SimThreadExponential

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: generates random numbers that follow the exponential distribution with the parameter lambda and fills them into the self tensor.

• Computation formula:

  $$f(x)=-\frac{1}{\lambda }\ln (1-u),u\sim \text{Uniform}(0,1]$$

Parameter Description

Parameter Name	Input/Output/Attribute	Description	Data Type	Data Format
self	Input/Output	Input and output tensor.	FLOAT16, BFLOAT16, FLOAT32	ND
count	Attribute	Number of generated random number elements.	INT64	ND
lambda	Attribute	lambda in the formula.	DOUBLE	-
seed	Attribute	Random number seed.	INT64	-
offset	Attribute	Random number offset value.	INT64	-

Constraint Description

• lambda must be greater than 0
• offset must be a multiple of 4 (Ascend 950)
• count must be equal to the total number of elements in the self tensor (Ascend 950)
• Only the ND format is supported

Invocation Description

Invocation Method	Sample Code	Description
aclnn invocation	test_sim_thread_exponential	Invokes the SimThreadExponential operator through the aclnnSimThreadExponential API.