Open Source C Profiling Software

The goal of the project is now to develop a user library called libpfm4 to help setup performance events for use with the perf_events Linux kernel interface. The development of the perfmon kernel subsystem, libpfm and pfmon has now stopped.

OProfile is a low-overhead, transparent profiler for Linux, capable of instruction-grain profiling of all processes, shared libraries, the kernel and device drivers, via the hardware performance counters.

Cinemagoer is a Python package useful to retrieve and manage the data of the IMDb movie database about movies, people, characters and companies. Platform-independent, it can retrieve data from both the IMDb's web server and a local copy of the whole db.

ParTools allows the interactive analysis of a C program execution profile and data dependencies to facilitate the discovery and selection of suitable parallelization candidates in a manual parallelization process. The flow does not assume any specific parallelization technique, thus it can be broadly applied. The original (serial) C source is automatically annotated to trace the execution profile and data dependencies at run-time. The annotated program is then executed using a significant (but small) data set selected by the developer. The data collected is cross-referenced with the original source and can be interactively analyzed graphically to determine the best parallelization candidates and techniques.

KCachegrind visualizes traces generated by profiling, including a tree map and a call graph visualization of the calls happening. It's designed to be fast for very large programs like KDE applications.

The goal of this project is to develop the OS-independent, obtrusive, customizable, extensible, generic logging and tracing software mechanism.

Performance profiler for Amiga AACE/Tao Intent software. Works for source in both C and VP. Includes filters to convert data into cvs spreadsheets. (Compiles under Linux as well, but no Linux build system is included)

ZH修改器库 B站账号: https://space.bilibili.com/419744583 QQ群号: 689948788

Libinstrument is a complete and easy way to do custom function instrumentation for C/C++. The project comes ready with classic applications of instrumentation, such as AOP (Aspect Oriented Programming), Concern and Side Effect injection, stack tracing, exception tracing, basic time profiling, callgraph profiling and other. A GC (Garbage Collector) module is also under development. Libinstrument is highly portable and decoupled. The project comes with a CMake build system, integration with IDEs (CLion, Eclipse e.t.c) is straightforward. Using lazy algorithms there is virtually zero overhead in benchmarks and minimum overhead in execution time. Libinstrument tries to be as non-intrusive as possible, while trying to help the developer offering basic reflection. There are Unit Tests for each class and method, testing is driven with CTest.

ATrace is a tracing tool uses the ptrace interface. ATrace allows tuning and troubleshooting of applications without modification of the source or object code and can be parameterized via config files and logs the addresses of executed instructions.

This project born a few years ago when I encountered a fatal bug on a production environment, unfortunately not replicable on my development machine. I spent many time finding a solution, using also freeware and commercial third-party tools and libraries, but none helped me because the bug crashed the process, and no of the above tools could be able to catch the exception before the process dying. Also, it was not possible to install a development environment onto the production machines, so the only solution was to develop a debugger which didn't need any user/developer interaction. I used many open source resources, then I decided to make the Bug Finder an open source project. It is built over a pluggable architecture to support other languages different from Borland Delphi (the one I used to develop my faulting application and the Bug Finder too). Here is the article http://www.codeproject.com/Articles/602794/Bug-Finder-a-real-Win32-extensible-passive-debugge .

The Cache emulator (shortly CE) can simulates the behavior of caches inside SMP system and compute the number of cache misses during a computation. All measurements are done in the "off-line" mode on the one CPU.

Diagonal can be used for: - getting descriptive statistics such as mean/median/mode with your program producing a sample - finding a root of an equation your program defines - calculating a fixed point of a function your program defines - detecting a cycle of a fuction your program defines as well as - decoding a VCDIFF file

FunctionCheck is a profiler for C/C++ programs, based on gcc V4.6.3+. Features are flat profile, cycles detection, call-graph, MIN/MAX time in functions, memory profiling, profiling control at execution...

An Extensible memory leakage detection system which can be turn on/off just including or not a C header

gcov-eclipse is an Eclipse plug-in that will extend CDT to provide code-coverage testing to C/C++ projects by using the gcov program. It will integrate into the CDT's launch and managed build system.

A Python programming environment providing memory sizing, profiling and analysis, and a specification language that can formally specify aspects of Python programs and generate tests and documentation from a common source.

This is a dynamic slicing tool for Java programs. The tool modifies the Kaffe virtual machine to collect the execution trace, and compress the trace on-the-fly. Please proceed to the tool's website http://jslice.sourceforge.net/ for download.

Kernel Analyzer is tool for Linux that monitor task preemptions and interruptions in the Linux Kernel. Basically it is a Kernel Patch, that comes also with a user proc interface, a KDB interface, and a Java GUI to display charts.

This project is a tool for beginners to understand why a MPI program works or doesn't. It aims simple MPI codes, with a modest number of Processes. It is a real time view of an executing code, providing help even when the program deadlocks.

A collection of performance analysis software that can assist with a variety of techniques useful for application software optimization and benchmarking. The current release provides support for analysis with hardware performance counters on Linux.

Performance profiler is designed to profile single and multi-threading software.

A collection of library code and tools for application execution profiling and performance testing. You can create stopwatches to time select portions of your code. You can measure differences (often to sub-millisecond accuracy) between clocks on different machines. You can log application events in a .csv format for subsequent analysis. You can also generate CPU loading logs in a .csv format.

pthreadw is a profiling library for multi-threaded programs. It can be used to automatically identify common problems related to threads that limit performance of parallel programs such as lock contention or load imbalance.

SLO profiles the data locality in your program, and afterwards suggests refactorings that can improve that data locality, leading to fewer cache misses and faster execution.