Intel VTune Amplifier

Basic Hotspots

Best for analyzing call paths to find where your code is spending the most time and discover opportunities for tuning your algorithms.

Applies to C/C++, Fortran, Java*, or Python* apps and more.

Basic Hotspots Bottom-up tab expanded

Advanced Hotspots

Best for analyzing an application or the entire system and getting kernel information with higher resolution from shorter sampling intervals.

Applies to C/C++, Fortran, or Java* apps and more, including apps in containers such as Docker* or LXC.

Advanced Hotspots Bottom-up tab expanded

Concurrency

Best for visualizing thread parallelism on available cores, finding areas with high or low concurrency, and identifying serial bottlenecks in your code.

Applies to C/C++, Fortran, or Java* apps and more.

Concurrency timeline with interrupts

Locks and Waits

Best for locating causes of low concurrency, such as heavily used locks and large critical sections.

Applies to C/C++, Fortran, Java*, or Python* apps and more.

Locks and Waits Bottom-up tab wait count and spin time

HPC Performance Characterization

Best for understanding how your compute-intensive OpenMP* or MPI app is using the CPU, memory, and floating point unit (FPU) resources.

Applies to C/C++ or Fortran apps and more.

HPC Performance Characterization viewpoint

General Exploration

Best for identifying the CPU pipeline stage (front-end, back-end, etc.) and hardware units responsible for your hardware bottlenecks.

Applies to C/C++, Fortran, or Java* apps and more, including apps in containers such as Docker* or LXC.

General Exploration Bottom-up tab with tooltip

Memory Access

Best for memory-bound apps to determine which level of the memory hierarchy is impacting your performance by reviewing CPU cache and main memory usage, including possible NUMA issues.

Applies to C/C++, Fortran, or Java* apps and more.

Top memory objects by latency

Get Started

Open a project and click the New Analysis button to get started.

Get started with your performance analysis

Other Analysis Types

Intel VTune Amplifier offers other analysis types that are helpful in specific use cases.

GPU Analysis

CPU/GPU Concurrency: Best for identifying whether your application is CPU or GPU bound by examining how your code executes on the CPU and GPU cores.
GPU Hotspots: Best for GPU-bound applications to identify which tasks are using the most GPU time.
GPU In-kernel Profiling: Best for GPU-bound applications to identify performance issues caused by memory latency or inefficient kernel algorithms.

Memory Analysis

Memory Consumption (Linux* OS targets only): Best for exploring memory consumption (RAM) over time and identifying memory objects allocated and released in your native Linux* or Python* application.

Platform Analysis

Disk Input and Output (Preview feature on Windows* OS): Best for monitoring usage of the disk subsystem, CPU, and processor buses.
System Overview: Best for understanding how interrupts (IRQ), frequency, threads, and sleep states impact system performance.

Other analysis tools are available as part of the Intel Parallel Studio or Intel System Studio.

Application Performance Snapshot: Best for a quick look at basic performance enhancement opportunities.
Intel Advisor: Best for optimizing vectorization.
Intel Inspector: Best for debugging memory and threading errors.
Intel Trace Analyzer and Collector: Best for MPI applications run in a cluster environment.

Learn More

The Intel Developer Zone website offers more information about Intel VTune Amplifier features and usage.

Legal Information

Intel and the Intel logo are trademarks of Intel Corporation in the U.S. and/or other countries.

*Other names and brands may be claimed as the property of others.

Intel® VTune™ Amplifier