Load values to VFP and NEON registers
There are different ways to load immediate values into NEON and VFP registers.
In NEON technology and in VFPv3 and later, the VMOV and VMVN instructions load a limited range of floating-point immediate values.
The NEON VMOV and VMVN instructions can also load integer immediates.
You can load any 64-bit integer, single-precision, or double-precision floating-point value from a literal pool, in a single instruction, using the VLDR pseudo-instruction.