Announcement

Collapse
No announcement yet.

AMD Catalyst 9.12 Hotfix released

Collapse
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • #31
    At least they got that fake Fermi out there . Seriously, nvidia has been making asses of themselves lately. "AMD's lead on DX11 does not matter". Yeah, right. They would be singing a different tune if their precious Fermi was out.
    The thing will be fast and monstrous, if the hype is to be believed. Just wish the damn card would be out now so it can drive prices down.
    Last edited by Melcar; 12-20-2009, 01:17 PM.

    Comment


    • #32
      Do you really think current ATI cards will be faster on LINUX? Well the current Linux games are not that demanding, Unigine based games would be more interesting - or what about ID Rage... Also why not use CUDA or OpenCL for some apps? If you don't know what you could do just search for E.T.

      Comment


      • #33
        Originally posted by Kano View Post
        If you don't know what you could do just search for E.T.
        You mean this?

        http://www.youtube.com/watch?v=l3w5gmdKdAQ

        Comment


        • #34
          Originally posted by Kano View Post
          Do you really think current ATI cards will be faster on LINUX? Well the current Linux games are not that demanding, Unigine based games would be more interesting - or what about ID Rage... Also why not use CUDA or OpenCL for some apps? If you don't know what you could do just search for E.T.
          "Do you really think current ATI cards will be faster on LINUX?"

          i believe in physical facts!

          2720 GFlops SP (MAD) on AMD 5870
          4640 GFLOPS SP (MAD) on AMD 5970


          1536 GFLOPS SP (MAD) on nvidia Fermi


          Nvidia can't win!

          " Also why not use CUDA or OpenCL for some apps?"

          yes why not use openCL on an AMD card ?

          Comment


          • #35
            I would say it is even hard to win for a 5870 against a gtx 285 on Linux. those numbers say nothing about gaming speed. Also often there are more apps directly for cuda than for opencl.

            Comment


            • #36
              So we have a choice between the NVIDIA Fermi which doesn't exist and ATI hardware which doesn't have drivers? Drivers that work on Fedora at least. Between the two I think that ATI has the easier task.

              Comment


              • #37
                Originally posted by Kano View Post
                I would say it is even hard to win for a 5870 against a gtx 285 on Linux. those numbers say nothing about gaming speed. Also often there are more apps directly for cuda than for opencl.
                ok why sould there be more cuda apps in the future than openCL apps?

                Cuda is the past! OpenCL is the future!

                and.... if the numbers do not matter no one will buy a new card ever,never!.....

                3 TFLOP's will every-time win again 1GFLOP.......

                Comment


                • #38
                  The only "FLOP" here is AMD Catalyst.

                  Comment


                  • #39
                    FLOPS don't always translate into 3D performance though. There are two paths Fermi can take:

                    1. The thing ends up being nvidia's HD2xxx blunder (delayed, under performing compared to the competition, power hungry), but with some nice features

                    2. Fermi blows everything out of the water, but availability and price (and delay) hurts its competitive edge

                    I'm betting it will be #2. No doubt it will be powerful and full of really nice features.
                    Last edited by Melcar; 12-20-2009, 05:35 PM.

                    Comment


                    • #40
                      here is some info - but of course that's from semiaccurate.

                      Comment


                      • #41
                        Originally posted by mirv View Post
                        here is some info - but of course that's from semiaccurate.
                        Yes Nvidia runs into a Death of Bankrupt.

                        but this article is FUD! but there is another article with much more "True"

                        "Nvidia GT300 yields are under 2%"

                        the fermiG300 is a monster big very super big chip.....

                        the chip by 80% yield rate are very very expensive!

                        but @2% yield rate.. fermiG300 is a Bankrupt!

                        they sould make mid chips passive Cooled with high Yield-rate and Opensource drivers.........

                        but..... they only do bullshit megabigchips low yield rate extrem hot chips and no opensource driver supportet by nvidia...........


                        the G300 Yield rate bankrupt nvidia be sure!

                        Comment


                        • #42

                          Comment


                          • #43
                            Originally posted by Qaridarium View Post
                            Yes Nvidia runs into a Death of Bankrupt.

                            but this article is FUD! but there is another article with much more "True"
                            You gotta be kidding me. At least I think you're spreading more FUDs than the quoted articles are.

                            nVidia does more things than just consumer graphics. Keep in mind that they also have Tegra, the Ion platform and the upcoming GeForce based on the Fermi architecture (read up on MIMD). On the market end, you should really compare the relative size of both companies. nVidia, with its graphics portfolio *alone*, garners a market cap of $10.040 billion, as compared to $6.64 billion from AMD's combined portfolio of CPU, GPU and chipset technologies. (Just to put things into perspective, Intel's market cap is a whopping $112.26 billion)

                            Now, the issue today is not about who has the higher theoretical GFLOPS (it says "theoretical", you see). The actual throughput is all that matters. As you can see, the default configuration from ATI Radeon HD5870 has 2720 GFLOPS of (theoretical) single-precision floating point performance. Compare that to a similarly-placed nVidia product, the nVidia Geforce GTX295, which has 1788 GFLOPS in performance. Now, I would expect the Radeon HD5870 to have 52% higher performance in every benchmark. In actuality, this isn't the case. The Radeon HD5870 is only marginally better, and sometimes worse than the GTX295. This 3DMark Vantage benchmark proves this. Remember, the current ATI cards (RV6xx - RV8xx) still use five-way VLIW units, and this architecture is one that is not easy to optimize for. Not forgetting the fact that Fermi boosts its efficiency by having parallel kernel support which previously didn't exist in its architecture. There are also a myriad of architecture changes - the SFUs are now decoupled from the SMs in a warp.

                            In addition, the yield problems with the 40 nm manufacturing process used at TSMC did affect *both* ATI and nVidia. If you haven't heard yet, the blog poster who said that nVidia has a < 1.7% yield on the GT3xx is a denounced ATI fanboy. I shan't comment further on this.

                            You should really read up on *real* sources - like Anandtech and the like. Disclaimer: I am typing this on a laptop with ATI Mobility Radeon HD4670, Catalyst 9.12 driver on Ubuntu.

                            Comment


                            • #44
                              Originally posted by Kano View Post
                              @Qaridarium

                              Fermi will be definitely the first choice for LINUX users. Most likely for Win too if you have got enough money Just because of the working features - not because of features that will work in the future. I gave up the idea that xvba will be ever fixed and that gallium3d approach to simulate vdpau/vaapi or whatever using shaders will most likely not work on low end cards - and buying medium/highend cards for that is wasted money. Using oss drivers for those cards is like paying for a porsche and driving a fiat. I definitely do NOT need kms, it does not matter if it flickers when it switches from vt to X. The 2-3s delay is not optimal, but how often do you need to do that?
                              are you paid for posting this bullshit?

                              Fermi will be no choice for most people. No matter which OS they use. Because it is broken by design, fat and expensive. But dream on.

                              Comment


                              • #45
                                Lets see when you can buy it, the cards for testing are already out there. Most likely soon for the press too.

                                Comment

                                Working...
                                X