Announcement

Collapse
No announcement yet.

Unigine Needs Your Help Testing Out Their New Hardware Detection

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

  • Unigine Needs Your Help Testing Out Their New Hardware Detection

    Phoronix: Unigine Needs Your Help Testing Out Their New Hardware Detection

    Unigine will soon be releasing their much-anticipated Superposition benchmark. This is their first tech demo / benchmark powered by Unigine Engine 2 and will be stunning for Linux users and don't mind stressing their high-end graphics card and OpenGL driver...

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    is it just me or does hardware detection destroy the purpose of a benchmark?

    Comment


    • #3
      Originally posted by cj.wijtmans View Post
      is it just me or does hardware detection destroy the purpose of a benchmark?
      Probably just you, I would like to know how my hardware compares to other hardware.

      That said, if they are using it for optimisation or to nerf some brands, that's a whole different matter. I doubt they would do this though, they want to sell licenses for their engine. They want it to look as good as possible on all hardware brands. Unlike 3dmark that uses their's for benchmarking only.

      Comment


      • #4
        Originally posted by cj.wijtmans View Post
        is it just me or does hardware detection destroy the purpose of a benchmark?
        It's useful if you want to know when you can enable the Vulkan renderer checkbox and when you can't.

        And speaking of renderers, Superposition was supposed to launch without Vulkan, but with DX12 support (with Vulkan coming at a later date). Does anyone know if that's still the case?

        Comment


        • #5
          Will check when I get home, would be interesting to see if it's multicard / PRIME aware

          Comment


          • #6
            Originally posted by dlq84 View Post

            Probably just you, I would like to know how my hardware compares to other hardware.

            That said, if they are using it for optimisation or to nerf some brands, that's a whole different matter. I doubt they would do this though, they want to sell licenses for their engine. They want it to look as good as possible on all hardware brands. Unlike 3dmark that uses their's for benchmarking only.
            you realize it nullifies your comparison right? Think about it.

            Comment


            • #7
              Originally posted by cj.wijtmans View Post
              is it just me or does hardware detection destroy the purpose of a benchmark?
              That depends on what it does, if it's only about performance reports then it's fine, if it's about fine tuning then it becomes problematic.
              They mentioned the first case in their FB post, when they explain what the users will gain, so that can be good, but they don't explain what they gain so who knows.

              Comment


              • #8
                Originally posted by geearf View Post

                That depends on what it does, if it's only about performance reports then it's fine, if it's about fine tuning then it becomes problematic.
                How is it problematic? Unless you're talking about benchmarks, it's pretty normal for an engine to choose different code-paths for different hardware to achieve higher performance.
                Perhaps some shader instructions execute faster on card A, but another different set of instructions (that achieve the same, or close to the same effect) will execute better on card B? Or maybe an API extension is better suited for vendor A, while the other extension that provides similar capabilities will be better of vendor B, even though both vendors support both extensions...

                Remember we're talking about a game engine; a benchmark should of course execute exacly the same code eveywhere, even though hardware vendors often detect the benchmarking software and replace shaders with their own hand-crafter ones for speed.

                Comment


                • #9
                  Looking at the post, it just seems like they're testing the hardware detection that's going into the benchmark itself, for tying the score to your hardware. They want to make sure the detection works properly across all (or at least most) systems. For example, it didn't properly detect my max CPU frequency or voltage.

                  Comment


                  • #10
                    Originally posted by mdias View Post

                    ...Unless you're talking about benchmarks, it's pretty normal for an engine to choose different code-paths for different hardware to achieve higher performance...
                    I think in case of Vulkan or DX12, this is pretty much mandatory. It's the primary reason developers wanted lower level APIs in the first place.

                    Comment

                    Working...
                    X