Crate rten_vecmath

SIMD-vectorized implementations of various math functions that are commonly used in neural networks.

For each function in this library there are multiple variants, which typically include:

• A version that operates on scalars
• A version that reads values from an input slice and writes to the corresponding position in an equal-length output slice. These have a vec_ prefix.
• A version that reads values from a mutable input slice and writes the computed values back in-place. These have a vec_ prefix and _in_place suffix.

All variants use the same underlying implementation and should have the same accuracy.

See the source code for comments on accuracy.

Functions

• erf
  Computes the error function.
• exp
  Computes e^val. Functionally equivalent to f32::exp.
• gelu
  Computes the GELU function. See vec_gelu.
• sigmoid
  Computes the sigmoid function, aka. the standard logistic function, 1. / (1. + (-x).exp()).
• silu
  Sigmoid Linear Unit (SiLU) function. This computes x * sigmoid(x).
• tanh
• vec_erf
  Vectorized error function.
• vec_erf_in_place
  Variant of vec_erf that modifies elements in-place.
• vec_exp
  Vectorized exponential function.
• vec_exp_in_place
  Variant of vec_exp that modifies elements in-place.
• vec_gelu
  Vectorized GELU function.
• vec_gelu_in_place
  Variant of vec_gelu that modifies elements in-place.
• vec_sigmoid
  Vectorized sigmoid function.
• vec_sigmoid_in_place
  Variant of vec_sigmoid that modifies elements in-place.
• vec_silu
  Vectorized Sigmoid Linear Unit (SiLU) function.
• vec_silu_in_place
  Vectorized Sigmoid Linear Unit (SiLU) function.
• vec_softmax
  Computes the softmax function over a slice of floats.
• vec_softmax_in_place
  Computes the softmax function over a slice of floats.
• vec_tanh
  Vectorized tanh implementation.
• vec_tanh_in_place