Intel® VTune™ Amplifier Tutorials

The following tutorials are quick paths to start using the Intel® VTune™ Amplifier. Each demonstrates an end-to-end workflow you can ultimately apply to your own applications.

Note

Most of the VTune Amplifier XE tutorials are also applicable to the VTune Amplifier for Systems. The Finding Hotspots - Fortan Sample Code, Finding Hotspots on the Intel® Xeon Phi™ Coprocessor, and Analyzing an OpenMP* and MPI Application tutorials are applicable only to the VTune Amplifier XE.

VTune Amplifier XE Tutorials

Take This Short TutorialLearn To Do This

Finding Hotspots
Duration: 10-15 minutes

C++ Tutorial
Windows* OS: HTML | PDF
Linux* OS: HTML | PDF
Sample code: tachyon_vtune_amp_xe

Fortran Tutorial
Windows* OS: HTML | PDF
Linux* OS: HTML | PDF
Sample code: nqueens_fortran

Identify where your application is spending time, detect the most time-consuming program units and how they were called.

Finding Hotspots on the Intel® Xeon Phi™ Coprocessor
Duration: 10-15 minutes

C++ Tutorial
Windows* OS: HTML | PDF
Linux* OS: HTML | PDF
Sample code: matrix_vtune_amp_xe

Identify where your native Intel Xeon Phi coprocessor-based application is spending time, estimate code efficiency by analyzing hardware event-based metrics.

Analyzing Locks and Waits
Duration: 10-15 minutes

C++ Tutorial
Windows* OS: HTML | PDF
Linux* OS: HTML | PDF
Sample code: tachyon_vtune_amp_xe

Identify locks and waits preventing parallelization.

Identifying Hardware Issues
Duration: 10-15 minutes

C++ Tutorial
Windows* OS: HTML | PDF
Linux* OS: HTML | PDF
Sample code: matrix_vtune_amp_xe

Identify the hardware-related issues in your application such as data sharing, cache misses, branch misprediction, and others.

Analyzing Disk Input/Output Waits
Duration: 10-15 minutes

C++ Tutorial
Linux* OS: HTML | PDF
Sample code: diskio

Analyze an I/O bound application that uses the system file cache and user buffer to work with the I/O device.

Identifying False Sharing
Duration: 10-15 minutes

C Tutorial
Linux* OS: HTML | PDF
Sample code: linear_regression

Identify false sharing.

Analyzing an OpenMP* and MPI Application
Duration: 60+ minutes

C++ Tutorial
Linux* OS: HTML
Sample code: https://github.com/CardiacDemo/Cardiac_demo

Identify issues in a hybrid OpenMP and MPI application using MPI Performance Snapshot, Intel Trace Analyzer and Collector, and Intel VTune Amplifier.

VTune Amplifier for Systems Tutorials

Take This Short TutorialLearn To Do This

Enabling Performance Collection on an Embedded Linux* System
Duration: 60+ minutes

C++ Tutorial
Linux* OS: HTML | PDF
Sample code: tachyon_vtune_amp_xe

Configure a remote Linux embedded system built with the Yocto Project* 2.1 environment for application analysis with VTune Amplifier sampling drivers. Analyze where your application is spending time and identify the most time-consuming program units with Advanced Hotspots analysis.

Finding Hotspots on an Android* Platform
Duration: 10-15 minutes

C++ Tutorial
Windows* OS: HTML | PDF
Linux* OS: HTML | PDF
Sample code: tachyon_vtune_amp_xe

Configure and run a remote Basic Hotspots analysis on an Android target system.

Analyzing Energy Usage on an Android* Platform
Duration: 10-15 minutes

Tutorial
Linux* OS: HTML | PDF
Windows* OS: HTML | PDF

Use the Intel Energy Profiler to run the Energy analysis with the Intel SoC Watch collector directly in the target Android system and view the collected data with the VTune Amplifier for Systems installed on the host Windows* or Linux* system.

Analyzing Energy Usage on a Windows* Platform
Duration: 20-30 minutes

Tutorial
Windows* OS: HTML | PDF
Sample code: Pi_Console.exe

Use the Intel Energy Profiler to run energy analysis of an idle system and a sample application with the Intel SoC Watch collector directly in the target Windows* system. Copy the results to the Windows host system and view the collected data with VTune Amplifier for Systems.

For more complete information about compiler optimizations, see our Optimization Notice.