Final Words

As I mentioned at the start of this comparison, we're trying to compare two SoCs in two platforms that may offer wildly different experiences than shipping devices based on these SoCs. The hope (on both sides) is that we'll see similar, but likely slightly lower performance in phones. The reality will have to wait until we have final hardware in hand.

Qualcomm's strengths are clearly single/lightly threaded CPU performance as Krait is able to offer some significant steps forward in that department. Tegra 3 can hold onto an advantage in heavily threaded apps, but I'm not entirely convinced that in phones we'll see a lot of that.

The bigger question is about power efficiency, and this is the one not as easily answered based on what we know today. Qualcomm gains a lot by being on a 28nm LP process, however it also has more power hungry cores on that process. Device level power efficiency for a given workload may truly improve as a result of having faster cores on a lower power process (race to sleep, lower power idle). Generally speaking however, single threaded performance often comes at the expense of core level power efficiency. That's the reason it's taken this long for a 3-wide out-of-order core to make it into a smartphone. Will Moore's Law, and the 28nm LP process in particular, be enough to offset the power consumption of a higher performance Krait core under full load? Depending on how conservative device makers choose to build their power profiles we may get varying answers to this question.

Tegra 3 on the other hand should be a known quantity from a power consumption standpoint. All of the A9s in Tegra 3 are power gated (unlike in Tegra 2) and there's the fifth core for light workloads. For typical usage models I would expect better battery life out of Tegra 3 phones compared to Tegra 2 counterparts since the extra cores will likely be power gated, and idle power consumption should be lower. It's only for the heavier workloads where all cores are engaged that the impact of Tegra 3 remains to be seen.

There's also the LTE component. Today we're focused on the SoC comparisons however the first MSM8960 devices will also benefit from having integrated 28nm LTE baseband as well. Qualcomm will also have discrete 28nm LTE baseband solutions as well (e.g. MDM9615) for device makers who choose not to use Qualcomm application processors.

We'll obviously figure all of this out in due time, but my final concern remains with the device vendors. Far too often we review great platforms that are burdened with horrible software sold under the guise of differentiation. We're finally on the cusp of getting some really powerful smartphone hardware, I do hope the device vendors do these SoCs justice.

GPU Performance
Comments Locked

49 Comments

View All Comments

  • Arnulf - Thursday, February 23, 2012 - link

    Quad core Krait in a tablet/notebook should do just fine competing not only with other ARM implementations but other architectures as well. I think this is going to be the Core2 of the ARM world, the first truly "good enough" CPU that can take all reasonable loads and last for 5+ years without becoming totally useless due to ubiquitous software bloat.
  • Death666Angel - Thursday, February 23, 2012 - link

    I want your crystal ball! Nao! :D
  • peter123 - Thursday, February 23, 2012 - link

    So can we conclude that a dual core krait will outrun any quad core A9 implementation?
    What about the omap4470?
  • metafor - Thursday, February 23, 2012 - link

    OMAP4470's dual memory controller may help it. But in many workloads, Krait will obviously still be ahead. The 4470's SGX 544 would likely -- given TI's history of high clockspeeds on the GPU -- outperform the Adreno 225 and possibly by a wide margin.
  • peter123 - Thursday, February 23, 2012 - link

    But besides a new GPU and a higher clock, the 4470 is a standard dual core A9 chip, isn't it? Or is there some other improvements?
  • metafor - Friday, February 24, 2012 - link

    Well, it runs the A9's at 1.8GHz IIRC. So that'll close the margins between it and 8960. There's no getting around the inherent architectural deficiency, of course but judging by the few benchmarks in the article, they don't seem to rely all that much on architecture and are more a function of just clockspeed.

    High-clocked A9 devices will likely benchmark well. We need better benchmarks.
  • mutil0r - Thursday, February 23, 2012 - link

    It all depends on the workload. Given most smartphone use cases, it wouldn't be difficult to imagine the krait being more useful. But it wouldn't be correct to write off the A9, especially compared to a krait which isn't a full blown A15. GPU seems to be another story altogether...as can be seen. The MDP device which I assume is developer only and hence all-out, is bested by the Transformer Prime. Until the Adreno 305 comes out krait will be bring up the rear on GPU benchmarks
  • peter123 - Thursday, February 23, 2012 - link

    Ok it's clear that until Qualcomm uses the Adreno 3xx the S4's GPU will be the not sso good side of this SoC. What I wonder is how the S4 will stand against a A9 quad core Exynos 4412 or other implementations. This will be I think the main contest over 2012 SoC supremacy.
  • metafor - Friday, February 24, 2012 - link

    Hrm? I understand Adreno 225 isn't exactly blowing anyone's mind but Tegra 3's GPU was ahead in 1 out of 5 benchmarks. And looking at the Basemark scenes, Adreno can be significantly faster.
  • Wishmaster89 - Saturday, February 25, 2012 - link

    And there is still probably some place left for newer and more optimized drivers, so I wouldn't call 225 worse than T3 GPU.

    We need more demanding benchmarks to truly test those new high performance GPU's.

Log in

Don't have an account? Sign up now