Questions tagged [cuda]

Computing architecture developed by Nvidia that allows programs to process algorithms in the graphics card GPU, instead of the computer's CPU.

Filter by
Sorted by
Tagged with
0 votes
1 answer
31 views

Cuda libraries not found for cuda 11 for ubuntu 20.04

I am using Nvidia VM on Azure with Ubuntu 20.04 I already had nvidia and cuda installed but hile running my program it still showed libraries not found nvidia-smi +-------------------------------------...
user avatar
  • 101
0 votes
0 answers
82 views

How to configure nvidia-cuda-mps-control so that there can be multiple users running on the same system

I have, for example, a 4 GPU system. I would like to be able to have 2 users each using MPS on 2 GPUs. In reading the nvidia documentation it looks like I would set CUDA_VISIBLE_DEVICES to specify ...
user avatar
1 vote
1 answer
35 views

How to check the health of a GPU

I have a GTX 1080Ti which I have been using as my personal deep learning card for about 3,5 years. Lately, I'm getting a lot of obscure CUDA errors. Training and inference code that was running fine ...
user avatar
  • 111
0 votes
0 answers
120 views

Tensorflow GPU not working on Ubuntu 20.04 (error message)

So, I tried to go through several tutorials (the latest being this one) to set up GPU support for TensorFlow on Ubuntu 20.04 and I always get the following message: joris@joris-N751JK:~$ python3.9 ...
user avatar
0 votes
0 answers
42 views

TensorFlow GPU on Ubuntu 20.04

The Tensorflow documentation details how to install Tensorflow with GPU support for Ubuntu 16.04 and 18.04. I can't find anything up to date for Ubuntu 20.04 however. How do you install Tensorflow ...
user avatar
0 votes
1 answer
23 views

Running DL Training on CUDA GPU (util 98%) does not impact gaming? Are CUDA cores not Render Cores?

I downloaded CUDA 11 to run some heavy (and I mean it, heavy) DL model training tasks that use low memory (2GB). I'm rocking a 3070 Ti with 8GB. However in task manager I can see CUDA utilization is ...
user avatar
  • 101
0 votes
0 answers
7 views

Cuda toolkit, cudnn, and tensorflow version confussion

I purchased a laptop having rtx3060 6 gb ( model: msi thin g65) and want to download comaptible version of cuda and cudnn for tensorflow. Downloded the cuda 11.2 with cudnn 8.1 install that properly ...
user avatar
0 votes
0 answers
33 views

Starting previously running Docker containers with GPU support

I recently set up WSL2 (Windows 10, 21H2) with CUDA/Docker support to train some neural networks. For this I followed the instructions from this guide: https://docs.nvidia.com/cuda/wsl-user-guide/...
user avatar
  • 111
-1 votes
1 answer
23 views

Is there anyway to decode a mp4 to bmp images with cuda hwaccel

ffmpeg 3.4.9 ubuntu16.04 I use follow command to decode a mp4 to bmp files (all in one),then I split 1.bmps to image array. ffmpeg -y -i 1632035082_1.mp4 -r 20/1 -vcodec bmp -f image2pipe - > ...
user avatar
  • 1
0 votes
0 answers
22 views

Unable to deactivate the Watchdog on second unused GPU on Xorg

I have an Ubuntu 20.04 system with two monitors and two Nvidia GTX gpus. Driver Version: 470.82.00 CUDA Version: 11.4 The two monitors are connected to the first GPU in PCI:1:0:0. The second GPU in ...
user avatar
0 votes
0 answers
501 views

"Cannot load libcuda.so.1" when running ffmpeg with hardware acceleration on WSL2 Windows

I am following NVIDIA's doc for building ffmpeg with hardware acceleration capabilities. I have also installed the appropriate driver for my GeForce GPU and did the CUDA toolkit setup for WSL2. I am ...
user avatar
1 vote
0 answers
95 views

try compile ffmpeg with cuda 11.1 on window10 but get error when run make -j 8

I am trying to compile ffmpeg with cuda 11.1 on Windows. I run configure like this: ./configure --arch=x86_64 --target-os=mingw64 --enable-cuda --enable-cuvid --enable-nvenc --enable-nonfree --enable-...
user avatar
  • 11
0 votes
0 answers
155 views

NumPy install via Anaconda for VS Code debugging

I'm trying to debug a PyTorch program using the debugger in VS Code on Windows 10. I've been able to do this previously on other machines, but something about my current configuration is not working. ...
user avatar
  • 101
1 vote
0 answers
211 views

cv2.cuda.getCudaEnabledDeviceCount() return 0 after visual studio build and with_cuda is set true for opencv using windows10

I want gpu to work in opencv , after CMake with_cuda true and build of (ALL_Build, Install) with no errors I found GPU not detected I use windows 10 I tried 3 times to build opencv , but Gpu not work ...
user avatar
  • 111
3 votes
0 answers
2k views

WSL 2 cannot see NVIDIA GPU drivers

I have Windows 10 along with Ubuntu 20.04.01 GNU/Linux 5.10.16.3-microsoft-standard-WSL2 x86_64 installed (latest for WSL2 - please see edits below- this has changed). I'm a Windows Insider user and ...
user avatar
0 votes
1 answer
103 views

13.022698] nvidia-modeset: Version mismatch: nvidia.ko(430.64) nvidia-modeset.ko(460.32.03)

I have been trying to get cuda 10.2 installed on ubuntu 18.04. I am getting this mismatch error. There are similar posts on stackoverflow. I tried deleting dpkg lines, and repeat the install script, ...
user avatar
  • 101
0 votes
2 answers
2k views

CUDA support for RTX 3080 (Laptop GeForce Notebook Products)

Does RTX 3080 for laptops already support CUDA and cuDNN for Deep learning requirements? I want to buy a new Razor Blade 15 with RTX 3080 and I don’t see currently any listing of this GPU on Nvidia ...
user avatar
0 votes
1 answer
845 views

Failled CUDA installation Ubunutu 18.04.5

I'm trying to install the CUDA toolkit with Ubuntu 18.04.5 for my GTX 3060 Ti. I've downloaded the file cuda_11.2.1_460.32.03_linux.run from NVidia's site followed the instructions and when then there ...
user avatar
  • 1
1 vote
1 answer
90 views

Is there a way to use Linux on Windows while utilizing nvidia CUDA?

VirtualBox cannot use CUDA. Is there a way around without using dual-boot?
user avatar
0 votes
0 answers
872 views

ffmpeg not setting up Nvidia card if it's not the first adapter

I just set up a 'new' PC with built-in Intel video and an Nvida card: mostly to speed up video processing with ffmpeg and other programs. At first the built-in Intel was disabled, running only the ...
user avatar
0 votes
1 answer
316 views

Error after installing CUDA on WSL 2 - RuntimeError: No CUDA GPUs are available

I am trying to install CUDA on WSL 2 for running a project that uses TorchAudio and PyTorch. I have done the steps exactly according to the documentation here. However, when I run my required code, I ...
user avatar
3 votes
0 answers
3k views

NVIDIA: “RuntimeError: No CUDA GPUs are available”

I am implementing a simple algorithm with PyTorch on Ubuntu. Two times already my NVIDIA drivers got somehow corrupted, such that running an algorithm produces this traceback: Traceback (most recent ...
user avatar
  • 31
3 votes
1 answer
2k views

Set keyframe interval in ffmpeg when using nvenc

OBS uses nvenc when encoding live streams. In the guide "NVIDIA NVENC OBS Guide", an advanced option is listed as: Keyframe Interval: Set to 2. Streaming platforms may limit what you can ...
user avatar
4 votes
2 answers
9k views

Understanding pixel format and profile when encoding 10-bit video in ffmpeg with nvenc

I am trying to encode a 10-bit H.265 video from a 8-bit H.264 source using ffmpeg with CUDA hardware acceleration. Without hardware acceleration, a typical command would be ffmpeg -i input.mkv -...
user avatar
1 vote
2 answers
412 views

Power of NVIDIA GPU out of limits (Nvidia A100)

I am executing a CUDA kernel in my A100 GPU and I've realized that the power consumption at some points is higher than nvidia-smi given range: The picture has been taken from nvtop. Is it something ...
user avatar
1 vote
1 answer
624 views

Cannot open NVIDIA Visual Profiler on Ubuntu 20.04

I've installed CUDA kit via apt-get following CUDA installation documentation. However, when I attempt to open NVIDIA Visual Profiler, I can't open it. By the log file I suppose it has something to do ...
user avatar
  • 121
1 vote
0 answers
856 views

NVIDIA-SMI has failed because it couldn’t communicate with the NVIDIA driver. Make sure that the latest NVIDIA driver is installed and running

System Spec: OS: ubuntu 18.04 GPU: Quadro RTX 4000 I have a fresh installed machine with ubuntu 18.04. To install CUDA 11 toolkit these are the command that i ran : wget https://developer.download....
user avatar
0 votes
1 answer
111 views

Does Nvidia rtx series still features plain cuda cores or is everything replaced by Tensor cores?

For a long time, consumer Nvidia Graphic cards supportted having plain cuda cores despite not being branded for accelerators. The problem in my case is while Tensor cores allow to perform cuda, they ...
user avatar
  • 1,671
1 vote
0 answers
160 views

Cuda enabled FFMPEG not showing any GPU usage

I've compiled ffmpeg 4.3.1 with cuda support using the Toolkit 11. However, when I run ffmpeg against an rtsp stream and transcode into mp4, the process never shows any GPU usage in ProcessExplorer.If ...
user avatar
4 votes
1 answer
4k views

How to install pytorch FROM SOURCE (with cuda enabled for a deprecated CUDA cc 3.5 of an old gpu) using anaconda prompt on Windows 10?

I have (with the help of the deviceQuery executable in C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\vX.Y\extras\demo_suite according to https://forums.developer.nvidia.com/t/what-is-the-compute-...
user avatar
0 votes
0 answers
447 views

How do you get FFmpeg script -hwaccel overlay_cuda to fade in and out an image?

The following FFmpeg hardware-acceleration script works fine. But when I try to apply a fade in and out to the overlayed image it breaks. Is there a solution? Working: ffmpeg -hwaccel cuda -...
user avatar
1 vote
0 answers
166 views

Installing CUDA in GCP VM instance ( Debian 10.x)

I am just coming up to speed with GPU & CUDA and going around in circles. My GPU is Nvidia Tesla T4. However, Google documentation is lacking https://cloud.google.com/compute/docs/gpus/install-...
user avatar
  • 111
0 votes
0 answers
88 views

Laptop won’t boot after installing CUDA tookit

Today I installed the CUDA toolkit on my laptop (NVIDIA GeForce GTX 1070 graphics card). After a restart my laptop won’t boot anymore. I, nor the CUDA installer, created a System Restore Point. I ...
user avatar
  • 123
0 votes
1 answer
2k views

how to uninstall and reinstall nvidia-drivers (linux 20.04)

I have recently installed ubuntu 20.04 on my laptop and facing some issues running tensorflow1.X-gpu version . The problem is with the installation of cuda, cudnn and nvidia-drivers . I want to use ...
user avatar
0 votes
1 answer
613 views

What exactly are compute shaders? [closed]

What are compute shaders? Refined Question: I need to be able to write a shader knowing whether it will be processed GPU side or if I need to do it CPU side. For instance I would like to create tiles ...
user avatar
1 vote
0 answers
840 views

Python: Do I need to install Tensorflow and Pytorch in two different conda environments?

Intro: I do not know whether I should install pytorch and tensorflow in separated environments if I want to install both. For conda tensorflow, I find at https://machinelearningspace.com/installing-...
user avatar
0 votes
1 answer
691 views

CUDA driver compatibility with nvfortran compiler from nvidia hpc sdk 20.7

I have installed the nvidia compilers (nvcc, nvfortran). I downloaded it from the NVIDIA HPC SDK v20.7 site. I then compiled non-cuda codes with nvfortran, and it works fine. But when i compile the ...
user avatar
0 votes
1 answer
387 views

Installing CUDA Toolkit 11 when your computer CUDA version says 10.1

I suspect that CUDA is not installed in my windows 10 machine, so I am planning to download and install it. For that I would use this link that allows me to get CUDA Toolkit 11. However if I do nvidia-...
user avatar
1 vote
1 answer
4k views

Do I need to install cuda separately after installing the NVIDIA display driver?

Is cuda already included in the installation of the graphics card display driver? The card has 192 cuda cores according to https://www.asus.com/Graphics-Cards/GT710-SL-2GD5/specifications/, and Cuda 3....
user avatar
0 votes
0 answers
115 views

Command 'nvcc' not callable from shell script

For my shell script, it is critical to check whether CUDA is installed by running nvcc --version. If I try to invoke it, it exits with following error: ./cuda.sh: line 17: nvcc: command not found ...
user avatar
1 vote
0 answers
197 views

All the folders under CUDA folder are Empty. (After installed the CUDA 10.1 on Ubuntu 18.04)

I met strange a problem after I installed the CUDA 10.1 on my Ubuntu 18.04 server. I found all the files under the CUDA folder are Empty! Can anyone help me with this issue? Thank you in advance for ...
user avatar
2 votes
0 answers
213 views

Why peer-to-peer (P2P) access between two Tesla K40c GPUs fails in CUDA?

I would like to run a CUDA C program using two Tesla K40 devices and enable peer-to-peer (P2P) between them as my data will be shared among the devices. My computer has the following deviceQuery ...
user avatar
0 votes
1 answer
68 views

Is there a way to get Cuda support for an older GeForce GT?

An older GPU doesn't seem to support Cuda? I am under the understanding that Cuda is only software so I assume it could somehow be forced to use it. It's an GeForce GT 530 PS: I've been told that my ...
user avatar
0 votes
1 answer
20 views

Failure in running Faster R-CNN repo

I have a MacBook Pro 16in with the following GPU: AMD Radeon Pro 5300M. I have been trying to run the demo in the Faster R-CNN repo here but I am not being able to run the demo. I think it might be ...
user avatar
  • 1
0 votes
2 answers
2k views

“Pixel format 'yuvj420p' is not supported” when converting image to video using CUDA hardware acceleration

I'm trying to convert an image to a video using CUDA hardware acceleration but I can't get it to work. The basic command I have is this one: ffmpeg -y -hwaccel cuvid -i tests/MediaSamples/...
user avatar
  • 5,787
2 votes
1 answer
1k views

How do I install Pytorch 1.3.1 with CUDA enabled

I have a conda environment on my Ubuntu 16.04 system. When I install Pytorch using: conda install pytorch and I try and run the script I need, I get the error message: raise AssertionError("Torch ...
user avatar
0 votes
0 answers
332 views

How to use GPU acceleration on Docker without DirectX on Windows Containers

Microsoft documents that GPU acceleration can be enabled on frameworks built on top of DirectX here NVidia's base Docker image for CUDA is Linux based here Question: How to enable GPU acceleration ...
user avatar
  • 1
2 votes
1 answer
37 views

cuda v100 and RTX2080 bandwidth fluctuations

I have a simple cuda kernel (adding two vectors of size N) pretty similar to to this cuda blog here. I only changed a few things, e.g. running the measurement over various sample. So, let this run for,...
user avatar
1 vote
0 answers
55 views

When I am installing Nvidia driver and Cuda, CentOS 7 cannot boot [image]

What is the reason preventing CentOS7 to boot when installing Nvidia driver and Cuda. I have tried two times. The first time only installed the driver and then when I restart the computer it hangs on ...
user avatar
3 votes
1 answer
1k views

How to kill all processes using a given GPU?

I use the CUDA toolkit to perform some computations on my Nvidia GPUs on Windows 7 SP1 x64 Ultimate. How to kill all processes that use a given GPU? (killing all processes at once)
user avatar

1
2 3 4 5