A quick overview of how to know what devices Tensorflow sees on your system in the video. Code snippet should be used in Python Anaconda.
|
1 2 |
from tensorflow.python.client import device_lib print(device_lib.list_local_devices()) |
Next: Install Tensorflow + Tensorboard + Keras + Anaconda Python in Windows
Learn how to use cooperative groups to make your parallel processing code more organized and manageable. The video walkthrough is 32+ minutes long and includes example source code.
Donate Hey guys, I did a video walkthrough of the default code that appears when you start a new CUDA project in CUDA Toolkit 9.0. Hopefully it will help you to better understand what is going on in the background […]
A very simple example of transferring data from the device (GPU) to the host (CPU) using CUDA. If you have any questions, contact me on twitter @cudaeducation or comment on the YouTube video. Download code: CUDA Transfer Data from Host to […]
Ray tracing is the latest and greatest technology in graphics processing today. It’s all made possible by nVidia graphics cards running CUDA. Just a little motivation for everyone to keep learning how to program the graphics chips. No can see […]
A quick comparison of GPU programming vs. CPU programming and the battles one has to face when programming in parallel.
Just discovered the CUDA GPU Occupancy Calculator spreadsheet that will help you increase the occupancy ratio of your applications. Occupancy is defined as [active warps]/[maximum warps]. You will always want your device cores to be used to its fullest potential […]
The following code is basically taking an array with 20 million integers and adding all the numbers together to get a final answer. I have heavily commented the code for your convenience. CREDIT: Professional CUDA C Programming by John […]