Current

Intermediate

Fundamentals of Accelerated Computing with CUDA Python

NVIDIA Deep Learning Institute (DLI) · NVIDIA · Updated March 2026

Platform rating

4.6/5

Champ rating

8.6/10

Duration

8 hours instructor-led

Classes

22

Accelerate Python applications using CUDA. Learn GPU programming fundamentals for massive parallel computing workloads.

What you'll get

Write GPU-accelerated Python code with CUDA

Optimize parallel computing workloads

Manage GPU memory and thread hierarchies

Profile and optimize CUDA applications

Course Curriculum

4 chapters

Fit

Best for

Developers

AI Engineers

Data Scientists

Technical Builders

Not ideal for

Learners seeking only entry-level overviews

Prerequisites & pricing

Prerequisites

Python proficiency

Pricing

Contact for pricing

Certification

Certificate

CUDA

GPU Computing

Python

Parallel Computing

NVIDIA

ShareCompare

Add to StackGo to Course

Alternatives to Fundamentals of Accelerated Computing with CUDA Python

Compare

Current

Champ's Pick

Deep Learning Fundamentals

Lightning AI · Lightning AI

4.8

8.8/10

10 units (self-paced)

Free 10-unit course teaching deep learning from fundamentals to practical model training with PyTorch and PyTorch Lightning.

Free

ViewAddCompare

Course on building game-playing bots with lookahead strategies and deep reinforcement learning using practical exercises.

Build computer vision solutions using Azure AI Vision. Learn image analysis, object detection, face recognition, and custom vision models.

Master GenAIOps practices for deploying and operating generative AI applications in production with Azure AI.