Mojo struct
TensorMapDataType
struct TensorMapDataType
Data type enumeration for TMA tensor map descriptors.
Specifies the element data type for TMA operations. The TMA hardware supports various numeric types including integers, floating-point, and specialized formats.
Implemented traits
AnyType,
Copyable,
ImplicitlyCopyable,
ImplicitlyDestructible,
Movable,
RegisterPassable,
TrivialRegisterPassable
comptime members
BFLOAT16
comptime BFLOAT16 = TensorMapDataType(SIMD(9))
Brain floating-point 16-bit format.
FLOAT16
comptime FLOAT16 = TensorMapDataType(SIMD(6))
IEEE 754 16-bit floating-point.
FLOAT32
comptime FLOAT32 = TensorMapDataType(SIMD(7))
IEEE 754 32-bit floating-point.
FLOAT32_FTZ
comptime FLOAT32_FTZ = TensorMapDataType(SIMD(10))
32-bit float with flush-to-zero for denormals.
FLOAT64
comptime FLOAT64 = TensorMapDataType(SIMD(8))
IEEE 754 64-bit floating-point.
INT32
comptime INT32 = TensorMapDataType(SIMD(3))
Signed 32-bit integer.
INT64
comptime INT64 = TensorMapDataType(SIMD(5))
Signed 64-bit integer.
TFLOAT32
comptime TFLOAT32 = TensorMapDataType(SIMD(11))
TensorFloat-32 format.
TFLOAT32_FTZ
comptime TFLOAT32_FTZ = TensorMapDataType(SIMD(12))
TensorFloat-32 with flush-to-zero for denormals.
UINT16
comptime UINT16 = TensorMapDataType(SIMD(1))
Unsigned 16-bit integer.
UINT32
comptime UINT32 = TensorMapDataType(SIMD(2))
Unsigned 32-bit integer.
UINT64
comptime UINT64 = TensorMapDataType(SIMD(4))
Unsigned 64-bit integer.
UINT8
comptime UINT8 = TensorMapDataType(SIMD(0))
Unsigned 8-bit integer.
Methods
from_dtype
static from_dtype[dtype: DType]() -> Self
Converts a Mojo DType to the corresponding TMA data type.
Constraints:
The dtype must be one of the supported types listed above.
Parameters:
- dtype (
DType): The Mojo data type to convert. Must be one ofDType.float32,DType.float16,DType.bfloat16,DType.uint8,DType.int64,DType.uint64,DType.float8_e4m3fn, orDType.float8_e8m0fnu.
Returns:
Self: The corresponding TensorMapDataType value.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!