Announcement

Collapse
No announcement yet.

Radeon ROCm 1.9.1 vs. NVIDIA OpenCL Linux Plus RTX 2080 TensorFlow Benchmarks

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

  • Radeon ROCm 1.9.1 vs. NVIDIA OpenCL Linux Plus RTX 2080 TensorFlow Benchmarks

    Phoronix: Radeon ROCm 1.9.1 vs. NVIDIA OpenCL Linux Plus RTX 2080 TensorFlow Benchmarks

    Following the GeForce RTX 2080 Linux gaming benchmarks last week with now having that non-Ti variant, I carried out some fresh GPU compute benchmarks of the higher-end NVIDIA GeForce and AMD Radeon graphics cards. Here's a look at the OpenCL performance between the competing vendors plus some fresh CUDA benchmarks as well as NVIDIA GPU Cloud TensorFlow Docker benchmarks.

    http://www.phoronix.com/vr.php?view=27235

  • #2
    It is a bit shocking and sad to see AMD so far behind now in compute. Hopefully new cards soon to come will address this.

    Comment


    • #3
      Originally posted by wizard69 View Post
      It is a bit shocking and sad to see AMD so far behind now in compute. Hopefully new cards soon to come will address this.
      As far as I'm concerned, it seems like the drivers just need improvement. Some of these tests show that a Vega 64 can outperform a 2080 so there's definitely real potential there. ROCm is still relatively young for such a complex project.

      Comment


      • #4
        And here I thought we'll finally see the ROCm port of Tensorflow matched against NV cards.

        Comment


        • #5
          Is it possible to extend this test with tensorflow-rocm for the Radeons?
          since 1.12 (I think) the rocm is part of the original tensorflow

          Comment


          • #6
            Originally posted by PinkyDemon View Post
            Is it possible to extend this test with tensorflow-rocm for the Radeons?
            since 1.12 (I think) the rocm is part of the original tensorflow
            Would need to see how its packaged, this testing is with nvidia GPU cloud docker image.
            Michael Larabel
            http://www.michaellarabel.com/

            Comment


            • #7
              Originally posted by Michael View Post
              Would need to see how its packaged, this testing is with nvidia GPU cloud docker image.
              There are some rocm dockers, but I didn't really use them. However "pip install tensorflow-rocm" works just like the tensorflow-gpu for nVidia

              Comment


              • #8
                Originally posted by schmidtbag View Post
                As far as I'm concerned, it seems like the drivers just need improvement. Some of these tests show that a Vega 64 can outperform a 2080 so there's definitely real potential there. ROCm is still relatively young for such a complex project.
                In fairness, the pattern I am generally seeing here is that we lose on synthetics but compete well on real-world applications. I'll ask about the Luxmark compile errors.

                Agree that it would be good to get Tensorflow etc... included in the tests. It's probably not reasonable to expect ROCm support included in NVidia's docker images, but my impression was that PTS tests usually built from source anyways.

                Comment


                • #9
                  Originally posted by bridgman View Post

                  In fairness, the pattern I am generally seeing here is that we lose on synthetics but compete well on real-world applications. I'll ask about the Luxmark compile errors.

                  Agree that it would be good to get Tensorflow etc... included in the tests. It's probably not reasonable to expect ROCm support included in NVidia's docker images, but my impression was that PTS tests usually built from source anyways.
                  Generally PTS does build from source, but in the instance of the NGC-TensorFlow test, it's using the NVIDIA Docker image since building it against all of the different CUDA components, etc, can be a bit finicky that it's much easier relying upon their official binary images. But will look into tensorflow-rocm and if it behaves nicely with just a Python pip install can get it added, wasn't aware the TensorFlow ROCM support was in good shape.
                  Michael Larabel
                  http://www.michaellarabel.com/

                  Comment


                  • #10
                    Thanks Michael. I'll see if we can get someone on our end to help...

                    Comment

                    Working...
                    X