.. _op_ai_onnx_Mul-7:

Mul - version 7
===============

This page documents version **7** of operator **Mul**. See :doc:`Mul` for the latest version (since version 14).

- **Domain**: ``ai.onnx``
- **Since version**: 7

Performs element-wise binary multiplication (with Numpy-style broadcasting support).

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

**Inputs**

- **A** (*T*): First operand.
- **B** (*T*): Second operand.

**Outputs**

- **C** (*T*): Result, has same element type as two inputs

**Type Constraints**

- **T**: Constrain input and output types to high-precision numeric tensors.
  Allowed types: tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64).

Differences with previous version (6)
-------------------------------------

**SchemaDiff**: ``Mul`` (domain ``'ai.onnx'``)

* old version: 6
* new version: 7
* breaking: no

**Documentation:**

* line similarity: 0.09 (+3/-18 lines)

.. code-block:: diff

    --- Mul v6
    +++ Mul v7
    @@ -1,19 +1,4 @@
    -Performs element-wise binary multiplication (with limited broadcast support).
    -If necessary the right-hand-side argument will be broadcasted to match the
    -shape of left-hand-side argument. When broadcasting is specified, the second
    -tensor can either be of element size 1 (including a scalar tensor and any
    -tensor with rank equal to or smaller than the first tensor), or having its
    -shape as a contiguous subset of the first tensor's shape. The starting of the
    -mutually equal shape is specified by the argument "axis", and if it is not set,
    -suffix matching is assumed. 1-dim expansion doesn't work yet.
    +Performs element-wise binary multiplication (with Numpy-style broadcasting support).
     
    -For example, the following tensor shapes are supported (with broadcast=1):
    -
    -  shape(A) = (2, 3, 4, 5), shape(B) = (,), i.e. B is a scalar tensor
    -  shape(A) = (2, 3, 4, 5), shape(B) = (1, 1), i.e. B is an 1-element tensor
    -  shape(A) = (2, 3, 4, 5), shape(B) = (5,)
    -  shape(A) = (2, 3, 4, 5), shape(B) = (4, 5)
    -  shape(A) = (2, 3, 4, 5), shape(B) = (3, 4), with axis=1
    -  shape(A) = (2, 3, 4, 5), shape(B) = (2), with axis=0
    -
    -Attribute `broadcast=1` needs to be passed to enable broadcasting.
    +This operator supports multidirectional (i.e., Numpy-style) broadcasting;
    +for more details please check the broadcasting behavior in ONNX.