h2sqrt

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

Obtains the square root of each element in the input data x.

Prototype

1
inline half2 h2sqrt(half2 x)
1
inline bfloat16x2_t h2sqrt(bfloat16x2_t x)

Parameters

Table 1 Parameters

Parameter

Input/Output

Description

x

Input

Source operand, input data.

Returns

Square root of each element in the input data.

  • If the input element is 0, the return value is 0.
  • If the input element is inf, the return value is inf.
  • If the input element is -inf, the return value is nan.
  • If the input element is nan, the return value is nan.

Restrictions

Each element of the input data x supported by this API must be greater than or equal to 0. Otherwise, the return value is nan.

For SIMT programming, this API is not supported.

Header File to Be Included

To use the half2 API, the simt_api/asc_fp16.h header file must be included. To use the bfloat16x2_t API, the simt_api/asc_bf16.h header file must be included.

1
#include "simt_api/asc_fp16.h"
1
#include "simt_api/asc_bf16.h"

Examples

For SIMD and SIMT programming:
1
2
3
4
5
__simt_vf__ __launch_bounds__(1024) inline void KernelSqrt(__gm__ half2* dst, __gm__ half2* x)
{
    int idx = threadIdx.x + blockIdx.x * blockDim.x;
    dst[idx] = h2sqrt(x[idx]);
}