GPU Workload

NVIDIA's only performance advantage on the SoC side compared to Clover Trail at this point is in its GPU. Tegra 3's GPU is faster than the high clocked PowerVR SGX 545 in Clover Trail. While we don't yet have final GPU benchmarks under Windows RT/8 that we can share numbers from, the charts below show power consumption in the same DX title running through roughly the same play path.

NVIDIA's GPU power consumption is more than double the PowerVR SGX 545's here, while its performance advantage isn't anywhere near double. I have heard that Imagination has been building the most power efficient GPUs on the market for quite a while now, this might be the first argument in favor of that heresay.

WebXPRT & TouchXPRT Wireless Web Browsing Battery Life Test
Comments Locked

163 Comments

View All Comments

  • flashbacck - Monday, December 24, 2012 - link

    "... Intel adopted a "no more surprises" policy... "

    What the F does that even mean? Don't build shitty products? Only upper management could come up with this genius policy.
  • magreen - Monday, December 24, 2012 - link

    Now we had a chance to hear your comment, and boy you're just a straight shooter with upper management written all over you.
  • lmcd - Tuesday, December 25, 2012 - link

    Intel's philosophy pays off in Windows, for sure.

    Now, they've got Qualcomm to beat. That's going to take a bit more doing than beating a year-old chip.
  • lunarx3dfx - Tuesday, December 25, 2012 - link

    I think several people misunderstood the purpose of this article. The purpose was to make the point clear that x86 could be performance/watt comparable to arm. Yes, clover trail is only beating a Tegra, but considering where Intel was only a year ago this looks promising. I don't see Anand being biased here, I see him making a point about power efficiency.
  • coolhund - Tuesday, December 25, 2012 - link

    Really? The x86 processor was an out of order architecture?
    Nope. Apples and oranges that way.
  • Gigaplex - Tuesday, December 25, 2012 - link

    So what if it's not out of order? That's got nothing to do with the ISA. ARM could build an out of order chip if they wanted.
  • coolhund - Tuesday, December 25, 2012 - link

    The A9 is out of order, so is the A15. Thats not what I meant.
  • yyrkoon - Tuesday, December 25, 2012 - link

    The myth where ARM did perform more power efficiently than x86 before Intel starting caring ?

    Simple matter of the fact is that A9 does not encompass what ARM *is* (Neither does Tegra 3 for that matter ), and there are far more ARM based processors out in the world than Intel. This will likely continue into the foreseeable future. Simply because "ARM" is not locked into a specific market in the compute space.

    Personally I am all for seeing Intel improve the power efficiency of their products. However, my own opinion is that Intel should either ditch atom, and improve their server, desktop, and mobile processors. And / or create another processor(s) that can decide on what it really wants to be. e.g. embedded application processor, or not.

    One thing is for sure. Intel has their work cut out for them if they want to compete with ARM in the embedded market. One thing worth mentioning that is kind of ironic. x86 is supposed to be the general purpose type processor, yet the usage of various ARM based processor seem to be more diverse.
  • wsw1982 - Tuesday, December 25, 2012 - link

    The atom want to be used in the smartphone and cheap tablet market, I think, at least now, Intel is quite clear about it. And it's very competitive now with the ARM solutions, so I don't see the reason why intel should abandon it along with the smartphone market. The core has been actually improved a lot and, to me, always the main focus of Intel.
  • beginner99 - Tuesday, December 25, 2012 - link

    ... to compare to tegra 3. I think most would agree that comparing to dual-core A15 the outcome would be vastly different. But then I think we should not get fooled by Intel. As was mentioned this is still only a derivative of the original Atom on a smaller node. For Intel this is IMHO just a current placeholder. The real deal will come with the complete new uArch for Atom and if they manage to "pull off a Core 2" again (which I believe) it won't look pretty for Team ARM.

Log in

Don't have an account? Sign up now