The First NVIDIA GeForce Benchmarks On The SteamOS Beta

[ninez]

This is quite understandable because Valve has modified Linux kernel with real time patches. Generally realtime kernel have lower latency but also lower peak performance.

Hopefully Michael will test SteamOS with unmodified 3.10 kernel. This should reveal what is the effect of the modifications.

Yes and no / it's probably more complicated than that / won't reveal anything really all that useful.

By default on -rt, most of your (threaded) IRQs are going to have a default rtprio of 50FF(fifo) - hence why 'rtirq' was made and/or people set those threads manually... All IRQs defaulting to 50FF isn't suitable at all and i doubt Valve would leave them as such (since that would have a negative impact on performance).... i also doubt Michael changed any of these settings - otherwise he would have mentioned it... Also, I am not sure how many HZ Ubuntu's kernel sets the kernel's tick too? (I believe Archlinux does 300HZ by defualt, while mine on RT is 1000HZ)...

if Ubuntu's is set to 300HZ, that may explain some of the difference, as SteamOS is set to 250HZ in it's kernel configuration file.

I think the only good way to reveal differences between their kernel and an unmodified, would be to have a SteamBox (which would be 'ideally configured' by Valve) and do the comparison there. (or if Michael can get some info on tuning his machine, as they would / get some useful pointers - then you might be able to get closer performance/accuracy)... I've been through all of SteamOS's kernel sources, kernel configs, etc. I've 1. diff'd their linux-rt patch against upstream 2. compared modified steam kernel (without RT applied, but with aufs and other bits applied) to Vanilla 3.10 and 3. inspected their debian source packages, as well.

[justmy2cents]

This is quite understandable because Valve has modified Linux kernel with real time patches. Generally realtime kernel have lower latency but also lower peak performance.

Hopefully Michael will test SteamOS with unmodified 3.10 kernel. This should reveal what is the effect of the modifications.

i might be wrong here, but big part of why they use modified kernel would probably be other reasons like input latency and sound (maybe graphics too, i trully don't know as this is just my guessing). sometimes games run visually fine and dandy, but when you try playing input lag is insufferable. killzone 2 prepatch on ps3 for example run steady (and damn beautiful) 30fps, but when you tried to shoot... lag. when you see this you kinda wish graphics would stutter instead of input. as long as game can provide 30fps, input latency will become defining factor on how playable it is. and it was not only killzone 2 on ps3. the bluetooth adding its own toll forced me to use my controller as wired in whole lot of games just to prevent my self from throwing them into trashbin. and with time, i never went back to unplugged version same as i'll never buy wireless controller again.

but, hey that is just me

[justmy2cents]

great benchmark. just one suggestion for "compare your own" part of article.

benchmarks would be much more informative if they were produced for valve proposed specs instead of bunch of graphics cards. that way anyone could see how his machine stacks against valves vision of "steambox". you could stick titan in pc with different bottleneck and still suffer terrible result. benchmark for complete spec on the other hand gives much clearer result

[hjhamala]

Comparing with previous benchmarks, the Steam was not higher.

This is quite understandable because Valve has modified Linux kernel with real time patches. Generally realtime kernel have lower latency but also lower peak performance.

Hopefully Michael will test SteamOS with unmodified 3.10 kernel. This should reveal what is the effect of the modifications.

[fedesog]

And impossible, unless you somehow control Microsoft, has 3DMark is based on DirectX.

Futuremark itself said, in their forum, they were keeping an eye on Valve back in February when Steam for Linux was released and I remember they actually pointed out that they follow directions of hardware companies more than software companies. Steam Boxes will be produced by hardware companies that will need something to prove that their version of Steam Box is faster than the one from the competition so as 3DMark exists on Android/iOS it will probably end up on Linux as well, maybe not soon but definitely not never.

[Andrecorreia]

3dmark existes for android

And impossible, unless you somehow control Microsoft, has 3DMark is based on DirectX.

3dmark existes for android

[winnitro]

Disappointed

Comparing with previous benchmarks, the Steam was not higher.

[iniudan]

Having 3DMark in Linux would definitely be useful!

And impossible, unless you somehow control Microsoft, has 3DMark is based on DirectX.

[M@yeulC]

As shown by other recent Phoronix tests (and more tests coming this month), Intel Haswell graphics with Mesa 10.0+ should be in fairly good shape for handling most Source Engine games.

Sure, but I thought that SteamOS only ships with mesa 9.2.2, with some valve custom changes :

Package: libglapi-mesa
Source: mesa
Version: 9.2.2-1+steamos1+bsos1
Architecture: i386
Maintainer: Debian X Strike Force <[email protected]>
Installed-Size: 170
Pre-Depends: multiarch-support
Depends: libc6 (>= 2.3.6-6~)
Multi-Arch: same
Homepage: http://mesa3d.sourceforge.net/
Priority: optional
Section: libs
Filename: pool/main/m/mesa/libglapi-mesa_9.2.2-1+steamos1+bsos1_i386.deb

Anyway, I am looking forward to see your next benchmarks. Keep on, Michael

[fedesog]

Thanks for the benchmarks. A comparison SteamOS vs other distros could be interesting although I actually don't expect much difference, I just checked the benchmark numbers for Unigine Engine on a GTX680 from the Ubuntu vs Win8 article (July) and they are basically the same.
I actually curious about comparison SteamOS vs Windows from other editorials (I just read that Ars is preparing one), not really to see the actual difference in performance but to see which games they are going to use as benchmarks. While they are probably not limited by an automated procedure the number of games with benchmarking functionality is quite limited compared to windows, actually the majority of games I see in windows reviews are not on Linux at all, including synthetics benchmarks. Having 3DMark in Linux would definitely be useful!