Developer Reference

  • 0.10
  • 10/21/2020
  • Public Content
Contents

Support Functions

Intel® oneAPI Math Kernel Library (oneMKL)
support functions are subdivided into the following groups according to their purpose:
The following table lists
Intel® oneAPI Math Kernel Library
support functions.
oneMKL
Support Functions
Function Name
Operation
Version Information
Returns
the
Intel® oneAPI Math Kernel Library
version.
Returns the
Intel® oneAPI Math Kernel Library
version in a character string.
Threading Control
Specifies the number of OpenMP* threads to use.
Specifies the number of OpenMP* threads for a particular function domain.
Specifies the number of OpenMP* threads for all
Intel® oneAPI Math Kernel Library
functions on the current execution thread.
Enables
Intel® oneAPI Math Kernel Library
to dynamically change the number of OpenMP* threads.
Gets the number of OpenMP* threads targeted for parallelism.
Gets the number of OpenMP* threads targeted for parallelism for a particular function domain.
Determines whether
Intel® oneAPI Math Kernel Library
is enabled to dynamically change the number of OpenMP* threads.
Specifies the number of partitions along the leading dimension of the output matrix for parallel
?gemm
functions.
Gets the number of partitions along the leading dimension of the output matrix for parallel
?gemm
functions.
Error Handling
Error handling function called by BLAS, LAPACK, Vector Math, and Vector Statistics functions.
Handles error conditions for the ScaLAPACK routines.
Error handling function called by the C interface to LAPACK functions.
Sets the custom handler of fatal errors.
Character Equality Testing
Tests two characters for equality regardless of the case.
Tests two character strings for equality regardless of the case.
Timing
Returns elapsed time in seconds. Use to estimate real time between two calls to this function.
Returns elapsed CPU clocks.
Returns CPU frequency value in GHz.
Returns the maximum CPU frequency value in GHz.
Returns the frequency value in GHz based on constant-rate Time Stamp Counter.
Memory Management
Frees unused memory allocated by the
Intel® oneAPI Math Kernel Library
Memory Allocator.
Frees unused memory allocated by the
Intel® oneAPI Math Kernel Library
Memory Allocator in the current thread.
Reports the status of the
Intel® oneAPI Math Kernel Library
Memory Allocator.
Reports the peak memory allocated by the
Intel® oneAPI Math Kernel Library
Memory Allocator.
Turns off the
Intel® oneAPI Math Kernel Library
Memory Allocator for
Intel® oneAPI Math Kernel Library
functions to directly use the system
malloc
/
free
functions.
Allocates an aligned memory buffer.
Allocates and initializes an aligned memory buffer.
Changes the size of memory buffer allocated by
mkl_malloc
/
mkl_calloc
.
Frees the aligned memory buffer allocated by
mkl_malloc
/
mkl_calloc
.
On Linux, sets the limit of memory that
Intel® oneAPI Math Kernel Library
can allocate for a specified type of memory.
Single Dynamic Library (SDL) Control
Sets the interface layer for
Intel® oneAPI Math Kernel Library
at run time.
Sets the threading layer for
Intel® oneAPI Math Kernel Library
at run time.
Replaces the error handling routine. Use with the Single Dynamic Library .
Replaces the progress information routine.
Replaces the routine handling
Intel® oneAPI Math Kernel Library
PARDISO pivots with a user-defined routine. Use with the Single Dynamic Library (SDL).
Conditional Numerical Reproducibility (CNR) Control
Configures the CNR mode of
Intel® oneAPI Math Kernel Library
.
Returns the current CNR settings.
Automatically detects the CNR code branch for your platform.
Miscellaneous
Provides progress information.
Enables dispatching for new Intel® architectures or restricts the set of Intel® instruction sets available for dispatching.
Set up the mode that ignores environment settings specific to
Intel® oneAPI Math Kernel Library
.
Enable or disable
Intel® oneAPI Math Kernel Library
Verbose mode.
Write output in
Intel® oneAPI Math Kernel Library
Verbose mode to a file.
Sets the implementation of the message-passing interface to be used by
Intel® oneAPI Math Kernel Library
.
Terminates
Intel® oneAPI Math Kernel Library
execution environment and frees resources allocated by the library.
Optimization Notice
Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.
Notice revision #20110804
This notice covers the following instruction sets: SSE2, SSE4.2, AVX2, AVX-512.

Product and Performance Information

1

Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice revision #20110804