List of performance analysis tools
General purpose, language independent
The following tools work based on log files that can be generated from various systems.
- TimeToPic visualizes a log file. If system has logging facility, its output can be shown on visual timeline. Developer can see from visualization what is happening on log. Can be used for code and "logic" level analysis. There are version for Windows and Linux. Supports log sizes up to 1 Gigabyte.
- time (Unix) - can be used to determine the run time of a program, separately counting user time vs. system time, and CPU time vs. clock time.
The following tools work for multiple languages or binaries.
|Name/Manufacturer||OS||Compiler/Language||What It Does||License|
|CPUProfiler by OsLe Tek||Linux, Windows, WinCE||Any application compiled for Intel, ARM, PowerPC architectures||Monitors CPU and memory usage of processes, and charts process stability during program development. Designed for program managers, allows remote monitoring and management of CPU profiling sessions through a web browser.||Proprietary|
|Allinea MAP by Allinea Software||Linux||C, C++, Fortran/Fortran90 applications and applications with MPI parallelism||Performance profiler||Proprietary|
|aprof||Linux||Any, including assembler||
Input-sensitive performance profiler based on Valgrind designed to help developers understand how an application’s performance scales as a function of its input data, exposing possible asymptotic inefficiencies.
|Free/open source (GPL)|
|AQtime by SmartBear Software||Windows||.NET 1.0 to 4.0 applications (including ASP.NET applications), Silverlight 4.0 applications, Windows 32- and 64-bit applications including C, C++, Delphi for Win32 and VBScript and JScript functions||Performance profiler and memory/resource debugging toolset||Proprietary|
|CodeAnalyst by AMD||Linux, Windows||C, C++, .Net, Java (works at the executable level)||GUI based code profiler; does only basic timer-based profiling on Intel processors. Based on OProfile.
As of Mar-2013, CodeAnalyst has been replaced by AMD CodeXL (see below).
|Free/open source (GPL) or proprietary|
|AMD CodeXL by AMD||Linux, Windows||For CPU profiling: C, C++, .Net, Java (works at the executable level).
For GPU profiling and debugging: OpenCL.
|A tool suite that includes both GPU and CPU profilers, as well as a GPU debugger and a static kernel analyzer.||Free|
|Caliper by HP||HP-UX with Intel Itanium Integrity platform (IA-64).||Profiling tool|
|DevPartner by Borland / Micro Focus||.NET, Java||Test suite that automatically detects and diagnoses software defects and performance problems.||Proprietary|
|DTrace by Sun Microsystems||Solaris, Linux, BSD, Mac OS X||Comprehensive dynamic tracing framework for troubleshooting kernel and application problems on production systems in real time.||Free/open source (CDDL)|
|Lucierna by Lucierna||Linux (any distribution, kernel 2.6+), Sun Solaris, HP-UX, AIX, MacOS X 10.7 +, MS Windows Server 2003, 2008||.NET, Java and PHP (for web sites and desktop software)||Application Performance Management||Proprietary|
|dynamoRIO by RIO ||Linux, Windows||Dynamic binary instrumentation framework for the development of dynamic program analysis tools.||Free/open source - BSD|
|dynaTrace by Compuware||Linux, Windows, iOS, Android, Azure, AWS, AIX, Solaris, HP/UX, zOS, zLinux||.NET, Java, PHP, HTML5, AJAX (for web sites), ObjectiveC/iOS, Java/Android, C/C++, CICS||Application Performance Management||Proprietary|
|DynInst||Linux, Windows, BlueGene/Q||API to allow dynamic injection of code into a running program||Free/open source|
|GlowCode||Windows||64-bit and 32-bit applications, C, C++, .NET, and dlls generated by any language compiler.||Performance and memory profiler which identifies time-intensive functions and detects memory leaks and errors||Proprietary|
|gprof||Linux/Unix||Any language supported by gcc||Several tools with combined sampling and call-graph profiling. A set of visualization tools, VCG tools, uses the Call Graph Drawing Interface (CGDI) to interface with gprof. Another visualization tool which interfaces with gprof is KProf.||Free/open source - BSD version is part of 4.2BSD and GNU version is part of GNU Binutils (by GNU Project)|
|IgProf||Linux||Any compiled language (C, C++, Fortran, etc.), python (cProfile) compatibility||Performance (sampling) and memory (heap, leaks, total dynamic allocations) profiler, plus dynamic binary instrumentation. Text and navigable webpage output with full call graphs.||GPL|
|Linux Trace Toolkit (LTT)||Linux||Requires patched kernel||Collects data on processes blocking, context switches, and execution time. This helps identify performance problems over multiple processes or threads. Superseded by LTTng.||GPL|
|LTProf||Windows||Visual C++, Borland CBuilder, Delphi and VB applications||CPU profiling tool||Commercial|
|LTTng (Linux Trace Toolkit Next Generation)||Linux||System software package for correlated tracing of kernel, applications and libraries||GPL/LGPL/MIT|
|OProfile||Linux||Profiles everything running on the Linux system, including hard-to-profile programs such as interrupt handlers and the kernel itself.||Sampling profiler for Linux that counts cache misses, stalls, memory fetches, etc.||Open Source GPLv2|
|OpenPAT||Linux, FreeBSD, OSX||Any compilable language including C, C++, Fortran and languages that compile to bytecodes such as Java and C# with appropriate toolchain configurations.||Statically instruments program assembly to call a tool with a stream of dynamic trace information when the program runs. Existing tools measure hotspot, control flow, data flow and other information.||Free and Open Source (requires registration)|
|Oracle Solaris Studio Performance Analyzer||Linux, Solaris||C, C++, Fortran, Java; MPI||Performance and memory profiler||Free|
|Paraver||Linux, Mac OS X, Windows ||For parallel computing clusters||Performance analysis tool based on trace files; allows viewing the progress of the application in a temporal axis and also perform accumulation of performance metrics in a table like regular profilers.||Free/open source (LGPL)|
|PGPROF by The Portland Group||Linux, MacOS X, Windows||C, C++, and Fortran applications using OpenMP and MPI parallelism||Sampling and compiler-based instrumentation for application profiling||Proprietary|
|PmcTools||FreeBSD||Provides non-intrusive, low-overhead and innovative ways of measuring and analysing system performance. It exploits the same underlying hardware counters as Linux' OProfile.|
|perf tools||Linux kernel 2.6.31+||Sampling profiler with support of hardware events on several architectures.||GPL|
|Performance Application Programming Interface (PAPI)||Various||Library for hardware performance counters on modern microprocessors|
|Pin by Intel||Linux, Windows||Dynamic binary instrumentation system that allows users to create custom program analysis tools||Proprietary but free for non-commercial use|
|pprof, part of gperftools by Google||Linux, Unix||Sampling profiler with context-sensitive call graph capability.||Open-source|
|Rational PurifyPlus||AIX, Linux, Solaris, Windows||Performance profiling tool, memory debugger and code coverage tool||Proprietary|
|Shark by Apple||Mac OS X (discontinued with 10.7)||Performance analyzer||Free|
|Shiny||Cross-platform||C, C++, Lua||Performance analyzer with call graphs and time allocations||Free/open source (MIT license)|
|SlowSpotter and ThreadSpotter by Acumem (Rogue Wave)||Linux, Solaris, Windows||Most compiled languages including Ada||Diagnose performance problems related to data locality, cache utilization and thread interactions.||Commercial|
|Sysprof||Linux||Sampling CPU profiler that uses a kernel module to profile the entire system, as opposed to a single application. It displays the time spent in each branch of the applications' calltrees.||GPLv2|
|Systemtap||Linux||Programmable system tracing/probing tool; may be scripted to generate time- or performance-counter- or function-based profiles of the kernel and/or its userspace.||Open source|
|Valgrind||Linux||Any, including assembler||System for debugging and profiling; supports tools to either detect memory management and threading bugs, or profile performance (cachegrind and callgrind). KCacheGrind, valkyrie and alleyoop are front-ends for valgrind.||Free/open source (GPL)|
|Vampir||Linux, Mac OS X, Windows||Any language supported by the VampirTrace or Score-P measurement infrastructures (currently C, C++, Fortran/Fortran90 with support for various parallelization paradigms like MPI, OpenMP and Pthreads)||Vampir is a visualization tool for analyzing trace files created with the open source measurement infrastructures VampirTrace and Score-P.||Proprietary|
|VTune Amplifier XE by Intel Corporation||Linux, Windows||C, C++, Fortran, .NET, Java||Tool for serial and threaded performance analysis. Hotspot, call tree and threading analysis works on both Intel and AMD x86 processors. Hardware event sampling that uses the on chip performance monitoring unit requires an Intel processor.||Proprietary|
|Windows Performance Analysis Toolkit by Microsoft||Windows||Freeware/proprietary|
|RotateRight Zoom||Linux||Supports most compiled languages on ARM and x86 processors.||Graphical and command-line statistical (event-based) profiler|
- Acumem SlowSpotter and Acumem ThreadSpotter
- AdaNav sometimes bundled with ObjectAda
- NightTrace and the instrumented RedHawk Linux kernel from Concurrent Computer Corporation
- RootCause from OC Systems
C and C++
- IBM Rational Purify
- AQTime Pro Performance profiler and memory allocation debugger can be integrated into Microsoft Visual Studio, Embarcadero RAD Studio or can run as a stand-alone application.
- Celero is an open source C++ library for building profile suites for projects in the same vein as unit testing and offers an API similar to GoogleTest.
- CodeTune is a free, easy to use, GUI-based profiler for Windows applications
- Embedded Profiler for gcc, MinGW, and Visual Studio
- Intel Parallel Studio contains Parallel Amplifier, which tunes both serial and parallel programs. It also includes Parallel Inspector, which detects races, deadlocks and memory errors. Parallel Composer includes codecov, a command line coverage tool.
- Parasoft Insure++ Provides a graphical tool that displays and animates memory allocations in real time to expose memory blowout, fragmentation, overuse, bottlenecks and leaks.
- Proffy For Windows, includes a C++ header and produces call graphs.
- Very Sleepy, a simple yet effective profiler which can profile any native Windows application with built-in debugging information (without need for recompilation). It is released under GPL.
- Visual Studio Team System Profiler is Microsoft's commercial profiler
- Profiny is platform-independent, includes a C++ header and supports both flat profiling and call-graph profiling.
- graprof is a C profiler for GNU/Linux systems that supports flat profiling, call-graphs and memory profiling, licensed under the GPL.
(see also "Multiple languages" section above)
- SamplingProfiler is a free sampling profiler CodeGear Borland Delphi.
- Spider is realtime performance profiler and memory allocation analyzer for Borland Delphi applications.
- AppPerfect Java Profiler
- CollectionSpy, a profiler that focuses exclusively on the Java Collections Framework.
- Eclipse Memory Analyzer, a memory analysis tool that also has some performance related features.
- Eclipse TPTP
- inspectIT - free performance diagnostics tool with very small overhead.
- JProbe, an enterprise class Java profiler by Quest Software
- JRockit Mission Control, a profiler with low overhead.
- mBProfiler, a profiler suitable for embedded devices
- Netbeans Profiler, a profiler integrated into the NetBeans IDE (internally uses jvisualvm profiler)
- OKTECH Profiler, an open-source, sampling and instrumentation Java profiler for Java 5+ applications; local or remote profiling; optional commercial support.
- Plumbr, Java memory leak detection and analysis.
- RootCause and RTI from OC Systems
- VisualVM is the profiler which comes with the Java Development Kit, it supports all needed features.
- Eclipse Yari by sourceForge.net.
- Nodetime for Node.js
- dynaTrace AJAX Edition is free Internet Explorer and Firefox performance tracing and diagnostics, based on dynaTrace/Compuware PurePath technology
- CLR Profiler is a free memory profiler provided by Microsoft for CLR applications.
- EQATEC Profiler is a performance profiler for .NET, Windows Phone7, .NET CF and Silverlight, free and licensed versions
- GlowCode is a performance and memory profiler for .NET applications using C# and other .NET languages. It identifies time-intensive functions and detects memory leaks and errors in native, managed and mixed Windows x64 and x86 applications.
- JetBrains dotTrace Profiler is a commercial performance and memory profiler for .NET, Silverlight, .NET CF 3.5, SharePoint, XBAP and XNA Framework
- NProf NProf was an open source statistical profiler for .NET. It is no longer actively developed
- Red Gate ANTS Performance Profiler is a commercial profiler for .NET
- Scitech .NET Memory Profiler - proprietary
- SlimTune A free profiling and performance tuning tool for .NET applications with an open source MIT License
- SpeedTrace Pro is a commercial performance analysis and tracing tool for .NET
- Telerik JustTrace is a commercial memory and performance profiler for .NET.
- Visual Studio
- Insight Profiler is a free performance profiler with call sequence recording. The homepage is in German but the actual software is English.
- Software Verify .NET Tool Suite is a commercial suite of profiling, memory leak detection and code coverage tools for .NET, ASP.NET, and WPF. There are also editions for C++ (native 32/64 bit), and other languages as well.
- Chronos .Net Performance Profiler is a free .NET performance profiler
- AMD CodeXL is a tool suite that contains an OpenCL GPU debugger and an OpenCL GPU profiler (in addition to a traditional CPU profiler). AMD CodeXL also includes an OpenCL static kernel analysis tool.
- cProfile, profile, and pstats modules are usually built-into Python 2.5+.
- "CodeXL". Retrieved 26 September 2013.
- The RIO Project: Runtime Introspection and Optimization
- "Smashing performance with OProfile" by Prasanna Panchamukhi
- "OpenPAT: The Open Performance Analysis Toolkit"
- "OpenPAT: Analysing Programs the Easy Way" by Dr Simon Spacey
- "Oracle Solaris Studio 12.3: Performance Analyzer". Oracle Corporation. Retrieved 26 September 2013.
- "Pin: building customized program analysis tools with dynamic instrumentation"
- "Profiling entire system activity with sysprof" by Ben Martin
- "Runtime Analysis and Memory Error Detection for C and C++". Retrieved 26 September 2013.
- "AppPerfect Java Profiler". Retrieved 26 September 2013.
- "Plumbr". Retrieved 26 September 2013.
- "26.4. The Python Profilers". Retrieved 26 September 2013.