Catalog > All Topics

NVIDIA- Accelerating CUDA C / C++ Applications with Multiple GPUs (FAC- A-CUDA-A-MGPU)

NVIDIA
8 Hours
Download Course Outline
$500.00
Request a Quote
Credit not applicable
Share
Schedule
Export to CSV
  • No schedule events found for this course.
      • PC
        Private Class
        Privately train a group of your employees at your facility, virtually, or any of our locations.
    Request
  • LCLive Classroom
    Live Classroom
    Learn and interact with your instructor and peers in-person in our classrooms.
  • VCVirtual Classroom
    Virtual Classroom
    Attend any of our instructor-led classes virtually regardless of your physical location.
  • PCPrivate Class
    Private Class
    Privately train a group of your employees at your facility, virtually, or any of our locations.
  • GTRGuaranteed to Run
    Guaranteed to Run
    GTR classes are guaranteed to run as promised and delivered.
Course Summary
Show All

Description

This workshop teaches the fundamental tools and techniques for accelerating C/C++ applications to run on massively parallel GPUs with CUDA®. You’ll learn how to write code, configure code parallelization with CUDA, optimize memory migration between the CPU and GPU accelerator, and implement the workflow that you’ve learned on a new task—accelerating a fully functional, but CPU-only, particle simulator for observable massive performance gains. At the end of the workshop, you’ll have access to additional resources to create new GPU-accelerated applications on your own.

Objectives

At the conclusion of the workshop, you’ll have an understanding of the fundamental tools and techniques for GPU-accelerating C/C++ applications with CUDA and be able to:

  •  Write code to be executed by a GPU accelerator
  •  Expose and express data and instruction-level parallelism in C/C++ applications using CUDA
  •  Utilize CUDA-managed memory and optimize memory migration using asynchronous prefetching
  •  Leverage command line and visual profilers to guide your work
  •  Utilize concurrent streams for instruction-level parallelism
  •  Write GPU-accelerated CUDA C/C++ applications, or refactor existing CPU-only applications, using a profile-driven approach

Prerequisites

Basic C/C++ competency, including familiarity with variable types, loops, conditional statements, functions, and array manipulations. No previous knowledge of CUDA programming is assumed.

Outline

Introduction
(15 mins)

  •  Meet the instructor.

  • Create an account at courses.nvidia.com/join

Accelerating Applications with CUDA C/C++
(120 mins)
Learn the essential syntax and concepts to be able to write GPU-enabled C/C++ applications with CUDA:

  •  Write, compile, and run GPU code.

  •  Control parallel thread hierarchy.

  •  Allocate and free memory for the GPU.

Break (60 mins)
Managing Accelerated Application Memory with CUDA C/C++
(120 mins)
Learn the command line profiler and CUDA managed memory, focusing on observation-driven application improvements and a deep understanding of managed memory behavior:

  •  Profile CUDA code with the command line profiler.

  •  Go deep on unified memory.

  • Optimize unified memory management.

Break (15 mins)
Asynchronous Streaming and Visual Profiling for Accelerated Applications with CUDA C/C++
(120 mins)
Identify opportunities for improved memory management and instructionlevel parallelism:

  • Profile CUDA code with the NVIDIA Visual Profiler.

  • Use concurrent CUDA streams.

Final Review
(15 mins)

  •  Review key learnings and wrap up questions.

  • Complete the assessment to earn a certificate.

  •  Take the workshop survey.