FilesLast commitLast update
8 days ago
2 months ago
2 months ago
8 days ago
8 days ago
8 days ago
8 days ago
8 days ago
10 days ago
README

FresnelSin

English | 简体中文

Product Support Status

Product Supported
Ascend 950PR&950DT products √
Atlas A3 products √
Atlas A2 products √
Atlas 200I/500 A2 inference products ×
Atlas inference products √
Atlas training products √

Function Description

  • Operator function: computes the Fresnel sine integral S(x) = integral_0^x sin(pi*t^2/2) dt.

  • Computation formula:

S(x)=∫0xsin⁡(π2t2)dtS(x) = \int_{0}^{x} \sin\left(\frac{\pi}{2} t^{2}\right) \mathrm{d}t

Parameter Description

Parameter Name Input/Output/Attribute Description Data Type Data Format
x Input Input parameter for the Fresnel sine integral computation, which is x in the formula. BFLOAT16, FLOAT16, FLOAT ND
y Output Output parameter of the Fresnel sine integral computation, which is S(x) in the formula. BFLOAT16, FLOAT16, FLOAT ND

Constraint Description

  • The DOUBLE (FP64) data type is not supported.
  • The number of dimensions (rank) of x ranges from 0 to 8, and 0-dimensional scalar inputs are supported.
  • Empty tensors (0 elements) are supported as inputs: the Tiling on the host side short-circuits and returns directly, and the output is an empty tensor with the same shape (handled automatically).
  • Non-contiguous tensor inputs are supported (handled automatically on the host side).
  • Dynamic shape support: dynamic shapes and dynamic ranks are supported (-1 for an unknown dimension / -2 for an unknown rank).

Invocation Description

Invocation Method Invocation Sample Description
Graph-mode invocation test_geir_fresnel_sin Invokes the FresnelSin operator through the graph mode.