S3 Linux Driver Outperforms Its Windows Twin In Nexuiz 75
An anonymous reader writes "Chrome Center has done some benchmarks with the proprietary S3 Chrome 400/500 Driver on Linux and Windows. They compared Nexuiz frame rates on a Phenom II system with a S3 430 GT — the surprising result: The Linux driver outperforms its Windows equivalent, offering frame rates about twice as high on average. The question now: Is the Linux driver that good or the Windows driver that bad?"
Only Minimum framereat changes (Score:5, Interesting)
BBH
Re: (Score:2)
Yeah, I wonder how much of the difference is Windows+Nexuiz vs. Linux+Nexuiz, excluding the driver aspect.
Re: (Score:2)
Re:Only Minimum framereat changes (Score:4, Insightful)
What I'm interested in is a timeline of the benchmark. I want to see how long each run stays are maximum and minimum. I'm curious as to how consistent the framerates are for either OS.
Re:Only Minimum framereat changes (Score:5, Funny)
I thought it was the song that remains the same.
I must be getting old.
Re: (Score:3, Interesting)
Nexuiz is notoriously unoptomized in its model vertex count and perhaps other areas. I wouldn't be surprised if it's CPU bound in ways that other games aren't.
I would say the latter... (Score:3, Insightful)
Oh FP?
Re: (Score:2)
The windows driver is just that bad. It probably has tons of bloat and previous artifacts from older video drivers that were simply copy/pasted into the new one, with many obsolete functions, while the linux version was recently written from scratch and does not have that issue.
OpenGL is such a large API that it's possible that Nexuiz runs faster on linux since the linux drivers does a better job with some calls. Perhaps Nexuiz was one of the games the Linux devs used in their testing.
IOW, it's possible that the Windows drivers perform better on other games.
Re: (Score:2)
IOW, it's possible that the Windows drivers perform better on other games.
Like Nethack.
Although more seriously: Actually testing whether Windows drivers perform better on other games is rather unfeasible. True 1:1 comparisons are limited to games that exist onto both platforms (Doom, Nexuiz, BZFlag...). Anything else starts depends on the quality of WINE.
Graphic features? (Score:4, Interesting)
way back in Quake 3 days I thought Linux was running Quake3 faster than Windows on my nvidia card, only to realize the linux driver did not have one of the graphics features turned on, which caused it to run faster with the same in game settings.
Re: (Score:2)
The Vista graphics path is roughly the same as having compiz enabled under Linux. I wouldn't be surprised if the Linux benchmarks were with compiz turned off...
Most fullscreen games disable WDDM on Vista, but even if Nexuiz don't WDDM is not much of a performance hit as long as you got enough graphic memory for whatever WDDM needs + the game.
Hopefully in future versions of Windows it will be impossible to turn off WDDM.
Re: (Score:2)
Re: (Score:2)
Hopefully in future versions of Windows it will be impossible to turn off WDDM.
Ok, I know you meant Aero...
Why would you want that?
I'm using KDE4, and I love the ability to flip off the compositing on a whim. Maybe my video card just sucks, but I do notice that it makes fullscreen video and games smoother. I do sometimes find myself wishing that fullscreen games would automatically disable it, so I didn't have to remember to flip that switch myself -- although it is, literally, a toggle switch as a widget on my desktop.
It seems to me kind of like being glad Windows can't boot without
Re: (Score:2)
Why would you want that?
I got two monitors. On games that don't turn off aero I can use the secondary monitor to surf the web, and if that's impossible (some apps stop the mouse from going to the second monitor) alt+tab is much quicker. Also apps and games that turn off aero has to be closed to get aero back on - which means I can't pause a game and have the windows desktop behave the way I'm now used to.
It seems to me kind of like being glad Windows can't boot without a video card.
Windows can't boot wihout a video card?
Re: (Score:2)
On games that don't turn off aero I can use the secondary monitor to surf the web, and if that's impossible (some apps stop the mouse from going to the second monitor) alt+tab is much quicker.
Ah, I see.
On Windows, it actually bugs the hell out of me that games both insist on running on my "primary" monitor (the one with the taskbar, which ever it happens to be), and won't turn off the other one -- which is why I have a black desktop background on it. I see your point for games like MMOs, that I'd be playing a lot, and might want to have a guide or an IM window open -- but for single-player games like a Half-Life episode, I'd much rather not have the distraction.
On Linux, I tend to keep my MMOs i
Re: (Score:1, Troll)
Believe it or not, people actually try to justify this.
I presume by "justify" you mean "look at me funny and say 'why the hell do you care'" ?
However, it still seems moronic that I don't have the choice -- how difficult can it be to simply disable the graphical subsystem? Doesn't it kind of show that Windows was never meant to be a server OS?
No. Not in the slightest. Why would it ? Nobody except OCD, anal-retentive UNIX nerds would even give it a second thought, let alone expend effort trying to "f
Re: (Score:2)
I presume by "justify" you mean "look at me funny and say 'why the hell do you care'" ?
That's part of it, yes. You'd know the other part if you bothered to read the rest of my post.
Nobody except OCD, anal-retentive UNIX nerds
And embedded system designers. Not all of them are iPhones.
None of the "graphical stuff" in Windows is in the kernel.
No, I didn't say it was. However, I still don't know a way of running a desktop or server Windows OS without a video card.
Again: Why would this be at all difficult?
Re: (Score:2)
And embedded system designers. Not all of them are iPhones.
Here I was thinking we were discussing the retail versions of Windows.
Again: Why would this be at all difficult?
It probably isn't. However, you need to justify the development change itself (and the work involved), the QA, and support for both it, and all the stuff it breaks. Where's the payoff for that in making a group of people happy who would almost certainly never be your customers in the first place ?
Re: (Score:2)
you need to justify the development change itself (and the work involved), the QA, and support for both it, and all the stuff it breaks.
I'm including that under "not very hard". How much QA would you need? How much support -- and why not call it an unsupported feature? Is there really that much chance it would break anything, especially if left off by default?
Where's the payoff for that in making a group of people happy who would almost certainly never be your customers in the first place ?
That assumes you're right about "anal-retentive Unix nerds", which I'm disputing.
So your argument amounts to, it would be really easy, but they can't do it because they're a large company, which means any feature must serve a purpose, and costs quite a bit more than it should due to la
Re: (Score:2)
Internal laptop monitor? No, not really.
I suppose the CRT/LCD button might work...
Other reasons (Score:4, Insightful)
There should be benchmarks for how other cards perform as well. It could just be Nexuiz isn't performant under load on windows.
Vista (Score:4, Interesting)
Re: (Score:1, Informative)
Oh, yeah, Microsoft employees lurk here and sometimes get mod points. I almost forgot.
Re: (Score:2, Informative)
A moderation of Troll would have been correct. The comment introduces an unlikely culprit that doesn't apply in this scenario as an opportunity to gripe about something that isn't even on-topic.
Re: (Score:3, Interesting)
Why wouldn't it be DRM related? I don't know anything technical about this DRM and I am an anti-DRM zealot. ...And, it seems logical that no matter how well executed, DRM is an extra step on something (video output) that should logically imply some sort of cost for that extra step and if this is a very competitive field why shouldn't DRM have an impact?
Dogun just says that other cards should be compared which seems not to have anything to do with DRM... Unless this is the only card with DRM or something?
Ser
Re: (Score:3, Informative)
Why wouldn't it be DRM related? I don't know anything technical about this DRM and I am an anti-DRM zealot. ...And, it seems logical that no matter how well executed, DRM is an extra step on something (video output) that should logically imply some sort of cost for that extra step and if this is a very competitive field why shouldn't DRM have an impact?
Because the DRM is only active if you are playing back DRM-encumbered media with a DRM-capable player. I think it's reasonably safe to assume that neither
Re: (Score:3, Informative)
I note that the tests were done using windows vista. I wonder if this could have anything to do with the encrypted video path.
Only if this Nexuiz thing enables the Protected Path. Do you seriously think it does ?
About Nexuiz (Score:2)
The game's screenshots reminds me more of Unreal Tournament than Quake though. Has anyone here played it? What does it play like?
Re: (Score:3, Informative)
Nexuiz (2.4.2) plays like UT, a fast paced FPS. It is my favorite free linux game (not that anyone elses favorite is worse, but this one is mine).
The new version (svn) adds many features like teams and CTF, a better scoreboard, and is also much prettier (updated textures).
Re: (Score:2)
Re: (Score:2)
What is "translocator"?
There is still this "laser" weapon that allows you to rocket jump at a small sacrifice to your own health. But that is usually only useful for navigating the level, or maybe I'm just not that good.
Re: (Score:2)
Re: (Score:2)
Ohhhhhh, now I remember. No, they don't have that in nexuiz.
Re: (Score:1)
Nexuiz 2.4.2 does not have a translocator device. But, the latest version has a Porto weapon, divVerent the lead developer spent a long time last July and August writing the code for it.
Nexuiz 2.5 is about to be released.
Bunny hopping (Score:1)
Quake style bunny jumping is so off putting
Would it be as off-putting if the character models looked like cartoon rabbits or hares?
Re: (Score:1)
Nexuiz has had CTF for ever, as well as Key Hunt (my personal favourite) and lots of other game types. The only new game type added since 2.4.2 is Onslaught. Blub's new scoreboard is very good, the developers have added a team score element to CTF.
Nexuiz 2.5 is about to be released, although the developers keep on adding new features (shakes head). You can download the code and compile it yourself, it's very easy.
Re: (Score:2)
Then did they just add it to single player? Because I don't remember it being in the campaign for 2.4.2.
Re: (Score:1)
Re: (Score:2)
I don't like the physics system. There's too much sliding-- path dependency. Feels almost like Tribes/Legends*.
The grapple is a neat gameplay element, but the implementation is terrible-- the line from you to the grapple point jitters back and forth across the screen.
Legends is a free Tribes game; worth checking out.
Re: (Score:1, Troll)
You (yes, you) know (do you?), it's (well, it might not be, but who knows) really hard (not easy, at least according to me) to read (decypher) your post.
It could be even better if we had the source code. (Score:1)
Apparently, the drivers are supposed to be GPL, but no actual source was released. [phoronix.com]
Re: (Score:1)
Re: (Score:2)
It's funny you mention Nvidia since the open source version of the NFORCE drivers were so good that Nvidia tells people to use the in-kernel drivers.
yet another (Score:3, Insightful)
yet another meaningless statistic of "Program X runs better on System Y because driver Z is faster on said system"..
Frame rate twice as high.. (Score:1, Funny)
You mean it's 2fps instead of 1fps?
This is S3 we're talking about right?
Horrible stats (Score:1, Flamebait)
These statistics are useless. You can't just test one game and draw your conclusions to be that it's the driver.
At least test with more then one game you cherry picked because it gives faster speeds. That's the kind of shit Microsoft does.
I hope this author gets banned from slashdot because I fucking hate these kind of tactics.
Re: (Score:1)
Well if they have any sense, they'll realise that their products are more suited for nettops and netbook (lapbook?) type products, and a lot of these are using Linux because they're cheap devices that Windows adds too much cost to. So it's +$50 for XP, or $0 + desktop effects in Linux.
Of course a lot of this is dependent on their parent company VIA actually releasing Nano in meaningful quantities, and the current S3 graphics core getting into VIA chipsets (I think the chipsets are stuck at Chrome 3).
Obligatory bad car analogy (Score:4, Funny)
The S3 drivers for Windows and Linux are like a Ferrari and Lamborghini. Pretty close by themselves. But the Ferrari (Windows driver) is hitched to a trailer loaded with a backhoe (Windows).
Not surprising (Score:2)
Wrong question (Score:1)
The question now: Is the Linux driver that good or the Windows driver that bad?
Wrong question. In fact, that's not even a real question; it's just two sides of the same coin. The real question is whether the Linux driver performs better because it's coded better than the Windows driver, or whether it's because of some deficiencies in the Windows driver architecture, Windows graphics stack or the Windows OS itself. In other words, is this truly a case where Linux is better than Windows? Or is this just a case of one driver being better than another. If it's the latter (as the "questi