Using the ILP64 Interface vs. LP64 Interface
The
ILP64 libraries use the 64-bit integer type (necessary for indexing large arrays, with more than 2
Intel® oneAPI Math Kernel Library
31
-1 elements), whereas the LP64 libraries index arrays with the 32-bit integer type.
The LP64 and ILP64 interfaces are implemented in the Interface layer. Link with the following interface libraries for the LP64 or ILP64 interface, respectively:
- libmkl_intel_lp64.aorlibmkl_intel_ilp64.afor static linking
- libmkl_intel_lp64.dyliborlibmkl_intel_ilp64.dylibfor dynamic linking
The ILP64 interface provides for the following:
- Support large data arrays (with more than 231-1 elements)
- Enable compiling your Fortran code with thecompiler option-i8
The LP64 interface provides compatibility with the previous
versions because "LP64" is just a new name for the only interface that the
versions lower than 9.1 provided. Choose the ILP64 interface if your application uses
for calculations with large data arrays or the library may be used so in the future.
Intel® oneAPI Math Kernel Library
Intel® oneAPI Math Kernel Library
Intel® oneAPI Math Kernel Library
On 64-bit platforms, selected domains provide API extensions with the
_64
suffix (for example,
SGEMM_64
) for supporting large data arrays in the LP64 library. This enables you to mix data types in one application. The selected domains and APIs include the following:
- BLAS: Fortran-style APIs for C applications and CBLAS APIs with integer arguments
- LAPACK: Fortran-style APIs for C applications and LAPACKE APIs with integer arguments
Intel® oneAPI Math Kernel Library
Compiling for LP64/ILP64
The table below shows how to compile for the ILP64 and LP64 interfaces:
Fortran
| |
---|---|
Compiling for ILP64
| ifort
-i 8
- I<mkl directory> / include ... |
Compiling for LP64
| ifort
- I<mkl directory> / include ... |
C or C++
| |
Compiling for ILP64
| ic c
- DMKL_ILP64
- I<mkl directory> / include ... |
Compiling for LP64
| ic c
- I<mkl directory> / include ... |
Linking of an application compiled with the
or
option to the LP64 libraries may result in unpredictable consequences and erroneous output.
-i
8-
DMKL_ILP64Coding for ILP64
You do not need to change existing code if you are not using the ILP64 interface.
To migrate to ILP64 or write new code for ILP64, use appropriate types for parameters of the
functions and subroutines:
Intel® oneAPI Math Kernel Library
Integer Types
| Fortran
| C or C++
|
---|---|---|
32-bit integers
| INTEGER*4 or
INTEGER(KIND=4) | int |
Universal integers for ILP64/LP64:
| INTEGER without specifying
KIND | MKL_INT |
Universal integers for ILP64/LP64:
| INTEGER*8 or
INTEGER(KIND=8) | MKL_INT64 |
FFT interface integers for ILP64/LP64
| INTEGER without specifying
KIND | MKL_LONG |
To determine the type of an integer parameter of a function, use appropriate include files. For functions that support only a Fortran interface, use the C/C++ include files
*.h
.
The above table explains which integer parameters of functions become 64-bit and which remain 32-bit for ILP64. The table applies to most
functions except some Vector Mathematics and Vector Statistics functions, which require integer parameters to be 64-bit or 32-bit regardless of the interface:
Intel® oneAPI Math Kernel Library
- Vector Mathematics:Themodeparameter of the functions is 64-bit.
- Random Number Generators (RNG):All discrete RNG exceptviRngUniformBits64are 32-bit.TheviRngUniformBits64generator function andvslSkipAheadStreamservice function are 64-bit.
- Summary Statistics:Theestimateparameter of thevslsSSCompute/vsldSSComputefunction is 64-bit.
Refer to the
Developer Reference for more information.
Intel® oneAPI Math Kernel Library
To better understand ILP64 interface details, see also examples.
Limitations
All
function domains support ILP64 programming but FFTW interfaces to
:
Intel® oneAPI Math Kernel Library
Intel® oneAPI Math Kernel Library
- FFTW 2.x wrappers do not support ILP64.
- FFTW 3.x wrappers support ILP64 by a dedicated set of functionsplan_guru64.