FYI: https://code.google.com/p/aprof/
Строит зависимость сложности функции от RMS (Read Memory Size), т.е. количества обращений функции к памяти.
Анонс на comp.unix.programmer:
Hi everyone,
We are developing a new Valgrind tool called aprof, a performance profiler for C/C++ designed to help developers understand how an application’s performance scales as a function of its input data. The tool automatically generates, for each executed function, a 2D chart that relates performance to input size, yielding clues to the «big Oh» of the underlying algorithm and exposing possible asymptotic inefficiencies. Charts that analyze the input workloads are also generated, among many others.
The tool and a profile visualizer have been brewing for some time and we think they are mature enough to be released. For the time being, we're keeping them at:
https://code.google.com/p/aprof
Please check the wiki for a manual and a brief tutorial explaining the main goals of our profiler and how to use it. For an example of the kind of info one can get from aprof see, e.g., Frank Reininghaus' blog http://tinyurl.com/oyuud99.
We would be happy to hear about any experience, difficulties, questions, or suggestions about aprof.
Cheers, Emilio Coppa
