amd falls. if it weren't for amd's hexa core alternative, the only way you can buy hexa core is through intel $999.99 asking price. competition is good for consumer people.

 

[kcorp2003]

[citation][nom]HansVonOhain[/nom]You fail. By the time you reach those sizes, the interconnect paths are going to be limited by electron traveling. Those are the complications of Quantum Computing. By that time, there is going to be a new medium built instead of silicon wafer.[/citation]



intel themselves set this goal for 2022 @ 4nm
This tech site covered it

http://www.xbitlabs.com/news/cpu/display/20090822094141_Intel_Outlines_Process_Technology_Roadmap.html

 

[kcorp2003]

[citation][nom]jprahman[/nom]Not going to happen. After you pass a certain component size quantum tunneling get so bad that further process shrinks are nearly impossible. Basically quantum tunneling means that electrons pass through the insulating dielectric materials and large leakage currents result, much higher than what we currently see. If I recall correctly 16nm is the smallest process that can be achieved with conventional silicon technology. Further miniaturization and clock speed increases will require the use of new materials like graphene.[/citation]

intel themselves set this goal for 2022 @ 4nm
This tech site covered it

http://www.xbitlabs.com/news/cpu/display/20090822094141_Intel_Outlines_Process_Technology_Roadmap.html

 

[joelmartinez]

It's gonna overclock like crazy

 

[rebturtle]

However, the architecture will remain similar to Sandy Bridge, but reduced down to a smaller die thanks to 22 nm manufacturing.

So newer, faster, more efficient, but can't read hard drives after 2 years? Sign me up! - lol

 

[eddieroolz]

Well it's just a downscale, so it shouldn't be that difficult.

 

[JOSHSKORN]

Oh wow...and I thought I wanted Sandy Bridge...never mind! Ivy Bridge here I come!

 

[Wish I Was Wealthy]

Yeah,I actually think the same as JOSHSKORN now since I have read the above article about Taipei 2011 Computex Show...Can any body go or is it just for invites...Also I have already bought two processors of the Sandy Bridge design (core i7 2600k & core i7 2600),but I gave the Asus P8P67 Deluxe motherboard back with the faulty cougar chipset and got in return with me adding some extra cash a core i7 870 with a Asus P7H55-M/USB3 so I can play around for 3 to 6 months until the newly made cougar chipsets based mother boards arrive back in town again...Maybe I should of just asked for cash totally back and saved for the ivy bridge gear since they will share the same LGA 1155 socket pinset number...

 

[silverblue]

Showing Ivy Bridge this early is a bit silly in my honest opinion. There are people out there who don't believe Sandy Bridge is a big enough improvement over Nehalem and they're only going to wait for Ivy Bridge before parting with their money.

If AMD's on the ball, Bulldozer will have been on the market for a few weeks before the demonstration. If not, well... never mind.

Ivy Bridge looks to be just a way of getting 6 or more cores into the space formerly afforded to 4 cores on the 32nm node. Aside of having extra cores and a lower manufacturing process, the CPU side of Ivy Bridge doesn't sound any more powerful. If they want to keep power and heat under control with the additional cores, they can't realistically clock it too highly.

I'd like to know what Intel are doing to increase Ivy Bridge's performance on a per-core basis, if they are at all. They're also probably not worried about Bulldozer as concerns the desktop space; even if it ends up being an integer crunching monster, that's not so useful on the desktop, and as it doesn't appear to offer a significant floating point boost over Stars, it's likely to fall short on that side of things, at least with the first generation. It's the server market that may just provide AMD with the most wins.

I hate waiting for Bulldozer. I just want to see how it stacks up with Sandy Bridge.