Earlier this week Intel let a little bit of information leak about Haswell, which is expected to be one of the main focal points of next week's Intel Developer Forum. Haswell is a very important architecture for Intel, as it aims lower on the TDP spectrum in order to head off any potential threat from ARM moving up the chain. Haswell still remains very separate from the Atom line of processors (it should still be tangibly faster than IVB), but as ARM has aspirations of higher performance chips Intel needed to ensure that its position at lower power points wasn't being threatened.

The main piece of news Intel supplied was the TDP target for Haswell ULV (Ultra Low Voltage) parts is now 10W, down from 17W in Sandy and Ivy Bridge. The standard voltage Haswell parts will drop in TDP as well, but it's not clear by how much. Intel originally announced that Haswell would be focused on the 15 - 25W range, so it's entirely possible that standard voltage parts will fall in that range with desktop Haswell going much higher.

Intel also claims that future Haswell revisions may push even lower down the TDP chain. At or below 10W it should be possible to cram Haswell into something the thickness of a 3rd gen iPad. The move to 14nm in the following year will make that an even more desirable reality.

Although Haswell's design is compete and testing is ahead of schedule, I wouldn't expect to see parts in the market until Q2 2013.

Early next year we'll see limited availability of 10W Ivy Bridge ULV parts. These parts will be deployed in some very specific products, likely in the convertible Ultrabook space, and they won't be widely available. Any customer looking to get a jump start on Haswell might work with Intel to adopt one of these.

The limited availability of 10W ULV Ivy Bridge parts does highlight another major change with Haswell: Intel will be working much closer than it has in the past with OEMs to bring Haswell designs to market. Gone are the days when Intel could just release CPUs into the wild and expect its partners to do all of the heavy lifting. Similar to Intel's close collaboration with Apple on projects like the first MacBook Air, Intel will have to work very closely with its PC OEMs to bring the most exciting Haswell designs to market. It's necessary not just because of the design changes that Haswell brings, but also to ensure that these OEMs are as competitive as possible in markets that are heavily dominated by Apple (e.g. the tablet market).

Don't expect any earth shattering increases in CPU performance over Ivy Bridge, although I've heard that gains in the low double digits are possible. The big gains will come from the new GPU and on-package L4 cache. Broadwell (14nm, 2014) will bring another healthy set of GPU performance increases but we'll likely see more than we did from IVB with the transition to Haswell on the graphics side.

Configurable TDP and connected standby are both supported. We'll also see both single and dual-chip platforms (SoC with integrated IO hub or SoC with off-chip IO hub), which we've known for a while. We'll get more architectural details next week, as well as information about all of the new core and package power states. Stay tuned.

Comments Locked

43 Comments

View All Comments

  • JarredWalton - Friday, September 7, 2012 - link

    I'm going to be very curious to see if Intel can do something to dramatically reduce the amount of power their iGPU uses under load. Currently, HD 4000 at 1.1GHz can use around 10-12W, while the CPU portion of an IVB ULV chip can use another 12-16W depending on the task. Put them together and you have to throttle part of the chip in order to stay within a 17W TDP. At 10W TDP, I can't see Intel getting much better than HD 4000 performance.
  • wicketr - Friday, September 7, 2012 - link

    I would imagine the 17 TDP (and future 10 TDP) does not include the load of the iGPU.
  • blandge - Friday, September 7, 2012 - link

    It does.
  • JarredWalton - Friday, September 7, 2012 - link

    Here's the article we did on the topic with the ASUS UX31A:
    http://www.anandtech.com/show/6194/8
  • Khato - Friday, September 7, 2012 - link

    I'm also quite curious to see where it actually lands. In theory much of the reason for Intel's lackluster performance/power efficiency is that they're running a smaller number of EUs at higher frequency. By lowering operating frequency and hence voltage but increasing the number of EUs, performance can increase with lower power, but at the cost of greater die area.

    In fact, there's an interesting little experiment that could be done here with IVB - run some basic benchmarks on HD4000 with a maximum graphics frequency of somewhere in the 600MHz-800MHz range and decreased graphics voltage to compare against stock HD2500. That'll give a good impression of what kind of power savings is possible with same performance via spending more die space and lowering frequency.
  • Loki726 - Friday, September 7, 2012 - link

    There's also a decent amount of improvement they can make on the GPU architecture side to get more of a boost. It should be fun to see where it lands.
  • IntelUser2000 - Friday, September 7, 2012 - link

    I don't think its that simple in Intel's case. Their process is compared to TSMC, lower density, but has much superior drive current characteristics, which allows for higher frequency. It may be better for them to pursue higher clocks and smaller die than with other manufacturers.
  • JKflipflop98 - Sunday, September 9, 2012 - link

    Who told you that? It's wrong.
  • Mr Perfect - Friday, September 7, 2012 - link

    Low double digit increase means something in the teens? If this is marginally faster then IVB, which was marginally faster then SNB, what's prompting people to upgrade if they already have socket 1155?
  • Shadow_k - Friday, September 7, 2012 - link

    IVB was about 3-7% faster then SNB in terms of CPU performace

    their is no point in upgrading from 1155 to 1150. If you want some huge IGP improvements than go for it and lower TDP

Log in

Don't have an account? Sign up now