IN5050 - nVIDIA GeForce GPU Resources & FAQ
Page for resources and frequently asked questions for the Jetson TX1 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/CUDA machines in the lab at Simula.
Remember that you have to SSH into oslo.mlab.no (or oslo.simula.no) to access the lab-net at Simula. From here you can ssh to "tegra-x.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 | Tegra X1 | GM20B | 4 GB | 2 (256) | 5.3 | Operational |
| tegra-2.mlab.no | Tegra X1 | GM20B | 4 GB | 2 (256) | 5.3 | Operational |
| tegra-3.mlab.no | Tegra X1 | GM20B | 4 GB | 2 (256) | 5.3 | Operational |
| tegra-4.mlab.no | Tegra X1 | GM20B | 4 GB | 2 (256) | 5.3 | Operational |
| tegra-5.mlab.no | Tegra X1 | GM20B | 4 GB | 2 (256) | 5.3 | Operational |
| tegra-6.mlab.no | Tegra X1 | GM20B | 4 GB | 2 (256) | 5.3 | Reserved |
GPU Programming Resources
Paper on optimizing the Motion JPEG encoder for Cell and GPU (access from UiO)
Nvidia CUDA Toolkit 9.0 Documentation
Application Note - CUDA for Tegra
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 TX1 Development Kits. Your CPU code should be optimized for 64-bit ARMv8, and the GPU code should be optimized for the Maxwell architecture (Compute 5.x).
Q: What software do I need if I want to run on my own GPU?
A: Here at Simula, we are running Ubuntu 16.04 LTS (ARM 64-bit) with CUDA 9.0 from NVIDIA. You have to download both a CUDA-certified driver and CUDA 9.0 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.