__float_as_int

Applicability

Function Usage

Reinterprets the bits of a floating-point number as a signed integer, reading the stored bits in signed integer format.

Prototype

1

inline int __float_as_int(const float x)

Parameters

Returns

Signed integer reinterpreted from the bits in the input floating-point number. Special scenarios are described as follows:

• If x is nan, the return value is 2143289344.
• If x is inf, the return value is 2139095040.
• If x is -inf, the return value is -8388608.

Restrictions

For SIMT programming, this API is not supported.

Header Files to Be Included

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

1

#include "simt_api/device_functions.h"

Examples

1
2
3
4
5

__simt_vf__ __launch_bounds__(1024) inline void kernel__float_as_int(__gm__ int32_t* dst, __gm__ float* x)
{
    int idx = threadIdx.x + blockIdx.x * blockDim.x;
    dst[idx] = __float_as_int(x[idx]);
}