buildroot/arch/Config.in.arm

585 	  most projects. It supports both the 'soft' floating point
586 	  model (in which floating point instructions are emulated in
587 	  software) and the 'softfp' floating point model (in which
588 	  floating point instructions are executed using an hardware
589 	  floating point unit, but floating point arguments to
592 	  The 'softfp' floating point model is link-compatible with
593 	  the 'soft' floating point model, i.e you can link a library
596 	  However, passing the floating point arguments in integer
598 	  a floating point unit, and you don't have pre-compiled
600 	  better floating point performances.
602 	  If your processor does not have a floating point unit, then
610 	  floating point model. This model uses the floating point
611 	  unit to execute floating point instructions, and passes
612 	  floating point arguments in floating point registers.
614 	  It is more efficient than EABI for floating point related
616 	  that has been pre-built for the 'soft' or 'softfp' floating
619 	  If your processor has a floating point unit, and you don't
643 	  This option allows to use software emulated floating
651 	  This option allows to use GCC's default floating point unit.
657 	  This option allows to use the VFPv2 floating point unit, as
670 	  This option allows to use the VFPv3 floating point unit, as
686 	  This option allows to use the VFPv3 floating point unit, as
701 	  This option allows to use the VFPv4 floating point unit, as
716 	  This option allows to use the VFPv4 floating point unit, as
732 	  in some ARMv7 processors, as a floating-point unit. It
733 	  should however be noted that using NEON for floating point
743 	  units for floating point operations. Note that some ARMv7
753 	  floating point unit, as available in some ARMv7m processors
762 	  floating point unit, as available in some ARMv7m processors
774 	  floating point unit, as available in some ARMv7m processors
784 	  This option allows to use the ARMv8 floating point unit.
791 	  This option allows to use both the ARMv8 floating point unit
792 	  and the NEON SIMD unit for floating point operations.