AMD Radeon Catalyst: Windows 7 vs. Ubuntu 12.04 LTS

[phoronix]

Phoronix: AMD Radeon Catalyst: Windows 7 vs. Ubuntu 12.04 LTS

Now having compared the graphics driver performance between Microsoft Windows 7 and Ubuntu 12.04 Linux for the NVIDIA driver with the GeForce GTX 680 and the multi-platform Intel performance for Sandy Bridge and Ivy Bridge, here's a look at the AMD Catalyst driver performance with the Radeon HD 7950 graphics card when running between Windows 7 and Ubuntu Linux.

http://www.phoronix.com/vr.php?view=17375

[mitcoes]

Ubuntu Studio is also LTE

It has a low latency kernel

Kernel that can be installed for testing

MS WOS has a 300 Hz kernel, Ubuntu a 100 Hz one, and Ubuntu Studio a 1000 Hz

As easy as:

sudo apt-get install linux-headers-lowlatency
sudo apt-get install linux-lowlatency
sudo update-grub

And of course use metacity instead of compiz for opengl benchmarks

All of this was said last MS WOS vs Ubuntu benchmarks

Why not improve this tests with this suggestions?

My Linux gaming is better with low latency kernels, and with Sabayon, but that is other article, opengl gaming performance between Ubuntu, Arch, Sabayon and Suse or Fedora with high and low latency kernels.

[bug77]

That's rather impressive for AMD, Radeon used to lag significantly behind on Linux.

[talvik]

Why not improve this tests with this suggestions?

There are literally thousands of variations that can be tested. Different kernels, compiler flags, window managers, distros, hardware, drivers...
If you combine every variation you will and up with millions of tests. You want low latency kernels, a kwin dev wants tests with 4 different compositor backends each with 3 different configs...

[kUrb1a]

I'm glad that AMD finally uped their game when it comes to gaming on Linux but theres a lot to be desired.Im also trying low latency kernel right now,...not playing well with kde.

[PsynoKhi0]

There are literally thousands of variations that can be tested. Different kernels, compiler flags, window managers, distros, hardware, drivers...
If you combine every variation you will and up with millions of tests. You want low latency kernels, a kwin dev wants tests with 4 different compositor backends each with 3 different configs...

Not to mention: how many poke around these options? I think this test is a fair "out-of-the-box" comparison. Which I guess is relevant for the intended audience of the benchmarked operating systems.
Also, submitting results to OpenBenchmarking is available to anyone. Wanna see tweaked benchmarks? Roll up your sleeves and get to it.

I second bug77's comment, I too would have thought the results would show a larger delta in windows' favor.

[F i L]

Not to mention: how many poke around these options? I think this test is a fair "out-of-the-box" comparison. Which I guess is relevant for the intended audience of the benchmarked operating systems.
Also, submitting results to OpenBenchmarking is available to anyone. Wanna see tweaked benchmarks? Roll up your sleeves and get to it.

I second bug77's comment, I too would have thought the results would show a larger delta in windows' favor.

It is a fair "out of box" for Ubuntu users (which, granted, makes up a large part of Linux users), but that's not entirely fair considering the recent Phoronix article showing Unity and KDE being significantly slower (in visual performance) than Gnome3, XFE, & LXDE. Linux Mint is very popular and sports a distro of all three (Cinnamon instead of Gnome3) as do many others. So I would like to see out-of-the box visual benchmarks with a Linux system that's geared towards higher visual performance.

I'm not sure why the author chooses to use Ubuntu over Arch or other build-it-yourself distros first (as a sort of peak performance case-senerio for Linux) and Ubuntu (with default settings) as a side comparison. Let people know what their machines are capable of with Linux, even if it requires a bit of tweaking or distro-switching to get there.

[efikkan]

It would be nice with a Direct3D comparison for the Unigine benchmarks, just as a reference to compare the healthiness of the OpenGL performance.

Otherwise, good work

mitcoes:
In your experience, how much does the low latency kernel impact the performance of different games/benchmarks?

[soupbowl]

@F i L

Go to http://openbenchmarking.org/ and do that yourself. Its already been explained 100 times why he does it the way he does it.
No matter what distribution he used or settings there would be more like you posting here crying he did not use a certain flag here
or tweak a setting there. Its about default installs, and arch's default is the prompt.

[kokoko3k]

@F i L

Go to http://openbenchmarking.org/ and do that yourself.

Are you going to pay him a windows7 license and/or the same hardware used in the test?
I'm asking just to make some sense to your reply.

Anyway, i still ask for benchmarks to be made without any WM and in fullscreen, even with the other default ubuntu configuration.