Slashdot Mirror

GP is right. Some tech journalist made a flawed deduction and the resulting entirely false story spread virally, even to slashdot. According to their official statement, Nvidia is simply updating its GPU drivers to help mitigate the CPU security issue, a normal and expected move that will be followed by many software vendors since spectre (specifically CVE-2017-5753) actually represents a new class of security vulnerabilities - like "buffer over-read" but different.

In answer to your post, while GPUs do support branching, they don't engage in branch prediction, which makes them immune. In simple terms, superscalar CPUs process data in a "scalar" fashion, but use all kinds of tricks (like speculative execution) to perform more ops per cycle than would be possible for an equivalent scalar design (hence "super"). While superscalar designs fulfill strong market pressure for high per-thread performance, they comes at the cost of using a lot of silicon (and power). Also, one of these "superscalar tricks" just now has turned out too tricky for its own good.

In contrast, GPUs take a whole different approach in getting around the inherent bottleneck of a scalar design: they perform simple operations on a whole array worth of data at once, and can be seen as a cluster of hundreds of simplified scalar CPUs running in parallel (to give an example of "simplified": they commonly share instruction decoding logic to some extent). The advantage of this approach is that you can use silicon for actual computations that would otherwise be "wasted" on "superscalar tricks", which is why GPUs have such phenomenal computational throughput per unit of power consumption compared to CPUs. The disadvantage is that your workload needs to be optimized for this design, which isn't always possible, leave alone easy. They're great for graphic rendering, though. ;)

Anyhow, given the above, you can see that some would argue that going superscalar would defeat the whole point of a GPU living alongside a CPU in the same box...

Holy shit this is bad reporting. Nowhere on the Nvidia page does it say that GPUs are actually affected by Spectre or Meltdown. It's in fact impossible since GPUs don't perform speculative execution. On top of that, GPUs don't run kernel code (so cannot leak it), don't run an OS, have a completely different architecture to begin with and so on.

So what's this announcement about? It's a driver update to mitigate Spectre/Meltdown which could potentially affect the driver's CPU code. This has also been confirmed by Nvidia many days ago.

Shameful reporting by Engadget, not that I'm surprised considering they barely qualify as "tech" reporting.

This update is actually a good one, it finally fixes the Diagonal Tearing Problem with Nvidia Optimus Laptops.

"Topping out at less than a third the power consumption of a 1080" yeah, except not. Normally I wouldn't even both correcting just another ransom person spouting completely wrong information. But you have been going on and on about it, talking about how you *refuse* to use something so power hungry and inefficient, and how you're so clever cause what you use is *of course* way better perf/watt.

That would be nice and all if it were true, but it's complete bullshit. TDP of a 960 is 120W, per Nvidias site. See for yourself: https://www.geforce.com/hardwa...

The 1080 TDP is 180W, Nvidia significantly improved the power usage of the 10 series compared to the previous 900 series cards for equal or greater performance levels, like the 1080 vs 980 ti. https://www.nvidia.com/en-us/g...

If you were actually right, your continued mentioning of it would be kind of annoying, but that's ok. But since you're actually not even close to right, it's just obnoxious to keep reading the same bullshit spewed out over and over again. So you aren't oddly principled about using only the best perf/watt components, you're just ignorant. Sorry.

That's actually not all that surprising. The GTX 1080 is rated at 180 Watts.

The switch should have no problem with 1080p, it is using the Tegra X1 chip, which is capable of 4k at 60fps.

This is so painfully wrong that I have to correct it. The Tegra has a hardware decoder that can handle 4K video. It specifically supports the H.265 and VP9 codecs, which are widely used for streaming.

I would be absolutely shocked if the Tegra can render 3D scenes at 4K and 60 Hz, given that high end desktop GPUs pulling 200W have trouble with it. In fact, the Tegra X1 has only 40% of the power of an outdated mid-level GeForce card. The Tegra X1 has 256 CUDA cores compared to the 640 cores in the GeForce 750 Ti.

And Nintendo's patch notes are so vague as to be meaningless. You can speculate on what they did all you want. But based on your gross misunderstanding of the SOC's capabilities, I do not assign much credibility to your speculation.

I just checked my Task Scheduler, and none of those Nvidia telemetry tasks identified by MajorGeeks have ever run. I've just enabled "tasks history" (i.e.: chron logs) from admin to see if it's actually doing anything. The tasks only appear when you run Task Scheduler with admin rights, so access is restricted to users with administrator rights. From the history, I think this telemetry might be in the works, but not running yet.

It's possible that since it is an admin task and I run in a limited user account (standard account), it's not triggering the task, but the tasks are supposed to be triggered by login of "any user," with a daily report at 12:45 on my machine if there's no login to trigger, so I can't see how that's happening. This all should be working, but it appears to be dead at this time on my machine with the latest drivers.

I do have GeForce Experience 3 installed, and it *is* asking for a login, however. So it seems they're tagging *something* to an account.

The GeForce forums are a shitstorm of "ditch the login" posts in every GFX thread. People are threatening boycotts, etc. It's really quite interesting. Here's the initial feedback thread when GFX 3 went live. Bring popcorn.

5 years? It was 12 years ago when I dropped them. I couldn't stand their DirectX 8 regressions on Geforce2-4's (and not the crappy FX lineup suspiciously). And they NEVER fixed their palette slow bug or the text mode BSOD.

Can't really blame you on that, I've still got a Geforce 3 around here somewhere and really ATI could have had something against them for that period if they'd simply gotten their shit together with their drivers.

Funny though how all the negative nvidia comments are voted down though, almost like someone is really butthurt. Oh here's the thread on them wanting to have rigs and videocards shipped to them as well. Including the whining from the fanboys that it's all the customers fault. Including a snippet on it.

The card is designed for data mining and neural network research; it's not for games or even remotely intended to be used for them.

Bullshit.

http://www.geforce.com/hardwar...
"With the DNA of the worldâ(TM)s fastest supercomputer and the soul of NVIDIA® Keplerâ architecture, GeForce® GTX TITAN GPU is a revolution in PC gaming performance."

I admit I don't completely know who they focus on with the Titan cards.
10-11 Tflops single precision performance with this one.
317-343 Gflops double precision.
159-171 Gflops half precision (shouldn't that one be higher?)

The idea with the more professional card is to hit 5+ Tflops of couble precision performance?
http://wccftech.com/nvidia-pas...

I don't really know where the Titan cards fall between the consumer cards and the professional cards.
Once re-released as the GTX 1080Ti it will definitely be a gamers card.

I guess without further evidence saying "yes it is!" is just as good as saying "no it isn't!"

It's an expensive gaming card but those who want this performance now only have this option.

Ha ha, no. Apple and Intel are tight, and Apples tend to get the best, latest intel chips that will fit within the (ever thinner) machine they're building. Easy to look up.

The problem with Apples they aren't very upgradeable. You're often stuck with what you get, and maxing it out at purchase time tends to cost a lot more than equivalent upgrades on the street... assuming those upgrades would fit, which they probably won't.

You buy a Mac because it has a warranty, will be sold in its same configuration for at least a year so getting support is easy, and will be repairable for as many as 5 years or more (my 2010 Macbook Pro just got cut off the list this year). Most other consumer electronics have the lifespan of a fruitfly. That Sony Vaio isn't a 2011 model, it's a VWETB236623626-ASD23423 that had a two-week production run and was replaced months before Sony cleared out a thousand of them for sale at Best Buy. Your Apple will be current for at least a year... but a year in, it'll still be sold with the same, now aging, CPU. Trade-off. That's why you check the Buyer's Guide at MacRumors.com before you buy.

But it's FUD that they're putting 2-year old crap in new models. Except, maybe, when you consider the GPU. It will be recent hardware, but it's mid-range performance compared to the best of what's out there. Because top-of-the-line desktop GPU's like the GTX Titan doesn't fit an iMac, and sure as shit not in a laptop or a Mini. Apple doesn't build an affordable desktop, and even if a funny-looking Mac Pro is on your radar, Apple does a frustratingly bad job of updating it as newer, faster chips come out.

So, there you have it. For most of what people buy Macs for, this isn't a problem. But nobody thinks of a Mac as a gaming rig. A recent Mac will play, Steam runs on it, but if you're serious about gaming you're serious enough to build a PC rig.

There is already GPU for this with more than 1000 processing unit. For example, the nVidia GeForce GTX 980 has 2048 cores. http://www.geforce.com/hardwar...

Why wouldn't it be able to? Nvidia publishes drivers on a regular basis.

Linux x64 (AMD64/EM64T) Display Driver 361.42 (Mar 30, 2016)

The feature list can be seen on sites like: http://www.geforce.com/hardwar...
http://www.geforce.com/hardwar...
http://www.geforce.com/hardwar...
https://developer.nvidia.com/w...
If Linux has that gpu support vs CPU bound, thats great :)

The feature list can be seen on sites like: http://www.geforce.com/hardwar...
http://www.geforce.com/hardwar...
http://www.geforce.com/hardwar...
https://developer.nvidia.com/w...
If Linux has that gpu support vs CPU bound, thats great :)

The feature list can be seen on sites like: http://www.geforce.com/hardwar...
http://www.geforce.com/hardwar...
http://www.geforce.com/hardwar...
https://developer.nvidia.com/w...
If Linux has that gpu support vs CPU bound, thats great :)

But the Get Windows 10 app will not let me proceed, instead telling me that NVIDIA has not made the GPU compatible and giving a link to shop for a new PC. Should I take a screenshot? Is there a recommended half-height discrete GPU to use instead of the integrated one? (Because the case is compact, a full-height GPU will not fit.) Should I follow the instructions in this thread to create USB install media? Or should I just leave that PC at Windows 7 and then attempt to Linux it once Windows 7 reaches end of extended support in a few years?

Windows 10 is known to actually destroy some monitors.

As long as you don't have to register just to download the damn thing, it's still better than Nvidia's drivers. At least you can ignore the social media and notification features, you can't even get an Nvidia driver without handing over a working email address and creating an account.

Maybe Intel are the way to go, but even they have a system notification feature. Like AMD's, it can be disabled.

Where on Earth are you trying to download Nvidia's drivers? Nvidia's download page and the results page don't have anything even resembling a demand for an email address, unless you count the 'Subscribe to our newsletter' nonsense at the top-right corner of the page (which you shouldn't be, because you can download drivers all day long without doing that).

As long as you don't have to register just to download the damn thing, it's still better than Nvidia's drivers. At least you can ignore the social media and notification features, you can't even get an Nvidia driver without handing over a working email address and creating an account.

Maybe Intel are the way to go, but even they have a system notification feature. Like AMD's, it can be disabled.

Where on Earth are you trying to download Nvidia's drivers? Nvidia's download page and the results page don't have anything even resembling a demand for an email address, unless you count the 'Subscribe to our newsletter' nonsense at the top-right corner of the page (which you shouldn't be, because you can download drivers all day long without doing that).

I just sent it back to the vendor (under warranty) because the latest OS update caused the speakers to melt.

While browsing the net I noticed the smell of burnt plastic, and quickly noticed the edges (where the speakers are) was too hot to touch. Turned the thing off but they were cooked.

Then I found I wasn't alone... https://forums.geforce.com/default/topic/834884/shield-tablet/speakers-damaged-after-3-0-update/

Apparently somehow the speakers got fed DC current while doing nothing in particular. Impressive if you ask me.

And a lot of "your driver stopped responding so we turned it off, then back on again."

That's the infamous nvidia TDR problem, and has been plaguing their drivers and cards since the very early R.208.xx series drivers. Said TDR problem has been so bad that ~4 years ago they were paying to ship PC's to California for testing to determine the cause of it. It's been on-going since 2008 and they haven't fixed it, or have been working on 'trying to fix it' since then.

The last time nvidia fixed it in mid 2011, it was due to the cards throttling the core voltage down to control the amount of heat being generated. This caused problems in a lot of cards, especially cards which had flaky GPU's that didn't handle voltages well. Well it was fixed for all of about one driver release then it was right back to where it was again.

Irate owners of NVidia graphics cards have taken to support forums to complain that automatically-installed drivers installed have broken their computers.

That would be 17 posters on the NVIDA GeForce drivers forum. Windows 10 Display Driver Feedback Thread

Interestingly the problem has also been experienced by Forbes contributor Paul Monckton who has done some digging and explained to me that the fault lies in a conflict between Windows Update and Nvidia's own driver and software management tool the 'Nvidia GeForce Experience'.

Many PC components and peripherals come with bundled software that automatically manages driver updates already. PC makers also often bolt on driver update management software onto their PCs (Lenovo is a notable example) which then has the potential to conflict with driver updates delivered by Windows Update.

''It looks like driver version 353.54 [the latest at time of writing] is available only via Window Update,'' Monckton told me. ''The problem is the Nvidia GeForce Experience then tried to downgrade that to the previous version while claiming the previous version was actually newer.''

The problem is compounded by the fact that Windows Update doesn't actually reveal driver version numbers prior to install or warn the user in advance so pinpointing something that has suddenly caused problems can be hard to identify.

Given Windows 10 updates cannot be stopped the most obvious solution is to uninstall third party driver management and hand it all over to Windows Update to avoid clashes. This potentially simplifies matters by providing an all-in-one update service, but it does mean taking away control from specialist companies over their own products.

Windows 10 Automatic Updates Start Causing Problems

Nvidia is really starting to piss me off with their proprietary shit like this, Gsync and their 'nVidia hair' bollocks for games.

There's a lot more than just this stuff, too. Since they went from the 9x00 series to the three-digit GTX series, they've been making more and more proprietary and/or user-hostile decisions as time passes.

Sometime around the GTX switch, for example, they started crippling OpenGL calls not used by games to artificially slow down "gaming" GPUs vs. their more expensive workstation counterparts. There are other examples if you search, but in that one the guy that wrote it re-implemented the OpenGL call via shader and got a massive speed increase because the driver couldn't artificially cripple the shader the same way. He also noticed that, not only did performance drop going from a GTX 200 series card to a GTX 480 series, but that it dropped further going to a GTX 680.

Another example is related to PCI-e passthrough of graphics cards in virtualization. This used to be possible with NV cards, as demoed by Ubisoft in this YouTube video. They used GTX 460 cards, with one passed through to the guest OS to get near-native GPU performance in a VM. Fast forward a generation or two and you have to do shit like this to get the same functionality because nvidia started arbitrarily restricting it. (see also this).

There's also this shit where they removed features from the Linux driver for "feature parity" with Windows.

I've been an nvidia user since the late 90s (started with a Riva TNT card), but the GTX 660 in this aging system is going to be my last until nvidia cleans up its act, if it ever does. Based on what I knew about nvidia's support prior to the 600 series, I bought the 660 intending to do VGA passthrough from a Linux host -- use the GTX 260 as the host GPU, with the 660 on a Windows guest for reboot-free gaming -- and was pretty pissed to find out it got crippled for that purpose. Then I was even more pissed when, later, I found out about the OpenGL crippling and their removal of driver features for Linux users.

So, never again. I'll deal with whatever warts AMD's GPUs and drivers have because they, at least, don't artificially limit niche features to up-sell you to $2000+ GPUs. They don't even do it for their CPUs; even their bog-standard consumer CPUs can be used for niche things like VGA passthrough because AMD doesn't lock them away behind slightly different SKUs and a price hike.

The GPU actually has thousands of cores. For example, the GeForce 980 ti has 2816 cores. Compared with a CPU, those cores are much simpler, and they run at a lower clock speed, but for extremely parallelizable operations, a GPU will stomp a CPU easily. That's the reason you see GPUs becoming a major factor in supercomputers. More generalized supercomputers are hybrid systems.

At least the part about:

The vast majority of changes in driver updates for AMD and nVidia are hacks for specific games to fix their broken shit and get them to not run like ass.

Is quite true I'm afraid. NVidia frequently releases "Game Ready" drivers tuned for a specific game. Usually for high-profile new game releases, such as the Witcher 3 most recently.

This most recent batch of new "Game Ready" drivers fucked up my and other users systems by frequently crashing, causing the driver and the display to reset, sometimes even on the desktop while browsing. Sometimes this happens multiple times within a minute, rendering some games unplayable. This is one of the threads on the latest clusterfuck on this issue: NVidia display driver stops responding.

Still no fix from NVidia.

A good summary. Here is Nvidia's overview of G-SYNC.

1. Actually the current claim is that FPGA is mostly for DRM, as it's basically a DRM wrapper around activesync, which is what G-sync appears to be. According to the guy behind this discovery at least.
2. Factually incorrect. G-sync is in fact inferior to Adaptivesync in refresh rate range in the current implementation. G-sync range is 30-144Hz, where Adaptivesync can handle (depending on the scaler) 36-240Hz, 21-144Hz, 17-120Hz and 9-60Hz.
Source: http://www.geforce.com/hardwar...
http://www.anandtech.com/show/...
3. In general, when someone uses a word "experience" to describe something as simple as syncing refresh rate, you know you're about to read some marketing bullshit. You certainly delivered, by arguing that alpha leaked driver delivering worse results than finished product is evidence of superiority of finished product.
5. Correct. However this is not about the driver, but what finding the fact that G-sync "mobile" is actually Activesync in a wrapper means for previous statements of Nvidia on the topic. Specifically that it means that a lot of those statements have been lies.
And then there's the issue of the claim that G-sync is actually activesync in a DRM wrapper, presented by the original source that got its hands on the driver.

Hmmm... Again, no mention of the spontaneously cracking trim, which Nvidia lied about and said was fixed, but it turns out it wasn't fixed and they are still randomly cracking, and now Nvidia refuses to respond to their customers which are demanding an answer in the form of a petition? Or how about the notoriously weak WiFi antenna, which can be blocked by "holding it wrong".

Or how about the shoddy screen which scratches very easily because it lacks Gorilla Glass, or how about how the battery drains incredibly fast, how the screen distorts from barely pressing it, how it loses charge even while plugged in, and how it gets incredibly hot and actually melted two units and almost burnt down houses according to the Nvidia forums?

This tablet is a cheap ass fucking joke that was pushed out the door with zero testing, and now Nvidia tries to sweep all the issues under the rug. But oh lookie, a 7 year old game is being released, how innovative!

This article is pure payola.

Hmmm... Again, no mention of the spontaneously cracking trim, which Nvidia lied about and said was fixed, but it turns out it wasn't fixed and they are still randomly cracking, and now Nvidia refuses to respond to their customers which are demanding an answer in the form of a petition? Or how about the notoriously weak WiFi antenna, which can be blocked by "holding it wrong".

Or how about the shoddy screen which scratches very easily because it lacks Gorilla Glass, or how about how the battery drains incredibly fast, how the screen distorts from barely pressing it, how it loses charge even while plugged in, and how it gets incredibly hot and actually melted two units and almost burnt down houses according to the Nvidia forums?

This tablet is a cheap ass fucking joke that was pushed out the door with zero testing, and now Nvidia tries to sweep all the issues under the rug. But oh lookie, a 7 year old game is being released, how innovative!

This article is pure payola.

Gsync does help with input lag / latency. From the horse's mouth, it's mentioned numerous times: http://www.geforce.com/hardwar...

G-sync is about syncing output of the buffer to frame rate to avoid tearing. It does nothing to latency.

JIT rendering also made it to maxwell btw, but that's a whole different story.

http://www.geforce.com/whats-n...

I'd say price point matter more at this point.

I would prefer to have an Nvidia card and I would prefer to have monitor synced to the GPU.

As is Adaptive-Sync may be a standard of DisplayPort 1.2a but even the new Nvidia cards only have DisplayPort 1.2 and who knows what Nvidia will do. It suck to get an Nvidia card if they are retarded and decide not to support Adaptive-Sync but I don't want anything else either because Nvidia make the best products. :/

Some time some idiot lectured me using this:
http://www.geforce.com/hardwar... .. except it's not the same thing (that person may have also lectured me about DX12 which may have been correct (in that all Nvidia DX11 graphic cards will support DX12.))

Nope http://www.geforce.com/hardwar... . Trust me I have tried and they don't allow you to drive more than four even in SLI mode.

Finally it has monitor ports, which implies you can drive 5 , nope only 4.

I can get a PC that is more powerful with the same amount of RAM for that price.

it won't have 8GB of GDDR5 RAM will it.

The CPU in the PS4 is the performance equivalent of a low end PC processor, such as a dual core Pentium.

BS. That's 8 1.6 GHz cores in the PS4.

The GPU, being integrated, is also pretty low end.

You're thinking like a Filthy PC Gamer bourgeoisie philistine. Integrated doesn't mean the same thing in console land. The PS4's GPU is is a customized version of AMD's 7870 GPU, with 2 CUs disabled.
That's not a traditional "integrated" GPU like you're implying.
It is most certainly better than the GT640 I've got in this Fedora machine.

Let me find a machine to compare:

http://www.amazon.com/Dell-i36...

Lets see that costs $379, has a dual core CPU, 4GB of RAM and intel HD graphics. Can that thing even run Watch Dogs?
No.

http://www.geforce.com/games-a...

It's been all this time and multi-monitor (sorry, "TwinView") and SLI is still not supported? I'm starting to give up hope that it ever will be. My options are to either get a new, single, video card; or reconfigure X and lose my extra monitors while I'm in-game, and then do it again when I'm done; or just not use SLI at all. It was supported on Windows Vista, for crying out loud.

Except that Titan isn't really a gaming card.

OK, tell that to NVidia:

GeForce GTX TITAN Z is a gaming monster, built to power the most extreme gaming rigs on the planet. With a massive 5760 cores and 12 GB of 7 Gbps GDDR5 memory, TITAN Z gives you truly amazing performanceâ"easily making it the fastest graphics card weâ(TM)ve ever made.

This is a serious card built for serious gamers.

Hard to get more definitive than that.

OK, you can argue that NVidia is simply lying; that they engineer these for professional applications and then make a rebadged version to score an easy buck by conning ego-driven gamers. But what kind of defense is that?

http://la.nvidia.com/object/nz...

"The Way It's Meant to be Played"
Nvidia pays you shitload of money for participating in this program, and can additionally guarantee certain sale goals (by bundling your product with their GPUs).
In order to participate you only have to do two things, insert nvidia ad clip at the start of the game, and let nvidia rape your codebase.

On paper Nvidia pays you for joint marketing campaign, but deep down in the paperwork you are letting them decide what your codebase will look like.

Oh look, what a coincident: Watch dogs, game that is crippled on AMD, is a participant
http://www.geforce.com/getwatc...

They just need to stop treating LCD displays as if they were CRT displays. See NVidia G-Sync

http://www.geforce.com/hardwar...

I tried to find some hard data on either statement. It looks like the model number in TFS is a typo, and the test I found that showed results with BF4 neglected to explain what the medium settings are. It does, however, show us an average of 28fps, which would support your definitely not 30fps by a hairsbreadth. Now if only there were some technology to make that difference from 20fps count...

GTX650 or better: http://www.geforce.com/hardware/desktop-gpus/geforce-gtx-650/specifications
Few cards have multiple HDMI ports, so you'd probably want DisplayPort to HDMI converters.

nVidia has at least three versions of the GT630, each fairly different from one another. None of these would be an amazing accomplishment to beat, although they are more powerful than Intel's normal integrated offerings.

BUT the reality is that Arm SoCs are cutting into both intel and amd. The shine is off the 45-65 watts small space heater chipsets and the race to heat whole rooms with 100 watt plus chips is over.

Power = power. Or less vaguely, electricity = computational power; more = better.

Low-end stuff is going low-power but if you want a system to do video editing+encoding, CAD, compilation of large software or any of the other common problems then buying a mobile phone glued to the inside of a normal desktop chassis is a really dumb idea. [In short: Workstations are not going anywhere. Professionals will still use them, just home user penetration will drop off.]

Good points, but it all comes down to bang for buck. Most graphic houses use high powered servers and a few high powered work stations. The market for small form factor devices that pack a decent punch at low wattage on the desktop is still there. People using game consoles for net access in the living room proves one thing there is a market for something quiet small and with a fair computational punch. Microsoft and Sony have gone for the closed ecosystem approach to the users living rooms.

There is room for something like a Steambox that can do much more and more importantly if this same device can easily be converted into a desktop full fledged computer it might catch on with more than just gaming. Nvidia is already trying to rev up the market but they do not have the marketing skills to make it work as they are up against a wall of competition and essentially they have no access to retail store space and no way to showcase what they are really capable of doing on devices without Microsoft and Windows getting in the way.

This is why they need to collaborate with someone like AMD and go head to head against the Wintel juggernaut. It can be done. By and large the general public hates Windows and this is not at all because of the companies that manufactured the components and computers. Sure sell Windows on the device for those that insist upon it, but if Microsoft turns around and bullies you for selling a genuine dual boot system, joe public might just be with you this time around. Advertise your steam linux install as a new and revolutionary multipurpose operating system with full fledged pc capabilities as well as being a great gaming console.

After all FFMPEG is already being used just about everywhere on the planet except on a straight install of Windows or Mac! Go after the jugular and do things with OpenGL and FFMPEG on Linux that leaves DirectX and Windows in the dust. Again it can be done! Samsung is already cleaning up with smart TVs and they all use some form of the Linux kernel in combination with FFMPEG. Let Microsoft bang down your door and threaten you with their hoard of little weasel lawyers. If the public thinks they are being prevented from having something by a bully like Microsoft it could really pay off in a hurry! Like I said the Samsung/Apple war did wonders for Samsung to say the least.

Wow, not only did you not read the article, you didn't even look at the pictures, did you?

I looked at the pictures. I saw artifacts from scaling 1024x768 4:3 aspect ratio content to 1600x900 16:9 aspect ratio content from source material encoded at 1024x768, with intentional watermarking to identify the iTunes account that the data was pulled down from. Do you often watch your television with a microscope?

The cable is advertised as doing "up to 1080". It does not.

I'm not sure I buy the information in the blog post. Specifically, the thing that drives the EDID negotiation is the display device; it states what resolutions it supports, and the device driving the display picks from that list and advertises it back to the display. If the EDID negotiation in the display device isn't working correctly (many don't), or the information communicated over the input port is just plain incorrect, then it's going to negotiate down using the set of defaults that the device providing the input signal uses when the display device fails to adhere to the standard.

I've already pointed out that there are a large number of Samsung Televisions which will not negotiate EDID on inactive channels. This causes problems with Samsung Chromebooks when used with these televisions, unless you hook them up to the default HDMI input so that the input channel is active at the time. Ideally, the Linux video stack would workaround this problem by reattempting to negotiate an EDID periodically until it was either successful, or hell froze over, whichever came first. When Google was working on the Chromebooks and first encountered the problem, Samsung was able to supply beta firmware updates for the Television to allow the negotiation to happen on unselected but electrically active channels.

So those numbers in that blog post are for the EDID information being advertised by the display, and it's no wonder that the display is only offering 1600x900 (I would not be surprised if instead of a Samsung TV, the problem device was a DELL monitor instead).

Here's another TV that has the same problem as some of the Samsung TV's; it's a Kogan KGN1080P32VAA, and it actually fails to advertise the correct EDID information at all. You can work around the problem by stuffing fake EDID information into the nVidia card driver, but it's not at all surprising that Apple doesn't provide you with the ability to do this with their cable: https://forums.geforce.com/default/topic/478250/working-around-tvs-with-defective-edids-useedid-works-but-kills-hdmi-audio/

Alternately, you can continue to buy crappy displays with busted firmware, and workaround the handshake issue by buying a box like this one: http://www.vidabox.com/products_dr_doctor_hdmi.php to let you set the handshake see by the Apple cable to be correct.

Did you look at the picture? Those are not scaling artifacts: there is noise around edges. Those look like artifacts from MPEG or a similar compression algorithm. If it was just scaling, it would introduce aliasing patterns, which is not what they are talking about.

Unless they ripped the content themselves from a DVD to load onto the iPad Mini, I'm going to go with them having either downloaded a torrent (notoriously bad compression artifacts), or having downloaded it from the iTunes store (720P, always scaled, 1024x768, different aspect ratio from what was being displayed).

Next thing I know, you'll be claiming that Apple didn't replace all the already transcoded content on the Inktomi CDN with new, higher resolution content over night!

What does that have to do with this discussion?

It's all encoded at 1024x768 4:3 aspect ratio; that's what it has

A GTX680 has a maximum power usage of 195 W.

http://www.geforce.com/hardware/desktop-gpus/geforce-gtx-680/specifications

Really? Try this page.
http://www.geforce.com/drivers/results/49740
Still plenty of support for the 7 series.

The Mac Pro desktop has a ATI Radeon HD 5770 card. If you look at ATI's 5000 series list, you'll see that's right in the middle of the product line. Considering how much the system as a whole costs, some people feel that's not good enough.

The problem isn't that a midrange 5000 series isn't "good enough" (it actually is for a lot of people), it's that the 5770 is getting pretty old in the tooth. The Mac Pro hasn't been seriously updated in ages.

The "Retina" MacBook pros have an even worse problem. The NVIDIA GeForce GT 650M is also nowhere near the top of their mobile line

No, that's not actually a problem at all. The only reason the 650M isn't regarded as "top of the mobile line" is that NVidia's top "mobile" GPUs are ridiculous 100 watt chips which are only found in ridiculous 10-pound 17" Alienware gaming "laptops", and the like. In other words, they're chips which are "mobile" in name only.

The 650M is pretty much the fastest GPU NVidia makes for practical laptops (that is, ones which are thin, light, and have a decent battery life). And unlike the situation with the Mac Pro, it is a current generation GPU.

A fair number of people pushing it hard have discovered it's really not capable of keeping up with that system's 2880 x 1800 display very well.

Links? Most people I've seen said something along the lines of "scrolling was a bit herky in 10.7.x but is just fine in 10.8".

Now, if you're talking gaming rather than ordinary desktop use, then yeah. 2880x1800 is a lot more pixels than 99% of desktop gaming GPUs are expected to drive, so it's not too surprising that lots of games slow down. But that's easily fixed by rendering at a lower res and upscaling, which looks better than you might expect.

The problem is the graphics GPU, not the CPU. The Mac Pro desktop has a ATI Radeon HD 5770 card. If you look at ATI's 5000 series list, you'll see that's right in the middle of the product line. Considering how much the system as a whole costs, some people feel that's not good enough.

The "Retina" MacBook pros have an even worse problem. The NVIDIA GeForce GT 650M is also nowhere near the top of their mobile line. But the resolution being driven is one of the highest available. A fair number of people pushing it hard have discovered it's really not capable of keeping up with that system's 2880 x 1800 display very well.

>> Linux has everything they need

except driver support from nvidia

http://www.geforce.com/drivers/results/50195
http://www.geforce.com/drivers/results/50196

>> Linux has everything they need

except driver support from nvidia

http://www.geforce.com/drivers/results/50195
http://www.geforce.com/drivers/results/50196

Maybe something will finally use those 8-core processors and 1536-core graphics cards.