So I got to tinker with one of the miniand Xplus devices. About $100 lands you an A10 with 1gb of RAM and a HDMI output. Comes with android 4 and is very easy to get to run Fedora 17.
Under android this thing ranges down to 2 watts with wifi up, around 3 under moderate use and 4 watts with a reasonable browser load put on it (mjpeg streaming to firefox). All with wifi up.
My growing little "openssl speed" comparison now has another value point. For ciphers this A10 does about as well as an n9. For md5 shown below, it is the best cat in the camp by a good way:
The next tests will be the floating point and simd stuff, which is why I'm interested in the chip. One little discovery, the wifi seems to be very short range, the nexus 7 is happy to connect to one of my APs but I get the minix dropping the connection all the time to that AP from the same room. Don't let the cute aerial fool you it seems.
C++, Linux, libferris and embedded development. Yet another blog from yet another NARG.
Showing posts with label openssl. Show all posts
Showing posts with label openssl. Show all posts
Friday, October 12, 2012
Monday, June 18, 2012
More ARMses my precious!
Following up from my previous post using "openssl speed" to test the performance of little ARM based Linux machines, I now have OLPC, Cubox, Pandaboard, Xoom (Tegra2), and the little TP-Link 3020 (400Mhz) unit. Given the price of the 3020, it is quite a nice little computing device. The main limitations are 10/100 nic and 32mb of RAM. The Panda and Cubox numbers were generously contributed by suihkulokki in a comment to the last round of my numbers. It makes sense for the n9 to be faster than the others, since speed is a critical factor for such new phones.
Moving along to the Digest speeds below, it is interesting how well the sha1 speeds hold up for the tp-link device. And conversely how strange the numbers are for the Xoom running Tegra2/ICS. The suspicion is that the compiler plays a major role where too...
Hmm, Beagle Bone, Marvell 2Ghz ARM from a device like the QNAP TS-419PII would also be nice on the charts. hardware also accepted ;-p~~
Moving along to the Digest speeds below, it is interesting how well the sha1 speeds hold up for the tp-link device. And conversely how strange the numbers are for the Xoom running Tegra2/ICS. The suspicion is that the compiler plays a major role where too...
Hmm, Beagle Bone, Marvell 2Ghz ARM from a device like the QNAP TS-419PII would also be nice on the charts. hardware also accepted ;-p~~
Wednesday, June 6, 2012
An ARMs race, with a core i7 in there too for relativity
After doing some power benchmarking recently (1.2ghz kirkwood with gb net up = 5watts) I decided to work out how fast these arms can do useful work^TM. In the running is a Synology ds212j, DreamPlug running the Freedombox, Nokia n9 mobile phone, and an Intel 2600k just for working out where those relative numbers sit when compared to a desktop machine.
The above image shows the cipher performance of "openssl speed" across many machines. The 2600k is only single threaded, so could be many times faster in real world use by taking advantage of the cores. One interesting point right off the bat is that the 1.2Ghz kirkwood in the synology NAS is bested by the 1.0ghz CPU of the Nokia n9. Arms is not arms.
Removing the overload from the Intel i7 2600K from the graph we see that the Dreamplug is very close to the ds212j in terms of performance.
On the other hand, the digests show a distinct advantage to the Dreamplug setup. Again the n9 has a nice little lead on the others. Since a mobile phone can perform some useful work, one should perhaps also be demanding the NAS also offer handy features as well as just serving data blocks.
The RSA sign and verify graphs both show the same large slump for the ds212j unit. So for connection heavy workloads there would seem to be a large difference to the throughput you might get for the ARM you choose. On the other hand, the Dreamplug and ds212j both have similar performance on steam ciphers. So if connections are longer term then the difference will be less.
I would love to add benchmarks for the CuBox and QNAP 2ghz (TS-219PII) NAS units. It would also be interesting to use after market software on the ds212j and see the difference.
The above image shows the cipher performance of "openssl speed" across many machines. The 2600k is only single threaded, so could be many times faster in real world use by taking advantage of the cores. One interesting point right off the bat is that the 1.2Ghz kirkwood in the synology NAS is bested by the 1.0ghz CPU of the Nokia n9. Arms is not arms.
Removing the overload from the Intel i7 2600K from the graph we see that the Dreamplug is very close to the ds212j in terms of performance.
On the other hand, the digests show a distinct advantage to the Dreamplug setup. Again the n9 has a nice little lead on the others. Since a mobile phone can perform some useful work, one should perhaps also be demanding the NAS also offer handy features as well as just serving data blocks.
The RSA sign and verify graphs both show the same large slump for the ds212j unit. So for connection heavy workloads there would seem to be a large difference to the throughput you might get for the ARM you choose. On the other hand, the Dreamplug and ds212j both have similar performance on steam ciphers. So if connections are longer term then the difference will be less.
I would love to add benchmarks for the CuBox and QNAP 2ghz (TS-219PII) NAS units. It would also be interesting to use after market software on the ds212j and see the difference.
Subscribe to:
Comments (Atom)







