Intel Many Integrated Core Architecture Support

This section describes Intel MKL functions to support the use of Intel Xeon Phi coprocessors and especially Automatic Offload mode, when the computations are automatically offloaded to the coprocessors.

The mkl_mic_enable function enables Intel MKL to offload computations to Intel Xeon Phi coprocessors automatically, while the mkl_mic_disable function disables automatic offloading.

Important

Automatic Offload supports only OpenMP* threaded Intel MKL.

Optional work-division control functions enable you to specify the fractional amount of work to distribute between the host CPU and the coprocessors in the Automatic Offload mode. Work division is a fractional measure ranging from 0.0 to 1.0. For example, setting work division for the host CPU to 0.5 means to keep half of the computational work on the host CPU and move half to the coprocessor(s). Setting work division to 0.25 for a coprocessor means to offload a quarter of the computational work to this coprocessor while leaving the rest on the host CPU.

Other functions enable more control over computational resources of Intel Xeon Phi coprocessors.

Note

The support functions for Intel MIC Architecture take precedence over the respective environment variables.

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

For more complete information about compiler optimizations, see our Optimization Notice.