Cache & Memory Hierarchy

Qualcomm has a three level exclusive cache hierarchy in Krait. The lower two levels are private per core, while the third level is shared among all cores. Qualcomm calls these caches L0, L1 and L2.

Each Krait core has an 8KB L0 cache (4KB instruction + 4KB data cache). The L0 cache is direct mapped and accessible in a single cycle. Qualcomm claims an 85% hit rate in this level 0 cache, which helps save power by not firing up the larger L1 cache. The hierarchy is exclusive so L0 data isn't necessarily duplicated in L1.

Each core also has a 32KB L1 cache (16KB instruction + 16KB data). The L1 4-way set associative and can also be accessed in a single cycle. There's no way prediction at work here. With 1 cycle latency to both L0 and L1, the primary advantage here is power.

Krait Cache Architecture
  Size Architecture Frequency
L0 4KB + 4KB Direct Mapped Core
L1 16KB + 16KB 4-way set associative Core
L2 1MB (dual core) or 2MB (quad core) 8-way set associative 1.3GHz max

The L2 cache is shared among all cores. In dual-core designs the L2 cache is sized at 1MB (up from 512KB in Scorpion), while quad-core Krait SoCs will have a 2MB L2. Krait's L2 cache is 8-way set associative.

While the L0 and L1 caches operate at core frequency and are on the same voltage plane as their associated core, the L2 cache is separate. To save power the L2 cache runs at its own frequency (up to 1.3GHz depending on the currently requested performance level). The L2 cache is on its own power plane and can be power gated if necessary.

Although Scorpion featured a dual-channel LPDDR2 memory controller, in a PoP configuration only one channel was available to any stacked DRAM. In order to get access to both 32-bit memory channels the OEM had to implement a DRAM on-package as well as an external DRAM on the PCB. Memory requests could be interleaved between the two DRAM, however Qualcomm seemed to prefer load balancing between the two with CPU/GPU accesses being directed to the lower latency PoP DRAM. Very few OEMs seemed to populate both channels and thus Scorpion based designs were effectively single-channel offerings.

Krait removes this limitation and now OEMs can utilize both memory channels in a PoP configuration (simply put two 32-bit DRAM die on the PoP stack) or in an external configuration. The split PoP/external DRAM organization is no longer supported. This change will hopefully mean we'll see more dual-channel Krait designs than we saw with Scorpion, which will in turn improve performance.

Process Technology and Clock Speeds

Krait will be the world's first smartphone CPU built on a 28nm process. Qualcomm is working with both TSMC and Global Foundries, although TSMC will produce the first chips. Krait will be built, at first, on TSMC's standard 28nm LP process. According to Qualcomm there's less risk associated with TSMC's non-HKMG process. Qualcomm was quick to point out that the entire MSM8960 SoC is built on a 28nm LP process compared to NVIDIA's 40nm LPG design in Kal-El. From Qualcomm's perspective, 40nm G transistors are only useful at reducing leakage at high temperatures but for the majority of the time a homogeneous LP design makes more sense.

Just like Scorpion, Krait places each core on its own voltage plane driven at its own clock frequency. Cores can be clocked independently of one another, which Qualcomm insists gives it a power advantage in many workloads.

The first implementation of Krait will be in a dual-core 1.5GHz MSM8960, however a second revision of the silicon will be introduced next year that increases clock speed to 1.7 - 2.0GHz. Qualcomm claims that at the same 1.05V core voltage, Krait can run at 1.7GHz vs. 1.55GHz for Scorpion. At these two clock speeds and at the same voltage, Qualcomm tells us that Krait consumes 265mW of power vs. 432mW running an undisclosed workload. Although it should be possible to draw more power than Scorpion under load, Krait should hopefully be able to improve overall power efficiency by completing tasks quicker and thus dropping down to idle faster than its predecessor. Smartphone and tablet battery life should remain the same at worst and improve at best, as a result.

Krait Architecture The Adreno 225 GPU
POST A COMMENT

108 Comments

View All Comments

  • Zingam - Saturday, October 8, 2011 - link

    And in that case you don't really need a tablet. Tablets would be very useful if they could deliver some kind of alternative user input and display. For instance: holographic displays (like in sci-fi movies) and voice control and input. That would actually make these mobile devices truly useful. The current generation and the coming generations would be nothing more than mobile browser and mp3/mp4 player. Reply
  • FunBunny2 - Saturday, October 8, 2011 - link

    And, if it could work at all, how well would voice control work outside of an anechoic chamber (with a lone user talking to it)? But, I agree, tablets (used for decades in warehouses, by the way) will soft keyboards and the like are just a cheap and dirty way around the I/O issue. Reply
  • bjacobson - Saturday, October 8, 2011 - link

    wow not sure what happened there.

    What I mean is we'll get a quad core phone with 4GB of RAM and all we'll need is a tablet to dock it to. The tablet will have the other connectivity options-- HDMI, USB, etc which will let the non-gamers replace their desktops and the people not needing Windows for business, replace their laptops.
    Reply
  • dagamer34 - Saturday, October 8, 2011 - link

    The dedicated gaming desktop will largely be obsolete in a few years. Games are much more GPU dependent than CPU dependent. What we will see is the era of external graphics cards which you can hook up to your laptop to play on your monitor @ 1080p with all the special effects turned up. Then you "undock" and rely on the integrated GPU to get longer battery life.

    Best of both worlds!
    Reply
  • Death666Angel - Friday, October 7, 2011 - link

    Thanks for the write up, pretty interesting stuff to come next year. Hopefully developers will embrace the new power, so that I can make fuller use of my Galaxy S2. I don't think I'll upgrade that soon though, pretty content with Galaxy S2 and it was expensive enough for now. I'll see what Christmas 2012 brings. :D Reply
  • cnxsoft - Friday, October 7, 2011 - link

    Back in February, Qualcomm also announced the quad-core Snapdragon APQ8064 would be ready in 2012. Any news on that ? Reply
  • HighTech4US - Friday, October 7, 2011 - link

    Nvidia's roadmap clearly shows Kal-El+ as mid 2012 and 28nm Wayne at the end of 2012

    http://www.androidcentral.com/nvidias-tegra-roadma...
    Reply
  • BoyBawang - Saturday, October 8, 2011 - link

    Does it mean all Krait cores will be manufactured in LP like the Companion CPU of Kal-EL for energy efficiency that's why it won't go beyond 2ghz even at 28mm? Reply
  • skydrome1 - Saturday, October 8, 2011 - link

    I know this article's on the Krait architecture, but in your comparison of the 2011/2012 SoC roadmap, I think you left out one very promising competitor: the ST Ericsson Nova A9600.

    Could this be included? And will there be any updates on this upcoming SoC?

    On the whole, the 2012 roadmap looks really good. But I personally am looking forward to PowerVR's Series 6, the Cortex A15 MP and NVIDIA's Wayne the most.
    Reply
  • Zingam - Saturday, October 8, 2011 - link

    Hollyday season 2013 Reply

Log in

Don't have an account? Sign up now