backtop


Print 65 comment(s) - last by M4gery.. on Jun 30 at 12:57 PM


Haswell CPUs will contain vector processors and a more power on-die GPU. The chips are designed to power the next generation of "Ultrabooks".  (Source: ASUSTek)

An Intel corporate blog post seemed to confirm both the presence of vector coprocessor silicon and a 2013 release date for the 22 nm Haswell.  (Source: Intel)
Company looks to new 22 nm architecture to hold off AMD and ARM Holdings

Intel Corp. (INTC) has dropped a few hints to its upcoming 22 nm Haswell architecture, currently under development by the company's secret Oregon team.  In a post on the Intel Software Network blog titled "Haswell New Instruction Descriptions Now Available!", the company reveals that it plans to launch the new CPU in 2013.

Haswell will utilize the same power-saving tri-gate 3D transistor technology that will first drop with Ivy Bridge in early 2012.  Major changes architecturally reportedly include a totally redesigned cache, fused multiply add (FMA3) instruction support, and an on-chip vector coprocessor.

The vector process, which will work with the on-die GPU, was a major focus of the post.  The company is preparing a series of commands called Advanced Vector Extensions (AVX), which will speed up vector math.  It writes:

Intel AVX addresses the continued need for vector floating-point performance in mainstream scientific and engineering numerical applications, visual processing, recognition, data-mining/synthesis, gaming, physics, cryptography and other areas of applications. Intel AVX is designed to facilitate efficient implementation by wide spectrum of software architectures of varying degrees of thread parallelism, and data vector lengths.

According to CNET, Intel's marketing chief Tom Kilroy indicates that Intel hopes for the new chip's integrated graphics to rival today's discrete graphics.  

Intel has a ways to go to meet that objective -- its on-die GPU in Sandy Bridge marked a significant improvement over past designs (which were housed in a separate package, traditionally), however it also fell far short of the GPU found in Advance Micro Devices (AMD) Llano Fusion APUs.

Intel has enjoyed a love/hate relationship with graphics makers AMD and NVIDIA Corp. (NVDA).  While it's been forced to allow their GPUs to live on its motherboards and alongside its CPUs, the company has also fantasized of usurping the graphics veterans.  Those plans culminated in the company's Larrabee project, which aimed to offer discrete Intel graphics cards.

Now that a commercial release of Larrabee has been cancelled, Intel has seized upon on-die integrated graphics as its latest answer to try to push NVIDIA and AMD out of the market.  Intel is promoting heavily the concept of ultrabooks -- slender notebooks like the Apple, Inc.'s (AAPL) MacBook Air or ASUTEK Computer Inc.'s (TPE:2357) UX21, which feature low voltage CPUs and -- often -- no discrete GPU.

Mr. Kilroy reportedly wants ultrabook manufacturers using Haswell to shoot for target and MSRP of $599 USD, which would put them roughly in line with this year's Llano notebooks from AMD and partners.  It's about $100 USD less than current Sandy Bridge notebooks run.

Intel faces pressure from a surging ARM Holdings plc's (ARMH) who is looking to unveil notebook processors sometime next year.



Comments     Threshold


This article is over a month old, voting and posting comments is disabled

RE: wow no kidding
By Targon on 6/24/2011 8:17:26 PM , Rating: 2
Ageia failed because the framerates were horrible when the PPU was being used. Think back to the original 3G cards, where 3DFX dominated, and WHY. There were the 3DFX Voodoo cards, and then you had all the others, most of them not really improving the framerates, even though graphics clarity WAS better.

The Voodoo and Voodoo 2, better graphics, and faster performance, it was a win/win. Look at physics, where if you turn it on, your framerates go down so much you want to turn it off. Software acceleration with the feature on is the only thing that would make the PPU seem like an improvement.


RE: wow no kidding
By epobirs on 6/24/2011 9:34:56 PM , Rating: 2
Ageia was always dooomed even in their best case scenario of delivering something in their discrete product that couldn't be matched on pure performance by the GPU makers. The best they could hope for was to turn a big profit on a buyout by one of the big GPU companies.

The problem was that they could never hope to have a slam dunk, you either have our card or your stuff is hopelessly inferior, situation. The most that they could hope for was a brief window when a few games would get a lot of mileage out of the card. The technology wasn't sufficiently different from what GPGPU enables, meaning the next GPU generation would always offer a substantial chunk of what the discrete card offered but effectively for free in the end users eyes.

Worse, high-end users faced a choice between adding a PPU card or a second GPU card. The latter choice was arguably more versatile, albeit more costly in most cases where the card is fairly recent and strong.

So, even if it worked perfectly and gained wide support, Ageia couldn't ever offer a killer value proposition against the likes of Big GPU.


RE: wow no kidding
By Samus on 6/25/2011 7:34:29 AM , Rating: 2
Hearing Intel talk up their 'next-gen graphics' is like listening to a broken record, and dates back about as far as vinyl as well.

I simply fail to imagine how Intel will out-engineer AMD in GPU design. Having an enemy in nVidia and a direct competitor in AMD, they will have to source their own engineering team, which no matter how well funded, will simply not outpace nVidia or AMD in 2 years.


RE: wow no kidding
By ekv on 6/26/2011 2:43:41 AM , Rating: 2
quote:
I simply fail to imagine how Intel will out-engineer AMD in GPU design.
By and large I'd have to agree with you there. However, it is fair to say that Intel has superior manufacturing capabilities, and that their stumbles (Cougar Point SATA Bug) lately have been relatively minor (contrast with Phenom). In comparison, AMD/ATI and NVidia are rather tied to TSMC, though neither they or GlobalFoundries et al. have and/or can match Intel.

Intel has also shown somewhat surprising adaptability recently in terms of CPU architecture. AMD has seemingly been stagnant, though quite the opposite is likely true, perhaps due to budget / cash-flow difficulties. Which goes to show once again that a sound economic position can help you [buy engineers].


RE: wow no kidding
By HollyDOL on 6/29/2011 2:42:53 PM , Rating: 2
I wouldn't underestimate Intel. Don't forget they can afford to throw much more money in the project. Probably much more than AMD and nVidia could put in together.
That in combination with current technological advantage they have could create them path to really get competitive gpu. Not saying it will, just it could be possible.


"A lot of people pay zero for the cellphone ... That's what it's worth." -- Apple Chief Operating Officer Timothy Cook














botimage
Copyright 2014 DailyTech LLC. - RSS Feed | Advertise | About Us | Ethics | FAQ | Terms, Conditions & Privacy Information | Kristopher Kubicki