Intel® VTune™ Profiler
Quickly Find and Fix Performance Bottlenecks and Realize All the Value of Your Hardware
Performance Analysis for Applications & Systems
Intel® VTune™ Profiler optimizes application performance, system performance, and system configuration for HPC, cloud, IoT, media, storage, and more.
- CPU, GPU, and FPGA: Tune the entire application’s performance―not just the accelerated portion.
- Multilingual: Profile Data Parallel C++ (DPC++), C, C++, C#, Fortran*, OpenCL™, Python*, Google Go* programming language, Java*, Assembly, or any combination.
- System or Application: Get coarse-grained system data for an extended period or detailed results mapped to source code.
- Power: Optimize performance while avoiding power- and thermal-related throttling.
Develop in the Cloud
Get what you need to build, test, and optimize your oneAPI projects for free. With an Intel® DevCloud account, you get 120 days of access to the latest Intel® hardware—CPUs, GPUs, FPGAs—and Intel oneAPI tools and frameworks. No software downloads. No configuration steps. No installations.
Download the Toolkit
Intel VTune Profiler is included in the Intel® oneAPI Base Toolkit, which is a core set of tools and libraries for developing high-performance, data-centric applications across diverse architectures.
Features
Get the Big Picture and the Critical Details
With today’s variety of computer architectures, a performance profiler must be able to diagnose many kinds of bottlenecks. Intel VTune Profiler includes:
- System and Application Overview Profiles: These identify where to focus tuning or how to configure systems. They collect less data and can run for a longer time.
- Application Performance Snapshot is designed for clusters with thousands of ranks.
- Platform Profiler is well suited to cloud servers.
- Performance Snapshot examines individual applications.
- Focused Profiles: These take a more detailed look at different classes of bottlenecks such as compute, memory, threading, accelerator offload, throttling, or I/O. Precise profiling information is annotated onto the code source.
Turn Raw Data into Answers
Performance optimization is a bit like solving a mystery. You gather the evidence, analyze it, and make sense of what’s really going on. Summaries, tips, filtering, and annotations make you more productive.
- Source View: See the profiling results on your source
- Timeline Filtering: Focus on bottlenecks as they change with time
- Summary Reports: Get the big picture and tips for further analysis
Now Available as a Server
Intel VTune Profiler can be installed as an application or a server. A server installation lets a small group of users:
- Access with a web browser
- Share results with other users who have server access
- Profile any target by preinstalling the collector agent or pushing from the server via SSH
What's New in 2021?
Accelerator Profiling
- Offload cost profiling identifies unnecessary data transfers. Explore GPU offload analysis.
- GPU analysis adds DPC++ and multi-GPU support, SIMD metrics, OpenMP* offload pragma awareness, a new memory diagram, and a simplified driver.
- Application Performance Snapshot adds GPU analysis.
- FPGA analysis adds DPC++ support, stall and data transfer by compute unit, and a simplified workflow.
- Intel® Iris® Xe MAX graphics support helps you deliver applications optimized for Intel's first discrete GPU.
New Profiles
- Processor Trace finds short performance anomalies like page faults, system calls, or thread switches.
- CPU, GPU, and FPGA active power analysis debugs throttling, optimizes for a power budget, and tunes flops per watt.
Better Workflow
- Intel® VTune™ Profiler server improves security and is easier to deploy with preinstalled collection agents.
- Platform Profiler gains a simplified setup and remote workflow.
- Open-source communication agent simplifies adding performance analysis to real-time operating systems.
Better Data
- I/O analysis has a better summary plus additional DDIO and MMIO metrics.
- Docker containers have more meaningful IDs.
- Discover the latest features and capabilities.
Get Started
Download
Intel VTune Profiler is a part of the Intel® oneAPI Base Toolkit.
Try It Out
Follow the Get Started Guide and use an introductory code sample to see how Intel VTune Profiler works.
Learn Analysis Techniques
Browse the cookbooks to see if there are recipes for analysis of your performance bottlenecks.
Documentation & Code Samples
Documentation
- Install Guides:
Windows* | Linux* | macOS* - User Guide
- Processor Tuning Guides
- Release Notes
- System Requirements
Training
Cookbooks
Videos
Boost CPU Performance with Intel® VTune™ Profiler
Snapshot Your Application Performance and Improve
Have a Heart: Love Your Hybrid Programs
How NUMA Affects Your Workloads
How to Analyze & Optimize Long Workload Runs with Platform Profiler
Profile Heterogeneous Computing Performance with Intel® VTune™ Profiler
Specifications
Processor:
- Intel® 64 architecture processors that support Intel® Streaming SIMD Extensions 2 instructions
GPUs:
- Intel® Processor Graphics Gen9 and above
- Xe architecture
FPGAs:
- Intel® Arria® 10 and Intel® Stratix® 10 FPGA
Languages:
- Data Parallel C++ (DPC++)
- C and C++
- C#
- Fortran
- OpenCL programs
- Google Go programming language
- Java
- Python
Development environments:
- Windows: Microsoft Visual Studio*
- Linux: Eclipse*
Host operating systems:
- Windows
- Linux
- macOS
Target operating systems:
- Windows
- Linux
- FreeBSD
- Android
- Wind River Linux
- Yocto Project
Compilers:
- Compilers from Intel
- Microsoft* compilers
- GNU Compiler Collection (GCC)*
- Other compilers that follow the operating system standards
Threading analysis:
- OpenMP*
- Intel® oneAPI Threading Building Blocks
- Native threads
Distributed environments:
- MPI (MPICH-based, OpenMPI)
For more information, see the system requirements.
Intel® Advisor
This design and analysis tool achieves high application performance through efficient threading, vectorization and memory use, and GPU offload on current and future Intel hardware. It supports C, C++, Fortran, DPC++, OpenMP, and Python.
- Offload Advisor: Get your code ready for efficient GPU offload even before you have the hardware
- Automated Roofline Analysis: See performance headroom against hardware limitations and get insights for an effective optimization roadmap.
- Vectorization Advisor: Enable more vector parallelism and get guidance to improve its efficiency
- Threading Advisor: Model, tune, and test threading design options
- Flow Graph Analyzer: Create, visualize and analyze task and dependency-computation
Get Help
Your success is our success. Access these support resources when you need assistance.
Ready to Get Started?
Product and Performance Information
Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.