Quad-Core ODROID-X Battles NVIDIA Tegra 3

[phoronix]

Phoronix: Quad-Core ODROID-X Battles NVIDIA Tegra 3

While not as popular as NVIDIA's Tegra 3 ARM SoC, the Samsung Exynos 4412 quad-core ARM Cortex-A9 found on cheaply priced ODROID-X can actually outperform the quad-core NVIDIA ARM processor. Here are benchmarks of the $129 USD ODROID-X benchmarked against the NVIDIA Tegra 3 reference tablet and a PandaBoard ES running the Texas Instruments OMAP4460.

http://www.phoronix.com/vr.php?view=17793

[deanjo]

Hey Michael, next time you bench these boards can you please test the USB speed by doing a simple file copy test?

[DeepDayze]

Hey Michael, next time you bench these boards can you please test the USB speed by doing a simple file copy test?

What use that would be, unless its to check to see if the USB ports are USB2 compatible.

Nice board, so would love to see this as a nettop or even a micro-desktop box. With the performance this board exhibits it should do well for most audio/video stuff

[madjr]

What use that would be, unless its to check to see if the USB ports are USB2 compatible.

Nice board, so would love to see this as a nettop or even a micro-desktop box. With the performance this board exhibits it should do well for most audio/video stuff

maybe OUYA might consider this?

anyway i would love a future mk802 to be based on this.

[deanjo]

What use that would be, unless its to check to see if the USB ports are USB2 compatible.

Nice board, so would love to see this as a nettop or even a micro-desktop box. With the performance this board exhibits it should do well for most audio/video stuff

Why? Because many ARM boards have horrible USB throughput and well below their USB rated spec throughput and varies a lot from solution to solution.

[curaga]

Ethernet testing would be good too, because on many of these the ethernet is actually via USB, which causes huge cpu usage and also limits it to below even 100 Mbps. The Pi has it via USB, for example.

[ldesnogu]

Nice tests!

When will we see an Atom/Medfield vs Cortex-A9 battle again? I'm tired reading people claims that Medfield is faster even though I know it isn't

[brent]

Well, Atom often *is* faster than Cortex-A9, mostly because of high clock speed and good single-threaded performance. Cortex-A15 changes the game, though.

[artivision]

Well, Atom often *is* faster than Cortex-A9, mostly because of high clock speed and good single-threaded performance. Cortex-A15 changes the game, though.

No its not!!!

[schmidtbag]

Hey Michael, next time you bench these boards can you please test the USB speed by doing a simple file copy test?

Same here, I can't seem to get a direct answer if each USB port is its own host or if every one is shared by a hub. This is a big deal with boards like these.