Quantcast

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

GPUs mixing graphics and compute

QuizzicalQuizzical Member LegendaryPosts: 22,127
Everyone who follows GPUs knows that AMD had a far more efficient GPU architecture than Nvidia during Nvidia's Fermi generation.  That is, comparing the Radeon HD 5000/6000 series to the GeForce 400/500 series.  Then with Kepler, Nvidia got a slight lead, comparing the Radeon HD 7000/Radeon R 200 series to the GeForce 600/700 series.  With Maxwell, Nvidia has really pulled away, with the GeForce 900 series massively more efficient than the Radeon R 300 series.  That's true by whatever metrics you prefer, whether performance per mm^2, performance per watt, performance per $ to build the cards, or whatever.  Right?

Wrong.  That's because you're only considering graphics.  Up through Nvidia's Tesla generation, their GPUs were really only built for graphics, and if you wanted to try to use them for anything else, good luck.  With Fermi, Nvidia tried to make an architecture more suited to general-purpose compute.  Compared to previous Nvidia GPUs or even the contemporary AMD GPUs, they succeeded.  AMD, meanwhile, would keep their GPUs focused purely on graphics for another two years.  While AMD GPUs could be used for non-graphical things, their VLIW architectures were very restrictive in what they could handle well, so non-graphical performance was at minimum a pain to code for, and performance would often be dismal.

With GCN, the situation flipped.  Now AMD and Nvidia were both trying to make their GPUs work both for graphics and non-graphical compute.  But Nvidia was focused more heavily on graphics, while AMD put more non-graphical stuff in.  The extra stuff AMD put in came at a cost, and made Kepler slightly more efficient than GCN at graphics.  With Maxwell, Nvidia made an architecture focused purely on graphics, and the non-graphical stuff was out entirely.

So what is this non-graphical stuff?  The most publicized things are double-precision (64-bit floating point) arithmetic and ECC memory, but they're hardly the only things.  FirePro versions of AMD's Hawaii chip of AMD's Hawaii chip (Radeon R9 290/290X/390/390X) absolutely slaughter every other chip ever made in double-precision arithmetic, whether GeForce, Quadro, Tesla, Xeon, Opteron, Xeon Phi, POWER, ARM, Cell, FPGAs, or anything else you can think of.  It beats a GeForce GTX Titan X by about a factor of 14.  Seriously, fourteen.  Getting a Quadro version doesn't help the Titan X, either, and there is no Tesla version.  It beats AMD's own Fiji chip by about a factor of five.  The nearest competitor is Nvidia's best Tesla chip, which the FirePro beats by about 83%.

It takes a lot of dedicated silicon to offer that sort of world-beating double-precision arithmetic performance.  And the silicon to do that is completely disabled in Radeon cards.  Not that it would be used at all for graphics even if it weren't disabled.  Think that has an impact on making the chip less efficient for graphics?  Fiji doesn't have it, which is part of what allows Fiji to be so much more efficient than Hawaii.

Now, double-precision arithmetic tends only to be present in the top end chip of a GPU generation.  AMD and Nvidia have figured out that it's not that expensive to design two versions of your shaders for a generation rather than one:  one with the double-precision units and one without.  But some things that are in primarily for non-graphical compute use aren't so easy to cut out, but rather, filter all the way down the line.

For example, let's consider register space.  In launching the Tesla K80, Nvidia used the GK210 chip, which is basically a GK200 with double the register space per SMX, but fewer SMXes to compensate.  With 6.5 MB of registers, GK210 has more register space than any other chip Nvidia has ever made.  That's considerably less register space than AMD's Tonga, let alone the higher end chips, Hawaii and Fiji.  It's a similar story with local memory capacity and bandwidth, where AMD put in massively more of it than Nvidia, and far more than was plausibly useful for games.

Not that long ago, Phoronix reviewed the Radeon R9 Fury X on Linux, and noted that it was substantially slower than the GeForce GTX Titan X at games, but also substantially faster at compute.  Their conclusion was that compute works well, but AMD needs to put more work into drivers to get gaming performance up to the standards for how well compute works.  Their conclusion was mistaken, however.  They didn't realize it, but the difference they were measuring was in silicon, not drivers.  While Fiji isn't intended as a compute chip, it has the stuff that all GCN chips have that were put in for non-graphical reasons.

It's also important to understand that this is something can change instantly going from one generation to the next.  If, in the next generation, one GPU vendor decides to focus purely on graphics, while the other puts a ton of stuff in for non-graphical compute, the former GPU vendor will predictably be better at graphics and the latter at compute.  Either GPU vendor could independently make either decision (or somewhere in between), however, and can make such a decision independently with every new architecture that they make.

That said, with subsequent die shrinks, there may well be less of a need for GPU vendors to pick their trade-offs here.  Performance is increasingly limited by power consumption rather than die space.  A "typical" full node die shrink can increase your power use per mm^2 by about 40%, as it doubles the transistor count while only reducing power per transistor by about 40%.  An ARM bigwig a while back publicly raised the possibility of "dark silicon" on future chips, that is to say, parts of the chip left completely unused because if you make the chip smaller, you can't have enough pads to get data to and from it.

That may make it possible for GPU vendors to put in all of the compute stuff they want, but power gate it off on GeForce and Radeon cards so as not to waste power, while still including all of the graphics stuff that they want.  Larger caches as mentioned above don't burn much power.  That may be a waste of die space on GeForce and Radeon cards, but if the alternative is dark silicon, so what?
«1

Comments

  • fodell54fodell54 Member RarePosts: 859
    AMD is garbage. I've had 3 AMD card in builds and always traded them out for Nvidia. AMD always and I mean always releases horribly optimized drivers as well as substandard cards. I really don't know where all the test results comes from because every card I've personally own give shit performance. I understand that you're an AMD fan Quiz but at least from my perspective I have never had a good experience with them and will never go back to using one of their cards. No matter the price point or what the test results say.

     I'm sure there are more people here with similar experiences.
  • Thomas2006Thomas2006 Member RarePosts: 1,152
    fodell54 said:
    AMD is garbage. I've had 3 AMD card in builds and always traded them out for Nvidia. AMD always and I mean always releases horribly optimized drivers as well as substandard cards. I really don't know where all the test results comes from because every card I've personally own give shit performance. I understand that you're an AMD fan Quiz but at least from my perspective I have never had a good experience with them and will never go back to using one of their cards. No matter the price point or what the test results say.

     I'm sure there are more people here with similar experiences.

    I agree with you..  I ended up trading out 2 7870's for a single Nvidia 780 ti. Have not ever had as much trouble with graphics cards as I have had with ATI. And I have used several ATI cards throughout the years. After switching back to NVidia with the 780 several years back I won't switch back to ATI for any reason.
  • RidelynnRidelynn Member EpicPosts: 7,061
    To paraphrase PT:
    There's {a nVidia Fanboy} born every minute
  • GruntyGrunty Member EpicPosts: 8,657
    edited August 2015
    I haven't had a problem with either brand's products that was directly related to that product's hardware. I've destroyed a couple of cards by using crap PSUs though. At times each brand has had problems with drivers.  

    I used to buy only nVidia cards largely because AMD/ATI's driver support and updates sucked.  That was several years ago.
    "I used to think the worst thing in life was to be all alone.  It's not.  The worst thing in life is to end up with people who make you feel all alone."  Robin Williams
  • QuizzicalQuizzical Member LegendaryPosts: 22,127
    I would like to suggest that if reading a post that argues that whichever GPU vendor puts more non-graphical compute stuff into their architecture is less efficient at graphics that generation, and that both main GPU vendors have been on both sides of this in the last six years, makes you think that whoever wrote that post must be a fan of one particular vendor, that's pretty strong evidence that you're a heavy fan of the other.

    Really, though, whether you're a fan of one GPU vendor or another is off-topic.  And discovering that one high end card works better than two lower end cards and blaming it on the maker of the lower end cards is further off topic.  This thread is about trade-offs between graphics and compute.
  • DeivosDeivos Member EpicPosts: 3,692
    Kind of talking to the wrong crowd for the most part in that regard. Only side of the fence most consumers are on is the upfront notion of GPU performance for the use of gaming, and many aren't all that apt to consider what other types of operations or activities the card might be called on for and how it performs in that regard.

    The compute element is a wee bit of an esoteric issue for gamers as a result. While it's good for those that want to utilize the card's power for running complex processes or looking at ways to split performance with a CPU, if it doesn't affect graphical performance then it's out of sight and out of mind to those that only care for such.

    On a personal end, I'd be happy to see better options for such implementation. The shrinking die size and capacity to gate access to parts of the chip depending on it's tasks would go a long way in helping it remain efficient while also having the compute power for complex rendering and processing when necessary.

    "The knowledge of the theory of logic has no tendency whatever to make men good reasoners." - Thomas B. Macaulay

    "The greatest enemy of knowledge is not ignorance, it is the illusion of knowledge." - Daniel J. Boorstin

  • IcovaIcova Member UncommonPosts: 33
    Yeah why not ? I assume the cost would be more, most people dont need it, but for those that do, they have access to cards that meet their needs assuming they also game. Unless it's too much of a niche, which I'm inclined to doubt.

    And for those who only need a gaming card, they get the dark silicone version, at a better price point.

    If I'm getting what your saying, that is.




    I endeavor to understand the thinking of those who have shaped our world, yet I lack the ability to insert my head, that far, up my ass.

  • rounnerrounner Member UncommonPosts: 713
    Talk about thinking inside the box. I wrote this years ago http://www.malleegum.com/timspages/Misc/Mega.html where 64 bit precision would make a huge impact. Things have moved on from back then to even more benefit for real time terrain generation to path finding to collision detection. And that's only traditional non experimental work.
  • RidelynnRidelynn Member EpicPosts: 7,061
    rounner said:
    Talk about thinking inside the box. I wrote this years ago http://www.malleegum.com/timspages/Misc/Mega.html where 64 bit precision would make a huge impact. Things have moved on from back then to even more benefit for real time terrain generation to path finding to collision detection. And that's only traditional non experimental work.
    Good site to read, thanks for sharing. I found your work interesting
  • HulluckHulluck Member UncommonPosts: 830
    edited August 2015
    Hey Quiz,

    I just read that Nvidia has problems supporting DX12 on Maxwell while AMD does not. . Async compute, whatever that is but supposedly gives AMD a edge. just read a little about it this morning. But supposedly it has the developers of Ashes of Singularity posting and blogging about it. A huge post on it over at overclock.net. This been talked about here?

    http://www.overclock.net/t/1569897/various-ashes-of-the-singularity-dx12-benchmarks/1210#post_24357053

    Post edited by Hulluck on
  • QuizzicalQuizzical Member LegendaryPosts: 22,127
    Hulluck said:
    Hey Quiz,

    I just read that Nvidia has problems supporting DX12 on Maxwell while AMD does not. . Async compute, whatever that is but supposedly gives AMD a edge. just read a little about it this morning. But supposedly it has the developers of Ashes of Singularity posting and blogging about it. A huge post on it over at overclock.net. This been talked about here?

    http://www.overclock.net/t/1569897/various-ashes-of-the-singularity-dx12-benchmarks/1210#post_24357053

    If one GPU vendor can do something and the other can't, and that something isn't obviously incredibly useful, then it's probably not going to be used in games at all outside of titles sponsored by the vendor that can do it.  Both DirectX and OpenGL have had compute shaders for several years, allowing you to do whatever computations you need for graphics wherever you want them.  I'm not aware off-hand of any games that actually use them, though I could certainly believe that there are such games out there and I'm simply not aware of them.

    Indeed, it's a tribute to the increasing compute versatility of GPUs from both vendors that "older" GPUs mostly support DirectX 12 at launch, rather than having to make radical changes in silicon.  That typically hasn't happened at all with older versions of the APIs, at least for major versions rather than minor steps.
  • QuizzicalQuizzical Member LegendaryPosts: 22,127

    Deivos said:
    Kind of talking to the wrong crowd for the most part in that regard. Only side of the fence most consumers are on is the upfront notion of GPU performance for the use of gaming, and many aren't all that apt to consider what other types of operations or activities the card might be called on for and how it performs in that regard.

    The compute element is a wee bit of an esoteric issue for gamers as a result. While it's good for those that want to utilize the card's power for running complex processes or looking at ways to split performance with a CPU, if it doesn't affect graphical performance then it's out of sight and out of mind to those that only care for such.

    On a personal end, I'd be happy to see better options for such implementation. The shrinking die size and capacity to gate access to parts of the chip depending on it's tasks would go a long way in helping it remain efficient while also having the compute power for complex rendering and processing when necessary.
    I'm not trying to argue that gamers should care about GPU compute.  Most probably shouldn't.  I was trying to offer a more unified theory of what has happened in the GPU industry over the course of the last six years than merely "boo this vendor, yay that one".  Yes, it's esoteric, but I also think it's interesting.
  • QuizzicalQuizzical Member LegendaryPosts: 22,127

    rounner said:
    Talk about thinking inside the box. I wrote this years ago http://www.malleegum.com/timspages/Misc/Mega.html where 64 bit precision would make a huge impact. Things have moved on from back then to even more benefit for real time terrain generation to path finding to collision detection. And that's only traditional non experimental work.
    I don't see where you need 64-bit precision for anything there. I'm not saying you don't, but only that I don't see it.

    Do remember that 64-bit is always going to carry a large performance hit as compared to 32-bit.  For starters, you can only do half as many computations simply because that's all the data you can get from registers.  Fiji has about 50 TB/s of register bandwidth (yes really, 50 terabytes), and lots of other GPUs are well into the tens of TB/s, so it's not like it's trivial to add more.

    Some 64-bit computations manage to be half as fast as 32-bit.  For example, a 64-bit xor is really just two 32-bit xors (which is how a GPU will handle them).  But double-precision multiplication means you need a 52x52 multiply for the mantissa, as opposed to a mere 24x24 for single-precision.  Put a huge focus on that and maybe you can get 1/4 of the computations of if you had put the focus on single-precision instead.

    For graphical purposes, the GPU doesn't need global coordinates, so wanting to do things on a planetary scale doesn't mean you need 64-bit precision on the GPU.  You can keep that data on the CPU and have a GPU handle things in a more local coordinate system where 32-bit precision is plenty.
  • HulluckHulluck Member UncommonPosts: 830
    edited August 2015
    Edit:  I guess it doesn't matter. As to early to know what is what. I did see people saying that it's been a issue for awhile and until now everyone overlooked it. It also seems to be needed for DirectX 12.  So is this feature core to DirectX 12 function good or not? I guess is a better question.

    People have said no reason to rush out and change card brands. Way to early for that. I just know if I just bought a 980TI, I'd be upset.  Do they have DirectX 12 markings on the packaging? I just saw it and noticed people were getting stirred up. No mention of it here. Thought that I would ask.

    No agenda. I use whatever. Have owned both brands.
    Post edited by Hulluck on
  • RidelynnRidelynn Member EpicPosts: 7,061
    The difficult part is: You can have DirectX-12 compliant on the label, and that means a lot of different things. Pretty much, Microsoft allows you to be "Compliant" at certain levels ("Feature Level") so long as your driver can handle all their various API calls. There's nothing saying that all those calls have to be performed by the GPU though. This is how Intel's integrated GPU gets to be called DirectX 12 compliant (Feature Level 12_1), even though it's not exactly that capable.

    Apart from that, I bought a 980 a while back. I didn't regret my purchase when the 980Ti was announced. I don't regret my purchase today. Maybe in 2-3 years when I get something that I want to play on DX12 and it actually starts bogging down I will regret it, but that's a bridge I'll cross if and when I get there, and even then, if I have to upgrade after several years of use, that's about what I had intended when I originally purchased it anyway. DX12 compatible games will be counted on one hand for the near-term future, and the future of DX12 really rests in the reception of those critical first wave of titles.
  • DeivosDeivos Member EpicPosts: 3,692
    Quizzical said:
    I'm not trying to argue that gamers should care about GPU compute.  Most probably shouldn't.  I was trying to offer a more unified theory of what has happened in the GPU industry over the course of the last six years than merely "boo this vendor, yay that one".  Yes, it's esoteric, but I also think it's interesting.
    Well yeah, and I do find it interesting.

    Just saying, a website full of people for which there's only a finite subset that even cares or understands your commentary might not be the optimal locale as a good bit of people will have it fly over their heads and give a response like ride and grunty hopping on the vendor bandwagon.

    But for those of us that like reading it, thank you for posting. ^_^

    "The knowledge of the theory of logic has no tendency whatever to make men good reasoners." - Thomas B. Macaulay

    "The greatest enemy of knowledge is not ignorance, it is the illusion of knowledge." - Daniel J. Boorstin

  • HulluckHulluck Member UncommonPosts: 830
    Ridelynn said:
    The difficult part is: You can have DirectX-12 compliant on the label, and that means a lot of different things. Pretty much, Microsoft allows you to be "Compliant" at certain levels ("Feature Level") so long as your driver can handle all their various API calls. There's nothing saying that all those calls have to be performed by the GPU though. This is how Intel's integrated GPU gets to be called DirectX 12 compliant (Feature Level 12_1), even though it's not exactly that capable.

    Apart from that, I bought a 980 a while back. I didn't regret my purchase when the 980Ti was announced. I don't regret my purchase today. Maybe in 2-3 years when I get something that I want to play on DX12 and it actually starts bogging down I will regret it, but that's a bridge I'll cross if and when I get there, and even then, if I have to upgrade after several years of use, that's about what I had intended when I originally purchased it anyway. DX12 compatible games will be counted on one hand for the near-term future, and the future of DX12 really rests in the reception of those critical first wave of titles.
    Several years of use is good. No reason to complain at all.  If a TI doesn't fully support DirectX 12.  It just came out. That's a lot of money.  I don't know if it does or doesn't. They said Maxwell though. I was just asking if anyone really knows what's going on. Saw nothing about it over here and I stumbled on that thread. Because two developers are having Nvidia related issues with DirectX 12.

    People in that thread  even stated that more testing needed to be done. To be fair I haven't found the post but someone from AMD supposedly said that nobody fully supports DirectX 12 currently even though their cards seem to be handling it better according to that thread. Seems like a big deal for no one to be talking about. I guess people are just waiting to see.
  • GruntyGrunty Member EpicPosts: 8,657
    edited September 2015
    Deivos said:
    Quizzical said:
    I'm not trying to argue that gamers should care about GPU compute.  Most probably shouldn't.  I was trying to offer a more unified theory of what has happened in the GPU industry over the course of the last six years than merely "boo this vendor, yay that one".  Yes, it's esoteric, but I also think it's interesting.
    Well yeah, and I do find it interesting.

    Just saying, a website full of people for which there's only a finite subset that even cares or understands your commentary might not be the optimal locale as a good bit of people will have it fly over their heads and give a response like ride and grunty hopping on the vendor bandwagon.

    But for those of us that like reading it, thank you for posting. ^_^
    Which vendor wagon did I hop on? I said that several years ago AMD/ATI use to have poor driver support. I also said that several years ago that was why I only bought nVidia at that time.

    Quzzical's posts are always interesting to read even if at times I don't understand half of what is said.  Educating those who are ignorant of something is a worthwhile cause.
    Post edited by Grunty on
    "I used to think the worst thing in life was to be all alone.  It's not.  The worst thing in life is to end up with people who make you feel all alone."  Robin Williams
  • DeivosDeivos Member EpicPosts: 3,692
    Yeah I apologize, I kinda scrolled up and down too quickly when writing my post to notice I grabbed the wrong names, I meant to refer to fodell54 and thomas2006.

    Sorry! >_<

    "The knowledge of the theory of logic has no tendency whatever to make men good reasoners." - Thomas B. Macaulay

    "The greatest enemy of knowledge is not ignorance, it is the illusion of knowledge." - Daniel J. Boorstin

  • Thomas2006Thomas2006 Member RarePosts: 1,152
    Hulluck said:
    Hey Quiz,

    I just read that Nvidia has problems supporting DX12 on Maxwell while AMD does not. . Async compute, whatever that is but supposedly gives AMD a edge. just read a little about it this morning. But supposedly it has the developers of Ashes of Singularity posting and blogging about it. A huge post on it over at overclock.net. This been talked about here?

    http://www.overclock.net/t/1569897/various-ashes-of-the-singularity-dx12-benchmarks/1210#post_24357053


    This is off topic but something to remember is that Ashes of Singularity was originaly a ATI Mantel focused game and they put a lot of time into the engine to support Mantel. So I take what they say about ATI and Nvidia with a grain of salt when just awhile back they had all there chips in one side at the expense of all else.
  • skeaserskeaser Member RarePosts: 4,097
    http://wccftech.com/nvidiaamd-marketshare-graph-shows-3-4-gamers-nvidia-gpu/ I'm not alone in saying that I don't care what hardware AMD offers as long as their software sucks.
    Sig so that badges don't eat my posts.


  • QuizzicalQuizzical Member LegendaryPosts: 22,127
    edited September 2015
    Hulluck said:
    Ridelynn said:
    The difficult part is: You can have DirectX-12 compliant on the label, and that means a lot of different things. Pretty much, Microsoft allows you to be "Compliant" at certain levels ("Feature Level") so long as your driver can handle all their various API calls. There's nothing saying that all those calls have to be performed by the GPU though. This is how Intel's integrated GPU gets to be called DirectX 12 compliant (Feature Level 12_1), even though it's not exactly that capable.

    Apart from that, I bought a 980 a while back. I didn't regret my purchase when the 980Ti was announced. I don't regret my purchase today. Maybe in 2-3 years when I get something that I want to play on DX12 and it actually starts bogging down I will regret it, but that's a bridge I'll cross if and when I get there, and even then, if I have to upgrade after several years of use, that's about what I had intended when I originally purchased it anyway. DX12 compatible games will be counted on one hand for the near-term future, and the future of DX12 really rests in the reception of those critical first wave of titles.
    Several years of use is good. No reason to complain at all.  If a TI doesn't fully support DirectX 12.  It just came out. That's a lot of money.  I don't know if it does or doesn't. They said Maxwell though. I was just asking if anyone really knows what's going on. Saw nothing about it over here and I stumbled on that thread. Because two developers are having Nvidia related issues with DirectX 12.

    People in that thread  even stated that more testing needed to be done. To be fair I haven't found the post but someone from AMD supposedly said that nobody fully supports DirectX 12 currently even though their cards seem to be handling it better according to that thread. Seems like a big deal for no one to be talking about. I guess people are just waiting to see.
    I wouldn't put much stock in performance early in development.  GPU programming can be finicky, where you do something slightly wrong and performance drops by a factor of five.  Or ten.  That means there's a substantial learning curve to GPU programming if you want to optimize your code reasonably well.  Even for veteran GPU programmers, though, any time you pick up a new architecture or API, it takes a little time to figure out what it likes and what it doesn't, and during that time, you do get some outlandish, broken performance results.

    If you're inclined to cause trouble, it's not merely easy to write code that one vendor's GPUs will run massively faster than the other.  It's easy to write code that one vendor's GPUs will run well, while the other's gives random junk rather than correct computations, or even crashes outright.

    If DirectX 12 games start launching and show a very strong preference for one particular GPU vendor's architecture, that's a different story entirely.  But let's see it in launched games, not early experiments, before we make a big fuss about it.

    While there things that one GPU vendor handles very well and the other doesn't, it's generally because the other vendor never anticipated that you might want it for games.  See bitcoin mining, for example:

    http://www.hardocp.com/article/2011/07/13/bitcoin_mining_gpu_performance_comparison/2

    That's got a single AMD GPU beating out the top end 3-way and 4-way SLI configurations of the day in an algorithm that trivially scales to arbitrarily many GPUs.  AMD put a rotate instruction in their architecture and Nvidia didn't, so AMD won by ridiculous margins if you needed lots of rotate.

    If games decide that they really need something that one GPU vendor included and the other didn't, then things could get interesting.  I don't expect that to happen, though.
  • t0nydt0nyd Member UncommonPosts: 510
    Well it does seem that certain developers were doing things such as forcing tessellation on objects not even visible to skew benchmarks.
  • HulluckHulluck Member UncommonPosts: 830
    edited September 2015
    That's the conclusion I started coming to about the time of my last post.  They were making a big stink before good testing had been done from multiple sources. They even spoke up and said that later in that thread between my postings. As well as the thing from AMD saying no one had DirectX 12 cards released yet. Never did find that statement. Not saying bad intentions from anyone. Guess I am a bit gullible at times.

    I'm familiar with bitcoin mining. Reason I ended up with a GTX 770. All the new AMD cards had released and were gone as soon as they hit the shelves. I did get a decent deal on the card because of holiday sales.  I want to buy a top end card though next time I buy one. Other expenses (new manual transmission for my jeep.) and I guess I am going to wait and see what next Gen offers. Even though I have no idea how far away that is.

    t0nyd nothing new from either side.  Turning off features that don't work with your card.
  • breadm1xbreadm1x Member UncommonPosts: 374
    edited September 2015
    Witch compute powers its the same as with gaming.
    Some games like AMD some like Nvidia.
    To me AMD has allways been better at 64Bit double presicion floating point.
    And the later Nvidia cards even had that limited so only the tesla card had it.
    (witch is bs since its just the software that does it)
    I own and used both side for computing power.
    I have racks with 4 5870's and with 4 gtx570's some calculation run better on Nvidia some better on the AMD's
    In gaming i found the biggest problems with AMD card's
    Has somthing to do with Antialiassing or driver wise.
    Still i have a r9 290x for gaming :pleased:
    And i am writing this on a pc that has a 580 in it while looking at a rack with 2 GTX275 in it.
    Standing on a rack with 2 5770's in it.
    Some like Nike some like New Balance other like (Matrox) Adidias.
    I buy a card when i wanna buy one, witch one dont realy care, i go for the one that gives me what i want at the time.
    Sometimes its Nvidia sometimes its AMD.
    Next year my 290X gets old and will get replaced with a HBM2 card, witch one i dont know.
    AMD using coolermaster pump (witch is just a relabeled chinese pile of shit) on a Fury X sure as hell made me think about going Nvidia again.
    In the first week i sold 13 FuryX from witch 9 ! returned the cards and took a 980TI back home due to loud pump noises.

    My mini big ITX game cube :P

Sign In or Register to comment.