The most recent (Aug 17) distro is Linaro Precise 12.08 with your typical USB driver offerings... thus...
root@linaro-ubuntu-desktop:~# more /sys/bus/usb/devices/usb1/product
S5P EHCI Host Controller
root@linaro-ubuntu-desktop:~# more /sys/bus/usb/devices/usb2/product
EXYNOS OHCI Host Controller
but I will see if I can find out what the USB max speeds are; the ODROID-X has the same smsc chipset that the Pandaboard has for the network / USB stack combo...
is that more or less the HW powering the samsung galaxy S3?
(screen and radio sections excluded of course)
the performances of those little boards are getting interesting.
Another generation and they'll be the perfect entry level for inexpensive and tiny computing (netbooks and net-tops)
I just hope the performance per watt stays on the path of ARM tradition (i.e. way better than intel)
Ouch, if so, scratch this board too for NAS use.
Originally Posted by SolarNet
ARm vs Intel/AMD
It would be better this article if as benchmark you put a Intel/AMD similar in performance with the ARM results.
Someday ARM or ARM in arrays will be at our desktops.
Now it is at some servers, and benchmarking between ARM / Intel/AMD price + energy costs /performance are significative
Based on OpenSSL results, Tegra3 appears to be running at just 1.3GHz
In order to get usable benchmark results, just having a sane kernel + sane toolchain is enough (the distro is irrelevant). Looks like we are not there yet?
This is typically why I'd like to see such a benchmark. A9 is faster than Atom and its single-thread performance is higher. The only benchmark where I saw Atom faster is external memory bandwidth (and even then it was comparing a desktop Atom vs an A9 smartphone).
Originally Posted by brent
I noticed there are no compiler switches reported in the benches. Has that something to do with ARM or is it some triviality that slipped passed me?
EDIT: One possible triviality just occured to me, is it because it is being compared to older runs where compiler switches are not reported?
I believe that is the case... also, it does not look like it is posting the architecture info (and dmesg etc) to the OB systems directory. Will see if I can diagnose that as well on another benchmark run.
We now have the board hooked up to a WattsUp meter and it never jumps over 6W... it was running blogbench at 414% of CPU* at 6W for a second or 2... not stressing the memory simultaneously though so I will need to find a good benchmark for that. Indeed, it is tough to find a benchmark that stresses the whole system simultaneously.
* it was usually 398% or lower... not sure what to divine from a 414% usage... is there a Cortex-M in there somewhere? :)
Not hard really. Just run stream and dgemm with large datasets simultanously. If you want to include disk, it gets a bit more tricky to do it well I guess. You will find both in HPC Challenge (stream is in PTS too).
If you want to push power consumption make sure NEON is being used on the 4 cores. Video encoding/decoding with FFmpeg and 4 threads should do it :)
Originally Posted by SolarNet