620 questions
1
vote
1
answer
76
views
Android : drawing on canvas from another canvas, bad performance
I have a custom view where in onDraw(Canvas canvas), I need to draw on offscreen canvas, then draw the bitmap of offscreen canvas on view's canvas.
Here the code in the view class :
Bitmap bitmap = ...
- 735
0
votes
0
answers
132
views
Is it possible to enable Hardware Acceleration in chromium without GPU on Azure App Service's machine?
I'm running headless Chromium with Puppeteer in my Azure Web App Service's container:
const browser = await puppeteer.launch({
headless: true,
executablePath: await this.browserDownloader....
- 21
0
votes
0
answers
92
views
Transparent / Absolute Canvas above animation causes GPU glitches
I made a small one pager which uses framer for scroll animations. I wanted to add a small smoke effect when scrolling past over a certain section.
The overall effect seems to function but it wrecks ...
- 8,613
0
votes
1
answer
161
views
How a neural network is mapped to a GPU? [closed]
I want to understand when a GPU executes a neural network, how the operations are mapped to the GPU's hardware resources. I am familiar with the architecture of GPUs (especially NVIDIA) and I ...
- 1,098
2
votes
2
answers
607
views
Hardware acceleration for the Android Emulator - AEHD not working (STOPPED state) on the laptop with Windows 11 Home
I bought an Asus Rog Strix Laptop which comes with Windows 11 Home.
I want to use it for both Android development and gaming.
So based on the docs I checked the status of Android Emulator hypervisor ...
- 11.9k
0
votes
0
answers
195
views
Custom components with Direct2D paint
I have a project with alot of painted controls, such as grids, coloring, shapes, images, and so on. I decided to try using GPU acceleration to make the entire solution smoother and faster so that a ...
- 31
0
votes
0
answers
536
views
Running PyTorch MPS acceleration on Apple M1, get "Placeholder storage has not been allocated on MPS device!" error, but all seems to be on device
I've noticed that a few folks have had this problem. I'm running the nightly build of PyTorch 2.4.0.dev20240326 and am trying to use my Mac's GPU to speed up training. I'm encountering the dreaded &...
0
votes
0
answers
48
views
Does `zero padding` in CNN increase the inference time due to frequent data transfer between CPU and GPU?
I think the zero-padding in CNN is a very annoying operation when designing a DNN accelerator or an NPU. So I want to know that if zero-padding is executed on CPU or GPU in modern ML framework like ...
- 11
3
votes
0
answers
150
views
Decode h264 frame using android hardware accelerated decoder in gstreamer
I am trying to make a pipeline to get h264 encoded stream using gstreamer with hardware encoding.
Below is that working pipeline:
"ahcsrc ! capsfilter caps=video/x-raw,width=1280,height=720,...
0
votes
0
answers
30
views
In VSC and other apps, when i scroll the text becomes black and turns normal after a very short delay 100ms. It is really annoying
When i open up VSC and other apps the text on the editor, extension page etc. turns black and reappears after a very short time. This issue is not version related as i have this for over 6 months. ...
-1
votes
2
answers
398
views
Can't initialize "h264_mediacodec" for hw accelerated decoding, FFMPEG, Android
I am trying to create hw accelerated decoding on Android through JNI and following this example but, unfortunately, avcodec_get_hw_config returns nullptr.
I have also tried using ...
- 94
1
vote
1
answer
450
views
failed to create HWDeviceContext for h264 and Videotoolbox using FFmpeg for iOS
I am attempting to decode an h264 video using hardware accelaration in FFmpeg, specially for iOS devices and utilizing VideoToolbox hardware device. While I have successfully generated decoder context,...
- 229
1
vote
1
answer
381
views
Coil AsyncImage Software rendering not supported for Pictures that require hardware acceleration
I'm running into a crash while using Coil AsyncImage with hardware acceleration. I've seen that I can use allowHardware(false) to resolve the crash, but not entirely sure of where to implment this.
I'...
- 1,168
1
vote
1
answer
1k
views
Visual Studio 2022 (MAUI/Xamarin) Android Device Manager does not support AEHD
On my brand new Win11 Pro machine (AMD Ryzen 9 7950X) my Visual Studio 2022 Enterprise installation (v17.7.6) doesn't use hardware acceleration when I disable Hyper-V and enable AEHD (or GVM).
Short ...
- 832
0
votes
0
answers
141
views
Using Hardware acceleration in different fragments
I use single activity approach in my app and I have 2 fragments. In first fagment I have GLSurfaceView and it dosen't work correctly, when hardwareAccelerated="false". In second fragment I ...
- 11
1
vote
1
answer
322
views
Compose setShadowLayer alternative below API 29
So actually I have a modifier extension function to show a shadow in a composable. I'm using the code that created in this answer .
This is the code:
fun Modifier.advancedShadow(
color: Color = ...
- 424
0
votes
1
answer
2k
views
Checking VP9 hardware video decode support on Apple Silicon
I'm trying to check whether a device running on Apple Silicon supports hardware video decode of VP9.
I know empirically (from using Chrome and Safari) that VP9 decode is supported in hardware on Apple ...
- 22.9k
0
votes
2
answers
835
views
WPF and hardware acceleration with a discrete graphics card
I need to display a point cloud. For this I use C# and WPF (HelixToolkit). Each point is displayed as a tetrahedron (because the minimum number of triangles). Problem: while the cloud is moving, it is ...
- 49
1
vote
1
answer
271
views
VK_KHR_acceleration_structure and VK_KHR_raytracing_pipeline aren't presented whereas they are available in vkconfig (RTX2060)
I want to use VK_KHR_acceleration_structure and VK_KHR_raytracing_pipeline VkDevice extensions in my project. The problem is that vkPhysicalDeviceExtensionProperties has no those extensions whereas ...
- 31
0
votes
1
answer
123
views
Optaplanner - does processor impacts the compute time
We are using Optaplanner in a project for 4-5 years now. As the business requirements grow we added a more and more rules. But now we are at a point where it takes around 10 days to generate an ...
- 342
2
votes
3
answers
127
views
Matlab produces different matrix product results depending on computation form
In Matlab, I compute a rotation of a collection of 2D points in two ways: one by a regular matrix-matrix product, and the other by iterative vector-matrix products, as follows.
>> points = % ...
- 191
0
votes
1
answer
5k
views
FFmpeg invalid data found when processing input with D3D11VA and DXVA2 hw acceleration
I'm currently porting my Android streaming app to Windows and for decoding the h264 video stream I use FFmpeg with possible hardware acceleration. Last two weeks I was reading a lot of documentation ...
- 594
1
vote
0
answers
819
views
Transcoding ERROR : jellyfin-ffmpeg/lib/dri/iHD_drv_video.so init failed
Here is my problem, I switched from Jellyfin Win10 to Jellyfin via OMV6 Portainers (official images).
I have I7-2600S (VAAPI)
Except that the transcoding doesn't work anymore, in the Jellyfin logs I ...
3
votes
0
answers
929
views
OpenCV + CUDA: Different outcomes on CPU vs GPU
The Problem
I was coding an image processing application to identify unicolor circular objects in an image. I'm doing this using OpenCV 4.7.0 for C++. To develop the necessary functionality, I ...
- 404
-1
votes
1
answer
115
views
How to determine which port has invoked an sc_thread if the thread is sensitive to multiple ports in SystemC?
I have a thread which is sensitive to an array of ports.
In this thread I want to find out which port had triggered this thread so that i can read the value of that port?
Is there a way to determine ...
- 1
-2
votes
1
answer
105
views
Samsung NVMe 980 PRO and Alfais 4390 M.2 Nvme Ssd Ngff To Pcie 3.0 X16 compatibility [closed]
Dear Friends I need help.
Is the following combination compatible?
What will be the maximum write and read speed I will get, AS MegaBytes?
I will be glad to hear for your comments.
1- Samsung NVMe 980 ...
1
vote
1
answer
2k
views
WebGl 2 is not defined in Google Chrome despite hardware acceleration enabled
I'm trying to use WebGL 2 on a website but I can seem to get it to work on my PC. Says it's not available. I can't figure out if it's the graphics driver or OpenGL's version, but here's some info. Any ...
- 553
2
votes
1
answer
1k
views
How can the JVM be accelerated using a GPU? [closed]
While this question is similar to what's here and there in that the problem being addressed is about the same, It's different since it's about finding ways to actually accelerate the JVM itself rather ...
- 881
0
votes
0
answers
45
views
What hardware acceleration functions does common processors have
I've been searching for hardware acceleration explanations and I came across this one .
It says that hardware acceleration is "when you have hardware designed to accelerate a specific function&...
0
votes
1
answer
404
views
VideoToolbox hardware encoded I frame not clear on Intel Mac
When I captured video from camera on Intel Mac, used VideoToolbox to hardware encode raw pixel buffers to H.264 codec slices, I found that the VideoToolbox encoded I frame not clear, causing it looks ...
- 2,098
0
votes
0
answers
2k
views
How to correctly use h264_amf on Windows?
I'm trying to use hardware encoding with FFMPEG on Windows 10 with AMD Radeon r5 M330 DGPU on laptop : HP-AC026-TX. FFMPEG version is 5.1.2-full_build-www.gyan.dev from gyan.dev. I'm using this :
...
- 386
0
votes
1
answer
537
views
OpenCV VideoWriter (Gstreamer + NVENC) freezes for more than 3 streams
I am trying to setup a multi-stream hardware accelerated (Nvidia's NVENC) encoding system using Opencv compiled with Gstreamer backend as well as nvenc and nvdec plugins baked into Gstreamer.
The ...
- 21
1
vote
1
answer
254
views
How does hardware accelerated scrolling work in modern devices?
In VGA mode of the PC and in some older game consoles, it is possible to scroll the display by a pixel by incrementing a register.
This only uses a single CPU instruction.
In modern devices, including ...
- 1,168
2
votes
1
answer
191
views
How to dispatch Kernel to AMD integrated GPU?
AMD provides lots of ressources regarding what instructions can be run on their integrated GPUs:
http://developer.amd.com/wordpress/media/2013/12/AMD_GCN3_Instruction_Set_Architecture_rev1.1.pdf
...
- 294
1
vote
0
answers
457
views
Using SpringBoot with Nvidia GPU (CUDA)
I am working on how to offload some workload to GPU using CUDA in SpringBoot project. To help me explain my question better, let me suppose that we want to implement a REST API to do matrix-vector ...
- 11
11
votes
1
answer
41k
views
How to check ffmpeg hardware acceleration status
Several questions regarding hardware acceleration with ffmpeg (which I think is NOT same question as this one):
How can I tell if my version of ffmpeg support hardware acceleration or not, and what ...
- 2,276
1
vote
1
answer
2k
views
Tensorflow Lite Android: Both GPU delegate and NNAPI delegate are slower than CPU
I am currently evaluating and comparing the performance of some tensorflow models on different smartphones. I am testing the MNIST and CIFAR10 databases. The strange thing is, when i try to speed up ...
- 11
5
votes
0
answers
501
views
Getting android.widget.Editor.drawHardwareAccelerated (Editor.java) exception only on Android 8 and 8.1 versions
I have lost a week (now months) trying to figure out what exactly causing this problem, but no luck:(
This problem started happening in my app after a recent update, which changed the entire project ...
- 1,359
3
votes
2
answers
5k
views
Enabling Hardware Acceleration for Headless Chromium with Playwright
I'm currently working on some E2E tests using a combination of Github Actions, Playwright, and headless Chromium. Now, currently my tests take quite a while (tens of seconds for simple tests) which is ...
2
votes
0
answers
732
views
Android webview to bitmap but hardware accelerated
TL;DR: What is the hardware accelerated replacement of this code?
myBitmap = Bitmap.createBitmap(1280, 720, Bitmap.Config.ARGB_8888);
myWebView.layout(0, 0, 1280, 720);
...
- 21
2
votes
0
answers
650
views
Parsec flatpak fails to load libraries, disabling hardware acceleration
I recently switched to Pop!OS, however, for some reason Parsec refuses to run properly with hardware acceleration. It tries to open the driver. /usr/lib/x86_64-linux-gnu/dri/nvidia_drv_video.so is ...
- 583
0
votes
2
answers
2k
views
Why pyav package in python can not recognize h264_cuvid codec while ffmpeg can do?
I have a python script as below to read byte_stream from video. I want to use h264_cuvid code to do GPU hardware accelerating instead of CPU encoding or decoding. my FFmpeg does have h264_cuvid codecs ...
- 61
1
vote
0
answers
539
views
How to get the Intel UHD Graphics 605 i915 videocard working with Vulkan?
i have an Intel UHD Graphics 605 (i915) and i want to use it with Vulkan/ncnn.
The information from this site is, that Vulkan should work with version 1.1.103:
https://technical.city/de/video/UHD-...
- 13
4
votes
0
answers
2k
views
Is it possible to program GPU in pure Haskell?
I wonder, whether I can write code, which ought to be evaluated by GPU, in pure Haskell.
For example, a function for multiplication of two large matrices in GPU have (theoretically) no side effects, ...
- 1,832
0
votes
1
answer
669
views
Improve use of processor during training of ML model
I am using a new pc with intel i5 11th generation processor for machine learning.
Usually when I train a model, I open the default 'task manager' by windows to check how processor and memory are used ...
- 135
3
votes
0
answers
1k
views
ffmpeg macos hardware acceleration: use more GPU
I am trying to use ffmpeg to convert some videos to MP4.
I have a Mac, and am using h464_videotoolbox to use hardware acceleration.
ffmpeg -hide_banner -loglevel fatal -stats -i in.ts -vcodec ...
5
votes
3
answers
12k
views
Is it possible to turn off all CSS animations in Chrome?
I have a weird issue where if I play an animation on one of my 3 monitors, YouTube videos on any other monitor crashes. I did fix this by disabling hardware acceleration in chrome://flags, but a new ...
- 6,608
1
vote
1
answer
743
views
How to accelerate finding all-pairs shortest path with GPU using rapids cugraph?
I'm trying to get a list of nodes like APSP (all pairs short path) and want to use rapids cugraph for GPU acceleration.
Researched a bit and created this script which is working but it's very slow. I ...
2
votes
1
answer
4k
views
Electron Linux Video Hardware Acceleration
Im having a hard time getting hardware acceleration for videos working in electron running on Linux (ARM64) and Linux (Intel64). Im not sure if this is an issue with the flags electron is using for ...
- 922
8
votes
1
answer
2k
views
Three.js/WebGL running on integrated GPU instead of dedicated
I'm learning Three.js and created a simple app with it expecting it to run on my dedicated GPU, but task manager shows 0% GPU utilization (all values) while the scene is rendering and 80-90% ...
- 285