5.5.2. NEON and VFP data types

Data type specifiers in NEON and VFP instructions consist of a letter indicating the type of data, usually followed by a number indicating the width. They are separated from the instruction mnemonic by a point. Table 5.5 shows the data types available in NEON instructions. Table 5.6 shows the data types available in VFP instructions.

Table 5.5. NEON data types

 8-bit16-bit32-bit64-bit
Unsigned integerU8U16U32U64
Signed integerS8S16S32S64
Integer of unspecified typeI8I16I32I64
Floating-point numbernot availableF16F32 (or F)not available
Polynomial over {0,1}P8P16not availablenot available

Table 5.6.  VFP data types

 16-bit32-bit64-bit
Unsigned integerU16U32not available
Signed integerS16S32not available
Floating-point numberF16F32 (or F)F64 (or D)

See Polynomial arithmetic over {0,1} for further information about operations on polynomials over {0,1}.

The datatype of the second (or only) operand is specified in the instruction.

Note

  • Most instructions have a restricted range of permitted data types. See the instruction pages for details. However, the data type description is flexible:

    • If the description specifies I, you can also use S or U data types

    • If only the data size is specified, you can specify a type (I, S, U, P or F)

    • If no data type is specified, you can specify a data type.

  • The F16 data type is only available on systems that implement the half-precision architecture extension.

Copyright © 2002-2010 ARM. All rights reserved.ARM DUI 0204J
Non-ConfidentialID101213