GPU usage oscillates every 1-2 sec when running VR program












0















I have a Alienware Windows computer running this virtual reality software called High Fidelity (HF). For academic research, we're using this program to allow multiple people to occupy the same virtual space and make design decisions. We had our first pilot today, which is the first time all three of our rendering computers were running for >1h. In addition to handling screen-recording software and VR rendering, one computer is also the server for the other two computers. That computer gave us a BSOD today mid-experiment.



Normally that wouldn't be enough to go on, but a few minutes before that point, all three participants noted the items they had drawn where "flashing" in and out of existence. The drawings were made of small 3D cylinders, and I'm intuiting that the VR program won't draw smaller / farther-away objects when the GPU load is really high. So for some reason the GPU load was cycling between low and high, and then after a few minutes of that, the computer acting as the server BSOD'd. I don't know for sure if they're related, but I think it's likely.



So for the next session, I kept tabs on computer usage with Windows Task Manager, and saw a really weird effect. GPU usage was consistently 66-67% according to Task Manager, but when I sorted all processes by GPU usage, the HF process oscillated between using either 67% or 0% of the GPU - but no other process was high on GPU when HF was low. When HF showed 0%, all other processes read 0% GPU usage.




  • How do I stop the 'flashing' effect and have High Fidelity render more consistently?

  • Is the crash related to the GPU usage?

  • How do I prevent future crashes?


[I've also posted in the High Fidelity forums as well. I'm hoping that some magic knowledge of the code / render pipeline they have alongside some magic knowledge of Windows and GPUs here might solve the problem.










share|improve this question



























    0















    I have a Alienware Windows computer running this virtual reality software called High Fidelity (HF). For academic research, we're using this program to allow multiple people to occupy the same virtual space and make design decisions. We had our first pilot today, which is the first time all three of our rendering computers were running for >1h. In addition to handling screen-recording software and VR rendering, one computer is also the server for the other two computers. That computer gave us a BSOD today mid-experiment.



    Normally that wouldn't be enough to go on, but a few minutes before that point, all three participants noted the items they had drawn where "flashing" in and out of existence. The drawings were made of small 3D cylinders, and I'm intuiting that the VR program won't draw smaller / farther-away objects when the GPU load is really high. So for some reason the GPU load was cycling between low and high, and then after a few minutes of that, the computer acting as the server BSOD'd. I don't know for sure if they're related, but I think it's likely.



    So for the next session, I kept tabs on computer usage with Windows Task Manager, and saw a really weird effect. GPU usage was consistently 66-67% according to Task Manager, but when I sorted all processes by GPU usage, the HF process oscillated between using either 67% or 0% of the GPU - but no other process was high on GPU when HF was low. When HF showed 0%, all other processes read 0% GPU usage.




    • How do I stop the 'flashing' effect and have High Fidelity render more consistently?

    • Is the crash related to the GPU usage?

    • How do I prevent future crashes?


    [I've also posted in the High Fidelity forums as well. I'm hoping that some magic knowledge of the code / render pipeline they have alongside some magic knowledge of Windows and GPUs here might solve the problem.










    share|improve this question

























      0












      0








      0








      I have a Alienware Windows computer running this virtual reality software called High Fidelity (HF). For academic research, we're using this program to allow multiple people to occupy the same virtual space and make design decisions. We had our first pilot today, which is the first time all three of our rendering computers were running for >1h. In addition to handling screen-recording software and VR rendering, one computer is also the server for the other two computers. That computer gave us a BSOD today mid-experiment.



      Normally that wouldn't be enough to go on, but a few minutes before that point, all three participants noted the items they had drawn where "flashing" in and out of existence. The drawings were made of small 3D cylinders, and I'm intuiting that the VR program won't draw smaller / farther-away objects when the GPU load is really high. So for some reason the GPU load was cycling between low and high, and then after a few minutes of that, the computer acting as the server BSOD'd. I don't know for sure if they're related, but I think it's likely.



      So for the next session, I kept tabs on computer usage with Windows Task Manager, and saw a really weird effect. GPU usage was consistently 66-67% according to Task Manager, but when I sorted all processes by GPU usage, the HF process oscillated between using either 67% or 0% of the GPU - but no other process was high on GPU when HF was low. When HF showed 0%, all other processes read 0% GPU usage.




      • How do I stop the 'flashing' effect and have High Fidelity render more consistently?

      • Is the crash related to the GPU usage?

      • How do I prevent future crashes?


      [I've also posted in the High Fidelity forums as well. I'm hoping that some magic knowledge of the code / render pipeline they have alongside some magic knowledge of Windows and GPUs here might solve the problem.










      share|improve this question














      I have a Alienware Windows computer running this virtual reality software called High Fidelity (HF). For academic research, we're using this program to allow multiple people to occupy the same virtual space and make design decisions. We had our first pilot today, which is the first time all three of our rendering computers were running for >1h. In addition to handling screen-recording software and VR rendering, one computer is also the server for the other two computers. That computer gave us a BSOD today mid-experiment.



      Normally that wouldn't be enough to go on, but a few minutes before that point, all three participants noted the items they had drawn where "flashing" in and out of existence. The drawings were made of small 3D cylinders, and I'm intuiting that the VR program won't draw smaller / farther-away objects when the GPU load is really high. So for some reason the GPU load was cycling between low and high, and then after a few minutes of that, the computer acting as the server BSOD'd. I don't know for sure if they're related, but I think it's likely.



      So for the next session, I kept tabs on computer usage with Windows Task Manager, and saw a really weird effect. GPU usage was consistently 66-67% according to Task Manager, but when I sorted all processes by GPU usage, the HF process oscillated between using either 67% or 0% of the GPU - but no other process was high on GPU when HF was low. When HF showed 0%, all other processes read 0% GPU usage.




      • How do I stop the 'flashing' effect and have High Fidelity render more consistently?

      • Is the crash related to the GPU usage?

      • How do I prevent future crashes?


      [I've also posted in the High Fidelity forums as well. I'm hoping that some magic knowledge of the code / render pipeline they have alongside some magic knowledge of Windows and GPUs here might solve the problem.







      graphics-card gpu task-manager vive






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked Jan 25 at 1:18









      Mark MillerMark Miller

      993




      993






















          0






          active

          oldest

          votes












          Your Answer








          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "3"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          autoActivateHeartbeat: false,
          convertImagesToLinks: true,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: 10,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });














          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fsuperuser.com%2fquestions%2f1398165%2fgpu-usage-oscillates-every-1-2-sec-when-running-vr-program%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes
















          draft saved

          draft discarded




















































          Thanks for contributing an answer to Super User!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fsuperuser.com%2fquestions%2f1398165%2fgpu-usage-oscillates-every-1-2-sec-when-running-vr-program%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          Popular posts from this blog

          "Incorrect syntax near the keyword 'ON'. (on update cascade, on delete cascade,)

          Alcedinidae

          RAC Tourist Trophy