CUDA is used to accelerate CPU-only applications by making them run on GPUs . These CUDA applications are massively parallel and way faster than their CPU-only counterparts. Experience C/C++ application acceleration by:Parallelizing applications to run on GPUsOptimizing applications by using CUDA techniques like memory managementLearning techniques like concurrency and CUDA streamsLearning tools like Nsight Systems to profile and identify bottlenecks
Upon completion, you’ll be able to accelerate and optimize existing C/C++ CPU-only applications using the most essential CUDA techniques and Nsight Systems. You’ll understand an iterative style of CUDA development that will allow you to ship accelerated applications quickly.
Prerequisities
- Basic C/C++ competency including familiarity with variable types, loops, conditional statements, functions, and array manipulations. No previous knowledge of CUDA programming is assumed.
Suggested Resources to Satisfy Prerequisites
Tools, Libraries, and Frameworks Used
Related Training
- Accelerating CUDA C++ Applications with Concurrent StreamsA self-paced course to learn more intermediate CUDA C++ concurrency techniques after completing this course.
- Scaling Workloads Across Multiple GPUs with CUDA C++A self-paced course to learn more intermediate CUDA C++ multi-GPU techniques after completing this course.
For additional hands-on training through the NVIDIA Deep Learning Institute, visit www.nvidia.com/dli.
Course Details
Duration: 8 hours
Price: Paid
Subject: accelerated computing
Tags: c, c++, accelerated computing
Enroll Now