Help Center/ Atlas 300 Application (Model 3000)/ TE API Reference/ Compute APIs/ te.lang.cce.vsub(lhs, rhs)
Updated on 2022-03-13 GMT+08:00
View PDF
Share

te.lang.cce.vsub(lhs, rhs)

Subtracts one tensor from the other tensor by element. The data types of the elements must be the same. The supported types are float16, float32, and int32. The data types int8 and uint8 are converted to float16.

This API is defined in elewise_compute.py.

Parameter Description

  • lhs: left tensor, tvm.tensor type
  • rhs: right tensor, tvm.tensor type

Return Value

res_tensor: lhs – rhs, tvm.tensor type

Calling Example

shape = (1024,1024)
input_dtype = "float16"
data1 = tvm.placeholder(shape, name="data1", dtype=input_dtype)
data2 = tvm.placeholder(shape, name="data2", dtype=input_dtype)
res = te.lang.cce.vsub(data1, data2)
Parent topic: Compute APIs