Intel Linux Driver Now Nearly As Fast As Windows OpenGL Driver

An anonymous reader writes "Intel's open-source Linux graphics driver is now running neck-and-neck with the Windows 8.1 driver for OpenGL performance between the competing platforms when using the latest drivers for each platform. The NVIDIA driver has long been able to run at similar speeds between Windows and Linux given the common code-base, but the Intel Linux driver is completely separate from their Windows driver due to being open-source and complying with the Linux DRM and Mesa infrastructure. The Intel Linux driver is still trailing the Windows OpenGL driver in supporting OpenGL4."

Comments

woo

[nomadic]

This should convince anyone that open source linux software can compete with windows, given 22 years.

Re:woo

[epyT-R]

This has little to do with the architecture and mostly to do with vendor support. This has always been a problem for non-windows OSes. Even apple's opengl isn't exactly the best in terms of performance. Linux easily outperforms it when using nvidia's driver.

Re: woo

[tysonedwards]

Microsoft blew its right foot off with Windows 8.
They went to the doctor to get it reattached with Windows 8.1 only to wake up to find out that a second left foot was attached in place.

Re: woo

[ericloewe]

Let's hope they get their right left foot replaced with a right foot in Windows 8.2.

Re: woo

[TheGratefulNet]

maybe windows 8.11, 'windows for podgroups'. not sure if that's an official project name or not...

Re: woo

[EMN13]

unless, of course, you count phones...

Re: woo

[mewsenews]

How does microsoft do so much user testing and have no idea these products are going to be colossal flops?

I can't imagine the reasoning that went on behind the push for Windows 8:

"Let's unify our mobile and desktop interfaces, because we have a stranglehold on the desktop, people will gravitate towards our mobile offerings"

The public responds "we hate this" and they choose to do it anyway? Don't they do focus groups? Didn't they anticipate that people are disgusted by a touch interface on their keyboard+mouse system?

I'm fascinated and horrified but I'm also pleased because I am not fond of Microsoft, but what the hell do they think they are doing?

Re: woo

[fuzzyfuzzyfungus]

Microsoft blew its right foot off with Windows 8. They went to the doctor to get it reattached with Windows 8.1 only to wake up to find out that a second left foot was attached in place.

Unfortunately, Win7's dual-left-foot support was actually pretty good; but was removed because you can't operate the imaginary ipad-killing tablet that Balmer dreams about with two left feet...

That's the weird thing about Win8: Vista, while a failure, at least had the decency to founder largely because everything kept from XP was antique and everything scrapped and rebuilt was immature. Win8 started out as a product that people (at least the Windows-using ones) mostly liked, and then was systematically mutilated until the release date. That takes talent.

Re: woo

[0123456]

I'm fascinated and horrified but I'm also pleased because I am not fond of Microsoft, but what the hell do they think they are doing?

Surviving. They don't believe the desktop will exist in a few years, so owning it won't matter.

Of course, if you go out of your way to destroy desktop Windows in pursuit of tablet market share, it becomes a self-fulfilling prophecy.

Intel

[Frosty Piss]

Someone smells a game plaform....

Re:Intel

[gl4ss]

oh they've been wanting to get into the game for a loong time now. pick any time between this and 10 years ago and they've always been one year from releasing a chip that could compete with atiamd/nvidia.

Re:Intel

[binarylarry]

True although look at the game console situations. In past generations the consoles used some PowerPC variant from IBM.

This time they're using x86 but not Intel. Intel has made a mint off the PC platform and now Valve is going to PCize the game console industry with SteamOS.

What do you think Intel's next move is going to be? What did they do when Microsoft did this to the PC market?

Re:Intel

[beelsebob]

Bear in mind that today's 5000 series actually does compete pretty bloody well with nVidia and AMD. It's near impossible to get a faster GPU in a thin and light laptop. The GeForce 740m is the same speed as it, the 750m is getting into power brackets that can't be put in a thin and light, and is only about 10-20% faster than the 5200 pro.

For me, Intel is doing a pretty impressive job of catching up. We've gone from intel being no where in terms of GPU performance to being able to equal the best nVidia and AMD can do at least in the power constrained market.

Re:Intel

[mrbluze]

We're also hitting diminishing returns with game graphics. It used to be generational differences between games was huge but these days can you really tell the different between this years shooter and last years shooter?

Barely.

You mean they might actually start to give a toss about playability?

Re:Intel

[Ardyvee]

For the trained eye? Sure. For the masses? No. The difference we'll see will be mostly in the little details (hair/fur, clothing [maybe we'll finally get clothing that actually behaves like clothing instead of a mesh on all characters], reflections and just generally better lighting, non-shitty water [it's coming, it's coming!], and just maybe we'll stop using sprites for beams and related) , and the amount of things in the scene (and their detail).

Re:Intel

[epyT-R]

We'll see what happens when games are no longer saddled by 2005 era gpu technology. When that happens, I suspect the gap between intel's best gpus and nvidias/amd's midrange will widen considerably. You can see this is already apparent in the graphs of that anandtech article. As rendering demands go up, the gap widens. Intel's integrated gpus just won't have the vram bandwidth that the dedicated cards provide, nevermind the raw fillrate. This is because of limited die real estate and power draw requirements compared with those discrete gpu competitors.

Have they gotten better? Of course. They're miles ahead of their old GMA9xx crapola..

Re:Intel

[DarkOx]

Intel my be looking at Linux as a "second tier" gaming platform. Steam may very well end up like the Netflix Streaming of video games, and Intel might be happy to have their CPU/GPU package in a low end Steam box.

My bet, and Steam as well as GOG are already showing this is there pretty good market for back catalog titles if you price them cheaply enough and make it super easy customers to purchase/install/play. That includes curating a catalog that will run on inexpensive modest hardware. You can also keep costs down not paying the Windows tax if you can make GNU/Lunux/Wine transparent to the user and work properly.

This is all gravy as far as the publishers are concerned. They are not generating any revenue off five+ year old titles otherwise if they grab additional revenue off their past work why would they pass it up. I don't think they risk cannibalizing their new release AAA catalog either if anything they will cannibalize the used market they don't seem to much care for anyway. So they will be on board.

Intel will be there to sell the chips, which Intel might be able to produce in their second class fabs rather than leasing them out again squeezing a little more revenue from prior investments.

Re:Intel

[Anonymous Coward]

Punctuation is what triggers the bug!!!

Re:Intel

[Bengie]

Geometry calculations scale with the cube of the number of polygons. Non-ray-tracing engine's days are numbers and ray-tracing is soon(tm). Ray tracing is O(1 K), where K is large, current engines are O(n^3 K) where K is small. N is becoming an issue.

Thank you Gabe Newell

[Dega704]

Hence why even non-gamers were so excited about Valve's gambit. Even with the few games released so far, it has brought tons of much-needed development effort to the areas GNU/Linux was lacking in. Imagine how things will be if SteamOS & Co. succeed and it becomes a major gaming platform. Free software purist or not, everyone is going to benefit.

Re:Linux DRM

[Guy Harris]

This is the problem with using DRM and other 3-letter acronyms in the article body; they become quite ambiguous.

Yup. Direct Rendering Manager, not Digital Rights Management.

(Having worked on Server Message Block protocol implementations, seeing "SMB" stand for "Small and Medium Businesses" gives my brain heartburn. :-))

Re:Well supposedly X is old and busted.

[Guy Harris]

So how come the new hotness of the Windows video system is only as good as this apparently old and knackered XWindows system

Did the tests in question go through the X server, or were they rendering images by directly talking to the graphics hardware and largely bypassing the X server, using the X server mainly for 2D stuff?

Re:What about for non-curernt hardware?

[DMJC]

Actually yes you will see a benefit. Every driver revision brings new OpenGL features which the older hardware supports. So if your card can render OpenGL 4.1 in Windows then it will eventually render OpenGL 4.1 on Linux. Optimisations that speed up the overall implementation of OpenGL apply to all generations of cards as long as they are non-hardware specific optimisations.

NOT neck and neck

[Sits]

The headline is bad/misleading - many of those benchmarks are showing a disparity of more than 10% between the drivers. Using the numbers from the Phoronix article, Linux results are the highest number from any Linux driver (there are many cases where the most recent driver was not the best) to try and prove headline:

Linux = [35.88, 140.90, 43.37, 23.5, 32.23, 19.17, 25.17, 16.68, 99.24, 63.94, 46.80, 29.46]
Windows = [41.47, 162.88, 36.57, 27.0, 31.46, 19.37, 24.47, 16.85, 104.04, 65.15, 55.05, 36.63]
for i in range(len(Linux)):
  diff = abs(round((1 - Linux[i]/Windows[i])*100, 1))
  "Windows win by %d.1%%" % (diff) if Linux[i] < Windows[i] else "Linux . win by %d.1%%" % (diff)

'Windows win by 13.1%'
'Windows win by 13.1%'
'Linux . win by 18.1%'
'Windows win by 13.1%'
'Linux . win by 2.1%'
'Windows win by 1.1%'
'Linux . win by 2.1%'
'Windows win by 1.1%'
'Windows win by 4.1%'
'Windows win by 1.1%'
'Windows win by 15.1%'
'Windows win by 19.1%'

So out of 12 results, 5 showed a 10%+ difference between Linux and Windows Intel drivers in favour of Windows and 1 showed a 10%+ difference in favour of Linux. The conclusion that the drivers are neck and neck does not follow from the premise for around 40% of the results and that's when being unfairly generous to Linux!