ARM Cortex-A15 vs. NVIDIA Tegra 3 vs. Intel x86
Phoronix: ARM Cortex-A15 vs. NVIDIA Tegra 3 vs. Intel x86
Last week I shared some early benchmarks of the Samsung Chromebook while running Ubuntu Linux. The Samsung Chromebook is very interesting since it's one of the few readily available computers on the market employing an ARM Cortex-A15 processor rather than Cortex-A9 or other models. The Cortex-A15 found in the Samsung Exynos 5 Dual SoC proved to be very powerful and this Chromebook was quite a good deal with it being trivial to load Ubuntu Linux (and other distributions) while costing only $250 USD for this ARM-based laptop. In the past week I have carried out additional ARM Cortex-A15 benchmarks, including a comparison of its performance the the NVIDIA Tegra 3 quad-core ARM "Cardhu" tablet and several Intel Atom/Core x86 systems.
This is what it should have been from start. I used phoronix-test-suit to compare your benchmarks with mine (Core i3) to figure out the difference and I should say that ARM has come a long path. With Cortex A5X I think we will see something in the range of core series of Intel.
A suggestion: I know that you need some clicks to make enough funds to keep up your very good work (and I am grateful), but I really think you need to expand your reviews to be more through like Anandtech. One have to read a lot of your articles to grasp the idea of what is going on "in a single matter". In that case your site will be more worthy of citations! This way it is more of a go to phoronix and try to find the thing that you are looking for. Which most people won't.
That makes a quad-core A15 almost competitive with low-end Intel where massive parallelisation is possible, and probably significantly better for battery life. Can't wait to see how the ARM v8 cores compare.
That simply won't happen. Aside from needing the extra clicks due to ads to keep going, AnAndTech also has a much larger staff where they can devote more time to each article... Meanwhile, I single-handedly bang out every article on Phoronix.
Originally Posted by mmrezaie
This is really interesting. I wonder how the Apple A6 would do since it's after all the most powerfull ARM soc today. But I guess that would be difficult to test unless PTS is ported to iOS.
If I remember correctly the Exynos 5 has a TDP of 4 W compared to the Atom D525's 13 Watt, and yet the Exynos 5 is mostly faster. And again, it's not even the fastest ARM soc available. This is after Intel has spent several years developing the atom. I can't help to think that perhaps the x86 is too complex to ever be really power efficient.
Michael, to test the PPW, try using a CLI tool like dpms or xset to turn off the displays and calculate the power difference. I know there are other pieces of hardware like the motherboard that will increase wattage but overall that might be a 5W difference, which you can just inform readers.
Anyways, so much for Otellini's dismissive behavior of ARM. I knew his attitude was naiive.
I believe most of the support for Cortex A15 is going to arrive in Ubuntu 13.04, so it can probably do significantly better with Ubuntu 13.04 in benchmarks. I hope you'll do another series of benchmarks then, either with this or with whatever quad core A15 is in the market by then. I suspect the next ARM Chromebook will have that, too.
Exynos 5 is beast
Wow, Samsung Exynos 5 is beast!
Very good test!
I prefer dual core 2.5Ghz A15 to quad core 1.6Ghz A15.
I don't think we'll really see a dual core 2.5 Ghz A15 in the market, especially in phones. It's not really possible to do that at 28nm, and by the time you go with 20nm, it's already time to switch to Cortex A57, so you're better off using that. I think we'll even see dual core 3 Ghz Cortex A57 in 2015 or so, at 14nm. 3 Ghz ARM processors should be possible at 14nm, while maintaining the same low power level.
Originally Posted by Tempestglen