Announcement

Collapse
No announcement yet.

The Open-Source Linux Graphics Card Showdown

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

  • #31
    @Qaridarium

    First of all intel produces already cpus for other companies. Also until recently when amd paid lots of money to be fully independent from the factory part they had a contract that they needed to produce the cpus there. Now they could produce anywhere but i do not know if they want to pay intel to create their chips. Usually the layout needs to be optimizied for the production way as well, so you can not only shrink it and it still works. amd already pays for x86 patents, so intel gets a few cents from every cpu amd sells (or maybe $, dont know the contract). the 22nm production is most likely not fully optimized as intel only sells the quad cores right now. those are much more expensive compared to the dual cores. For better profit the yield must be high enough, that was the main problem for amd and their factory as well as for tsmc who produces the gpus for amd + nvidia. Every shrink needs some time to be fully optimized. if amd pays well and intel has spare capacities i dont see a problem why intel would not produce the chips, they get money in any way, but of course less when amd produces em somewhere else.

    Comment


    • #32
      Originally posted by Kano View Post
      @Qaridarium

      First of all intel produces already cpus for other companies. Also until recently when amd paid lots of money to be fully independent from the factory part they had a contract that they needed to produce the cpus there. Now they could produce anywhere but i do not know if they want to pay intel to create their chips. Usually the layout needs to be optimizied for the production way as well, so you can not only shrink it and it still works. amd already pays for x86 patents, so intel gets a few cents from every cpu amd sells (or maybe $, dont know the contract). the 22nm production is most likely not fully optimized as intel only sells the quad cores right now. those are much more expensive compared to the dual cores. For better profit the yield must be high enough, that was the main problem for amd and their factory as well as for tsmc who produces the gpus for amd + nvidia. Every shrink needs some time to be fully optimized. if amd pays well and intel has spare capacities i dont see a problem why intel would not produce the chips, they get money in any way, but of course less when amd produces em somewhere else.
      None of that matters.
      All that matters is that AMD's got

      Comment


      • #33
        Originally posted by droidhacker View Post
        I also question the performance tests. Intel is known for playing games in order to benchmark higher. It wouldn't surprise me one bit if there was something sneaky in the CPU that knows when someone else's GPU is attached and does something like cutting memory bandwidth. Intel is known for pulling sneaky crap, like designing CPUs FOR the benchmarks, rather than the real workload.
        This is also why Intel was sued over ICC, At best it only allows non Intel 64 bit CPUs have SSE2, in 32 bit it pushes them into 486 mode. The most obvious example of this is the SuperPi benchmark.

        Comment


        • #34
          Originally posted by Kano View Post
          Thats incorrect. The gpu part has got different voltage pins, you can select the differently to gpu voltag on Z boards. The default is that it is disabled as soon as you add a PCI-E gfx card, but you can force it to stay enabled if you want to use it together with virtu (on win). Intel even sells chips with disabled gpu part, not yet for ivb, but for snb like:

          http://ark.intel.com/compare/52273,52274

          Just a matter of time, then intel has got too many ivb cpus without working gpu and wants to sell those too
          If I'm not mistken aren't Intel's GPUs just a 2nd chip on the same CPU package while AMD's have both as part of the same chip? Hence why the APUs have their own CPU socket?

          As for the non IGP parts, thats not what the OEMs want, they want just the single chips so they can cut costs, they don't want to have to install a GPU as well.
          Last edited by Kivada; 04-27-2012, 04:46 PM.

          Comment


          • #35
            Often you get pci-e cards together with cpus with gpu integrated. Not because of so much higher speed (as they mainly use low cost cards that could not be the real reason), but just to write some fancy things like 2gb vram (for the extra slow chip) or similar onto the flyer.

            Comment


            • #36
              Originally posted by Kivada View Post
              If I'm not mistken aren't Intel's GPUs just a 2nd chip on the same CPU package while AMD's have both as part of the same chip?
              No. The Clarkdale/Ironlake combo was what you describe (hence the different name for CPU and GPU), but Sandy Bridge and Ivy Bridge are a combined CPU+GPU chip, just like AMD APU.

              Comment


              • #37
                Originally posted by Gusar View Post
                No. The Clarkdale/Ironlake combo was what you describe (hence the different name for CPU and GPU), but Sandy Bridge and Ivy Bridge are a combined CPU+GPU chip, just like AMD APU.
                Actually no what he's talking about is CPU+GPU on the same CPU die, his question relates to it being two chips on the same die, or one that's just one chip, and at least Sandy Bridge it is still 2 chips on one package according to the analysis, with a pipe between them, I haven't seen an analysis of Ivy Bridge yet, but since it's a die shrink + more units I would imagine that it would be the same for that too

                Comment


                • #38
                  So, in conclusion: at the moment the free Intel drivers are the best at using the most of the hardware.

                  Sounds fair enough to me. I am still happy with my Radeon HD 4670 though - I like hardware with a developing future.

                  Still, credit where credit is due - well done Intel.

                  Comment


                  • #39
                    Originally posted by Luke_Wolf View Post
                    Sandy Bridge it is still 2 chips on one package according to the analysis, with a pipe between them
                    Hmm, can someone (preferably an Intel dev) confirm that? If I'm wrong, I'd like to know, so that I won't be saying wrong stuff in the future anymore.

                    Comment


                    • #40
                      Originally posted by droidhacker View Post
                      Colors are funny things to work with mathematically. The main thing you need to keep in mind is that you have to treat colors as THREE numbers, not just ONE.
                      To make it even more complicated, the human eye is naturally more sensitive to certain colors than others, so it makes sense to divide into smaller regions in certain spectrums and not others.

                      Comment


                      • #41
                        Originally posted by Gusar View Post
                        Hmm, can someone (preferably an Intel dev) confirm that? If I'm wrong, I'd like to know, so that I won't be saying wrong stuff in the future anymore.
                        No, i'm pretty sure starting with Sandy Bridge it's 1 chip on 1 package.

                        There is just a pipe between the 2 sections of the chip, so communication between the 2 is exactly the same as if it was on a different chip, but it's built as one.

                        AMD iGPUs are the same. Actually, not quite - Sandy/Ivy Bridge share the L3 cache with the GPU, while AMD doesn't have that ability. Unless Trinity adds that, which it might.

                        Eventually they will get better integrated, and you'll probably see things like the CPU transferring floating point operations onto the GPU hardware, but i don't know how far out that is.

                        Comment


                        • #42
                          HD4000 linux vs. winsows; windows OGL3.3?

                          could we have comparison between Ivybridge OGL linux and Windows drivers? Some time back there was such comparison provided on phoronix for sandybridge and it was very helpful. Thanks!

                          I found info here on geeks3d.com that Ivybridge Windows driver supports OGL3.3. Do you see same result?

                          Thanks again!

                          Comment


                          • #43
                            I think only SNB shared the 3rd level cache, IVB does not.

                            Comment


                            • #44
                              Obligatory post making fun of some random typo in the article that will never be corrected:

                              Holy thermo-nuclear GPU Batman!! The Radeon HD 4670 idles at 766 Watts??? Surely it must produce a truckload of heat

                              Comment


                              • #45
                                Originally posted by droidhacker View Post
                                Colors are funny things to work with mathematically. The main thing you need to keep in mind is that you have to treat colors as THREE numbers, not just ONE.
                                It's worth remembering that there are different ways to represent colour: the way you are describing is the RGB colour space, and should be treated as 3 separate numbers for (hopefully) obvious reasons. If you use the HSV (Hue, Saturation, Value: https://en.wikipedia.org/wiki/HSV_color_space) colour space then it is reasonable to fix the saturations and values and choose equidistant values for the hue.

                                Comment

                                Working...
                                X