AMD Catalyst Is the Broken Wheel For Linux Gaming

An anonymous reader writes: Tests of the AMD Catalyst driver with the latest AAA Linux games/engines have shown what poor shape the proprietary Radeon driver currently is in for Linux gamers. Phoronix, which traditionally benchmarks with open-source OpenGL games and other long-standing tests, recently has taken specially interest in adapting some newer Steam-based titles for automated benchmarking. With last month's Linux release of Metro Last Light Redux and Metro 2033 Redux, NVIDIA's driver did great while AMD Catalyst was miserable. Catalyst 14.12 delivered extremely low performance and some major bottleneck with the Radeon R9 290 and other GPUs running slower than NVIDIA's midrange hardware. In Unreal Engine 4 Linux tests, the NVIDIA driver again was flawless but the same couldn't be said for AMD. Catalyst 14.12 wouldn't even run the Unreal Engine 4 demos on Linux with their latest generation hardware but only with the HD 6000 series. Tests last month also showed AMD's performance to be crippling for NVIDIA vs. AMD Civilization: Beyond Earth Linux benchmarks with the newest drivers.

Comments

ATI/AMD has had shitty drivers for 20 years

[msobkow]

ATI's drivers sucked in the '90s. They sucked in the '00s.

Why, praytell, would we expect them not to suck in the '10s?

Re:ATI/AMD has had shitty drivers for 20 years

[red_dragon]

Because they do have a tendency to improve. Jerry Pournelle used to write regularly about his problems with ATI cards in his column on BYTE. They typically followed the same pattern: install new card; install drivers; see computer crash regularly; upgrade drivers; see computer crash less often; upgrade drivers again; see computer run more or less stably.

Then he'd upgrade to the next shiny ATI card and do it all over again, since the new drivers bore little resemblance to the old ones.

Re:ATI/AMD has had shitty drivers for 20 years

[Mashiki]

Don't worry, Nvidia has had shitty drivers for the last 6 or so. So they're catching up. Otherwise there wouldn't have been that series of nvidia drives that cause incorrect fan throttling that burned up cards. Or the problem with TDR's that plagued the 299 through 330's, that's only two years worth. And of course the problem with those drives was so bad that they were paying for PC's to be shipped to California for testing. Of course that particular problem revolved around voltage issues, and the cards being forced into a lower-voltage setting that would cause the card to become unstable. That was their solution to overheating. And then of course we've got the on-going problem with firefox and hardware acceleration on the cards, either causing corruption of the browser, or right up crashes. Then there was the drivers that caused hardlocks on 400,500,600,700 series cards.

I say all of that as someone who's owned 22 nvidia cards over the last 15 years. It was the TDR problem that broke it for me, and I switched to AMD after having swore them off in the 90's. I haven't looked back, and am happier with my 7970.

Re:ATI/AMD has had shitty drivers for 20 years

[HBI]

ATI's hardware was fine hardware back in the day, but their software was regrettable. My first card was an ATI EGA (!) Wonder 800 back just before third-party VGA hit the streets. Then I had a VGA Wonder. Both were fine cards. The 8514/A compatible ATI card was also delicious. Then things headed downhill.

I see no reason to buy their equipment anymore.

Re:ATI/AMD has had shitty drivers for 20 years

[brxndxn]

AMD is most certainly not a shit company ~ you have a shit opinion. AMD was pounded into the ground financially by Intel competing unfairly when AMD had the clear performance advantage. Intel made their agreements so companies like HP would actually save money if they went 100% Intel even though the market was clearly calling for AMD processors. This was made obvious when AMD offered to give free processors to HP and HP still refused. Since Intel is basically a monopoly and our regulatory agencies are run by ball-less cowards, AMD has a tiny research and development budget compared to both Intel and Nvidia. AMD continues to exist with research money being their only real limitation. History shows that AMD can create processors that outperform Intel with less than a quarter of Intel's research budget. AMD has nowhere near a quarter of Intel's research budget at the moment. As far as ATI/Nvidia competition, Nvidia tends to make things as proprietary as possible while AMD makes them more open. AMD's graphics hardware tends to be more advanced while having a simpler design than Nvidia. However, AMD's very limited software/driver development budget keeps AMD graphics cards performing less than optimally. Further, my experience of gaming on Linux a few months ago gave me no issues with the Metro 2033 Redux and my Radeon 7970.. so I am going to take this 'benchmark' with a grain of salt. Perhaps the latest driver is slow or has a bug - but they do tend to get fixed from my experience. Even if you hate AMD as a company, you can thank them for the reasonable prices of CPUs and graphics cards. Without AMD, both become extremely expensive.

Re:ATI/AMD has had shitty drivers for 20 years

[Torp]

I agree with you about the unfair treatment of AMD, but Linux graphics drivers have been shitty since Ati was an independent company. Just get a NVidia card if you want 3D in Linux. Inquire about Ati in another 5 years.

Re:ATI/AMD has had shitty drivers for 20 years

[binarylarry]

Are you high? Nvidia's linux drivers have been the gold standard on the platform for years...

Re:ATI/AMD has had shitty drivers for 20 years

[ihtoit]

my first offboard GPU was a 4MB Rage Pro - which I've still got, have since upgraded it to 8MB with the simple addition of a SODIMM. It read 16MB as 8MB and ran OK if slow, it read 8MB and ran as fast as with the base 4MB but was unstable as hell, so I did some hunting and found a 4 and used that.

Re:ATI/AMD has had shitty drivers for 20 years

[CajunArson]

Pray, could you tell me about how Intel "illegally" pounded ATI -- you know, the discrete graphics card company -- into the ground illegally? I know that way way back in the day, long before AMD's very ill-advised $6 Billion boondoggle buyout -- that Intel tried to launch a discrete graphics card, but it didn't go anywhere and didn't seem to phase Nvidia, AMD, or 3dfx (yes, it was THAT old) in the slightest.

P.S. --> If Big Bad Intel was really that Big & Bad at "pounding" AMD, then where did AMD get that $6 Billion for a massive buyout of ATi in the first place??

P.P.S. --> Why is it that Nvidia, ARM licensees, and everyone else seem to have no fear of Intel, but whenever it comes to AMD the only thing we hear are these made-up persecution fantasies? Is everyone else... or maybe is it just AMD?

Re:ATI/AMD has had shitty drivers for 20 years

[ihtoit]

my laptop runs Compiz Fusion just fince, thank you.

And it's an AMD APU.

Re:ATI/AMD has had shitty drivers for 20 years

[Gliscameria]

Informative or Insightful just aren't sufficient. There needs to be a "Spot On" modpoint for comments like this.

Re:ATI/AMD has had shitty drivers for 20 years

[Mashiki]

Except that the parent poster wasn't talking about 'nix drivers. They were talking about drivers in general...but I could see how that's confusing.

Re:ATI/AMD has had shitty drivers for 20 years

[TFlan91]

byte.com -> http://www.informationweek.com... -> 404...

Such a shame

Re:ATI/AMD has had shitty drivers for 20 years

[sconeu]

Aren't Nvidia's drivers identical for both Win and Linux? I thought the binary blob was the core of the Windows driver.

Re:ATI/AMD has had shitty drivers for 20 years

[Enry]

AMD was the only company directly competing with Intel on the desktop/server markets. NVidia and ARM were embedded or other and thus didn't compete directly. Remember that the only reason we're still using x86 hardware instead of Itanium is because AMD bolted 64-bit on and it became a hit. Enough so that Intel uses it now.

AMD likely has (well had) cash from all the other things they did, just like other chipmakers.

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

Bah. The Graphics Solution is where it's at! Glorious CGA rendered on monochrome!

Re:ATI/AMD has had shitty drivers for 20 years

[HBI]

I never had one, but did it have the delicious CGA snow? (related to refresh)

Re: ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

Otherwise known as Windows 8.

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

Oh man, memories... I think I still have a box with a dozen or so Rage3d cards in it somewhere, they were so common back then, and were great to just have to toss into a server for a console. Definitely wouldn't use them for gaming in this day and age, but I've kept them around for some reason - as a basic video card to toss in to a linux/bsd server, etc, if the on-board video dies.

Re:ATI/AMD has had shitty drivers for 20 years

[Wootery]

As far as ATI/Nvidia competition, Nvidia tends to make things as proprietary as possible while AMD makes them more open.

Correct: CUDA, SLI, Physx, G-Sync, Shield Portable/GRID. AMD tend to either hop on board the open follow-up technologies (OpenCL, OpenGL compute shaders, DirectCompute) or create their own technologies which tend to be more open (FreeSync, Crossfire).

Mantle is an interesting one: it's open, but Nvidia aren't interested. This seems kinda reasonable: Mantle seems to have served well as a wake-up call that it's possible to create more efficient graphics APIs, so we can expect the next-gen OpenGL and Direct3D APIs to catch up to Mantle and far reduce its relative merits.

Whether this trend of openness with AMD is because they're just nice like that, or because they're generally playing catch-up... I guess Mantle would imply they do it 'voluntarily', but again, it was never going to have the sort of lock-in effect that CUDA does.

Re:ATI/AMD has had shitty drivers for 20 years

[buckfeta2014]

I always felt that ATI (pre-AMD)'s Windows drivers weren't that bad. After starting to use Linux in the early 00's, I had to switch to Nvidia, and I haven't looked back. Yeah, they're both binary drivers, but Nvidia always worked better for me in Linux, and in cases where I dual-booted, this really made the difference as to which card I bought.

Re:ATI/AMD has had shitty drivers for 20 years

[cheesybagel]

AMD got the $6 billion to buy ATI by spending the cash reserves they had to build their next generation fab. The result is that after they bought ATI they had to sell their manufacturing operations sliding even further into irrelevance as their costs are much higher than Intel.

Re:ATI/AMD has had shitty drivers for 20 years

[cheesybagel]

AMD generally relies more on open standards because they simply don't have the resources to reinvent the wheel all the time like the incumbents do.

Re:ATI/AMD has had shitty drivers for 20 years

[cheesybagel]

NVIDIA's latest Windows drivers have been shit. I stopped counting the amount of graphics driver restarts I've had.

Re:ATI/AMD has had shitty drivers for 20 years

[drinkypoo]

Then he'd upgrade to the next shiny ATI card and do it all over again, since the new drivers bore little resemblance to the old ones.

Two points. 1, they now bear striking resemblance to the old ones, they now are the old ones with support for new cards. That's how modern video drivers work. 2, they bore striking resemblance to the old drivers then, too, as they were shit release after release.

I've been watching ATI drivers crash Windows since Windows 3.1 and the Mach32. Others have seen it even longer. Why anyone ever gives them money is beyond me. The last time I did it, I took a chance on some integrated graphics based on an old core and they never did work right and caused me endless headaches. Now I just don't run anything that uses 3D graphics on that machine, and I use it for OBD-II diagnosis. Since it's running windows, I had to upgrade it to a dual-core processor just to have it do that decently, but that's a different rant.

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

That has nothing to do with their driver problems. Their driver problems are caused by a culture that says it's OK for hardware engineers to write firmware and software. That's the way they started and that legacy has continued to the current day. Even when they get competent developers, the culture forces them to build on top of the previous shit.

Re:ATI/AMD has had shitty drivers for 20 years

[drinkypoo]

AMD is most certainly not a shit company

Sorry, you're behind the times.

AMD was pounded into the ground financially by Intel competing unfairly when AMD had the clear performance advantage

Yes, that's true, and now they are a shit company. And ATI is much of that.

Re:ATI/AMD has had shitty drivers for 20 years

[Kjella]

Well, AMD certainly has their own less than stellar moves too. Ever since AMD bought ATI in 2006 they've been talking about synergies but to be honest, I'm not seeing it. An "APU" performs very, very similar to the same CPU+GPU if you compare cores on the CPU side and shaders on the GPU side. They talk a lot of heterogeneous computing, but apart from their own tech demonstrations there's hardly any software written with custom code paths just for AMD and only their APUs.

AMD could have licensed GPU designs from both ATI and nVidia and had both as allies against Intel. They could have used the billions they spent on the ATI deal to counter Intel Core with better process technology or new CPU designs instead of playing with graphics. Instead they pot committed to ATI and paired one underdog with another underdog giving Intel+nVidia every reason to put the thumbscrews on them. And if they were afraid Microsoft would buy out ATI, then nVidia would have been their new best friend. I guess AMD had a bad case of hubris.

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

AMD was the only company directly competing with Intel on the desktop/server markets. NVidia and ARM were embedded or other and thus didn't compete directly. Remember that the only reason we're still using x86 hardware instead of Itanium is because AMD bolted 64-bit on and it became a hit. Enough so that Intel uses it now.

AMD likely has (well had) cash from all the other things they did, just like other chipmakers.

That's not really true about a lack of competition in the home & office desktop/workstation/server markets. Thinking offhand, there was also Cyrix (x86 compatible), IBM (PowerPC), DEC/Compaq (Alpha), Sun (Sparc), and Motorola (68k). The real story here is how x86 came to dominate so many market segments. With Amd64 crushing Itanium, Intel became something of a victim of its own success.

Re:ATI/AMD has had shitty drivers for 20 years

[brxndxn]

I suppose you think Intel developed AMD64 instruction set too..

Re:ATI/AMD has had shitty drivers for 20 years

[CajunArson]

In no way shape or form is Mantle "open".

Don't believe me? Go ahead and link to the online documentation that tells me how to make a triangle pop up on a screen using Mantle.... Go ahead I'm waiting.

That's not even taking into account the fact that Mantle works with Windows and uh... Windows.

Direct3D: Also not "open" but anyone with a working Windows installation can still write & compile programs that use Direct3D to do graphics without any further licensing needed, and Direct3D is documented.

OpenGL: Actually is Open and if you keep up with the newer releases you'll note that a lot of the miraculous features promised in Mantle seem strangely similar to features that were already available in OpenGL.....

Re:ATI/AMD has had shitty drivers for 20 years

[jellomizer]

EGA and VGA didn't have much in terms of drivers.
ATA made the EGA card. But when you ran the game it will ask you for.

1. CGA (Interrupt Mode 1)
2. Monochrome (Interrupt Mode 2)
3. EGA (Interrupt Mode 7)

Re:ATI/AMD has had shitty drivers for 20 years

[Lumpy]

because ATI fanbois expect ATI to not suck some day.
The one reason I stick with Nvidia, their drivers dont completely suck,

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

We all have our own experiences. I got my only ATI card in 1995 for OS2/Warp. It took nearly two years, and several ATI software updates before the card would work reliably. I swore I would never get another ATI based video card...and it's now 20 years later, and I've avoided ATI/AMD GPU's like the plague.

I specified video cards for countless computers where I worked, and I only spec'd NVidia based video cards. ATI/AMD's losses from all this, if my experience is telling, must be enormous.

I do find their CPU's, while not up to Intel's stuff, are much cheaper and fine at the low to medium performance range.

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

Compiz Fusion! We've got a power user up in here!

Re:ATI/AMD has had shitty drivers for 20 years

[Wootery]

You're right, I should've been clearer. Mantle isn't really open (as you say, no freely available spec), but I understand AMD did offer it to Nvidia, and Nvidia refused (along the lines of oh look yet another graphics API, no we'll wait for DX12 thanks). The same cannot be said of PhysX or, to my knowledge, G-Sync.

Re:ATI/AMD has had shitty drivers for 20 years

[HBI]

ATI used to include floppies with their cards. Some of them were mode setting programs. Some of them were diagnostics. And some were drivers for particular DOS applications to allow their use with the advanced features of the ATI cards. The VGA Wonder even included full technical specifications.

That said, I never got any of their drivers to even work except the Mach32 driver on Windows.

Re:ATI/AMD has had shitty drivers for 20 years

[CajunArson]

I fully agree that PhysX and G-Sync aren't open either.

As for Mantle being Open there was the case of Intel asking about Mantle information -- and AMD declining the request.

http://www.pcworld.com/article...

Re:ATI/AMD has had shitty drivers for 20 years

[marsu_k]

I wish there was a "sad but true" mod. I've been running Linux on my desktop for over a decade now - dismissing all the snark about desktop Linux, it really has improved during that time. But what remains the same is "you want 3D, get NVidia". Although pretty much every chipset/driver is capable of running whatever composited window manager you like.

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

nVidia seems to get slammed regularly for being more closed and it's really quite ridiculous.

First, nVidia *also* supports plenty of open standards (they supported OpenCL before AMD did, they supported OpenGL Shader Language very early on (I'm not sure if ATI or nVidia came first, but neither of them were laggardly in adopting support for that), DirectCompute isn't really "more open" but nVidia supports that as well, etc.) Just because they offer their own alternative that is able to make better use of their hardware doesn't mean their support for open standards should be ignored.

Second, quite a few of the "closed" things you list that nVidia has created were created when there *was* no open solution. CUDA was released to the public a year and a half before the OpenCL specification was published. SLI hit the market ages before CrossFire. G-Sync is commercially available now and has been for some time, while FreeSync is not. "cg" (their proprietary shader language) was created when the OpenGL ARB was refusing to join the 21st century.

Third, quite a few of the "open" things you credit to AMD are not "open" in the slightest. FreeSync and Crossfire are not any more open than G-Sync and SLI respectively. Mantle is not at all open. Or if you still insist on calling these projects open, then CUDA, PhysX, SLI, G-Sync, etc are all also open. (In particular, it's worth noting there's nothing *stopping* AMD from writing their own CUDA compiler for their GPUs -- for instance, the Portland Group has an x86 compiler for CUDA.)

Lastly, most people making this argument tend to gloss over the fact that AMD/ATI has also tried (and usually failed) to make proprietary technologies. Everyone loves to rage about CUDA and vendor lock-in and nVidia is so evil, etc, but no one ever mentions how ATI tried to do the exact same thing at the same time with CTM or later with Brook+. The reason ATI is more "friendly" to open technologies is that their attempts at closed, vendor lock-in technologies have a nasty history of failing miserably, while some of nVidia's (CUDA, PhysX) are still going strong.

Re:ATI/AMD has had shitty drivers for 20 years

[Wootery]

That's that then. Nowhere near open.

At least no-one's claiming the Metal API is open.

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

Don't make me raise the spectre of Sci-Tech Display Doctor...

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

I think you're missing the point.

At some point you have to evaluate the company and it's products on the merits. Is the customer happy? Do they think they received decent value for the money? Would they select that product again, given a choice?

You've clearly selected AMD as some kind of preferred provider, and downrated NVIDIA. Why? Do you have a habit of protecting the weak? Do you rescue puppies in your spare time? You seem to almost treasure the poor market and technical performance of AMD as a badge of honour. Are you also holding out false hope for SmallTalk, MIPS, Next and Sun? Do you pine for the days of AltaVista?

AMD's job was to perform and succeed in spite of competition. Not cash in on a sympathy vote for performing poorly.

Re:ATI/AMD has had shitty drivers for 20 years

[Tough Love]

Sounds like your granddaddy's ATI hardware...

$ uptime
  15:55:56 up 171 days, 2:22, 25 users, load average: 0.76, 0.98, 1.26

$ lspci | grep AMD
01:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Park [Mobility Radeon HD 5430]
01:00.1 Audio device: Advanced Micro Devices, Inc. [AMD/ATI] Cedar HDMI Audio [Radeon HD 5400/6300 Series]

Zero glitches, hangs or weirdness in the last several years with this or my other Radeon cards. Using the Xorg drivers. Includes heavy OpenGL hacking and way too much Civ V.

Re:ATI/AMD has had shitty drivers for 20 years

[Tough Love]

The last bout I had with NVidia was really annoying. Switch to text console and, whee, nice black screen. Yum. Got to love that Quadro experience. That was just one of many severe glitches. Haven't run that binary NVidia crap for many years now, very happy with the open source Radeon drivers and nice hardware. I really need to wonder if/why you're trolling. Got anything to add based on your last ten years experience? Didn't think so.

Maybe one day Nouveau will catch up to where the Xorg Radeon drivers got to years ago. Wake me up when that happens, maybe then I will take another flyer on NVidia.

Just say no to crap binary video driver blobs, I don't care what hardware or bespoke OS you are talking about, proprietary crap is proprietary crap.

Re:ATI/AMD has had shitty drivers for 20 years

[drinkypoo]

Sounds like your granddaddy's ATI hardware...

The problem is, it happened too many times for me to even consider trying them again unless nVidia drops the ball completely. And since I've never had any Optimus hardware, I've never really had any problems with nVidia. I did once have an HP Elitebook with a QuadroFX1500 with a known die bonding problem, I guess that's an nVidia problem. But since I had a big fat warranty and it was only a problem because of their incompetence and bullshit, I'd rather blame HP. Besides, it's not like ATI's never made bad hardware.

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

Speaking as someone who bought the R9 290 back when it came out in late 2013, this is exactly it. When I initially got it, the drivers were unusable. Today, the drivers are more or less solid outside of 3D, but that's been improving with each release as well.

Re:ATI/AMD has had shitty drivers for 20 years

[drinkypoo]

NVIDIA's latest Windows drivers have been shit. I stopped counting the amount of graphics driver restarts I've had.

Please tell us what card you have, what game you're playing, and what rendering path you're using. And, I suppose, which windows version. I'm using ye olde Asus 450 GTS OC on Win7x64 and I have to say I've been very pleased with the stability across a range of titles, not all of which are old. Yeah, that's old and slow. I bought it cheap used, and it's fast enough for my purposes and relatively low-power — and I don't want to have to buy a new power supply.

Re:ATI/AMD has had shitty drivers for 20 years

[DeathSquid]

Anonymous Coward trolls: "Or hide in your anonymity and know you are a coward, your idealogy is FALSE and that you blindly and sheepishly support a failed system". How true.

Re:ATI/AMD has had shitty drivers for 20 years

[Tough Love]

OpenGL: Actually is Open and if you keep up with the newer releases you'll note that a lot of the miraculous features promised in Mantle seem strangely similar to features that were already available in OpenGL.....

The big deal in the recent OGL 4.5 release is direct state access, for huge efficiency and robustness gains, while also being easier to code. Long time coming, that, but better they should take their time and get it right.

I don't know that AMD was strongly influenced by OpenGL advances, it seems more the other way round. AMD seems to be backing the move to make OpenGL work more like Mantle.

Re:ATI/AMD has had shitty drivers for 20 years

[marsu_k]

Not trolling, this has been my experience. If you want real 3D performance, the proprietary crap is what gives it. And VDPAU is nice. There are some nuisances, with Optimus chipsets you have to use Bumblebee which is kind of annoying if you don't want to burn through your laptop battery in minutes, and AFAIK the driver still doesn't support XRandR 1.something (1.2, I think?), that would allow to alter multiple monitor settings from the settings of my DE instead of using nvidia-settings.

Having said that, I've pretty much given up PC gaming so I don't really need 3D anymore. Intel is just fine for a compositing desktop.

Re:ATI/AMD has had shitty drivers for 20 years

[hairyfeet]

They work wonderfully in Windows, haven't seen a major issue in their non beta drivers in years. As for the Linux drivers? AMD has been paying for devs to work on the FOSS drivers and they have said repeatedly their goal is to bring the FOSS drivers up to parity with the cards the proprietary release supports and then replace the proprietary with the FOSS so no duh its not as good, its not where their focus has been in at least a couple years.

Also remember Nvidia makes their drivers run "better" by just ripping out part of the graphics stack and replacing it with a binary blob, and its a company whose hostility to FOSS has caused Linus Torvalds to give them the bird. Finally remember their APUs are ahead of the CPU+GPU combo when it comes to the FOSS drivers so if you want to run AMD with Linux the APU is the way to go.

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

Now if only OpenGL could fix their lack of multi-threading support. Yes, they have some worker threads that run in the background, but they only allow one thread to write to the GL context at a time. Worker threads are actually really bad when it comes to thread scaling, but if you don't support multi-threading, then the worker threads are better than nothing.

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

i just trying with amd /ati after 2006 or so (x1950 i think it was).

control panel could barely force anything in any game, newer drivers were extremely hit and miss, customer support was unbelievably shitty (i went to great lengths to explain my issues, they reply "you have an issue somewhere" - no shit, fuckers; pc worked fine with an nvidia card; eventually found out the specific card had a steep undocumented psu 12v rail requirement), etc. etc. etc.

after this, a friend bought 2x ati cards for crossfire... the great majority of games saw WORSE performance in crossfire. he ended up just selling the second card.

im glad nvidia has competition (and theyre far from perfect), but id have to hear a metric shit-ton of positive news to reconsider another amd / ati card.

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

They work wonderfully in Windows, haven't seen a major issue in their non beta drivers in years.

If by "years", you mean "minutes".

I'm using an AMD graphics card on Windows 7 right now. Graphic glitches (paint failures leaving "ghosts" on the desktop background when you drag windows), performance glitches (frame rate drops in half for no reason every so often) and unusable Aero Glass (every few hours, refresh rate drops to 10Hz from 75Hz). The fact that the control center is written in .Net so takes about 30 seconds to unminimize from the tray is another thing I hate (plus the 5 seconds to switch between each tab after it does finally open). Finally, every time you upgrade the AMD drivers, it fucks up your window sizes (all windows are changed to 640x480 which Windows Explorer happily remembers as the "preferred" size on all new folder instances) and desktop icon locations (every icon in the bottom row pushed into the start of the next column which fucks it all up if you have any sort of organized grouping).

Best of all, it does not even deliver on the basic point of a graphics accelerator — everyone knows that AMD's OpenGL ICD is drastically slower than their Direct3D engine. If you have a lot of games or utility software that uses OGL instead of D3D (Console emulators typically use OpenGL since they're cross platform for example) then you get to enjoy unnecessarily worse performance.

If you want shit that just works properly, buy an nVidia card. I know I will be very soon, after 2 years with this POS I can safely say ATi completely deserved their reputation for shitiness.

Re:ATI/AMD has had shitty drivers for 20 years

[Eunuchswear]

Do you think all people have a right to healthcare? Do you think all people have a right to a minimum wage, and paid days off to boot, so that you can party like it's 1984?

Of course. Who doesn't?

Re:ATI/AMD has had shitty drivers for 20 years

[vakuona]

I would have to add that AMD management has also been asleep at the wheel. They are in the tech business. They ought to have tried to outflank Intel, rather than to take them head on.

For example, they should have jumped onto the Android phone bandwagon and just made a phone. They have a decent brand, and I am sure I would have bought their phone. They needed something that will give them good margins, and CPUs ain't it. Apple showed the world how to beat an 800 pound gorilla. Don't take them head on. Go left field.

Apple made outrageous margins on phone to the extent that they are now way more profitable than Microsoft. Honestly, even though I thought Apple would do well, I never saw that coming.

AMD cannot compete with Intel head on. No one can. You need God money to get anywhere close.

Re:ATI/AMD has had shitty drivers for 20 years

[DG]

Amen, amen, amen.

I have an HD 7880 in my Linux box, and it works very well with Catalyst.

The drivers have made some real strides lately, and I bet all the issues in the Phoronix article are addressed in the next release.

Re:ATI/AMD has had shitty drivers for 20 years

[Anonymous Coward]

You think AMD invented AMD64?

Talk to David Cutler at Microsoft.

Re:ATI/AMD has had shitty drivers for 20 years

[Wootery]

I don't think that's really it. I think it's rather that if they aren't first-to-market, the appeal of a proprietary technology is low (unless you can totally demolish the competition, of course).

If the choice was CUDA, OpenCL, and AMD's own technology, one can't see that AMD's own technology would see any real up-take. OpenCL is having a hard enough time as it is, even with its advantage of being open.

Also Freesync is an AMD-lead reinvention of the wheel - AMD are willing to 'do the real work' when it's necessary.

Re:ATI/AMD has had shitty drivers for 20 years

[Wootery]

CUDA was released to the public a year and a half before the OpenCL specification was published.

Yes. And is it open? No.

SLI hit the market ages before CrossFire.

I don't really have a problem with those two being closed, as I imagine they're inherently quite vendor-specific in their workings.

G-Sync is commercially available now and has been for some time, while FreeSync is not.

True. A recurring theme here is that Nvidia tends to be the first to innovate, with the open technologies playing catch-up.

FreeSync and Crossfire are not any more open than G-Sync and SLI respectively.

Apparently FreeSync really is open.

In particular, it's worth noting there's nothing *stopping* AMD from writing their own CUDA compiler for their GPUs -- for instance, the Portland Group has an x86 compiler for CUDA.

True, but unlike OpenCL it's controlled entirely by Nvidia, and I presume only OpenCL is documented for both the user and the implementer (though as you say, independent reimplementation is certainly possible anyway).

Lastly, most people making this argument tend to gloss over the fact that AMD/ATI has also tried (and usually failed) to make proprietary technologies.

Yep. Mantle is the obvious one. ATi Stream was ATi's proprietary CUDA competitor, which iiuc went nowhere.

The reason ATI is more "friendly" to open technologies is that their attempts at closed, vendor lock-in technologies have a nasty history of failing miserably, while some of nVidia's (CUDA, PhysX) are still going strong.

I agree. Personally I suspect it's because AMD just don't seem as good at innovating as Nvidia do. Nvidia seem to be much better at coming up with new ideas: see SLI, CUDA, G-Sync. I suspect that if AMD were as good, they too would make their solutions proprietary.

Re:ATI/AMD has had shitty drivers for 20 years

[Lonewolf666]

Well, AMD certainly has their own less than stellar moves too. Ever since AMD bought ATI in 2006 they've been talking about synergies but to be honest, I'm not seeing it. An "APU" performs very, very similar to the same CPU+GPU if you compare cores on the CPU side and shaders on the GPU side.

Depends on which kind of system we're talking about.

On low-end APUs, the concept works fine and not needing a discrete GPU is a nice cost advantage. But Intel's HD graphics is already becoming a serious competitor in that product range.

At the top end of the (desktop) APU spectrum, the APUs tend to become bottlenecked by memory and a similar combination of cores on the CPU side and shaders on the GPU side tends to win the benchmarks. The cost advantage of the APUs still makes them interesting, but check out offers with discrete GPUs too and read some reviews.

What could help AMD here is HBM as VRAM in future APUs, that would remove the memory bottleneck...

Re:ATI/AMD has had shitty drivers for 20 years

[AntiSol]

Because they do have a tendency to improve

Welcome, traveller! It would appear that you have somehow managed to slip through the fabric of spacetime into an alternate universe!

Can you tell me how you plan to get back? Can I come with you? Your universe sounds like a really nice place!

Re:ATI/AMD has had shitty drivers for 20 years

[blivit42]

Remembering back to some long ago slashdot stories, John Carmack had some interesting comments regarding driver quality in his 2002-02-11 .plan entry:

"My judgment was colored by the experience of bringing up Doom on the original Radeon card a year earlier, which involved chasing a lot of driver bugs. Note that ATI was very responsive, working closely with me on it, and we were able to get everything resolved, but I still had no expectation that things would work correctly the first time.

When I have a problem on an Nvidia, I assume that it is my fault. With anyone else's drivers, I assume it is their fault. This has turned out correct almost all the time."

Sounds like things haven't changed all that much in this respect...

hire new editors

[ihtoit]

The grammatical roadkill spewing forth lately is making my head hurt.

I'm done with AMD.

[Anonymous Coward]

I love their CPUs, but their GPU Linux history has been shockingly poor.

Re:I'm done with AMD.

[Anonymous Coward]

I used to recommend AMD over Intel to friends and family. Even chose it over Intel at work a few times. The performance just isn't there any more. I'm not talking about bullshit benchmark tests, either, I'm talking in the trenches use. Lately AMD CPUs are just not on par with Intel ones at all. It is pretty disappointing. It seems like instead of offering great alternatives to Intel at a more reasonable price it just evolved into providing cheap shitty processors.

Re:I'm done with AMD.

[Anonymous Coward]

Yeah, I'll go with your "in the trenches" anecdotal assessment over the "bullshit benchmark tests" every time. But then again, I'm insane.

Who want to play games on Linux?

[Anonymous Coward]

Uhh, the average age of gamers is above 30 http://www.statista.com/statistics/189582/age-of-us-video-game-players-since-2010/

Re:Who want to play games on Linux?

[Anonymous Coward]

He can't hear you over the ruffling of his neckbeard.

Re:Who want to play games on Linux?

[jeffmflanagan]

I hope you're trolling. The only alternative is that you're incredibly stupid.

Re:Who want to play games on Linux?

[jedidiah]

A number of my colleagues would dump Windows in a heartbeat if they could run their PC games on some other OS.

Breaking old cards

[phorm]

One of the reasons why I will probably not buy an ATI/AMD (for graphics), is that support for older hardware is pretty terrible. I have an Asus laptop which worked *beautifully* in both Windows/Linux.
Apparently, some people (not me) had issues with brightness control not working on the fglrx driver. AMD fixes that, and on my laptop (and others, according to Google) the backlight breaks. As soon as X initializes my backlight goes dark. In a bright room I can barely see that X otherwise started successfully and is displaying a login window.. It's been over a year. I've seen lots of chatter on fixes for the brightness-control button, but pretty much zip about the broken backlight.

I can use the Radeon driver so that X will work, but video is choppy and since I'm working on actually developing GL code, it's pretty much useless for that. So... core i7 processor, lots of RAM, decently powerful GPU, and a farked video driver that renders the whole thing useless.

I had actually been migrating more towards AMD from nVidia since their graphics drivers had shown promise since ATI was acquired, but frankly the nightmare of bug-support is pushing me back towards nVidia. It especially sucks for a laptop since I can't exactly replace the GPU on what it otherwise fully functional hardware.

Currently I'm picking at firegl_public.c and related modules attempting to merge the 13.25 driver with the 8.960 driver (I've been told that reverting to the older driver will allow the backlight to work, but in my case it won't compile under DKMS).

To any AMD Linux driver devs listening: I would be happy to work with you on this. Hell, I can ship you the damn laptop for a few months if you believe that would help develop a driver that works again.

Re:Breaking old cards

[Anonymous Coward]

To be fair, Nvidia is famous for this as well. The absolutely horrible Optimus driver on my ThinkPad T530 breaks if I install the latest drivers for it. I run Windows 8.1 as this is my work laptop. If I install the latest patch/update from Lenovo, it breaks. If I install the latest from Nvidia's site it breaks. If I install GeForce experience it balks at the age of the card, tells me most of the "features" don't work, then breaks the card.

I tried setting it to discreet only in the BIOS. Nothing. If I want to run Linux on this laptop, I basically have to forego the Optimus switching feature and pick either the built in Intel graphics or the Nvidia chip, not "both." Running Windows doesn't fair much better.

Optimus was a fucking stupid idea and shouldn't have been implemented anyway, but Nvidia's lack of fucks to give about older hardware is pretty obvious.

Re:Breaking old cards

[Anonymous Coward]

Don't be stupid. My T530 runs an Intel i7 processor, 16GB of Corsair Vengeance RAM, and two Samsung SSDs. Just because one website lists the low end version with an i3 doesn't mean that is the _only_ version.

Jesus...fucking dumb twats around today.

Re:Breaking old cards

[dkman]

My 4 year old Sager laptop has a GPU module (or slot, so it's essentially like RAM and can be replaced). When the graphic card decided to flip out a few weeks ago I searched around and they were around $230 shipping from China. Even though everything said to me that the problem was just the video card I decided to spend $1600 on a new Sager laptop. Since the old one was now disposable I decided to do the "bake the video card" trick (375 degrees for 10 minutes, in case you're interested - just remove all screws, heat sinks, and thermal paste). I let it cool, applied thermal paste, and gave it a shot - bam, worked like new. Since the new laptop was already in "processing" I decided to let it come anyhow.

The old one is an ATI (HD 6990M). It handles linux gaming alright, it really depends on the game. Windows gaming it's great at - I just don't boot window often. The new laptop has an nvidia because I do feel that the nvidia drivers will be better in linux. Over the past 20 years I've given both companies some love.

Re:Breaking old cards

[dkman]

Oh, I should warn that baking the video card does stink up the house - so use plenty of ventilation afterwards. You can also search youtube to see some other folks have success with it.

Re:Breaking old cards

[Anonymous Coward]

Since the i3 variant doesn't come with a Nvidia 5400 Optimus card in it, I assume that someone involved in tech, posting on a tech site, could draw the conclusion based on context...but whatever...it is easier to make off-hand, ill informed commentary.

Re:Breaking old cards

[spire3661]

Windows 8 can run well on a 16 GB partition and 1 GB of ram with a 1.3 GHZ Bay Trail Atom CPU.....

Re:Breaking old cards

[skids]

Same story here. It's one thing to retir support for older discrete cards out of the proprietary driver. Users of those cards tend to upgrade pretty frequently anyway. It's another thing entirely to retire support for embedded laptop chipsets, and while doing that, apparently not give the OpenSource maintainers good enough documentation on the power management/clocking in those chipsets to prevent overheats/instability.

I'm due for a new laptop here at work. My top requirement was "not AMD."

Re:Breaking old cards

[phorm]

Oh there's nothing wrong with the card that would require "baking" etc, it's purely a driver issue. They fixed a brightness-button issue and in turn something sets the backlight to 0 on my model.

Re:Breaking old cards

[ihtoit]

aftermarket parts are soooo hard to come by...

Re:Breaking old cards

[Anonymous Coward]

Considering the base T530 doesn't support a dGPU at all - yes, they are.

Re:Breaking old cards

[dkman]

I was only pointing out that there are laptops where the graphic card is in fact a "card"/module rather than something integrated into the motherboard. But they're not necessarily cheap to swap out.

Re:Breaking old cards

[Anonymous Coward]

Don't bother arguing with stupid. It's just a waste of your time.

Re:Breaking old cards

[starslash]

Fixed my old iMac's 4850 by baking, the card overheated with after a mac OS update :/ Still pretty sure apple caused it on purpose(conspiracy theory)

Waffle much?

[mandark1967]

From 2 weeks ago:

"...the latest Phoronix end-of-year tests show the AMD Catalyst Linux driver is beating Catalyst on Windows for some OpenGL benchmarks. The proprietary driver tests were done with the new Catalyst "OMEGA" driver. Is AMD beginning to lead real Linux driver innovations or is OpenGL on Windows just struggling?"

(http://linux.slashdot.org/story/15/01/03/1426208/amd-catalyst-linux-driver-catching-up-to-and-beating-windows?sdsrc=rel)

Re:Waffle much?

[bulled]

What ever drives the clicks...

Re:Waffle much?

[cupantae]

Beat me to it. I think the problem is that /. wants both sensational headlines and balanced reporting. What the hell does "X is the broken wheel for Y" mean anyway?
Both posted by soulskill, just 2 weeks apart. Shameful stuff.

Re:Waffle much?

[drinkypoo]

From 2 weeks ago:

"...the latest Phoronix end-of-year tests show the AMD Catalyst Linux driver is beating Catalyst on Windows for some OpenGL benchmarks. The proprietary driver tests were done with the new Catalyst "OMEGA" driver. Is AMD beginning to lead real Linux driver innovations or is OpenGL on Windows just struggling?"

There's no waffling there. The answer is that AMD's OpenGL support on Windows is struggling. And also that I am very glad I am an nVidia NAZI.

Re:Waffle much?

[Nemyst]

Did you read to the end of the sentence? OpenGL on Windows has always been a low priority thing, and since AMD's been struggling to make passable drivers it's completely unsurprising that they'd focus even less on that.

Re:Waffle much?

[Creepy]

It shows the transition - OpenGL has been a second class citizen for ATI/AMD for years and now is first class. With the PS4 using their chip and OpenGL they finally have a good reason to have extremely good OpenGL performance and dedicate development time to it, but I still remember when they wouldn't even support extensions.

nVidia has always had OpenGL as a first class citizen (for different reasons - CAD, then PS3, now mobile and Linux GRID arrays such as the one I use with VMWare VMs for GPU support).

Re:Waffle much?

[cheesybagel]

Yeah the XBOX One which also uses AMD chips. As will the next Nintendo console if the rumours are true..

Re:Waffle much?

[Anonymous Coward]

From 2 weeks ago:

"...the latest Phoronix end-of-year tests show the AMD Catalyst Linux driver is beating Catalyst on Windows for some OpenGL benchmarks. The proprietary driver tests were done with the new Catalyst "OMEGA" driver. Is AMD beginning to lead real Linux driver innovations or is OpenGL on Windows just struggling?"

(http://linux.slashdot.org/story/15/01/03/1426208/amd-catalyst-linux-driver-catching-up-to-and-beating-windows?sdsrc=rel)

Other Phoronix tests (including the recent benchmarks of Metro Redux and UE4 demos) that compare Nvidia vs. AMD proprietary drivers on Linux show that on average AMD is less competitive than on Windows. This can be explained in two ways: either AMD has inferior OpenGL drivers on both platforms, or Nvidia has inferior Direct3D drivers. Given the market share of the two APIs, which one makes more sense ?

Re:Waffle much?

[emblemparade]

Right: OpenGL on AMD/Linux is catching up with OpenGL on AMD/Windows.

But both suck relative to NVIDIA's implementation of OpenGL. AMD and NVIDIA are competitive on D3D, but that's no comfort to Linux users, where they simply cannot use their GPUs to their fullest potential.

Re:TOTAL FARK 4LYFE

[Anonymous Coward]

Im really sorry. please ignore this.

Re:Who want to play games on Linux?

[CaptainOfSpray]

700+ games ifor Linux in the Steam store. Clearly lots of people want to play games on Linux.

Re:Who want to play games on Linux?

[Anonymous Coward]

That's not a good thing.

Re:Who want to play games on Linux?

[Anonymous Coward]

Let me ask the all encompassing linux process

Oh, great SystemD, we beseech thee! Doth Linux aim most vigorously to become a toy OS for those of thirteen years of age akin to that greatest of despots, Windows?

I'd tell you what SystemD said in response, but it crashed trying to send email while PulseAudio and NetworkManager fought over which one would be the process to turn my AC on.

But the Open Source drivers are good

[Atmchicago]

My Radeon 6850 runs TF2 great on the OSS drivers. This is where things are headed, and if AMD keeps it up then Nvidia will have catching up to do. We're nearing the point where you can buy a graphics card, plug it in, and it "just works." The main issue is that it could take months for the bleeding edge to make it into the latest kernel, so brand new GPUs could be problematic. More to the point, in a few years an AMD APU might be both "good enough" for gaming, and also "just work." On Linux. That's saying something.

Re:But the Open Source drivers are good

[AqD]

Being able to utilize only 10% of your hardware is NOT good - there is a zero missing!

It sucks and you know it and that's why you're testing TF2 rather than real games on it. By real games I mean it should at least heat your GFX card to 80C and fans running in maximum speed.

Re:But the Open Source drivers are good

[Gliscameria]

So you can play a 7 year old game on a 4 year old card? That's not saying much.

Re:But the Open Source drivers are good

[Anonymous Coward]

The OSS drivers are awesome as an accomplishment, but they aren't good drivers. TF2 is almost 8 years old, the fact that it runs on your system isn't... impressive.

Re:But the Open Source drivers are good

[Tough Love]

We're nearing the point where you can buy a graphics card, plug it in, and it "just works." The main issue is that it could take months for the bleeding edge to make it into the latest kernel, so brand new GPUs could be problematic.

+1. All my latest Radeon installs have been: buy it, plug it in, it works. That is because I always check this matrix before deciding which card to buy. Note that it is now green all the way to the right on nearly every hardware feature you care about. A notable exception is OpenCL, which is WIP. If I wanted to develop with it right now, that would move me back to fglrx, and only that. Notice how the latest chipsets are the ones with OpenCL closest to prime time.

Re:But the Open Source drivers are good

[Tough Love]

So you can play a 7 year old game on a 4 year old card? That's not saying much.

It means that card could always play a 3 year old game. I'm running more recent games than that on random low end Radeons. Lots of Steam stuff, no complaints. I refuse to plug in the kind of card that runs the latest Far Cry full res on a 30 inch monitor with all features on just because I find the power suck, heat and fan noise really irritating. For the 99% of gamers who aren't hardcore shooter addicts, a $100 AMD card does the job perfectly well, and quietly.

Re:But the Open Source drivers are good

[Anonymous Coward]

By real games I mean it should at least heat your GFX card to 80C

Games don't do that anymore, they're all CPU limited, even on 4.5ghz Haswells. No one knows how to use more than one/two cores.

Re:But the Open Source drivers are good

[Anonymous Coward]

Also mesa matrix for checking opengl levels
http://mesamatrix.net/

Re:But the Open Source drivers are good

[Anonymous Coward]

By real games I mean it should at least heat your GFX card to 80C

Games don't do that anymore, they're all CPU limited, even on 4.5ghz Haswells. No one knows how to use more than one/two cores.

If that is true, then how it is possible that upgrading from a low to a high end GPU like a GTX 980 makes a major improvement to the frame rate in most games ? Also, if nothing uses more than two cores, then there would not be too much point using CPUs other than the Core i3, as the higher models are faster mainly because of having more cores. Games developed for the new consoles should definitely be optimized for more than two cores, as the AMD CPUs used in those have many cores, but relatively poor single threaded performance.

For something that heats the GPU to 80C on Linux, try the Unigine Heaven demo at maximum settings. Too bad the open source drivers cannot run it with tessellation enabled.

Re:But the Open Source drivers are good

[Anonymous Coward]

I refuse to plug in the kind of card that runs the latest Far Cry full res on a 30 inch monitor with all features on just because I find the power suck, heat and fan noise really irritating.

Then use an Nvidia Maxwell GPU, since those are more power efficient for gaming than the Radeons.

Re:But the Open Source drivers are good

[AqD]

Old games don't, but new games such as Rome 2 Total War can utilize 4+ cores and i5/i7 gives huge performance boost.

Re:But the Open Source drivers are good

[Tough Love]

Also mesa matrix for checking opengl levels
http://mesamatrix.net/

Yes, it's encouraging how much mesa work is already done even for OGL 4.5. Remember when mesa was stuck for years at 2.1 plus extensons? A very nice 2.1, but preventing serious use for a lot of modern rendering techniques.

At one time, mesa was pretty much a one man project, now there is obviously some serious funding behind it.

Re:But the Open Source drivers are good

[Gliscameria]

That's not the conversation. The market caters towards the high end cards, and if you have software that doesn't support them then that's a problem.

Re:Who want to play games on Linux?

[Immerman]

Right - all those gamers should be either working themselves to death trying to get ahead in a game that's rigged against them, or out getting drunk and shagging strangers. You know, socially acceptable ways to pass the time.

I can't even get smooth video playback on my AMD

[Anonymous Coward]

I decided to build my own video box around an AMD A6-5400k dual core processor which is advertised has having an integrated "discrete-level" GPU. The box has been unusable for video since every video program in Ubuntu (with both the catalyst and open source drivers) does not have smooth video playback. Instead, I get tearing and dropped frames.

It's really disappointing.

Try a modern game

[Sycraft-fu]

That it runs TF2 well isn't saying much. That wasn't very intense when it came out and it is very old. TF2 runs great on integrated Intel cards. Try a game that is a heavier hitter, and uses more modern API calls. Then you'll see issues.

Se what you are really saying is "A problem can be fixed by throwing enough hardware at it." Your GPU and CPU are unimaginably powerful compared to what was available in 2007. So of course it runs well, it could be running at 25% efficiency and still run well because your monitor's scan rate is the limiting factor.

However that's not so easy to do with new games that push the envelope. You can't just throw tons of hardware at them because they are already pushing the high end hardware that is out. So efficiency matters. If the driver is slow, you are going to have poor performance.

Further there is the issue of crashing. AMD drivers seem to have a tendency to 'asplode when you start throwing some of the new features at them. These features are there for a reason, they allow greater detail, more efficient rendering, new visuals, etc. If you can't support them, then that's an issue.

If you want a real test, fire up Metro Last Light Redux, see how that works.

Re:Try a modern game

[geekforhire]

I don't do much gaming these days, just not enough time, but I have always enjoyed the Borderlands series and my rig with a 6850 and the OSS drivers runs the latest Borderlands at 1080P with high quality options enabled just fine. It actually runs much nicer with the OSS drivers than the proprietary version with my dual head setup. The AMD driver only runs full screen games well if the secondary display is disabled and even then it has a habit of sucking.

Re:Who want to play games on Linux?

[Torp]

Wish i had mod points ;)

Re:Who want to play games on Linux?

[Anonymous Coward]

GNU/Quake runs super smooth on GNU/Linux.

Jaguar: Do the math

[tepples]

PlayStation 4 and Xbox One are essentially PCs built around AMD's Jaguar laptop APU, except with a locked-down BIOS instead of standard UEFI. Do the math.

Re:Jaguar: Do the math

[cupantae]

Jaguar laptop APU ... Do the math.

For god's sake mod this comment up.

In this thread:

[Anonymous Coward]

People hating on nVidia because their Linux driver isn't open source... ... Even though it pretty well sets a golden standard of performance for any platform.

And me, being happy that supercomputer and 3d movie people use their Linux driver, because there's no way they'd put up with the shit they get if it were just home linux users using it.

Their drivers might be garbage, the silicon's OK

[jhantin]

AMD got the $6 billion to buy ATI by spending the cash reserves they had to build their next generation fab. The result is that after they bought ATI they had to sell their manufacturing operations sliding even further into irrelevance as their costs are much higher than Intel.

It's not like they don't actually have a sensible plan, though. While they might not be able to catch Intel in the short run on high-end CPUs, some of their newer APUs (some of them outright SoCs) are surprisingly efficient little beasts built for the low-power market segment: silent or fanless mini PCs, tablets, ultraportables, and an assortment of bespoke embedded gadgets. While the CPU side trails Intel's, on-die GCN soundly demolishes any integrated graphics Intel puts out there.

Why do people still go AMD?

[kuzb]

AMD has been the broken wheel in gaming FOR DECADES. Honestly, leaving AMD products behind has vastly improved my overall computing experience.

Re:Why do people still go AMD?

[moogaloonie]

Brand loyalty I suppose... I chose AMD over Intel for CPU when putting my first PC together because I didn't want to support certain business practices of Intel. When AMD bought ATI, I started using AMD GPUs instead of nVidia (thinking they would work together more smoothly being from the same company). My previous system was a 4-core with Radeon HD, my current system is 8-core with R285. I have been quite happy with all of the AMD components I have used, and see no compelling reason to switch. I'm not a hardcore gamer, I mainly play Just Cause 2, Spin Tires and a few others... But 3D performance is still quite important to me for content creation.

On the other hand...

[Richy_T]

What's the deal with NVidia and on-board graphics? Have they exited the market? I recently had to replace a MB with onboard NVidia and wanted to find another with NVidia onboard (because drivers) but nada. Fortunately the drivers for the Athlon with onboard ATI were not hard to install and it works fine for what it's used for but it was just surprising and perhaps what was even more surprising was the lack of commentary. Like they just went out with a whimper.

Re:On the other hand...

[PayPaI]

Nvidia used to make integrated chipsets for Intel and AMD, what changed is Intel no longer licenses the chipsets for the i7+ and AMD is now a direct competitor with their purchase of ATI.

I disagree

[Anonymous Coward]

Latest drivers by phoronix kick ass

Re:Their drivers might be garbage, the silicon's O

[Tough Love]

Also, the AMD buyout gave ATI access to better process technology. Without that, ATI might have gotten stompted by NVidia and we would have a graphics monoculture on desktops right now. Yuck. For the same reason I am glad that AMD never stomped NVidia, though it came close.

Re:TOTAL FARK 4LYFE

[Anonymous Coward]

IF YOU REALLY WANT TO REDESIGN THE WEBSITE, BRING BACK THE 2006 VERSION! http://i.imgur.com/se56NGS.gif
/we did not get over Beta.

Re:Who want to play games on Linux?

[bejinx]

A number of my colleagues would dump Windows in a heartbeat if they could run their PC games on some other OS.

^^ yes, this.

Aww

[Anonymous Coward]

Come on. Give them a break. If you don't they'd be bankrupt and Nvidia won't have any competition to push their products to greater heights. Look at Intel, they don't have to lower the prices of their processors if they don't want to. It's called business.

Surprising results

[Anonymous Coward]

Surprising in the sense that they got the Catalyst driver to work under Linux at all. That's still in my to-do list, despite my many attempts.

Re:Who want to play games on Linux?

[Anonymous Coward]

The Steam Hardware Survey shows Linux usage at 1.16%. Clearly, few people actually play games on Linux. Windows 8 on the other hand, the OS that trolls claim no one wants to use, is at 31.29% and climbing.

Don't be that quick to praise NVIDIA

[Anonymous Coward]

I had been a long time NVIDIA blob driver user. There were some complaints that I had about it, but I never realized how many other problems it caused. I didn't like the NOUVEAU driver at the time because it just plain didn't work (crashes, blank screens, etc.). The NVIDIA driver didn't do that, and was (apparently) faster. Well NVIDIA is faster, but never works with new kernels. And I wanted to run a new kernel and gave nouveau a try again. Color me changed. It runs (slower) but I get terminal windows back too. And when X starts up, I don't have to go in and switch my dual-monitor setup when I log in (NVIDIA would always get it wrong, and writing to any file would be ignored. I even had the program save a file of its chosing, and then when I tried to get it to read back the file it (and only it) had written, it wouldn't. And it was a bug NVIDIA refused to fix. But that's not all. I could never (before) get blender to get along with povray. They just wouldn't get along no matter what. And now, (and its the only thing I've changed), suddenly I can render drawings and animations with both pieces of software without any hiccup. And nouveau is fast enough for low-end games. And the other benefit is that when I build new kernels, I never have to go into single user mode, and then build the driver separately. I would be one of those benefiting from the nouveau people putting more time into Fermi cards, but I am pretty darn happy even with what I have now.

Re:Who want to play games on Linux?

[Anonymous Coward]

A number of your colleagues are probably Linux zealots like yourself. That's not saying much.

geforce 2

[Osgeld]

was way overkill for frozen bubble 12 years ago, so im good when stuck in linux, I think half life will be just fine in this day and age (15+ years late, just like linux always is)

Nvidia is the way to go.

[DMJC]

Quite simply. Nvidia is going to be available as an open source solution via Nouveau with decent performance/stability. Long before ATi will have a stable proprietary or open source driver. Just look at the mesamatrix.net charts. Nvidia cards are ahead of ATi for implementing driver features via Nouveau. Reclocking support keeps getting more patches with every kernel release. It's not too far now until we get at least OpenGL 4.2 supported under open source drivers with decent speed on Nvidia. The closed drivers already do OpenGL 4.5 with great speed. ATi is holding the platform back and causing a lot of bad press for Linux gaming. It's time the community called them out on it.

Re:Nvidia is the way to go.

[Lonewolf666]

Now that is optimistic. Last time I checked, Nvidia was giving little to no hardware documentation to open source developers. Which really does not help projects like Noveau, as they have to rely on reverse engineering and it really slows them down.

Last time Phoronix tested the Noveau drivers, they were seriously outclassed by the Radeon drivers. Both in performance and features.

I use to always run AMD cards

[Anonymous Coward]

from 1999 to 2014, but switched to Nvidia just because there is a decent driver for it in Linux/Bsd. On windows the AMD driver is solid.

2014 called, they want their news back

[Gallomimia]

This isn't new information. It's been terrible for a long time. Why are you posting it, let alone putting it in the mailout? I've heard catalyst is pretty damn broken for windows too. So I have an ASUS oc2 radeon 7790 for sale. Replaced by my gtx780. Bye bye ati.

Re:Who want to play games on Linux?

[Anonymous Coward]

A number of my colleagues would dump their Legs in a heartbeat if they could run on some other limb.

Re:Who want to play games on Linux?

[DdJ]

Is Linux really aiming that hard at becoming a toy OS for thirteen year olds like Windows?

Speaking as an old-time Unix neckbeard, the best evidence I've got is that the answer is "yes". (cf. "systemd", "Network Manager")