[Bug Report] invalid erfc result

[hschoi4448]

Describe the bug
A clear and concise description of what the bug is.

To Reproduce
Steps to reproduce the behavior:
1.Copy and past below code

# SPDX-FileCopyrightText: © 2023 Tenstorrent Inc.

# SPDX-License-Identifier: Apache-2.0

import torch
import pytest
import tt_lib
from tests.tt_eager.python_api_testing.unit_testing.backward_ops.utility_funcs import data_gen_pt_tt, compare_results

import ttnn
from tests.tt_eager.python_api_testing.sweep_tests import (
    pytorch_ops,
    tt_lib_ops
)
from tests.ttnn.python_api_testing.sweep_tests import ttnn_ops

def data_gen_pt_tt(input_shapes, device, required_grad=False, val=1):
    pt_tensor = (torch.ones(input_shapes, requires_grad=required_grad) * val).bfloat16()
    tt_tensor = (
        tt_lib.tensor.Tensor(pt_tensor, tt_lib.tensor.DataType.BFLOAT16).to(tt_lib.tensor.Layout.TILE).to(device)
    )
    return pt_tensor, tt_tensor

@pytest.mark.parametrize(
    "input_shapes",
    (
        (torch.Size([1, 1, 32, 32])),
    ),
)
def test1(input_shapes, device):
    val = float('-1')
    in_data, input_tensor = data_gen_pt_tt(input_shapes, device, True, val=val)
    
    print("input_tensor", input_tensor)
    
    golden_tensor = pytorch_ops.erfc(in_data)
    tt_output_tensor_on_device = tt_lib.tensor.erfc(input_tensor)
    
    print("tt_output_tensor_on_device", tt_output_tensor_on_device)
    print("golden_tensor", golden_tensor)
    

2. Run with pytest

input_tensor ttnn.Tensor([[[[-1.00000, -1.00000,  ..., -1.00000, -1.00000],
               [-1.00000, -1.00000,  ..., -1.00000, -1.00000],
               ...,
               [-1.00000, -1.00000,  ..., -1.00000, -1.00000],
               [-1.00000, -1.00000,  ..., -1.00000, -1.00000]]]], shape=Shape([1, 1, 32, 32]), dtype=DataType::BFLOAT16, layout=Layout::TILE)
tt_output_tensor_on_device ttnn.Tensor([[[[ 1.00000,  1.00000,  ...,  1.00000,  1.00000],
               [ 1.00000,  1.00000,  ...,  1.00000,  1.00000],
               ...,
               [ 1.00000,  1.00000,  ...,  1.00000,  1.00000],
               [ 1.00000,  1.00000,  ...,  1.00000,  1.00000]]]], shape=Shape([1, 1, 32, 32]), dtype=DataType::BFLOAT16, layout=Layout::TILE)
golden_tensor tensor([[[[1.8438, 1.8438, 1.8438,  ..., 1.8438, 1.8438, 1.8438],
          [1.8438, 1.8438, 1.8438,  ..., 1.8438, 1.8438, 1.8438],
          [1.8438, 1.8438, 1.8438,  ..., 1.8438, 1.8438, 1.8438],
          ...,
          [1.8438, 1.8438, 1.8438,  ..., 1.8438, 1.8438, 1.8438],
          [1.8438, 1.8438, 1.8438,  ..., 1.8438, 1.8438, 1.8438],
          [1.8438, 1.8438, 1.8438,  ..., 1.8438, 1.8438, 1.8438]]]],
       dtype=torch.bfloat16, grad_fn=<ErfcBackward0>)

Expected behavior
A clear and concise description of what you expected to happen.

Screenshots
If applicable, add screenshots to help explain your problem.

Please complete the following environment information:

• OS: [e.g. Ubuntu 20.04]
• Version of software (eg. commit 729e6c6)
• Device: wormhole_b0

Additional context
Add any other context about the problem here.

[VirdhatchaniKN]

Hi @hschoi4448 , @eyonland , @jliangTT , @tt-aho , @rtawfik01
Fix provided for forward erfc op - PR Link
All post-commit tests - Link - PASSED

[hschoi4448]

input_tensor ttnn.Tensor([[[[-1.00000, -1.00000,  ..., -1.00000, -1.00000],
               [-1.00000, -1.00000,  ..., -1.00000, -1.00000],
               ...,
               [-1.00000, -1.00000,  ..., -1.00000, -1.00000],
               [-1.00000, -1.00000,  ..., -1.00000, -1.00000]]]], shape=Shape([1, 1, 32, 32]), dtype=DataType::BFLOAT16, layout=Layout::TILE)
tt_output_tensor_on_device ttnn.Tensor([[[[ 1.00000,  1.00000,  ...,  1.00000,  1.00000],
               [ 1.00000,  1.00000,  ...,  1.00000,  1.00000],
               ...,
               [ 1.00000,  1.00000,  ...,  1.00000,  1.00000],
               [ 1.00000,  1.00000,  ...,  1.00000,  1.00000]]]], shape=Shape([1, 1, 32, 32]), dtype=DataType::BFLOAT16, layout=Layout::TILE)
golden_tensor tensor([[[[1.8438, 1.8438, 1.8438,  ..., 1.8438, 1.8438, 1.8438],
          [1.8438, 1.8438, 1.8438,  ..., 1.8438, 1.8438, 1.8438],
          [1.8438, 1.8438, 1.8438,  ..., 1.8438, 1.8438, 1.8438],
          ...,
          [1.8438, 1.8438, 1.8438,  ..., 1.8438, 1.8438, 1.8438],
          [1.8438, 1.8438, 1.8438,  ..., 1.8438, 1.8438, 1.8438],
          [1.8438, 1.8438, 1.8438,  ..., 1.8438, 1.8438, 1.8438]]]],
       dtype=torch.bfloat16, grad_fn=<ErfcBackward0>)

Still has a problem. Please check again.

hash: a059360
arc: wormhole_b0

[umadevimcw]

@hschoi4448 PR is not yet merged

[VirdhatchaniKN]

Hi @hschoi4448 , @jliangTT
Fix merged : Link