IPC Increases: Double L1 Data Cache, Better Branch Prediction

One of the biggest changes in the design is the increase in the L1 data cache, doubling its size from 64 KB to 128 KB while keeping the same efficiency. This is combined with a better prefetch pipeline and branch prediction to reduce the level of cache misses in the design. The L1 data cache is also now an 8-way associative design, but with the better branch prediction when needed it will only activate the one segment required and when possible power down the rest.  This includes removing extra data from 64-bit word constructions. This reduces power consumption by up to 2x, along with better clock gating and minor adjustments. It is worth pointing out that doubling the L1 cache is not always easy – it needs to be close to the branch predictors and prefetch buffers in order to be effective, but it also requires space. By using the high density libraries this was achieved, as well as prioritizing lower level cache. Another element is the latency, which normally has to be increased when a cache increases in size, although AMD did not elaborate into how this was performed.

As listed above, the branch prediction benefits come about through a 50% increase in the BTB size. This allows the buffer to store more historic records of previous interactions, increasing the likelihood of a prefetch if similar work is in motion. If this requires floating point data, the FP port can initiate a quicker flush required to loop data back into the next command. Support for new instructions is not new, though AVX2 is something a number of high end software packages will be interested in using in the future.

These changes, according to AMD, relate to a 4-15% higher IPC for Excavator in Carrizo compared to Steamroller in Kaveri.  This is perhaps a little more what we normally would expect from a generational increase (4-8% is more normal), but AMD likes to stress that this comes in addition to lower power consumption and with a reduced die area. As a result, at the same power Carrizo can have both an IPC advantage and a frequency advantage.

As a result, AMD states that for the same power, Cinebench single threaded results will go up 40% and multithreaded results up 55%. The benefits are fewer however the further up the power band you go despite the increase, as the higher density libraries perform slightly worse at higher power than Kaveri.

Efficiency and Die Area Savings Power Saving and Power Consumption
POST A COMMENT

138 Comments

View All Comments

  • FlushedBubblyJock - Tuesday, June 9, 2015 - link

    they probably have their contrast off, clear type disabled, the wrong screen font, smoothing edges of fonts disabled, then he's probably a far sighted coke bottled glasses with bifocals... thus amd must be had in dooper high rezz at 14fps... Reply
  • meacupla - Wednesday, June 3, 2015 - link

    Ideally, what you'd get is a 2560x1440 screen with PROPER scaling to 1280x720, unlike what most monitors seem to do, which is a terrible job at scaling. Reply
  • SilthDraeth - Wednesday, June 3, 2015 - link

    I run a Kaveri on my desktop and it drives 1080p just fine. Anyways, most intel laptops in that same range run 1366x768 screens also. At least almost every laptop you find in a Staples, or a Walmart. Very few of the devices on display have a higher resolution screen, or IPS solution. Reply
  • yankeeDDL - Wednesday, June 3, 2015 - link

    Yes, *and* Intel's in that price range don't run games. Reply
  • FlushedBubblyJock - Tuesday, June 9, 2015 - link

    yes they do make sure you have hd3000 at least but that's cheap as beans Reply
  • Margalus - Wednesday, June 3, 2015 - link

    how is it an "issue that plagues AMD"? Are you saying AMD chips are buggy and crash at that resolution? Are you saying AMD graphics get corrupted at that resolution? Reply
  • medi03 - Thursday, June 4, 2015 - link

    Ditto.
    In fact, 1366x768 TN (!!!) screen is the main issue with AMD mobile chips.
    Reply
  • Drumsticks - Wednesday, June 3, 2015 - link

    The 45W A8-6500T scores 71 in Cinebench R15. Even assuming that 15W kaveri gets identical performance (I couldn't think of a 15w kaveri chip to check on bench) that puts it at 106, which is finally, finally even with broad well in the xps 13, or at least <10%.

    Skylake will probably add another 10% gap, but this is the closest AMD might be in the last seven years or so to catching up with Intel. And at half the price, they could seriously have the start of a comeback!
    Reply
  • xenol - Wednesday, June 3, 2015 - link

    My only problem with AMD and the marketing blurbs is that they're targeting niche markets for all intents and purposes. Despite what PC gamers want us to think how big PC gaming is, it's not exactly a majority player in the entire scheme of things and gaming on a laptop isn't really that accepted.

    And even if gaming is involved, it's usually not games that require beefy specs to begin with.
    Reply
  • Michael Bay - Wednesday, June 3, 2015 - link

    PC gaming by marketshare is on par with any pastgen/nextgen console and sometimes more than one. Reply

Log in

Don't have an account? Sign up now