Improving
Performance with Threading
Intel® oneAPI Math Kernel Library (oneMKL)
Intel® oneAPI Math Kernel Library
thread-safe
, which means that all Intel® oneAPI Math Kernel Library
?lacon)
work correctly during simultaneous execution by multiple threads. In particular, any chunk of threaded Intel® oneAPI Math Kernel Library
Intel® oneAPI Math Kernel Library
If you are using OpenMP* threading technology,
you can use the environment variable
OMP_NUM_THREADS
to specify the number of threads or the equivalent OpenMP run-time function calls. Intel® oneAPI Math Kernel Library
MKL_NUM_THREADS
, and equivalent Intel® oneAPI Math Kernel Library
Intel® oneAPI Math Kernel Library
By default, uses the number of
Intel® oneAPI Math Kernel Library
OpenMP
threads equal to the number of physical cores on the system.
If you
are using the Intel TBB threading technology, the OpenMP threading controls,
such as the
OMP_NUM_THREADS
environment
variable or
MKL_NUM_THREADS
function, have no effect. Use the Intel TBB application programming interface
to control the number of threads.
To achieve higher performance, set the number of
threads to the number of processors or physical cores, as summarized in
Techniques to Set the Number of Threads.
Product and Performance Information
|
---|
Performance varies by use, configuration and other factors. Learn more at
www.Intel.com/PerformanceIndex.
Notice revision #20201201
|