FCVTH

Operation

Converts between H and signed B/W/L/Q integer or S/D floating-point representations.

Assembler Syntax

FCVTH.{S|D}(z) Fn(s), Fn(d)

FCVTH.{B|W|L|Q}(z) Fn(s), Rn(d)

FCVTH.{B|W|L|Q}(z) Rn(s), Fn(d)

FCVTH.{B|W|L|Q}(z) <ea>(e), Fn(d)

FCVTH.{B|W|L|Q}(z) Fn(s), <ea>(e)

FCVTH.{S|D}(z) <ea>(e), Fn(d)

FCVTH.{S|D}(z) Fn(s), <ea>(e)

Privilege

Unprivileged

Required CPUID flags

FP

FP16_CONVERT

Repeat eligibility

REP eligible

Converts between the H conversion format in an Fn operand and the representation selected by the suffix. The integer suffixes are signed B/W/L/Q; .S and .D select binary32 and binary64. For Fn-to-Fn conversion, the source has the suffix format and the destination has H format. With one Fn and one Rn or memory operand, the Fn has H format and the other operand has the suffix representation. Floating-format EA sources are memory-only. H is a conversion and storage format; this instruction does not add scalar H arithmetic.

2.75in

Encodings

FCVTH.{S|D}(z) Fn(s), Fn(d)

Format: Instruction format for FCVTH.{S|D}(z) Fn(s), Fn(d)

2.75in FCVTH.{B|W|L|Q}(z) Fn(s), Rn(d)

Format: Instruction format for FCVTH.{B|W|L|Q}(z) Fn(s), Rn(d)

2.75in FCVTH.{B|W|L|Q}(z) Rn(s), Fn(d)

Format: Instruction format for FCVTH.{B|W|L|Q}(z) Rn(s), Fn(d)

2.75in FCVTH.{B|W|L|Q}(z) <ea>(e), Fn(d)

Format: Instruction format for FCVTH.{B|W|L|Q}(z) <ea>(e), Fn(d)

2.75in FCVTH.{B|W|L|Q}(z) Fn(s), <ea>(e)

Format: Instruction format for FCVTH.{B|W|L|Q}(z) Fn(s), <ea>(e)

dst — excluded: immediate [invalid_destination]

2.75in FCVTH.{S|D}(z) <ea>(e), Fn(d)

Format: Instruction format for FCVTH.{S|D}(z) <ea>(e), Fn(d)

src — excluded: immediate [invalid_source]

2.75in FCVTH.{S|D}(z) Fn(s), <ea>(e)

Format: Instruction format for FCVTH.{S|D}(z) Fn(s), <ea>(e)

dst — excluded: immediate [invalid_destination]