Intel tunes its compilers to optimize for its hardware platforms to minimize stalls and to produce code that executes in the smallest number of cycles.
Interprocedural optimization applies typical compiler optimizations (such as constant propagation) but using a broader scope that may include multiple procedures, multiple files, or the entire program.
Intel's compiler has been criticized for applying, by default, floating-point optimizations not allowed by the C standard and that require a special flags with other compilers such as gcc.
http://software.intel.com/en-us/intel-compilers/http://en.wikipedia.org/wiki/Intel_C%2B%2B_CompilerIntel(R) C++ Compiler Professional Edition for Linux* for non-commercial use.
Intel C++ Compiler optimization
$ CC=icc CXX=icc CFLAGS="-O3 -xK -ip -gcc -mtune=pentium-mmx -march=pentium3 -msse -fomit-frame-pointer -funroll-loops" CXXFLAGS="-O3 -xK -ip -gcc -mtune=pentium-mmx -march=pentium3 -msse -fomit-frame-pointer -funroll-loops" ./configure