Rate This Document
Findability
Accuracy
Completeness
Readability

svml128_exp2_f?

Compute the exponent value of the input vector with base 2.

Interface Definition

C interface:

float32x4_t svml128_exp2_f32(float32x4_t src);

float64x2_t svml128_exp2_f64(float64x2_t src);

Parameters

Parameter

Type

Description

Input/Output

src

  • For svml128_exp2_f32, src is of single-precision floating-point type.
  • For svml128_exp2_f64, src is of double-precision floating-point type.

Floating-point value of the input vector.

Input

Return Value

  • The base-2 exponential y of x is returned. y ∈ (0, +INF)
  • If the input is +0, the return value is +1.
  • If the input is -0, the return value is -1.
  • If input of expf is greater than 128, the return value is +∞. If the input of exp is greater than 1024, the return value is +∞.
  • If the input of expf is less than -150, the return value is +0. If the input of exp is less than -1075, the return value is +0.
  • If the input is +∞, the return value is +∞.
  • If the input is -∞, the return value is +0.
  • If the input is NaN, the return value is NaN.

Dependency

C: "ksvml.h"

Example

C interface:

    float32x4_t src = {0.0f, 2.0f, INFINITY, NAN};
    float32x4_t dst = svml128_exp2_f32(src);
    printf("%.15g  %.15g  %.15g  %.15g\n", dst[0], dst[1], dst[2], dst[3]); 
    /**
     *  Output dst:
     *     1  4  inf  -nan
     *
     */