AMDGPU Instructions Notation

Introduction

This is an overview of notation used to describe syntax of AMDGPU assembler instructions.

This notation mimics the syntax of assembler instructions except that instead of real operands and modifiers it provides references to their description.

Instructions

Notation

This is the notation used to describe AMDGPU instructions:

Operands

An instruction may have zero or more operands. They are comma-separated in the description:

The order of operands is fixed. Operands cannot be omitted except for special cases described below.

Notation

An operand is described using the following notation:

<name><tag0><tag1>…

Where:

  • name is a link to a description of the operand.
  • tags are optional. They are used to indicate special operand properties:
Operand tag Meaning
:opt An optional operand.
:m An operand which may be used with VOP3 operand modifiers or SDWA operand modifiers.
:dst An input operand which may also serve as a destination if glc modifier is specified.
:fx This is an f32 or f16 operand depending on m_op_sel_hi modifier.
:<type> Operand type differs from type implied by the opcode name. This tag specifies actual operand type.

Examples:

src1:m             // src1 operand may be used with operand modifiers
vdata:dst          // vdata operand may be used as both source and destination
vdst:u32           // vdst operand has u32 type

Modifiers

An instruction may have zero or more optional modifiers. They are space-separated in the description:

The order of modifiers is fixed.

Notation

A modifier is described using the following notation:

<name>

Where name is a link to a description of the modifier.