Monthly Subscription Starting at AED 99 + VAT

Introduction to Parallel Programming with CUDA
  • Level Professional
  • المدة 22 ساعات hours
  • الطبع بواسطة Johns Hopkins University
  • Offered by

عن

This course will help prepare students for developing code that can process large amounts of data in parallel on Graphics Processing Units (GPUs). It will learn on how to implement software that can solve complex problems with the leading consumer to enterprise-grade GPUs available using Nvidia CUDA. They will focus on the hardware and software capabilities, including the use of 100s to 1000s of threads and various forms of memory.

الوحدات

GPU Programming Specialization

    • 1 Videos
    • 2 Readings
    • 1 Discussion
Show info about module content

1 Discussions

  • Large Scale Data and Challenges Discussion

1 Videos

  • GPU Programming Specialization

2 Readings

  • Course Overview
  • Course Outline

Course Technical and Programming Expectations

    • 1 Videos
Show info about module content

1 Videos

  • Course Expectations

Coursera Lab and Assignment Usage

    • 1 Videos
    • 2 Readings
    • 1 Lab
    • 1 Programming
Show info about module content

1 Programming

  • Simple CUDA Project Assignment

1 Labs

  • Simple CUDA code Lab

1 Videos

  • Coursera Lab and Assignment Overview

2 Readings

  • VS Code and GitHub Resources
  • C++ Reading Material

CUDA Kernels

    • 1 Videos
    • 1 Readings
Show info about module content

1 Videos

  • Kernel Execution

1 Readings

  • Nvidia CUDA Software and Hardware Reading Materials

Converting CPU Divide and Conquer to Parallel Kernel Execution

    • 3 Videos
    • 1 Lab
    • 1 Programming
    • 1 Assignment
Show info about module content

1 Programming

  • Data Search Programming Assignment

1 Assignment

  • CPU to GPU Algorithm Conversion Quiz

1 Labs

  • CUDA Computation on Data Lab Activity

3 Videos

  • Divide and Conquer to GPU Algorithms
  • Module 2 Lab Overview Video
  • Module 2 Randomized Data Search Assignment Overview Video

Defining Kernel Thread and Data Layout via Blocks

    • 1 Videos
Show info about module content

1 Videos

  • Threads and Blocks

3-Dimensional Thread and Data Layout using Grids and Blocks

    • 1 Videos
Show info about module content

1 Videos

  • Threads, Blocks, and Grids

Execution of CUDA Kernel in 3-Dimensional Data/Thread Space

    • 2 Videos
    • 1 Programming
    • 1 Assignment
Show info about module content

1 Programming

  • Performing RGB to Grayscale on Image Data Assignment

1 Assignment

  • Multidimensional Data and Computation on the GPU Quiz

2 Videos

  • Multidimensional Gaussian Blur Kernel Example
  • Module2 Image Processing Assignment Overview Videos

Nvidia GPU Global Device Memory

    • 1 Videos
Show info about module content

1 Videos

  • Nvidia GPU Device Global Memory

Nvidia GPU Global Memory Analysis

    • 3 Videos
    • 1 Discussion
    • 1 Lab
Show info about module content

1 Discussions

  • Student CPU Memory and GPU Discussion

1 Labs

  • Nvidia GPU Device Investigation Commands Lab

3 Videos

  • Linux CLI GPU Device Identification
  • GPU Device Global Memory Investigation
  • Nvidia GPU Device Investigation Commands Lab Overview Video

Host Memory Allocation

    • 1 Videos
Show info about module content

1 Videos

  • Host Memory Allocation

Device Memory Allocation

    • 3 Videos
    • 1 Lab
    • 1 Programming
    • 1 Assignment
Show info about module content

1 Programming

  • Allocation and Assignment of Different Types of Host and Global Memory

1 Assignment

  • CPU and GPU Global Memory Quiz

1 Labs

  • Host and Device Global Memory Allocation Lab

3 Videos

  • Device Global Memory Allocation
  • Host and Device Global Memory Allocation Lab Overview Video
  • Allocation and Assignment of Different Types of Host and Global Memory Overview Video

Nvidia Shared/Constant Memory Hardware

    • 1 Videos
Show info about module content

1 Videos

  • Nvidia GPU Device Shared and Constant Memory Video Lecture

Nvidia GPU Shared and Constant Memory Analysis

    • 1 Videos
Show info about module content

1 Videos

  • GPU Device Shared and Constant Memory Investigation

Nvidia Shared Memory Allocation

    • 1 Videos
Show info about module content

1 Videos

  • GPU Device Shared Memory Allocation

Nvidia Constant Memory Allocation

    • 3 Videos
    • 1 Discussion
    • 1 Lab
    • 1 Programming
    • 1 Assignment
Show info about module content

1 Programming

  • CUDA Shared and Constant Memory Image Manipulation Assignment

1 Assignment

  • CUDA Constant and Shared Memory Quiz

1 Discussions

  • Shared and Constant Memory Discussion

1 Labs

  • CUDA Shared and Constant Memory Image Processing Lab

3 Videos

  • GPU Device Constant Memory Allocation
  • CUDA Shared and Constant Memory Image Processing Lab Overview Video
  • CUDA Shared and Constant Memory Image Manipulation Assignment Overview Video

Nvidia GPU Register Memory

    • 1 Videos
Show info about module content

1 Videos

  • CUDA GPU Device Register Memory

Nvidia GPU Register Memory Analysis

    • 1 Videos
Show info about module content

1 Videos

  • CUDA GPU Device Register Memory Investigation

Register Memory Allocation

    • 1 Videos
Show info about module content

1 Videos

  • CUDA GPU Device Memory Evaluation

Nvidia Memory Comparison

    • 2 Videos
    • 1 Discussion
    • 1 Lab
    • 1 Programming
    • 1 Assignment
Show info about module content

1 Programming

  • CUDA Device Memory Analysis Assignment

1 Assignment

  • Device Memory Quiz

1 Discussions

  • GPU Device Memory Analysis Discussion

1 Labs

  • CUDA Device Memory Lab

2 Videos

  • CUDA Device Memory Lab Overview Video
  • CUDA Device Memory Analysis Assignment Overview Video

Auto Summary

"Introduction to Parallel Programming with CUDA" is a professional-level course designed for IT and Computer Science enthusiasts. Taught by Coursera, it equips learners with skills to develop GPU-based parallel processing code using Nvidia CUDA. Focusing on both hardware and software capabilities, the course covers handling 100s to 1000s of threads and memory forms over 1320 minutes. Subscription options include Starter and Professional tiers, catering to those aiming to solve complex computational problems efficiently.

Chancellor Thomas Pascale
Instructor

Chancellor Thomas Pascale