run parallel programs in an HPC environment

use a compiler and to asses the effects of optimization switches available for compilers commercially available (e.g. PGI, NAG)

use efficient open source libraries (e.g. OpenBLAS, FFTW) or highly optimized vendor libraries (e.g. Intel-MKL, IBM-ESSL)

configure the relevant settings (e.g. by setting compiler and linker options), which determine how the application ought to be build with regard to the parallelization technique(s) used (e.g. OpenACC, C++ AMP)

use the profile guided optimization (PGO) technique

use software building environments like Scons, Waf, make, Autotools, CMake