You copied the Doc URL to your clipboard.

Floating-point linkage and computational requirements of compiler options

There are various valid combinations of FPU options and processors.

The following table sets out the FPU options, and their capabilities and requirements.

Table 5-14 FPU-option capabilities and requirements

FPU `name`	Hardware FP linkage	d0-d15 registers	d16-d31 registers	VFP instructions	Half precision	Single precision	Double precision
`softvfp`	No	No	No	No	No	No	No
`softvfp+vfpv2`	No	Yes	No	Yes	No	Yes	Yes
`softvfp+vfpv3`	No	Yes	Yes	Yes	No	Yes	Yes
`softvfp+vfpv3_fp16`	No	Yes	Yes	Yes	Yes	Yes	Yes
`softvfp+vfpv3_d16`	No	Yes	No	Yes	No	Yes	Yes
`softvfp+vfpv3_d16_fp16`	No	Yes	No	Yes	Yes	Yes	Yes
`softvfp+vfpv3_sp_d16`	No	Yes	No	Yes	Yes	Yes	No
`softvfp+vfpv4`	No	Yes	Yes	Yes	Yes	Yes	Yes
`softvfp+vfpv4_d16`	No	Yes	No	Yes	Yes	Yes	Yes
`softvfp+vfpv4_sp_d16`	No	Yes	No	Yes	Yes	Yes	No
`softvfp+fpv4-sp`	No	Yes	No	Yes	Yes	Yes	No
`vfp`	Yes	Yes	No	Yes	No	Yes	Yes
`vfpv2`	Yes	Yes	No	Yes	No	Yes	Yes
`vfpv3`	Yes	Yes	Yes	Yes	No	Yes	Yes
`vfpv3_fp16`	Yes	Yes	Yes	Yes	Yes	Yes	Yes
`vfpv3_d16`	Yes	Yes	No	Yes	No	Yes	Yes
`vfpv3_d16_fp16`	Yes	Yes	No	Yes	Yes	Yes	Yes
`vfpv3_sp_d16`	Yes	Yes	No	Yes	Yes	Yes	No
`vfpv4`	Yes	Yes	Yes	Yes	Yes	Yes	Yes
`vfpv4_d16`	Yes	Yes	No	Yes	Yes	Yes	Yes
`vfpv4_sp_d16`	Yes	Yes	No	Yes	Yes	Yes	No
`fpv4-sp`	Yes	Yes	No	Yes	Yes	Yes	No