Skip to main content

/

Docs

Nightly

v24.6

Log in

Mojo module

simd

Implements SIMD struct.

These are Mojo built-ins, so you don't need to import them.

Aliases​

  • ​BFloat16 = SIMD[bfloat16, 1]: Represents a 16-bit brain floating point value.
  • ​Byte = SIMD[uint8, 1]: Represents a byte (backed by an 8-bit unsigned integer).
  • ​Float16 = SIMD[float16, 1]: Represents a 16-bit floating point value.
  • ​Float32 = SIMD[float32, 1]: Represents a 32-bit floating point value.
  • ​Float64 = SIMD[float64, 1]: Represents a 64-bit floating point value.
  • ​Float8e4m3 = SIMD[float8e4m3, 1]: Represents a FP8E4M3 floating point format from the OFP8 standard.
  • ​Float8e4m3fnuz = SIMD[float8e4m3fnuz, 1]: Represents a FP8E4M3FNUZ floating point format.
  • ​Float8e5m2 = SIMD[float8e5m2, 1]: Represents a FP8E5M2 floating point format from the OFP8 standard.
  • ​Float8e5m2fnuz = SIMD[float8e5m2fnuz, 1]: Represents a FP8E5M2FNUZ floating point format.
  • ​Int16 = SIMD[int16, 1]: Represents a 16-bit signed scalar integer.
  • ​Int32 = SIMD[int32, 1]: Represents a 32-bit signed scalar integer.
  • ​Int64 = SIMD[int64, 1]: Represents a 64-bit signed scalar integer.
  • ​Int8 = SIMD[int8, 1]: Represents an 8-bit signed scalar integer.
  • ​Scalar = SIMD[?, 1]: Represents a scalar dtype.
  • ​UInt16 = SIMD[uint16, 1]: Represents a 16-bit unsigned scalar integer.
  • ​UInt32 = SIMD[uint32, 1]: Represents a 32-bit unsigned scalar integer.
  • ​UInt64 = SIMD[uint64, 1]: Represents a 64-bit unsigned scalar integer.
  • ​UInt8 = SIMD[uint8, 1]: Represents an 8-bit unsigned scalar integer.

Structs​

  • ​SIMD: Represents a small vector that is backed by a hardware vector element.