FilesLast commitLast update
2 months ago
3 months ago
16 days ago
7 days ago
3 months ago
16 days ago
7 days ago
1 month ago
14 days ago
README

AssignSub

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: completes the subtraction computation on the original tensor.

  • Computation formula:

outi=vari−valueiout_i = var_i - value_i

Parameter Description

Parameter Name Input/Output/Attribute Description Data Type Data Format
var Input The input tensor, which is var_i in the formula. BFLOAT16, FLOAT16, FLOAT, INT8, INT32, INT64, UINT8 ND
value Input The input tensor, which indicates the value to be subtracted from var_i and is out_i in the formula. BFLOAT16, FLOAT16, FLOAT, INT8, INT32, INT64, UINT8 ND
var Output The output tensor, which is out_i in the formula and shares the same address as var_i. BFLOAT16, FLOAT16, FLOAT, INT8, INT32, INT64, UINT8 ND
use_locking Attribute Optional. Specifies whether to use a lock to protect the update operation. bool ND

Constraint Description

None

Invocation Description

Invocation Method Invocation Sample Description
Graph-mode invocation test_geir_assign_sub.cpp Invokes the AssignSub operator by building a graph through the operator IR.