Enables or disables OpenMP* offloading compilation for the target pragmas. This option only applies to Intel® MIC Architecture. Option -qopenmp-offload is the replacement option for -openmp-offload, which is deprecated.
Syntax
Linux OS: | -qopenmp-offload -qno-openmp-offload |
OS X: | None |
Windows OS: | /Qopenmp-offload /Qopenmp-offload- |
Default
-qno-openmp-offload or /Qopenmp-offload- | OpenMP* offloading compilation is disabled. However, if option -qopenmp (Linux* and OS X*) or /Qopenmp (Windows*) is specified, the default is ON and OpenMP offloading compilation is enabled. |
Description
This option enables or disables OpenMP* offloading compilation for the target pragmas.
You can use this option if you want to enable or disable the offloading feature with no impact on other OpenMP features. In this case, no OpenMP runtime library is needed to link and the compiler does not need to generate OpenMP runtime initialization code.
If you specify this option with the -qopenmp (Linux* and OS X*) or /Qopenmp (Windows*) option, it can impact other OpenMP features.
Example
Consider the following:
-qno-openmp -qopenmp-offload ! Linux OS /Qopenmp- /Qopenmp-offload ! Windows OS
The above is equivalent to specifying only -qopenmp-offload (Linux* and OS X*) or /Qopenmp-offload (Windows*). In this case, only the offload library is linked, not the OpenMP* library, and only the !$OMP directives for TARGET are processed by no other !$OMP directives.
Consider the following:
-qopenmp -qopenmp-offload ! Linux OS /Qopenmp /Qopenmp-offload ! Windows OS
In this case, the offload library is linked, the OpenMP library is linked, and OpenMP runtime initialization code is generated.