Broadwell CPU Architecture

We’ll kick off our look at Broadwell-Y with Broadwell’s CPU architecture. As this is a preview Intel isn’t telling us a great deal about the CPU at this time, but they have given us limited information about Broadwell’s architectural changes and what to expect for performance as a result.

With Broadwell Intel is at the beginning of the next cycle of their tick-tock cadence. Whereas tock products such as Haswell and Sandy Bridge designed to be the second generation of products to use a process node and as a result are focused on architectural changes, tick products such as Ivy Bridge and now Broadwell are the first generation of products on a new process node and derive much (but not all) of their advantage from manufacturing process improvements. Over the years Intel has wavered on just what a tick should contain – it’s always more than simply porting an architecture to a new process node – but at the end of the day Broadwell is clearly derived from Haswell and will be taking limited liberties in improving CPU performance as a result.

Intel's Tick-Tock Cadence
Microarchitecture Process Node Tick or Tock Release Year
Conroe/Merom 65nm Tock 2006
Penryn 45nm Tick 2007
Nehalem 45nm Tock 2008
Westmere 32nm Tick 2010
Sandy Bridge 32nm Tock 2011
Ivy Bridge 22nm Tick 2012
Haswell 22nm Tock 2013
Broadwell 14nm Tick 2014
Skylake 14nm Tock 2015

All told, Intel is shooting for a better than 5% IPC improvement over Haswell. This is similar to Ivy Bridge (4%-6%), though at this stage in the game Intel is not talking about expected clockspeeds or the resulting overall performance improvement. Intel has made it clear that they don’t regress on clockspeeds, but beyond that we’ll have to wait for further product details later this year to see how clockspeeds will compare.

To accomplish this IPC increase Intel will be relying on a number of architectural tweaks in Broadwell. Chief among these are bigger schedulers and buffers in order to better feed the CPU cores themselves. Broadwell’s out-of-order scheduling window for example is being increased to allow for more instructions to be reordered, thereby improving IPC. Meanwhile the L2 translation lookaside buffer (TLB) is being increased from 1K to 1.5K entries to reduce address translation misses.

The TLBs are also receiving some broader feature enhancements that should again improve performance. A second miss handler is being added for TLB pages, allowing Broadwell to utilize both handlers at once to walk memory pages in parallel. Otherwise the inclusion of a 1GB page mode should pay off particularly well for servers, granting Broadwell the ability to handle these very large pages on top of its existing 2MB and 4K pages.

Meanwhile, as is often the case Intel is once again iterating on their branch predictor to cut down on missed branches and unnecessary memory operations. Broadwell’s branch predictor will see its address prediction improved for both branches and returns, allowing for more accurate speculation of impending branching operations.

Of course efficiency increases can only take you so far, so along with the above changes Intel is also making some more fundamental improvements to Broadwell’s math performance. Both multiplication and division are receiving a performance boost thanks to performance improvements in their respective hardware. Floating point multiplication is seeing a sizable reduction in instruction latency from 5 cycles to 3 cycles, and meanwhile division performance is being improved by the use of an even larger Radix-1024 (10bit) divider. Even vector operations will see some improvements here, with Broadwell implementing a faster version of the vector Gather instruction.

Finally, while it’s not clear whether these will be part of AES-NI or another instruction subset entirely, Intel is once again targeting cryptography for further improvements. To that end Broadwell will bring with it improvements to multiple cryptography instructions.

Meanwhile it’s interesting to note that in keeping with Intel’s power goals for Broadwell, throughout all of this Intel put strict power efficiency requirements in place for any architecture changes. Whereas Haswell was roughly a 1:1 ratio of performance to power – a 1% increase in performance could cost no more than a 1% increase in power consumption – Broadwell’s architecture improvements were required to be at 2:1. While a 2:1 mandate is not new – Intel had one in place for Nehalem too – at the point even on the best of days meaningful IPC improvements are hard to come by at 1:1, never mind 2:1. The end result no doubt limited what performance optimizations Intel could integrate into Broadwell’s design, but it also functionally reduces power requirements for any given performance level, furthering Intel’s goals in getting Core performance in a mobile device. In the case of Broadwell this means Broadwell’s roughly 5% performance improvement comes at a cost of just a 2.5% increase in immediate power consumption.

With that said, Intel has also continued to make further power optimizations to the entire Broadwell architecture, many of which will be applicable not just to Core M but to all future Broadwell products. Broadwell will see further power gating improvements to better shut off parts of the CPU that are not in use, and more generalized design optimizations have been made to reduce power consumption of various blocks as is appropriate. These optimizations coupled with power efficiency gains from the 14nm process are a big part of the driving force in improving Intel’s power efficiency for Core M.

Intel Broadwell Architecture Preview Broadwell GPU Architecture
POST A COMMENT

158 Comments

View All Comments

  • Krysto - Monday, August 11, 2014 - link

    M stands for Mediocre. The main reason they are hitting those TDP levels is because they are reducing performance for those specific chips that they claim to use little power.

    I also bet Broadwell will jump even higher in price than Haswell, which also jumped 40 percent over IVB, considering they're having significant yield issues.
    Reply
  • Grizzlebee - Monday, August 11, 2014 - link

    I'm looking at prices right now on Newegg and there is a 5-10$ difference between Ivy Bridge and Sandy Bridge in price. Not even close to 40%. Reply
  • Krysto - Monday, August 11, 2014 - link

    Original prices. Haswell is not the "mass market" chip for Intel, which means high volume, and can afford lower prices than initially, while IVB is low volume chip now, so it won't be much cheaper. Watch for when Broadwell comes out. It won't be just 10 percent more expensive than Haswell. Reply
  • bebimbap - Monday, August 11, 2014 - link

    I believe Krysto was referring to the jump in prices from IB to HW, and not SB to IB.
    But either case, I'll have to disagree with Kyrsto. prices seems to have decreased over the years if anything. don't forget, because of IPC gains you are paying the same for more performance.
    3570 = $210
    4590 = $200

    2320 = $190
    3330 = $190
    4430 = $180 w/ $10 off promo applied.
    Reply
  • Gondalf - Monday, August 11, 2014 - link

    All depends on from factor. If you want a tiny tablet, this is the only manner to do it.
    Or you do like Tegra K1 that scores 12W under full GPU operations??? Come on, put it in a slim convertible if you can.
    Reply
  • HardwareDufus - Monday, August 11, 2014 - link

    Pretty sure M stands for Mobile.

    Will be interesting to see what this means for Desktop variants. Want to see what improvements come the way of the GT3+ gpu.
    Reply
  • gostan - Monday, August 11, 2014 - link

    "and as we’ve seen with ARM based tablets so far they form a market that has continued to grow and continued to erode the x86 laptop market that Intel has dominated for so long."

    Is this your assumption or is it a fact? If the latter is true, can you provide some references?
    Reply
  • Ryan Smith - Monday, August 11, 2014 - link

    "If the latter is true, can you provide some references?"

    Sure.

    http://www.gartner.com/newsroom/id/2647517

    http://www.gartner.com/newsroom/id/2420816

    Gartner regularly tracks PC unit sales, and tablets are regularly cited as a factor. On a more micro level, I know several people who have reduced their PC usage over the last couple of years (and delaed PC replacements) due to their tablet use.
    Reply
  • Flunk - Monday, August 11, 2014 - link

    http://www.forbes.com/sites/haydnshaughnessy/2014/...

    Tablet sales are falling too. Perhaps there is no relation at all and just an overall tightening due to the market maturing.
    Reply
  • HanzNFranzen - Monday, August 11, 2014 - link

    that doesn't seem to be the case.

    http://techcrunch.com/2014/07/06/gartner-device-sh...
    Reply

Log in

Don't have an account? Sign up now