Visible to Intel only — GUID: GUID-9526F655-F46D-405B-952E-3FD3F36AA247
Visible to Intel only — GUID: GUID-9526F655-F46D-405B-952E-3FD3F36AA247
Math Libraries
The Intel® Fortran Compiler includes the following math libraries:
Library |
OS Support | Description |
---|---|---|
libimf.a |
Linux* and macOS | Intel® Fortran Compiler Classic and Intel® Fortran Compiler Math Libraries, in addition to libm.a, the math library provided with gcc* Both of these libraries are linked in by default because certain math functions supported by the GNU* math library are not available in the Intel® Fortran Compiler Classic and Intel® Fortran Compiler Math Library. This linking arrangement allows the GNU users to have all functions available when using ifort, with Intel optimized versions available when supported. libimf.a is linked in before libm.a. If you link in libm.a first, it will change the versions of the math functions that are used. Many routines in the libimf library are more optimized for Intel® microprocessors than for non-Intel microprocessors. |
libm.lib (static library) and libmmd.dll (the DLL version) |
Windows* | Math Libraries provided by Intel. Many routines in the libimf library are more optimized for Intel® microprocessors than for non-Intel microprocessors. |
Intel® Math Kernel Library (Intel® MKL) |
Linux, macOS , Windows | Math library of Fortran routines and functions that perform a wide variety of operations on vectors and matrices. The library also includes fast Fourier transform (fft) functions, as well as vector mathematical and vector statistical functions. For more information, see Using Intel® Performance Libraries with Microsoft Visual Studio* and the Intel® Math Kernel Library documentation. |
It is strongly recommended to use the default rounding mode (round-to-nearest-even) when calling math library transcendental functions and compiling with default optimization or higher. Faster implementations (in terms of latency and/or throughput) of these functions are validated under the default round-to-nearest-even mode. Using other rounding modes may make results generated by these faster implementations less accurate, or set unexpected floating-point status flags. This behavior may be avoided by -no-fast-transcendentals, which disables calls to the faster implementations of math functions, or by -fp-model strict, which warns the compiler that it cannot assume default settings for the floating-point environment.
Many routines in the Math Library are more optimized for Intel® microprocessors than for non-Intel microprocessors.
Product and Performance Information |
---|
Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex. Notice revision #20201201 |