Slashdot Mirror
Steam Machine Prototypes Use Intel CPUs, NVIDIA GPUs
An anonymous reader writes "Valve has revealed their first Steam Machines prototype details. The first 300 Steam Machine prototypes to ship will use various high-end Intel CPUs and NVIDIA GPUs while running their custom SteamOS Linux distribution. The Intel Haswell CPU + NVIDIA GPU combination should work well on Linux with the binary drivers. Using a range of CPUs/GPUs in the prototypes will allow them to better gauge the performance and effectiveness. Valve also said they will be releasing the CAD design files to their custom living room console enclosure for those who'd like to reproduce them."
Valve is careful to point out that these specs aren't intended as a standard: "[T]o be clear, this design is not meant to serve the needs of all of the tens of millions of Steam users. It may, however, be the kind of machine that a significant percentage of Steam users would actually want to purchase — those who want plenty of performance in a high-end living room package. Many others would opt for machines that have been more carefully designed to cost less, or to be tiny, or super quiet, and there will be Steam Machines that fit those descriptions."
By using Intel or AMD, they'd be giving the finger to the GPU vendor with the clearly superior hardware. Some of use actually just want the best computing package and don't care so much about the open source religion.
Intel i3 is now a high-end CPU?
It runs some games faster than an 8-core AMD...
Their objective is to maximize and/or evaluate possibly maximal performance -- not make people feel good about the work they're doing for the open source/Linux community. Calm down.
sig: sauer
What GPU would be better for Valve's Linux based OS? Intel is irrelevant, AMD/ATI Linux drivers are far beyond terrible, and all the open source drivers have terrible performance.
If you've checked the latest benchmarks, Intel is becoming more and more relevant each iteration.
Intel GPU's are fairly decent midlevel performers these days AND the *official* Intel drivers are open source.
Personally, I can't wait until the GPU goes the way of the math coprocessor. Fuck dealing with Nvidia and AMD's awful driver support.
Mod me down, my New Earth Global Warmingist friends!
nVidia is the dad that works long hours, comes home tired, and doesn't play with his kid. AMD is the drunkard abusing his children. :(
If you want Linux 3D graphics that are:
1) As fast as you get on Windows.
2) Support all the latest OpenGL features.
3) Have a full implementation of the latest OpenGL spec.
4) Are solid and stable.
Then the binary nVidia drivers are it. Nothing else comes close. Well for games, particularly new games, this matters. They are making use of the high end features modern GPUs have, they need high speed rendering, etc.
If another company wants to step up their Linux game then great, but right now it is go nV or go home. Their binary drivers are just head and shoulders above the rest. That may not matter for typical desktop use when the card is doing little else other than some desktop composition and maybe accelerated video playback but it matters a lot if you are trying to make a game render using the latest OpenGL 4.3/4.4 features and have it extremely fast and stable.
It hasn't worked with the millions of chips purchased by OEM's such as Sapphire etc, why do you think Valve would succeed? Blind hope?
Hell, it took ages for them to fix some of the completely retarded requirements for accessing OpenCL interface on Linux, and that was with a lot of people in the HPC field(both users/potential customers and vendors/potential resellers) begging them on their bare knees. It's been almost a year since I last looked at AMD's GPU's for a client, but they might STILL have the completely idiotic requirement of having X running if you want to access the OpenCL interface(Something nVidia doesn't require....)
Whoa, you're right. AMD *is* screwed!
RUGBYRUGBYRUGBY
Nvidia hardware isn't really clearly superior to AMD.. they rotate on who has the best hardware at various price points.
But sure, the point is that this hardware should do a specific job for gamers at a specific price point, if Nvidia GPU's are the best bet for that in this product price segment there's no reason to be an ideological crusader about it. The point is to be able to play games, not make the average couch potato start writing driver code on his TV.
Valve's own statistics show that gamers tend to prefer nVidia hardware. Because this is going to run Linux there really isn't a good alternative anyway. Intel Graphics are still a joke and AMD's drivers are still terrible. As much as free software guys hate it, the nVidia binary blob driver is the best supported 3D graphics driver on Linux.
I read the internet for the articles.
If you have a gaming PC already, then just run steam and put it in Big Picture mode if you want the same experience. This is for people who don't have gaming PCs and/or want to play in the living room on their TV.
I read the internet for the articles.
Personally, I can't wait until the GPU goes the way of the math coprocessor.
Probably shouldn't hold your breath on that...
Nice fallacy, namely your assertion that commercial vendors actually do any work, especially after-the-fact... you know, like all the updates MS has made to the registry editor over the years, or the extensive CLI functionality, and let us not forget their impressively powerful and flexible search/scheduling options they built into Outlook. /sarcasm
You keep using that word ("you")... but I do not think it means what you think it means. I believe the word you're looking for is "I", because if your assertion were true, Ubuntu, CentOS, Debian, FreeBSD and many others wouldn't exist - or wouldn't exist as they do today - with a huge amount of software being continuously developed by people who are happy to keep doing it so they have the tools they want/need to do what they want to do.
Maybe *you* kept getting ripped off because you were doing it wrong. Meanwhile, I'm going to go have drinks with my buddies from Redhat who get paid perfectly well.
"Inveniemus Viam Aut Faciemus" 'We will find a way... Or we will make one!' --Hannibal of Carthage
Other than promoting Linux, why do I want
I'm gonna stop you right there -- you're assuming this is for you. Well, it's not. It's for people who do have a use for this stuff, like e.g. people who want a good PC to play PC-games on and want it to be useable from the couch with a controller, but who don't want to have to go through the hassle of building one themselves.
Why?
Yep, good point. That's why I use Nouveau at home. But again, remember, this is a gaming device -- and a beta release one at that. They're after benchmarks, and their primary objective is to legitimize the Steam Box as a viable gaming device to the gamers -- people who have a particular interest in performance, not long term open source altruism.
sig: sauer
Nvidia hardware isn't really clearly superior to AMD.. they rotate on who has the best hardware at various price points.
But sure, the point is that this hardware should do a specific job for gamers at a specific price point, if Nvidia GPU's are the best bet for that in this product price segment there's no reason to be an ideological crusader about it. The point is to be able to play games, not make the average couch potato start writing driver code on his TV.
Not on Linux. nVidia consistently outperforms AMD, and is significantly more stable. And they have been actively working with Valve for quite some time to fix some show-stopping driver bugs.
I wouldn't consider drivers a serious issue. If Valve goes to AMD/ATI and says 'We'll buy a hundred thousand chips for the first production run, with potential sales of fifteen million to follow' I'm sure improved driver support would quickly follow.
Actually, nVidia has been actively working with them for over a year now fixing some significant driver bugs. And they haven't bought anything yet.
Intel is starting to plateau in the CPU business (they have no real competition), so I wouldn't be surprised if they looked at the current market and decided to put serious effort into the GPU biz.
They already have a loyal enthusiast following.
Mod me down, my New Earth Global Warmingist friends!
Midlevel? For non-gaming usage, perhaps. For gaming they're strictly low-end, or unusable.
There are three Intel GPUs on the desktop side - the HD 4600, the Iris 5100, and the Iris Pro 5200. In raw processing power, the first gets you 430GFLOPS, and the latter two get 830GFLOPS. For comparison, the *weakest* GPU in these Steam Machines pumps out 1880GFLOPS, and the top end maxes out around 4.5 TFLOPS.
And that's a spec that's biased towards Intel - they're more compute-heavy than bandwidth-heavy, and unfortunately most graphics tasks are bound by memory bandwidth. For Intel, the first two have a mere 25.6 GB/S of bandwidth, with Iris Pro adding an on-chip cache to bring it up to 75GB/S. But even the GeForce 660 beats that at 144GB/S, and the Titan doubles that. For those who may not be familiar, the 660 Ti (and the new-gen rebadge-with-enhancements, the 760) was considered a good medium-end card, with the vanilla 660 being for those a bit more budget-minded. The Titan, of course, is their "luxury" card, costing a full $1000, but it's currently the most powerful single-GPU card, period.
That's just their theoretical performance - the real test, of course, is actual game benchmarks. Nvidia is currently the best at getting the most performance from their hardware in actual games. AMD has more raw power, but their drivers aren't as efficient so Nvidia beats them more often than not. Intel's far worse than either - while Iris Pro should be able to go head-to-head with a GeForce 650, it actually tends to benchmark closer to the GeForce 640. Go look it up on Anandtech, if you're interested.
Now, is it impressive how much power Intel managed to get out of an IGPU? Yeah, it is. Honestly, I would be interested in seeing them scale up the design further - go from 40 EUs to 200 EUs, bolt on the memory controller from the Xeon Phi, and sell it as a dedicated card. Might be something they can do with the 22nm fabs once they move to 14nm? But in any case, calling their current offerings "medium-end" is misleading at best, and downright wrong at worst.
Actually, if you just look at the specifications, ATI/AMD has almost always had the (theoretically) most competitive hardware (GPU-wise), both in terms of performance/price ratio and often even in terms of raw computing power/memory bandwidth. AMD was even the first to come out with hardware support for compute on GPU (the first CTM/CAL betas came out before CUDA was ever mentioned anywhere), even if it required assembly progamming of the shaders (which you could often do without by using a layer such as BrookGPU).
However, their GPUs have been crippled by the most horrible software ecosystem possible. By and large the main culprit is ATI/AMD itself, who has constantly failed at producing high-quality, stable drivers and capable compilers for their shaders. A secondary culprit (which has finally been removed from the equation) is the architecture itself: up until the introduction of GCN, AMD shaders had a VLIW architecture (VLIW5 first, VLIW4 in the last releases before GCN) which were often not easily exploitable without heavy-duty restructuring and vectorization of your shader code: so you often found yourself with huge horsepower available, while only be able to exploit some 30-60% of it at best.
"I'm never quite so stupid as when I'm being smart" (Linus van Pelt)
The Dolphin Emu guys did a nice review of current OpenGL implementations.
Quick what do BSD,OSX,Solarius, Windows, and OS/2 have in common that Linux does NOT have? Why a stable ABI so that GPU makers don't HAVE to constantly crap out drivers to fix what Linus Torvalds breaks this week!
Bullshit, none of those listed has a stable ABI, for example the windows driver ABI changed from XP to XP64 and of course Vista and forwards, with a crapload of drivers no longer functioning as a result (the 'compability mode' sucks in general but even more so for drivers).
And since you don't have the source code to Windows drivers (99% chance they are proprietary) and the hardware vendors want you to buy new hardware instead of using your old they see this as a great excuse to drop support (cue the Vista driver fiasco), a ton of fully functioning older hardware was effectively deprecated when users moved from XP to Vista/Windows 7.
Windows gets support for all new hardware from vendors due to it's desktop monopoly, what has a more stable ABI benefited OSX, Solaris, OS/2 in terms of driver support? None of them has near the driver support Linux enjoys.
tell me can YOU take the driver that AMD or Nvidia released in 2008 and install it on the latest Linux with ZERO fuss or muss?
Beyond those two GPU drivers I never even have too, practically everything else is supported out-of-the box. Meanwhile those proprietary drivers are just a package manager command away, and automagically updated when I update the rest of the system. So I don't need no driver from 2008, thanks anyways.
Now its a bad joke. the ONLY reason you have any working drivers AT ALL is that companies like Nvidia shell out the ass for a dev team to do nothing but fix Torvalds messes!
Are you high? Are you equaling two discrete GPU drivers with 'any working drivers AT ALL' ?
Furthermore you seem to think that the proprietary vendors have to rewrite their entire drivers when the ABI changes, typically they need to make some changes to their shim code.
And the sad part? the part that just sticks it in and breaks it off? it was NOT done for design reasons, NOT done because he thinks its better on memory, or CPU or anything else, nope it was done for POLITICAL reasons!
It is PRACTICAL, as a proprietary driver is nothing but a black box which means it can't be fixed, debugged nor vetted against security issues, and then we have the fact that open source drivers can then be supported on all architectures where Linux runs (which is basically EVERYTHING), and not just the architectures which the proprietary vendor sees fit to support.
So yes it is by DESIGN. It is designed to be difficult (or at least not easy) to develop proprietary drivers against the kernel as it gives nothing but problems (again PRACTICAL) to the kernel developers and they want to make it clear that they don't want to support proprietary out-of-tree drivers.
And this 'hard stance' has delivered in droves as Linux has a staggering amount of hardware support out of the box, nothing else comes close, the only real holdouts these days are those discrete GPL vendors like NVIDIA and to a lesser extent AMD, meanwhile both NVIdia and AMD has recently started/increased their commitment to provide documentation for open source drivers, so things are moving in the right direction here aswell.
This in turn also helps the entire open source ecosystem, as open source drivers can be ported to other systems aswell, systems which would never see an official proprietary driver.
And finally it just makes sense, why the f*** should I be prevented from using the HARDWARE I BUY in the operating system of my choosing just because the hardware vendor doesn't find it worthy of support?
You can keep your proprietary-friendly, more stable driver ABI. I'll take open and thus: debuggable, improvable, security-examinable drivers (heck, entire system actually) and the largest-by-far hardware support out-of-the-box.