__floats2half2_rn

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 the input data x and y to the half type in line with the CAST_RINT mode, fills both the front and back parts of half2, and returns the converted half2 data.

Prototype

inline half2 __floats2half2_rn(const float x, const float y)

Parameters

**Table 1** Parameters
Parameter	Input/Output	Description
x	Input	Source operand.
y	Input	Source operand.

Returns

Result of converting the input float data to the half type in line with the CAST_RINT mode and filling both the front and back parts of half2

Restrictions

For SIMT programming, this API is not supported.

Header Files to Be Included

To use this API, the simt_api/asc_fp16.h header file must be included.

#include "simt_api/asc_fp16.h"

Examples

For SIMD and SIMT programming:

// Use small vectors to improve data movement efficiency.
__simt_vf__ __launch_bounds__(1024) inline void simt_floats2half2_rn(__gm__ float* input1, __gm__ float* input2, __gm__ half2* output, uint32_t input_total_length)
{
    uint32_t idx = blockIdx.x * blockDim.x + threadIdx.x;
    if (idx > input_total_length) {
        return;
    }
    output[idx] = __floats2half2_rn(input1[idx], input2[idx]);
}
__global__ __vector__ void cast_kernel(__gm__ float* input1,  __gm__ float* input2, __gm__ half* output, uint32_t input_total_length)
{
    asc_vf_call<simt_floats2half2_rn>(dim3(1024), input1, input2, (__gm__ half2*)output, input_total_length);
}

Parent topic: Type Conversion