Ubuntu 12.04 vs. Windows 7: Intel Sandy/Ivy Bridge Loses On Linux

[phoronix]

Phoronix: Ubuntu 12.04 vs. Windows 7: Intel Sandy/Ivy Bridge Loses On Linux

Here's a comparison of the Ubuntu 12.04 LTS versus Microsoft Windows 7 performance when it comes to using Intel Sandy Bridge and Ivy Bridge processors with integrated graphics. While the Sandy Bridge graphics performance was once faster when it came to OpenGL with the open-source Linux driver, that's no longer the case. The Linux OpenGL performance for both Sandy Bridge and Ivy Bridge hardware is now slower in most GL workloads than Intel's Windows 7 x64 driver.

http://www.phoronix.com/vr.php?view=17314

[M1kkko]

The Intel OTC developers are certainly interested in improving the situation, and I have already gotten them eloped with Valve.

Well, that's good news.

[schmidtbag]

Perhaps these results would be more encouraging if the results from last year were shown. Also, I'd like to have seen something other than Ubuntu performing the tests. Wasn't Unity one of the worst performers of all DEs, including KDE?

[Tgui]

Perhaps these results would be more encouraging if the results from last year were shown. Also, I'd like to have seen something other than Ubuntu performing the tests. Wasn't Unity one of the worst performers of all DEs, including KDE?

Good points made.

[bongmaster2]

Ubuntu 12.04 vs. Windows 7: Intel Sandy/Ivy Bridge Loses On Linux is defintely wrong
im using ubuntu 12.04 with oibaf ppa on i5 2400m with an external monitor at 1920x1080 and i get 40fps in lightsmark. so lower gpu clock older kernel with less optimisations lower cpu clock and external monitor and i still get 25% more fps then you. 31.77 vs 40. illl test drm-next and will report back. btw i use unredirect fullscreen windows in compiz

[bongmaster2]

Ubuntu 12.04 vs. Windows 7: Intel Sandy/Ivy Bridge Loses On Linux is defintely wrong
im using ubuntu 12.04 with oibaf ppa on i5 2400m with an external monitor at 1920x1080 and i get 40fps in lightsmark. so lower gpu clock older kernel with less optimisations lower cpu clock and external monitor and i still get 25% more fps then you. 31.77 vs 40. illl test drm-next and will report back. btw i use unredirect fullscreen windows in compiz

export vblank_mode=0 does not make a difference.
adiitionally im using only 1333 mhz single channel ram. so another limitation in comparison to his desktop i5.
drm-intel-experimental kernel 3.4.0-994-generic did not gave a performance boost.im going to test xonotic now

[Sonadow]

Perhaps these results would be more encouraging if the results from last year were shown. Also, I'd like to have seen something other than Ubuntu performing the tests. Wasn't Unity one of the worst performers of all DEs, including KDE?

Most of the recent Linux users who switched over approximately 3 years ago or earlier are very likely to be using these heavyweight + feature-heavy DEs, and not lightweight / minimalist DEs such as LXDE or XFCE, or even barebones window managers such as OpenBox, TWM, Fluxbox etc etc.

Benching on heavy DEs such as Gnome 3, Unity and KDE 4 will offer the closest 'real-world scenario' results as opposed to doing the tests on a minimalist window manager. People want to see how much they can expect from Linux under a typical desktop load that consists of a flashy DE with compositing enabled, and not some 'best-case scenario' where everything is done off an unaccelerated window manager.

Same reason why power users and enthusiasts in Windows run those ridiculously heavy benching tools such as PCMark, 3DMark, FurMark etc etc with full Windows Aero effects enabled instead of falling back to the simple Win 2000-style Classic theme.

[schmidtbag]

Most of the recent Linux users who switched over approximately 3 years ago or earlier are very likely to be using these heavyweight + feature-heavy DEs, and not lightweight / minimalist DEs such as LXDE or XFCE, or even barebones window managers such as OpenBox, TWM, Fluxbox etc etc.

Benching on heavy DEs such as Gnome 3, Unity and KDE 4 will offer the closest 'real-world scenario' results as opposed to doing the tests on a minimalist window manager. People want to see how much they can expect from Linux under a typical desktop load that consists of a flashy DE with compositing enabled, and not some 'best-case scenario' where everything is done off an unaccelerated window manager.

Same reason why power users and enthusiasts in Windows run those ridiculously heavy benching tools such as PCMark, 3DMark, FurMark etc etc with full Windows Aero effects enabled instead of falling back to the simple Win 2000-style Classic theme.

That is absolutely true and I'm well aware of that. I'm also well aware that Michael probably uses Ubuntu as the standard reference linux distro (kinda like how you use distilled water as the reference for finding acidity, temperature, reactivity, and so on due to it being of the most common compounds) however, Ubuntu is no longer the most used distro - Mint is, and Mint doesn't use Unity.

I was aware of your comment before I even posted my first one, so the reason I posted it in the first place was because Ubuntu (and unity for that matter) are not the "standard" anymore, and because Unity and KDE performed notably worse than all other DEs, including the composited ones such as GNOME 3. That extra performance loss is about how much Linux lagged behind Windows, more or less.

[kraftman]

The Intel OTC developers are certainly interested in improving the situation, and I have already gotten them eloped with Valve.

Intel is out of the game when comes to gaming. AMD or nVidia comparison will be much more interesting.

http://www.tomshardware.com/reviews/...w,3121-21.html

[AJenbo]

Ubuntu is no longer the most used distro - Mint is, and Mint doesn't use Unity.

Are you getting yours stats from distro watch viewrings? Every survay i have seen sayes mit is rising but fare aways from overtaking.