XO battery/performance

[Richard A. Smith]

On 05/30/2012 03:34 AM, Yioryos Asprobounitis wrote:

>> If you want an idea of low-level performance, I can suggest
>> running LMBench.
>>
>
> Got the Debian lmbench_3.0-a7 source that compiles and runs fine w/o bitkeeper.
> Run the hardware part of the tests on the XO-1.5 (os880) and xo-1.75 (os12- correct kernel) with the same configuration.
>
> What was striking was that the XO-1.75 used 25% of the battery for 1 run while the XO-1.5 used 65% of the battery!

If you are going to do more of this then you really need a better tool 
than just the battery SOC measurement.  olpc-pwr-log can sample the 
information on a periodic basis and then my processing scripts can run 
through those logs and produce various reports.

All of my tools are in my olpc-pwrlogs repo

git://dev.laptop.org/users/rsmith/olpc-pwrlogs

Let me know if you are interested and want to know how to use the tools.

> Most of the test had empty values but the informative ones (below) show that the XO-1.5 is better in basic integer operations and memory bandwidth while the XO-1.75 is better in float and double operations as well as in memory latency.
> I'm not sure how much this means for real life usage :-/

I'm very suspect of this measurement.  The 1.5 has a hardware floating 
point unit and the 1.75 is still using soft-float.  Its extremely 
unlikely that the floating point performance on 1.75 is better than the 1.5.

-- 
Richard A. Smith  <richard at laptop.org>
One Laptop per Child