Announcement

Collapse
No announcement yet.

NVIDIA GeForce GTX 1080 Ti Shows Off Strong OpenCL Performance

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

  • NVIDIA GeForce GTX 1080 Ti Shows Off Strong OpenCL Performance

    Phoronix: NVIDIA GeForce GTX 1080 Ti Shows Off Strong OpenCL Performance

    Yesterday, on the launch-day for the GeForce GTX 1080 Ti (GP102) graphics card, I posted GTX 1080 Ti OpenGL and Vulkan benchmarks while for those more interested in GPU compute performance, here are some preliminary OpenCL compute results.

    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
    How does that compare with the RX480 & Fury?

    Comment


    • #3
      Originally posted by phoronix View Post
      The GeForce GTX 1080 Ti though does consume more power than the GeForce GTX 1080 Ti
      Does it consume more power than itself?

      Comment


      • #4
        Originally posted by tildearrow View Post

        Does it consume more power than itself?
        Fixed, thanks.
        Michael Larabel
        https://www.michaellarabel.com/

        Comment


        • #5
          No FP64 performance figures when compared to the Titan X, Quadro's or even the original Titan? Because the reason why people generally buy Titan and Quadro series cards over regular old GeForce cards is that Nvidia hasn't hobbled their FP64 performance (FP64 performance doesn't matter all that much for most people who buy GeForce GPUs as they use them for games which use FP32 and FP16 and not FP64).
          Last edited by L_A_G; 10 March 2017, 10:03 AM.

          Comment


          • #6
            Originally posted by L_A_G View Post
            No FP64 performance figures when compared to the Titan X, Quadro's or even the original Titan? Because the reason why people generally buy Titan and Quadro series cards over regular old GeForce cards is because Nvidia hasn't hobbled their FP64 performance (FP64 performance doesn't matter all that much for most people who buy GeForce GPUs as they use them for games and games use FP32 and FP16 and not FP64).
            I unfortunately don't have the GTX TITAN X Pascal or any Quadros.
            Michael Larabel
            https://www.michaellarabel.com/

            Comment


            • #7
              Originally posted by Michael View Post

              I unfortunately don't have the GTX TITAN X Pascal or any Quadros.
              Didn't Nvidia send you one to review it at some point? Nvidia's obviously asked it back by now, but it shouldn't be inconceivable to think that you may still have some benchmark results on file.

              Comment


              • #8
                Originally posted by L_A_G View Post

                Didn't Nvidia send you one to review it at some point? Nvidia's obviously asked it back by now, but it shouldn't be inconceivable to think that you may still have some benchmark results on file.
                with old drivers and software..?

                Comment


                • #9
                  Originally posted by L_A_G View Post
                  No FP64 performance figures when compared to the Titan X, Quadro's or even the original Titan? Because the reason why people generally buy Titan and Quadro series cards over regular old GeForce cards is that Nvidia hasn't hobbled their FP64 performance (FP64 performance doesn't matter all that much for most people who buy GeForce GPUs as they use them for games which use FP32 and FP16 and not FP64).
                  OpenCL FP64 tests are needed, specially compared with the "old" Titan (1st and/or Black) as well as with Fury and RX480 which all gives good power-horse in double precision before claiming anything with respect to OpenCL capabilities of the 1080 Ti.


                  I would love to also see some OpenCL 2.x tests as well, also compared with AMD GPUs.

                  Thank you for these tests though.

                  Comment


                  • #10
                    Originally posted by L_A_G View Post
                    No FP64 performance figures when compared to the Titan X, Quadro's or even the original Titan? Because the reason why people generally buy Titan and Quadro series cards over regular old GeForce cards is that Nvidia hasn't hobbled their FP64 performance (FP64 performance doesn't matter all that much for most people who buy GeForce GPUs as they use them for games which use FP32 and FP16 and not FP64).
                    Yes!

                    FP64 tests are important and so comparison with the old/original Titan's (regular and Black) are needed as well as comparison with AMD's ship.

                    Thanks though, for these tests.
                    Last edited by adakite; 10 March 2017, 10:17 AM. Reason: typo

                    Comment

                    Working...
                    X