Using the Mathematical Acceleration Subsystem (MASS) libraries

IBM® Open XL Fortran is shipped with a set of Mathematical Acceleration Subsystem (MASS) libraries for high-performance mathematical computing.

The MASS libraries consist of a library of scalar Fortran routines described in Using the scalar library, a set of vector libraries tuned for specific architectures described in Using the vector libraries, and a set of SIMD libraries tuned for specific architectures described in Using the SIMD libraries. The functions contained in both the scalar and SIMD libraries are automatically called when appropriate compiler options are specified, but you can also call them explicitly in your programs. Note that accuracy and exception handling might not be identical in MASS functions and system library functions. The MASS functions must run with the default rounding mode and floating-point exception trapping settings.

To automatically use the scalar and SIMD MASS libraries, compile with any of the following sets of options:
  • -O2 -qhot -qnostrict
  • -O2 -qhot -qstrict=nolibrary
  • -O3
  • -O4
  • -O5

With these options, the compiler first attempts to SIMDize calls to system math functions by calling the equivalent SIMD MASS functions when appropriate. Otherwise, it automatically calls the equivalent MASS scalar functions.

For automatic use, the compiler uses versions of the MASS functions contained in the XLOPT library libxlopt.a, which is linked by default.

Compiling and linking a program with MASS describes how to compile and link a program that manually uses the MASS libraries, and how to selectively use the MASS scalar library functions in conjunction with the regular system libraries.