The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

Embed Size (px)

Citation preview

  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    1/30

    Full View Print

    The x86 Power Myth Busted: In-Depth Clover Trail Power Analysisby Anand Lal Shimpi on 12/24/2012 5:00:00 PMPosted in Tablets , SOC , Intel , Clovertrail , Surface , Acer

    The untold story of Intel's desktop (and notebook) CPU dominance after 2006 has nothing to do with novel newapproaches to chip design or spending billions on keeping its army of fabs up to date. While both of those are criticalcomponents to the formula, its Intel's internal performance modeling team that plays a major role in providing targets for both the architects and fab engineers to hit. After losing face (and sales) to AMD's Athlon 64 in the early 2000s, Inteladopted a "no more surprises" policy. Intel would never again be caught off guard by a performance upset.

    Over the past few years however the focus of meaningful performance has shifted. Just as important as absoluteperformance, is power consumption. Intel has been going through a slow waking up process over the past few years as

    it's been adapting to the new ultra mobile world. One of the first things to change however was the scope and focus of itsinternal performance modeling. User experience (quantified through high speed cameras mapping frame rates to user survey data) and power efficiency are now both incorporated into all architecture targets going forward. Building its next-generation CPU cores no longer means picking a SPECCPU performance target and working towards it, but delivering acertain user experience as well.

    Intel's role in the industry has started to change. It worked very closely with Acer on bringing the W510, W700 and S7 tomarket. With Haswell, Intel will work even closer with its partners - going as far as to specify other, non-Intel componentson the motherboard in pursuit of ultimate battery life. The pieces are beginning to fall into place, and if all goes accordingto Intel's plan we should start to see the fruits of its labor next year. The goal is to bring Core down to very low power levels, and to take Atom even lower. Don't underestimate the significance of Intel's 10W Ivy Bridge announcement .

    Although desktop and mobile Haswell will appear in mid to late Q2-2013, the exciting ultra mobile parts won't arrive untilQ3. Intel's 10W Ivy Bridge will be responsible for at least bringing some more exciting form factors to market between nowand then. While we're not exactly at Core-in-an-iPad level of integration, we are getting very close.

    http://www.anandtech.com/show/6529/busting-the-x86-power-myth-indepth-clover-trail-power-analysishttp://www.anandtech.com/show/6529/busting-the-x86-power-myth-indepth-clover-trail-power-analysishttp://www.anandtech.com/tag/tabletshttp://www.anandtech.com/tag/tabletshttp://www.anandtech.com/tag/sochttp://www.anandtech.com/tag/sochttp://www.anandtech.com/tag/intelhttp://www.anandtech.com/tag/clovertrailhttp://www.anandtech.com/tag/clovertrailhttp://www.anandtech.com/tag/surfacehttp://www.anandtech.com/tag/surfacehttp://www.anandtech.com/tag/surfacehttp://www.anandtech.com/tag/acerhttp://e/Users/57095807/Desktop/http://e/Users/57095807/Desktop/http://www.anandtech.com/show/6248/haswell-at-idf-2012-10w-is-the-new-17whttp://www.anandtech.com/show/6248/haswell-at-idf-2012-10w-is-the-new-17whttp://www.anandtech.com/show/6355/intels-haswell-architecturehttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/DSC_9166.jpghttp://www.anandtech.com/tag/tabletshttp://www.anandtech.com/tag/sochttp://www.anandtech.com/tag/intelhttp://www.anandtech.com/tag/clovertrailhttp://www.anandtech.com/tag/surfacehttp://www.anandtech.com/tag/acerhttp://e/Users/57095807/Desktop/http://e/Users/57095807/Desktop/http://www.anandtech.com/show/6248/haswell-at-idf-2012-10w-is-the-new-17whttp://www.anandtech.com/show/6355/intels-haswell-architecturehttp://www.anandtech.com/show/6529/busting-the-x86-power-myth-indepth-clover-trail-power-analysis
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    2/30

    To kick off what is bound to be an exciting year, Intel made a couple of stops around the country showing off that even itsexisting architectures are quite power efficient. Intel carried around a pair of Windows tablets, wired up to measure power consumption at both the device and component level, to demonstrate what many of you will find obvious at this point: thatIntel's 32nm Clover Trail is more power efficient than NVIDIA's Tegra 3.

    Page 1

    The untold story of Intel's desktop (and notebook) CPU dominance after 2006 has nothing to do with novel newapproaches to chip design or spending billions on keeping its army of fabs up to date. While both of those are criticalcomponents to the formula, its Intel's internal performance modeling team that plays a major role in providing targets for both the architects and fab engineers to hit. After losing face (and sales) to AMD's Athlon 64 in the early 2000s, Inteladopted a "no more surprises" policy. Intel would never again be caught off guard by a performance upset.

    Over the past few years however the focus of meaningful performance has shifted. Just as important as absoluteperformance, is power consumption. Intel has been going through a slow waking up process over the past few years asit's been adapting to the new ultra mobile world. One of the first things to change however was the scope and focus of itsinternal performance modeling. User experience (quantified through high speed cameras mapping frame rates to user survey data) and power efficiency are now both incorporated into all architecture targets going forward. Building its next-generation CPU cores no longer means picking a SPECCPU performance target and working towards it, but delivering acertain user experience as well.

    Intel's role in the industry has started to change. It worked very closely with Acer on bringing the W510, W700 and S7 tomarket. With Haswell, Intel will work even closer with its partners - going as far as to specify other, non-Intel componentson the motherboard in pursuit of ultimate battery life. The pieces are beginning to fall into place, and if all goes accordingto Intel's plan we should start to see the fruits of its labor next year. The goal is to bring Core down to very low power levels, and to take Atom even lower. Don't underestimate the significance of Intel's 10W Ivy Bridge announcement .

    Although desktop and mobile Haswell will appear in mid to late Q2-2013, the exciting ultra mobile parts won't arrive untilQ3. Intel's 10W Ivy Bridge will be responsible for at least bringing some more exciting form factors to market between nowand then. While we're not exactly at Core-in-an-iPad level of integration, we are getting very close.

    To kick off what is bound to be an exciting year, Intel made a couple of stops around the country showing off that even itsexisting architectures are quite power efficient. Intel carried around a pair of Windows tablets, wired up to measure power consumption at both the device and component level, to demonstrate what many of you will find obvious at this point: thatIntel's 32nm Clover Trail is more power efficient than NVIDIA's Tegra 3.

    http://www.anandtech.com/show/6355/intels-haswell-architecture/3http://www.anandtech.com/show/6355/intels-haswell-architecture/3http://www.anandtech.com/show/6248/haswell-at-idf-2012-10w-is-the-new-17whttp://www.anandtech.com/show/6248/haswell-at-idf-2012-10w-is-the-new-17whttp://www.anandtech.com/show/6355/intels-haswell-architecturehttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/DSC_9166.jpghttp://www.anandtech.com/show/6355/intels-haswell-architecture/3http://www.anandtech.com/show/6355/intels-haswell-architecture/3http://www.anandtech.com/show/6248/haswell-at-idf-2012-10w-is-the-new-17whttp://www.anandtech.com/show/6355/intels-haswell-architecture
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    3/30

    We've demonstrated this in our battery life tests already . Samsung's ATIV Smart PC uses an Atom Z2760 and features a30Wh battery with an 11.6-inch 1366x768 display. Microsoft's Surface RT uses NVIDIA's Tegra 3 powered by a 31Whbattery with a 10.6-inch, 1366x768 display. In our 2013 wireless web browsing battery life test we showed Samsung with a17% battery life advantage, despite the 3% smaller battery. Our video playback battery life test showed a smaller advantage of 3%.

    For us, the power advantage made a lot of sense. We've already proven that Intel's Atom core is faster than ARM's Cortex A9 (even four of them under Windows RT ). Combine that with the fact that NVIDIA's Tegra 3 features four Cortex A9s onTSMC's 40nm G process and you get a recipe for worse battery life, all else being equal.

    Intel's method of hammering this point home isn't all that unique in the industry. Rather than measuring power consumption at the application level, Intel chose to do so at the component level. This is commonly done by taking thedevice apart and either replacing the battery with an external power supply that you can measure, or by measuring currentdelivered by the battery itself. Clip the voltage input leads coming from the battery to the PCB, toss a resistor inline andmeasure voltage drop across the resistor to calculate power (good ol' Ohm's law).

    Where Intel's power modeling gets a little more aggressive is what happens next. Measuring power at the battery givesyou an idea of total platform power consumption including display, SoC, memory, network stack and everything else onthe motherboard. This approach is useful for understanding how long a device will last on a single charge, but if you're acomponent vendor you typically care a little more about the specific power consumption of your competitors' components.

    What follows is a good mixture of art and science. Intel's power engineers will take apart a competing device and probewhatever looks to be a power delivery or filtering circuit while running various workloads on the device itself. By correlatingthe type of workload to spikes in voltage in these circuits, you can figure out what components on a smartphone or tabletmotherboard are likely responsible for delivering power to individual blocks of an SoC. Despite the high level of integrationin modern mobile SoCs, the major players on the chip (e.g. CPU and GPU) tend to operate on their own independentvoltage planes.

    http://www.anandtech.com/show/6522/the-clover-trail-atom-z2760-review-acers-w510-tested/7http://www.anandtech.com/show/6522/the-clover-trail-atom-z2760-review-acers-w510-tested/7http://www.anandtech.com/show/6385/microsoft-surface-review/10http://www.anandtech.com/show/6385/microsoft-surface-review/10http://images.anandtech.com/reviews/SoC/Intel/CTvT3/DSC_9159.jpghttp://www.anandtech.com/show/6522/the-clover-trail-atom-z2760-review-acers-w510-tested/7http://www.anandtech.com/show/6385/microsoft-surface-review/10
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    4/30

    A basic LC filter

    What usually happens is you'll find a standard LC filter (inductor + capacitor) supplying power to a block on the SoC. Oncethe right LC filter has been identified, all you need to do is lift the inductor, insert a very small resistor (2 - 20 m) andmeasure the voltage drop across the resistor. With voltage and resistance values known, you can determine current andpower. Using good external instruments you can plot power over time and now get a good idea of the power consumptionof individual IP blocks within an SoC.

    Basic LC filter modified with an inline resistor

    Intel brought one of its best power engineers along with a couple of tablets and a National Instruments USB-6289 dataacquisition box to demonstrate its findings. Intel brought along Microsoft's Surface RT using NVIDIA's Tegra 3, and Acer'sW510 using Intel's own Atom Z2760 (Clover Trail). Both of these were retail samples running the latest software/driversavailable as of 12/21/12. The Acer unit in particular featured the latest driver update from Acer (version 1.01, released on12/18/12) which improves battery life on the tablet (remember me pointing out that the W510 seemed to have a problemthat caused it to underperform in the battery life department compared to Samsung's ATIV Smart PC? it seems like thisdriver update fixes that problem).

    I personally calibrated both displays to our usual 200 nits setting and ensured the software and configurations were asclose to equal as possible. Both tablets were purchased by Intel, but I verified their performance against my own reviewsamples and noticed no meaningful deviation. All tests and I've also attached diagrams of where Intel is measuring CPUand GPU power on the two tablets:

    Microsoft Surface RT: The yellow block is where Intel measures GPU power, the orange block is where it measures CPU

  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    5/30

    power

    Acer's W510: The purple block is a resistor from Intel's reference design used for measuring power at the battery. Yellow and orange are inductors for GPU and CPU power delivery, respectively.

    The complete setup is surprisingly mobile, even relying on a notebook to run SignalExpress for recording output from theNI data acquisition box:

    Wiring up the tablets is a bit of a mess. Intel wired up far more than just CPU and GPU, depending on the device and whatwas easily exposed you could get power readings on the memory subsystem and things like NAND as well.

    Intel only supplied the test setup, for everything you're about to see I picked and ran whatever I wanted, however Iwanted. Comparing Clover Trail to Tegra 3 is nothing new, but the data I gathered is at least interesting to look at. Wetypically don't get to break out CPU and GPU power consumption in our tests, making this experiment a bit moreilluminating.

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/DSC_9153.jpghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/w5100board.jpg
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    6/30

    Keep in mind that we are looking at power delivery on voltage rails that spike with CPU or GPU activity. It's not uncommonto run multiple things off of the same voltage rail. In particular, I'm not super confident in what's going on with Tegra 3'sGPU rail although the CPU rails are likely fairly comparable. One last note: unlike under Android, NVIDIA doesn't use its5th/companion core under Windows RT. Microsoft still doesn't support heterogeneous computing environments, soNVIDIA had to disable its companion core under Windows RT.

    {gallery 2497}

    Page 2

    Idle Power

    In all of these tests you're going to see three charts. The first will show you total platform power, measured at the battery,taking into account everything from SoC to display. The next shows you power measured at the CPU power deliverycircuit, and the third shows you power measured at the GPU power delivery circuit. All values are measured in watts, andare reported in 15ms intervals (although I sampled at 1KHz then averaged down to 15ms).

    For our first set of tests I simply wanted to get a feel for idle power. Both systems had all background syncing suspended,

    WiFi was connected, and we're just sitting at the Windows RT/8 Start Screen until the tablets reached a truly idle state.Note that idle under Windows RT/8 technically doesn't happen until the live tiles stop updating, which you'll see denotedby a drop in the idle power consumption in the graphs below.

    First up is total platform power consumption:

    Surface RT has higher idle power, around 28% on average, compared to Acer's W510. The last half of the graph showsthe tablets hitting true idle when the live tiles stop animating.

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/idle-total.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    7/30

    A look at the CPU chart gives us some more granularity, with Tegra 3 ramping up to higher peak power consumptionduring all of the periods of activity. Here the Atom Z2760 cores average 36.4mW at idle compared to 70.2mW for Tegra 3.

    The GPU specific data is pretty interesting - the GPU power rail shows much high power consumption than on Intel'sZ2760. As I didn't design Tegra 3, I don't know what else is powered by this rail - although you'd assume that anythingelse not in use would be power gated. Imagination Technologies' PowerVR SGX 545 does appear to be quite power efficient here, on average using 155mW while rendering the Start Screen.

    I wasn't happy with the peaks we were seeing when nothing was happening on the systems, so to confirm that nothingfunny was going on I threw both tablets into airplane mode and waited for full idle. Check out the tail end of the platformpower diagram:

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/idle-gpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/idle-cpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    8/30

    That's much better. Without the AP talking to each tablet's WiFi radio constantly, idle becomes truly idle. If you're curious,the power savings are around 47.8mW (average) for the W510 in airplane mode when fully idle.

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/idleairplane-cpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/idleairplane-total.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    9/30

    The GPU rail feeding the Atom Z2760 appears to hit a lower idle power when compared to NVIDIA's Tegra 3. Advantagesin idle power consumption are key to delivering good battery life overall.

    Page 3

    Power During Boot

    For the next test I measured power during a cold boot process. Here we're looking at power consumption from device off

    to hitting the Windows Start Screen:

    Now we get our first glimpse of active power and there's a definite advantage here for Intel. Peak power consumption for

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/boot-total.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/idleairplane-gpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    10/30

    the entire tablet tops out at just over 5W compared to 8W for Surface RT. Let's dig deeper to find what is responsible for the added power consumption:

    The difference in average CPU power consumption is significant. Tegra 3 pulls around 1.29W on average compared to0.48W for Atom. Atom also finishes the boot process quicker, which helps it get to sleep quicker and also contributes toimproved power consumption.

    GPU power is a big contributor as well with Tegra 3 averaging 0.80W and Atom pulling down 0.22W.

    Launching Word 2013

    As another simple test, I looked at power consumption while launching Microsoft Word 2013 on both platforms:

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/boot-gpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/boot-cpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    11/30

    Here both tablets seemed to finish in about the same time but if you look at the power consumption graph you'll see thatthe W510 actually took a little bit longer. The difference wasn't great enough to really change the power profile: NVIDIAconsumed 0.60W on average for its CPUs, while Intel pulled 0.48W on average:

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/word-cpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/word-total.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    12/30

    Once again, there's a pretty stark difference on the GPU rail which makes me wonder if we're not looking at more than justGPU power here. Either that or Tegra 3's GPU implementation isn't all that power efficient compared to Imagination's. For the raw averages you're looking at 0.73W for NVIDIA compared to 0.23W for Intel.

    Page 4

    SunSpider 0.9.1

    Now the fun stuff. Doing power profiles of our standard benchmarks gives us good insight into how well each vendor wasable to balance peak performance and average power. In general it's ok to burn more power for a short amount of time aslong as it means you'll get to sleep quicker. This was one of the fundamentals of the first transition to mobile from the early2000s.

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/word-gpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    13/30

    We already know that Intel completes SunSpider quicker thanks to its improved memory subsystem over the Cortex A9,but it also does so with much better average power (3.70W vs. 4.77W for this chart). A big part of the average power savings comes courtesy of what happens at the very tail end of this graph where the W510 is able to race to sleepquicker, and thus saves a good deal of power.

    JavaScript Performance

    Time in ms (Lower is Better) Kraken SunSpider RIA Bench Focus

    Acer W510 (Atom Z27601.8GHz) 33220.9ms 730.8ms 3959ms

    Microsoft Surface (Tegra 31.3GHz) 49595.5ms 981.1ms 5880ms

    Samsung ATIV Smart PC(Atom Z2760 1.8GHz) 33406.0ms 721.3ms 3752ms

    Apple iPad 4 (A6X) 19086.9ms 834.7ms -

    Google Nexus 10 (Exynos 5Dual) 11146.0ms 1384.1ms -

    I also used SunSpider as an opportunity to validate the results from Intel's tablets with my own review samples. Togenerate this chart I measured power, every second, at the wall with both devices plugged in and with a fully charged

    battery. The resulting power consumption numbers include the efficiency loss at the AC adapter but the general curveshoud mimic the results above:

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/sunspider-total.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    14/30

    Note that the results do generally line up, although measuring at the battery gives more accurate results for the deviceand using the NI DAQ I was able to get better granularity on the power measurements.

    Looking at CPU level power consumption we see a very even match between Atom and Tegra 3. Intel's advantage reallycomes from being able to complete the workload quicker (0.52W compared to 0.72W on average).

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/sunspider-cpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/verify.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    15/30

    Once again we see a pretty significant difference in power consumption on the GPU rail between these two platforms.

    Kraken

    Mozilla's Kraken benchmark is a new addition to our js performance suite, and it's a beast. The test runs for much longer than SunSpider, but largely tells a similar story:

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/kraken-total.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/sunspider-gpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    16/30

    RIABench

    RIABench's Focus Tests are on the other end of the spectrum, and take a matter of seconds to complete. What we get inturn is a more granular look at power consumption:

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/kraken-gpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/kraken-cpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    17/30

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/riabench-cpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/riabench-total.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    18/30

    Page 5

    WebXPRT

    I also included Principled Technologies' new HTML5/js web test suite WebXPRT in our power analysis. Like the rest of the

    tests, Intel already outperforms NVIDIA here but does so with lower power consumption. A big part of the advantagecontinues to be lower power consumption on the GPU rail, surprisingly enough.

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/webxprt-total.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/riabench-gpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    19/30

    TouchXPRT

    As our first native client test, we turned to PT's TouchXPRT 2013. As there is no "run-all" functionality in the TouchXPRTbenchmark, we had to present individual power curves for each benchmark. The story told here is really more of thesame. On the CPU side, Intel is able to deliver better performance at lower power consumption. On the GPU side,performance is good enough for these tasks but once again, is delivered at lower power consumption.

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/webxprt-gpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/webxprt-cpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    20/30

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/touchxprt1-cpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/touchxprt1-total.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    21/30

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/touchxprt2-total.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/touchxprt1-gpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    22/30

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/touchxprt2-gpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/touchxprt2-cpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    23/30

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/touchxprt3-cpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/touchxprt3-total.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    24/30

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/touchxprt4-total.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/touchxprt3-gpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    25/30

    Page 6

    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 GPUis 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 runningthrough roughly the same play path.

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/touchxprt4-gpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/touchxprt4-cpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    26/30

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/3d1-cpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/3d1-total.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    27/30

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

    Page 7

    Wireless Web Browsing Battery Life Test

    For our final test I wanted to provilde a snippet of our 2013 web browsing battery life test to show what its power profilelooked like. Remember the point of this test was to simulate periods of increased CPU and network activity, that couldcorrespond to more than just browsing the web but interacting with your device in general.

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/wirelessweb-total.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/3d1-gpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    28/30

    Those bursts of power consumption are the direct result of our battery life test doing its job. That the tasks should takeroughly the same time to complete on both devices, making this a good battery life test by not penalizing a faster SoC withmore work.

    Note that the W510's curve ends up lagging behind Surface RT's curve a bit by the end of the chart. This is purelybecause of the W510's garbage WiFi implementation. I understand that a fix from Acer is on the way, but it's neat to seesomething as simple as poorly implemented WiFi showing up in these power consumption graphs.

    I always think about GPU power consumption while playing a game, but going through this experiment gave me a newfound appreciation for non-gaming GPU power efficiency. Simply changing what's displayed on screen does burn anappreciable amount of power.

    http://images.anandtech.com/reviews/SoC/Intel/CTvT3/wirelessweb-gpu.pnghttp://images.anandtech.com/reviews/SoC/Intel/CTvT3/wirelessweb-cpu.png
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    29/30

    Page 8

    Final Words

    Ultimately I don't know that this data really changes what we already knew about Clover Trail: it is a more power efficientplatform than NVIDIA's Tegra 3. I summed up the power consumption advantage in the table below (I left out the GPUnumbers since I'm not totally clear with what NVIDIA attaches to the GPU power rail on Tegra 3):

    Power Consumption Comparison

    Surface RT W510 Surface RT (CPU) W510 (CPU)

    Idle 3.182W 2.474W 70.2mW 36.4mW

    Cold Boot 5.358W 3.280W 800mW 216mW

    SunSpider 0.9.1 4.775W 3.704W 722mW 520mW

    Kraken 4.738W 3.582W 829mW 564mW

    RIABench 3.962W 3.294W 379mW 261mW

    WebXPRT 4.617W 3.225W 663mW 412mW

    TouchXPRT (PhotoEnhance) 4.789W 3.793W 913mW 378mW

    GPU Workload 5.395W 3.656W 1432mW 488mW

    Across the board Intel manages a huge advantage over NVIDIA's Tegra 3. Again, this shouldn't be a surprise. Intel's32nm SoC process offers a big advantage over TSMC's 40nm G used for NVIDIA's Cortex A9 cores (the rest of the SoCis built on LP, the whole chip uses TSMC's 40nm LPG), and there are also the architectural advantages that Atom offersover ARM's Cortex A9. As we've mentioned in both our Medfield and Clover Trail reviews: the x86 power myth has beenbusted. I think it's very telling that Intel didn't show up with an iPad for this comparison, although I will be trying to replicatethis setup on my own with an iPad 4 to see if I can't make it happen without breaking too many devices. We've also justnow received the first Qualcomm Krait based Windows RT tablets, which will make another interesting comparison pointgoing forward.

    http://www.anandtech.com/show/5770/lava-xolo-x900-review-the-first-intel-medfield-phonehttp://www.anandtech.com/show/5770/lava-xolo-x900-review-the-first-intel-medfield-phonehttp://www.anandtech.com/show/6522/the-clover-trail-atom-z2760-review-acers-w510-tested/4http://www.anandtech.com/show/6522/the-clover-trail-atom-z2760-review-acers-w510-tested/4http://www.anandtech.com/show/5770/lava-xolo-x900-review-the-first-intel-medfield-phonehttp://www.anandtech.com/show/6522/the-clover-trail-atom-z2760-review-acers-w510-tested/4
  • 7/29/2019 The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis

    30/30

    Keeping in mind that this isn't Intel's best foot forward either, the coming years ahead should provide for some entertainingcompetition. In less than a year Intel will be shipping its first 22nm Atom in tablets, while NVIDIA will quickly toss Tegra 3aside in favor of the Cortex A15 based 28nm Wayne (Tegra 4?) SoC in the first half of next year. Beating up on SurfaceRT today may be fun for Intel, but next year won't be quite as easy. The big unknown in all of this is of course whathappens when Core gets below 10W. Intel already demonstrated Haswell at 8W - it wouldn't be too far fetched to assumethat Intel is gunning for Swift/Cortex A15 with a Core based SoC next year.

    Here's where it really gets tricky: Intel built the better SoC, but Microsoft built the better device - and that device happensto use Tegra 3. The days of Intel simply building a chip and putting it out in the world are long gone. As it first discoveredwith Apple, only through a close relationship with the OEM can Intel really deliver a compelling product. When left to their own devices, the OEMs don't always seem to build competitive devices. Even despite Intel's significant involvement in

    Acer's W510, the tablet showed up with an unusable trackpad, underperforming WiFi and stability issues. Clover Trail hasthe CPU performance I want from a tablet today, but I want Apple, Google or Microsoft to use it. I do have hope that theother players will wake up and get better, but for next year I feel like the tune won't be any different. Intel needs designwins among the big three to really make an impact in the tablet space.

    The good news is Microsoft is already engaged with Surface Pro. It's safe to bet that there will be a Haswell versioncoming as well. Now Intel just needs an iPad and a Nexus win.

    http://www.anandtech.com/show/6355/intels-haswell-architecture/4http://www.anandtech.com/show/6355/intels-haswell-architecture/4http://images.anandtech.com/reviews/SoC/Intel/CTvT3/DSC_9155.jpghttp://www.anandtech.com/show/6355/intels-haswell-architecture/4