Request for supporting dynamic loading OpenCL
I am developing a native app that utilizes OpenCL, Vulkan, and OpenXR, but I’ve encountered a significant roadblock: `libOpenCL.so` cannot be dynamically loaded with dlopen because it is not included in `/etc/public.libraries.txt`. While it’s technically possible to extract the library using `adb pull /vendor/lib/libOpenCL.so` and bundle it within the APK, this is not a scalable solution for supporting a diverse range of devices, even within the Meta ecosystem. I understand this limitation may be due to security considerations, but it’s worth noting that `libvulkan.so` is already accessible. Restricting developers to Vulkan forces additional effort to convert OpenCL kernels into SPIR-V, which seems unnecessary, IMHO. Providing support for `libOpenCL.so` would significantly enhance compatibility and streamline development. This is especially important given that many deep learning frameworks rely on dynamic loading of the OpenCL library through stub code.Known Issue: Closing Steam VR crashes Dash
Hi everyone! We're seeing a small group of Steam VR users finding that Dash is crashing on headset and that their PC is becoming unresponsive once they quit the app. The team is working on identifying and fixing the root cause of this issue, and right now the investigation shows that this is likely related to Hardware Accelerated GPU Scheduling being enabled when using certain Nvidia GPUs. If you're having this issue, there is a workaround In the meantime! You can prevent this happening by disabling the Hardware Accelerated GPU Scheduling feature. To do so, follow these instructions. If you need any further help or have noticed other bugs around Steam VR, please comment below. Let me know if you have any questions!
clGetPlatformIDs() failed by Adreno OpenCL sdk
Hello, I am developing on Meta Quest 3 using Adreno OpenCL SDK for programs running on GPU. However, when I try to run the OpenCL examples on Android Studio, there is an error of function clGetPlatformIDs() with error code -1001, saying that the function cannot find the platform on the device. I have searched this problem online, and linked libOpenCL.so and other related libraries to the source, but the problem still exists. How should I solve this problem? Thanks. Adreno OpenCL SDK v2.0: https://developer.qualcomm.com/software/adreno-gpu-sdk/tools
Black grid on camera frame when displaying point cloud
I am developing an application that receives and display a point cloud. When I try to render a point cloud (both with normal mesh or MaterialPropertyBlock and GPU) I get what it seems to be a black transparent canvas that follows my head. This is very annoying. I tried to change materials and shaders, to disable shadows, but I didn't find a way to get rid of this problem.
Meta Quest 3 GPU Crash
Hi, I am building a Quest VR game with Unreal Engine 4.27 from Meta github Fork. There's random crash from time to time. It seems GPU Management Unit has crashed. Here's a log of what happened. I can't find documentation on what this opcode means. Here's another time, this time with a different code: Any help will be appreciated!
Random spike in CPU usage and longer render times
Hello, I am a developer on a Unity app for Quest 2. We have a performance problem with our app that causes huge spikes in CPU usage. The app performs well and as we want it to at first, seen here captured by OVR metrics: All of the systems in the app test well and do not cause problems but after a certain amount of time doing various things, a user has a random random chance of having the framerate plummet. In this next picture, I experienced the bug and then returned to the login screen where the bug persisted: You can see that CPU usage has skyrocketed to a locked 100%. You would think that there is some process taking up frame time in the background. I took a look at the profiler on a build to see if there was a key culprit. Here is a frame under good conditions where performance is as expected: And after the bug, the frame looks like this: You can see that the player loop has almost doubled in duration, but the scripts portion of the frame is actually pretty much the same. The change is entirely in EarlyUpdate.XRUpdate and PostLateUpdate.FinishFrameRendering taking 5x as long as before. So why am I getting a huge CPU usage spike while also the rendering of the same workload is suddenly taking so much longer?? Is there any chance that the quest is downclocking under stress? Once this happens, there is no way to retrieve the old performance until you restart the app completely. There is no surefire way to trigger this to happen, it just randomly takes place when there's a decent amount going on and then stays forever. I do not understand what APP T and TW T mean in the OVR metrics panel as well, if those might lead to a culprit. Any ideas would be much appreciated, thank you.
Oculus using integraded GPU instead of Nvidia GPU
Hello everyone! I recently bought a Oculus Quest 2 and I have been having trouble with it. If I want to use my Oculus for Airlink it links and then it starts lagging so extremely much. Something around 1 or 2 frames per second probably. I can't play Beat Saber trough my Oculus or any other not Oculus store games. I have already tried several solutions that helped other people but nothing helps. Before you start typing my specs are not good enough, they are. It has been brought to my attention that my GPU is probably the problem. Oculus is using the integraded GPU from my computer instead of my Nvidia RTX 2060 GPU. Does anyone know how to fix this? I'm tired of not being able to enjoy my Oculus. If someone knows how to help please let me know Thankyou!
