The ATLAS (Automatically Tuned Linear Algebra Software) project is an ongoing research effort focusing on applying empirical techniques in order to provide portable performance. It provides C and Fortran77 interfaces to a portably efficient BLAS implementation, as well as a few routines from LAPACK.
Hoard is a scalable memory allocator (malloc replacement) for multithreaded applications. Hoard can dramatically improve your application's performance on multicore machines. No changes to your source are necessary; just link it in. Hoard scales linearly up to at least 64 processors. Supported platforms include Linux, Solaris, Mac OS X, and Windows.
DISLIN is a high-level, easy-to-use plotting library for displaying data as curves, bar graphs, pie charts, 3D-colour plots, surfaces, contours, and maps. Several output formats are supported, such as X11, VGA, PostScript, PDF, CGM, HPGL, TIFF, and PNG. Plotting extensions for the interpreter-based languages Perl, Python, and Java are also supported for most operating systems.
SLOCCount is a suite of programs for counting physical source lines of code (SLOC) in possibly large software systems. It can count physical SLOC for a wide number of languages. It can take a large set of files and automatically categorize their types using a number of different heuristics, and also comes with analysis tools.
TAU (Tuning and Analysis Utilities) is a set of tools for analyzing the performance of C, C++, Fortran and Java programs. It collects much more information than is available through prof or gprof, the standard Unix utilities, including per-process, per-thread, and per-host information, inclusive and exclusive function times, profiling groups that allow you to organize data collection, access to hardware counters on some systems, per-class and per-instance information, the ability to separate data for each template instantiation, start/stop timers for profiling arbitrary sections of code, and support for collection of statistics on user-defined events.