IN5050 - nVIDIA GeForce GPU Resources & FAQ
Page for resources and frequently asked questions for the Jetson AGX Xavier machines. If you have any other questions, please send an email to in5050@ifi.uio.no
The following table gives an overview of the status of the ARM machines at IFI.
Remember that you might have to SSH into login.ifi.uio.no to access the logon-machine for IN5050. From here you can ssh to in5050.mlab.no.
Username and password have been provided to all groups:
| Computer | GPU | GPU Core | Memory | Multiprocessors (CUDA Cores) | Compute Capability | Status |
| tegra-1.mlab.no | NVIDIA Tegra Xavier | GV11B | 16 GB | 8 (512) | 7.2 | Operational |
| tegra-2.mlab.no | NVIDIA Tegra Xavier | GV11B | 16 GB | 8 (512) | 7.2 | Operational |
| tegra-3.mlab.no | NVIDIA Tegra Xavier | GV11B | 32 GB | 8 (512) | 7.2 | Operational |
| tegra-4.mlab.no | NVIDIA Tegra Xavier | GV11B | 32 GB | 8 (512) | 7.2 | Operational |
GPU Programming Resources
Paper on optimizing the Motion JPEG encoder for Cell and GPU (access from UiO)
Nvidia CUDA Toolkit 10.0 Documentation
Application Note - CUDA for Tegra
Volta Compatibility Guide for CUDA Applications
Frequently Asked Questions
Q: Can I use my own GPU?
A: Yes, you can. However, we do not recommend this. The program has to compile and run on the Jetson AGX Xavier Development Kits. Your CPU code should be optimized for 64-bit ARMv8.2, and the GPU code should be optimized for the Volta/Turing architecture (Compute 7.x).
Q: What software do I need if I want to run on my own GPU?
A: Here at IFI, we are running Ubuntu 18.04 LTS (ARM 64-bit) with CUDA 10.0 from NVIDIA. You have to download both a CUDA-certified driver and CUDA 10.0 toolkit from NVIDIA. The CUDA SDK is optional, but it contains several useful functions.
Q: Are there any differences between the GPU on a Tegra, and a GPU connected with PCIe (dGPU)?
A: Yes! This is something you should be aware of, especially when writing code to transfer data between the host (CPU) and device (GPU) on the Tegra, the integrated GPU (iGPU) share the memory with the CPU. This application note explains some crucial differences.