Learn CUDA with Docker No NVIDIA GPUs required!

[mitsumi]

 

Genre: eLearning | MP4 | Video: h264, 1280x720 | Audio: aac, 44100 Hz
Language: English | VTT | Size: 723 MB | Duration: 2 hours

What you'll learn
How to code with CUDA, but without a GPU!
Basic knowladge about CUDA programming
Ability to desing and implement CUDA parallel algorithms

Requirements
Basic C or C++ programming knowledge
Description
WELCOME!

We present you the long waited approach to Learn CUDA WITHOUT NVIDIA GPUS! Finally, you can learn CUDA just on your laptop, tablet or even on your mobile, and that's it!

WHAT DO YOU LEARN?

We will demonstrate how you can learn CUDA with the simple use of: Docker: OS-level virtualization to deliver software in packages called containers and GPGPU-Sim, a cycle-level simulator modeling contemporary graphics processing units (GPUs) running GPU computing workloads written in CUDA or OpenCL. This course aims to introduce you with the NVIDIA's CUDA parallel architecture and programming model in an easy-to-understand way. We plan to update the lessons and add more lessons and exercises every month!

Virtualization basics

Docker Essentials

GPU Basics

CUDA Installation

CUDA Toolkit

CUDA Threads and Blocks in various combinations

CUDA Coding Examples

WHY CUDA?

CUDA provides a general-purpose programming model which gives you access to the tremendous computational power of modern GPUs, as well as powerful libraries for machine learning, image processing, linear algebra, and parallel algorithms.

DISCLAIMER

Some of the images used in this course are copyrighted to NVIDIA.

Who this course is for:
Any one who wants to learn CUDA programming, but does NOT have access to expensive GPUs

Screenshots
 

Download link:

Só visivel para registados e com resposta ao tópico.

Only visible to registered and with a reply to the topic.

Links are Interchangeable - No Password - Single Extraction