Intel® VTune™ Profiler Documentation
Documentation & Code Samples
Documentation
Code Samples
Get Started with Profiling
Matrix Multiply for Heterogeneous Applications
Learn how to profile a code that's compliant with SYCL* for CPU and GPU using Intel® VTune™ Profiler. The sample contains three implementations of matrix multiplication using different SYCL features.
Matrix Multiply for C Code Running on a CPU
Learn how to use Intel VTune Profiler to profile C code running on a GPU. Six different implementations with various levels of CPU optimizations are included.
Guided ISO3DFD OpenMP* Offload
This sample exposes some typical challenges you face when offloading applications onto OpenMP* offload devices and introduces techniques to resolve them.
Tachyon for Optimizing OpenMP or oneTBB Applications
Learn how to use Intel VTune Profiler to improve performance of parallelized applications using OpenMP or Intel® oneAPI Threading Building Blocks (oneTBB) running on a CPU.
Application Profiling Tutorials
Analyze Hot Code Paths Using Flame Graphs
Understand how you can use Flame Graphs to detect hot spots and hot code paths in Java* workloads using a sample application.
Identify imbalances and communications issues in MPI-enabled applications.
GPU Profiling Tutorials
Profile an OpenMP Offload Application That Runs on a GPU
Build and compile an OpenMP application offloaded onto an Intel GPU. Use Intel VTune Profiler to run analyses with GPU capabilities (HPC performance characterization, GPU offload, and GPU compute and media hot spots) on the OpenMP application, and then examine the results.
Profile a SYCL* Application Running on a GPU
Learn how to use Intel VTune Profiler to run a GPU analysis on the SYCL application and examine the results.
View Intel VTune Profiler Samples
View the Intel VTune Profiler Cookbook
View the oneAPI Samples Catalog
Learn how to access oneAPI code samples in a tool command line or IDE.
Training
Basics
Boost CPU Performance [2:00]
Seven Steps to GPU Application Performance
End-to-End Case Studies
How to Profile Application Performance [47:53]
Analyze Hybrid OpenMP and MPI Code
Profile Your Production Java Workloads in the Cloud [1:00:00]