The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis
by Anand Lal Shimpi on December 24, 2012 5:00 PM ESTWireless 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 profile looked like. Remember the point of this test was to simulate periods of increased CPU and network activity, that could correspond to more than just browsing the web but interacting with your device in general.
Those bursts of power consumption are the direct result of our battery life test doing its job. That the tasks should take roughly the same time to complete on both devices, making this a good battery life test by not penalizing a faster SoC with more 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 purely because of the W510's garbage WiFi implementation. I understand that a fix from Acer is on the way, but it's neat to see something 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 new found appreciation for non-gaming GPU power efficiency. Simply changing what's displayed on screen does burn an appreciable amount of power.
Facebook
Twitter
RSS
163 Comments
View All Comments
runner50783 - Monday, December 24, 2012 - link
This is why I don't care if you post your podcast on time : P, you guys are the best when it comes to technical analysis and reviews, you are the reference for the rest of the review sites, keep it up!Well, I guess graphics power may be the only advantage of tegra 3 over clover trail right now, and that may change with proper drivers too... Now it really makes little sense to have an RT based system, I feel bad for pulling the trigger on a Surface RT after playing with a Clover trail tablet, it was much faster on almost everything except games.
designerfx - Tuesday, December 25, 2012 - link
This is the first time in a long while that I've seen Anandtech declare that something which isn't accurately measured, is actually accurately measured and compared.I'm quite disappointed, honestly. 5th core on the Tegra is a significant part of what defines its power savings, and yet they're saying "Welp. It's about the same!".
I'm really questioning this a lot, Anand.
Deo Domuique - Thursday, December 27, 2012 - link
This is his yearly fat bonus by Intel :PAs for us, just ignore it and move on.
MrSpadge - Saturday, December 29, 2012 - link
What the ...?! If there's currently no way to enable the 5th core in Win 8, what exactly are they supposed to do? I'm sure Anand would love to repeat these tests if any way to fix this was available.. but right now that's how both devices perform. Call Tegra 3 crippled on Win 8 if you want, as that's what it apears to be.Activate: AMD - Saturday, December 29, 2012 - link
Whats the problem? They're comparing performance under the windows RT environment and Anand mentions on the very first page:"One last note: unlike under Android, NVIDIA doesn't use its 5th/companion core under Windows RT. Microsoft still doesn't support heterogeneous computing environments, so NVIDIA had to disable its companion core under Windows RT."
The only thing thats disappointing here is your inability to comprehend whats being tested.
Wolfpup - Thursday, January 3, 2013 - link
That would improve idle performance, but this is a real world test for the time being, and even still-Atom is more powerful, and yet uses less power, AND of course because it's more powerful, finishes doing work faster.Even if that fifth core were supported, this is still quite nifty.
The fact that I can, today, buy an actual x86 PC that can easily double as an iPad class ebook reader/light web browsing tablet is just amazing. (eInk's better, but you know what I mean).
Alexvrb - Thursday, December 27, 2012 - link
I'm not a huge fan of Tegra 3, but I wouldn't regret your Surface purchase too much. My dad has one, it's built better than any other tablet I've held. Plus Inte's solution is almost entirely unsatisfactory for 3D gaming. Intel is only using a single SGX 545 core. They clock it pretty high, but it isn't enough. The latest iPad uses a 4-core SGX 554 solution, and clocked right it seems to do pretty darn good on power too. Clocks aren't as high but it blows both the Tegra 3 and any ULV Atom out of the water.I'm not a huge fan of Apple either, but they generally use the most cutting-edge Imagination Technologies IP available. That might include Rogue (Series 6) in the next go around... Intel needs to get Series 6 in their chips ASAP.
Oh, and graphics drivers? Intel? Good luck! If this was Nvidia or AMD I might have agreed with you.
ssj3gohan - Monday, December 24, 2012 - link
This is really pornographic power electronics stuff. I do this stuff every day with my ultra-power efficient computer projects, but I didn't know that Intel walked around with this kind of a setup to show transparently what they are doing with power consumption.Good work, Intel. Now go and apply your knowledge to desktop platforms as well, because I'm kicking your ass here. I have yet to come across a desktop platform that cannot be made at least 50% more power efficient just through power electronics hacks.
madmilk - Monday, December 24, 2012 - link
Did anyone honestly think Intel, with a hundred times the revenue of ARM, would let themselves be devoured?Intel will still trouble entering the mobile device market because of the ISA lock-in ARM enjoys. On the other hand, ARM at this moment does not stand a chance in the (micro)server market either, especially as Intel increases its server Atom line.
tipoo - Monday, December 24, 2012 - link
Yeah, I think Intel will do fine and remain the 900lb gorilla in the mobile arena as well. ARM has the lead now, but once Intel has its sights set on something vital to its interests it tends to destroy the competition.