For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Mojo struct

AMDScheduleBarrierMask

struct AMDScheduleBarrierMask

Represents different instruction scheduling masks for AMDGPU scheduling instructions.

These masks control which types of instructions can be reordered across a barrier for performance optimization. When used with schedule_barrier(), the mask determines which instructions the compiler is allowed to move across the barrier point.

Implemented traits

AnyType, Copyable, Deinitable, Equatable, ImplicitlyCopyable, Intable, Movable, RegisterPassable, TrivialRegisterPassable, Writable

comptime members

ALL_ALU

comptime ALL_ALU = AMDScheduleBarrierMask(Int(1))

Allows reordering of all arithmetic and logic instructions that don't involve memory operations.

ALL_DS

comptime ALL_DS = AMDScheduleBarrierMask(Int(128))

Permits reordering of all Local Data Share (LDS) operations.

ALL_VMEM

comptime ALL_VMEM = AMDScheduleBarrierMask(Int(16))

Enables reordering of all vector memory operations (reads and writes).

DS_READ

comptime DS_READ = AMDScheduleBarrierMask(Int(256))

Enables reordering of LDS read operations only.

DS_WRITE

comptime DS_WRITE = AMDScheduleBarrierMask(Int(512))

Enables reordering of LDS write operations only.

MFMA

comptime MFMA = AMDScheduleBarrierMask(Int(8))

Allows reordering of matrix multiplication and WMMA instructions.

NONE

comptime NONE = AMDScheduleBarrierMask(Int(0))

No instructions can cross the barrier. Most restrictive option.

SALU

comptime SALU = AMDScheduleBarrierMask(Int(4))

Permits reordering of scalar arithmetic/logic unit instructions only.

TRANS

comptime TRANS = AMDScheduleBarrierMask(Int(1024))

Allows reordering of transcendental instructions (sin, cos, exp, etc).

VALU

comptime VALU = AMDScheduleBarrierMask(Int(2))

Permits reordering of vector arithmetic/logic unit instructions only.

VMEM_READ

comptime VMEM_READ = AMDScheduleBarrierMask(Int(32))

Allows reordering of vector memory read operations only.

VMEM_WRITE

comptime VMEM_WRITE = AMDScheduleBarrierMask(Int(64))

Allows reordering of vector memory write operations only.

Methods

__init__

def __init__(value: Int) -> Self

Initializes an AMDScheduleBarrierMask from an integer value.

This implicit constructor allows creating a barrier mask directly from an integer, which is useful for combining multiple mask flags using bitwise operations.

Args:

• ​value (Int): The integer value to use for the barrier mask.

__eq__

def __eq__(self, other: Self) -> Bool

Compares two AMDScheduleBarrierMask instances for equality.

Args:

• ​other (Self): The other AMDScheduleBarrierMask to compare with.

Returns:

Bool: True if the masks have the same value, False otherwise.

write_to

def write_to(self, mut writer: T)

Writes a string representation of the AMDScheduleBarrierMask.

Converts the mask to a human-readable string based on its value.

Args:

• ​writer (T): The object to write to.

__int__

def __int__(self) -> Int

Converts the AMDScheduleBarrierMask to an integer.

Returns:

Int: The integer value of the mask, which can be used with low-level APIs.