Need broadcast support for ttnn.div

[punithsekar]

Describe the bug
Need broadcast support for ttnn.div.

To Reproduce
Steps to reproduce the behavior:

1. Run the following code snippet

import torch 
import ttnn
import pytest

@pytest.mark.parametrize("device_params", [{"l1_small_size": 24576}], indirect=True)
def test_div(device):
    a=torch.randn(3,1)
    a_ttnn=ttnn.from_torch(a,layout=ttnn.TILE_LAYOUT,device=device)
    b=torch.randn(1,2)
    torch_output=a/b # output_shape = [3,2]
    b_ttnn=ttnn.from_torch(b,layout=ttnn.TILE_LAYOUT,device=device)
    ttnn_output=ttnn.div(a_ttnn,b_ttnn)

Expected behavior
To run without any error

Screenshots

   def __call__(self, *function_args, **function_kwargs):
>       return self.function(*function_args, **function_kwargs)
E       RuntimeError: TT_THROW @ ../ttnn/cpp/ttnn/operations/eltwise/binary/device/broadcast_height_multi_core_program_factory.cpp:25: tt::exception
E       info:
E       BinaryOpType cannot be mapped to BcastOpMath
E       backtrace:
E        --- /home/ubuntu/punith/tt-metal/ttnn/ttnn/_ttnn.so(+0x5d7a09) [0x7f5dc8676a09]
E        --- ttnn::operations::binary::BinaryDeviceOperation::BroadcastHeightMultiCore::create(ttnn::operations::binary::BinaryDeviceOperation::operation_attributes_t const&, ttnn::operations::binary::BinaryDeviceOperation::tensor_args_t const&, tt::tt_metal::Tensor&)

Please complete the following environment information:

• OS: Ubuntu 20.04
• Device: WH-n150

Additional context
Used in PETR model, in pos2posemb3d method.

[punithsekar]

fyi @saichandax