The ARM vs x86 Wars Have Begun: In-Depth Power Analysis of Atom, Krait & Cortex A15
by Anand Lal Shimpi on January 4, 2013 7:32 AM EST- Posted in
- Tablets
- Intel
- Samsung
- Arm
- Cortex A15
- Smartphones
- Mobile
- SoCs
SunSpider 0.9.1
The results get more interesting when we look at power consumption during active workloads. We'll start off with SunSpider, a mid-length JavaScript benchmark that we frequently use in our reviews:
At the platform level, Qualcomm's APQ8060 powered Dell XPS 10 falls in between Surface RT and Acer's W510. Active power looks very similar to the Intel powered W510, but performance is appreciably slower so total energy consumed is higher.
Looking at the CPU, the situation changes a bit. Intel's peak power consumption is similar to Tegra 3, while Krait manages to come in appreciably lower. I suspect that missing the L2 cache power island here is lowering Qualcomm's power consumption by 100 - 200mW but overall CPU-only power consumption would still be lower. Once again, at idle Krait seems to have a bit of an advantage as well.
The situation changes once we look at GPU power consumption, with Intel/Imagination having the clear advantage here.
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:
At the platform level, Acer's W510 has slightly higher peak power consumption compared to the Dell XPS 10 but it also completes the test quicker, giving it a better overall energy usage profile.
Looking at the CPU cores themselves, Qualcomm holds onto its lead here although once again, I suspect the margin of victory is exaggerated by the fact that we're not taking into account L2 power consumption for Qualcomm. Intel does deliver better performance, which allows the CPU to race to sleep quicker than on APQ8060A.
The comparison to Tegra 3 is not surprising, this is exactly what we've seen play out in our battery life tests as well.
RIABench
RIABench's Focus Tests are on the other end of the spectrum, and take a matter of seconds to complete. What we get in turn is a more granular look at power consumption:
Here the W510 consumes more power at the platform level, but drops to a lower idle state than the XPS 10. Surface RT clearly uses more power than both.
Krait's CPU level (excluding L2 cache) power consumption is once again lower than Atom's, but Atom completes the task quicker. In this case total energy usage is still in Qualcomm's favor. The fact that there's a discrepancy between CPU specific power results and the total platform results are partly due to the missing L2 cache power consumption data from the CPU power chart for Qualcomm, and partly due to differences in the tablets themselves.
Facebook
Twitter
RSS
140 Comments
View All Comments
gryer7421 - Friday, January 4, 2013 - link
aaaand then looses where it matters, the rest of the platform. one more process shrink and both will be on even terms in cpu power usage and then as a whole platform will start punching arm in the face.Wolfpup - Friday, January 4, 2013 - link
Huh? Did you read the article? Atom built on 32nm is competitive with ARM built on 28nm. Not only that, but it's looking like Haswell will realistically be able to compete here too, and we've got the second gen Atom coming up this year too...but TODAY'S Atom at an older process is competitive with ARM...what you're claiming is exactly the opposite of what the article says.JumpingJack - Friday, January 4, 2013 - link
I don't think we are looking at the same data, overall Atom appears to uses the same or less power than Krait and offers better performance in general.Homeles - Friday, January 4, 2013 - link
"Anyone with half a brain" would read the article before making such an idiotic statement.Rezurecta - Saturday, January 5, 2013 - link
wow. Way to belittle Anand's hard work...Great article! One of the many reasons I love this site. :)
Death666Angel - Friday, January 4, 2013 - link
The Star Wars theme to play in my head! Thanks for that! :DDeath666Angel - Friday, January 4, 2013 - link
"I wonder what an 8W Haswell would look like in a similar situation."Me too. However, considering that they 17W ULV parts only reach those numbers by throttling as well, I don't expect a lot.
carancho - Friday, January 4, 2013 - link
Amazing work. Congratulations! A couple of presentation suggestions:Next time please smooth some of the most important charts. The volatility makes it hard to see where the averages are. Take this chart: http://images.anandtech.com/reviews/SoC/Intel/CTvK... it could really benefit to have another copy with some additional smoothing.
Also, in power charts like this http://images.anandtech.com/reviews/SoC/Intel/CTvK... it would be helpful to have as a summary followup chart the power calculation done and presented as bar charts; otherwise we have to resort to calculate the differences in the areas below the lines with our eyes, and they can be deceiving.
carancho - Friday, January 4, 2013 - link
I hadn't reached the A15 part yet when writing this. Ignore the 2nd comment.amorlock - Friday, January 4, 2013 - link
I'm frankly amazed and impressed that Intel can get Haswell down to 8W but it's hard to imagine it in a mid range mobile device because of the likely unit cost. The reason Atom has stagnated until recently is because Intel doesn't want to create a chip that cuts into it's very profitable mainstream CPU market.