frexpf

Applicability

Product	Supported
Atlas 350 Accelerator Card	√
Atlas A3 training product/Atlas A3 inference product	x
Atlas A2 training product/Atlas A2 inference product	x
Atlas 200I/500 A2 inference product	x
Atlas inference product AI Core	x
Atlas inference product Vector Core	x
Atlas training product	x

Function Usage

Converts x to a normalized signed number in the range [1/2, 1) multiplied by an integral power of 2. Returns a normalized signed number. The exponent is stored in exp.

$\text{[math]}$

Prototype

inline float frexpf(float x, int *exp)

Parameters

**Table 1** Parameters
Parameter	Input/Output	Description
x	Input	Source operand.
exp	Output	Unified Buffer, Global Memory, or stack address, which is used to store the exponent with base of 2.

Returns

Converts x to a normalized signed number in the range [1/2, 1) multiplied by an integral power of 2 and returns the signed number.

If x is inf, the return value is inf and exp is 0.
If x is -inf, the return value is inf and exp is 0.
If x is nan, the return value is nan and exp is 0.

Restrictions

For SIMT programming, this API is not supported.

Header File to Be Included

To use this API, the simt_api/math_functions.h header file must be included.

#include "simt_api/math_functions.h"

Examples

For SIMD and SIMT programming:

In SIMD and SIMT programming, the address space qualifier must be explicitly used to indicate the address space. __gm__ indicates the Global Memory memory space, and __ubuf__ indicates the Unified Buffer memory space. No address space qualifier is required for the stack space.

__simt_vf__ __launch_bounds__(1024) inline void KernelFrexp(__gm__ float* dst1, __gm__ int* dst2, __gm__ float* x)
{
    int idx = threadIdx.x + blockIdx.x * blockDim.x;
    dst1[idx] = frexpf(x[idx], dts2 + idx);
}

Parent topic: Mathematical Functions