Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

CUDA Basics and 1D Operations

Go to class Write review

Overview

In this course, you will dive into the core mechanics of heterogeneous computing using C++ and CUDA. You will learn how to allocate GPU memory safely, transfer datasets correctly between the CPU and GPU, and configure block dimensions to execute and verify your first one-dimensional kernels.

Syllabus

Unit 1: Device Memory Allocation

Safe CUDA Calls
Build the Memory Helper
Hunt the Memory Bug
Safe GPU Cleanup
Closing the Memory Loop
Triple Array Challenge

Unit 2: Host to Device Transfer

Moving Data to Device
Bringing Results Home
Debugging CUDA Data Transfer
Complete CUDA Transfer Flow

Unit 3: 1D Vector Addition Kernel

Finding Thread Positions
Guarding Vector Addition
Cover Every Vector Element
A New Vector Operation
Making GPU Results Reliable
Scaling a Vector on CUDA

Unit 4: Robust Grid Stride Loops

Safe Steps in CUDA
Stride Across the Grid
Launching the Full Grid
From Threads to Strides
Multiply Across the Grid
Grid Stride Detective

Reviews

Start your review of CUDA Basics and 1D Operations