# Copyright (c) 2022 Graphcore Ltd. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import torch
import torch.nn as nn
from core.utils import Precision


class ERF_GELU(nn.Module):
    def __init__(self, precision=Precision.FP32):
        super().__init__()
        self.precision = precision

    def forward(self, x):
        if self.precision is Precision.FP32 or self.precision is Precision.FP16:
            cdf = 0.5 * (1.0 + torch.erf(x / (2.0**0.5)))
            return x * cdf
        else:
            x_float = torch.ops.poptorch.internal_cast(x, "FLOAT")
            cdf = 0.5 * (1.0 + torch.erf(x_float / (2.0**0.5)))
            out = x_float * cdf
            out = torch.ops.poptorch.internal_cast(out, "FLOAT16")
            return out