You copied the Doc URL to your clipboard.

ARM Compiler armlink User Guide : --fpu=name


Specifies the target FPU architecture.



Where name is the name of the target FPU architecture. Specify --fpu=list to list the supported FPU architecture names that you can use with --fpu=name.

The default floating-point architecture depends on the target architecture.


Software floating-point linkage is not supported for AArch64 state.


If you specify this option, it overrides any implicit FPU option that appears on the command line, for example, where you use the --cpu option.

The linker uses this option to optimize the choice of system libraries. The default is to select an FPU that is compatible with all of the component object files.


ARM® Compiler 6 does not support hardware floating-point linkage when using the armclang -mcmse option.

The linker fails if any of the component object files rely on features that are incompatible with the selected FPU architecture.


NEON support is disabled for SoftVFP.


The default target FPU architecture is derived from use of the --cpu option.

If the processor you specify with --cpu has a VFP coprocessor, the default target FPU architecture is the VFP architecture for that processor.

Related reference

Related information