BitwiseAnd¶

BitwiseAnd - 18¶

Version¶

name: BitwiseAnd (GitHub)
domain: main
since_version: 18
function: False
support_level: SupportType.COMMON
shape inference: True

This version of the operator has been available since version 18.

Summary¶

Returns the tensor resulting from performing the bitwise and operation elementwise on the input tensors A and B (with Numpy-style broadcasting support).

This operator supports multidirectional (i.e., Numpy-style) broadcasting; for more details please check Broadcasting in ONNX.

Inputs¶

A (heterogeneous) - T:

First input operand for the bitwise operator.
B (heterogeneous) - T:

Second input operand for the bitwise operator.

Outputs¶

C (heterogeneous) - T:

Result tensor.

Type Constraints¶

T in ( tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8) ):

Constrain input to integer tensors.

Examples¶

default¶

import numpy as np
import onnx

node = onnx.helper.make_node(
    "BitwiseAnd",
    inputs=["x", "y"],
    outputs=["bitwiseand"],
)

# 2d
x = create_random_int((3, 4), np.int32)
y = create_random_int((3, 4), np.int32)
z = np.bitwise_and(x, y)
expect(node, inputs=[x, y], outputs=[z], name="test_bitwise_and_i32_2d")

# 3d
x = create_random_int((3, 4, 5), np.int16)
y = create_random_int((3, 4, 5), np.int16)
z = np.bitwise_and(x, y)
expect(node, inputs=[x, y], outputs=[z], name="test_bitwise_and_i16_3d")

_bitwiseand_broadcast¶

import numpy as np
import onnx

node = onnx.helper.make_node(
    "BitwiseAnd",
    inputs=["x", "y"],
    outputs=["bitwiseand"],
)

# 3d vs 1d
x = create_random_int((3, 4, 5), np.uint64)
y = create_random_int((5,), np.uint64)
z = np.bitwise_and(x, y)
expect(
    node, inputs=[x, y], outputs=[z], name="test_bitwise_and_ui64_bcast_3v1d"
)

# 4d vs 3d
x = create_random_int((3, 4, 5, 6), np.uint8)
y = create_random_int((4, 5, 6), np.uint8)
z = np.bitwise_and(x, y)
expect(node, inputs=[x, y], outputs=[z], name="test_bitwise_and_ui8_bcast_4v3d")