5.4.1. Function Reference - 5.2 English - 68552

AOCL API Guide (68552)

Document ID
68552
Release Date
2025-12-29
Version
5.2 English
void aocl_gemm_gelu_tanh_f32(const md_t n, float *x, const md_t incx)#

Performs GELU activation (tanh approximation) on a float vector.

Parameters:
  • n[in] Number of elements in the vector.

  • x[inout] Pointer to the vector.

  • incx[in] Stride between consecutive elements in the vector. aocl_gemm_gelu_tanh_f32

void aocl_gemm_gelu_erf_f32(const md_t n, float *x, const md_t incx)#

Performs GELU activation (erf approximation) on a float vector.

Parameters:
  • n[in] Number of elements in the vector.

  • x[inout] Pointer to the vector.

  • incx[in] Stride between consecutive elements in the vector. aocl_gemm_gelu_erf_f32

void aocl_gemm_softmax_f32(const md_t n, float *x, const md_t incx)#

Performs softmax activation on a float vector.

Parameters:
  • n[in] Number of elements in the vector.

  • x[inout] Pointer to the vector.

  • incx[in] Stride between consecutive elements in the vector. aocl_gemm_softmax_f32

See Also