Runtime Exception when relu is followed by a clip

@hariharans29
Describe the bug
Similar to #9753, on opset version 14, when relu is followed by a clip clip(relu(i1),-1,1), and input i1 is torch.float64 data type, ORT raises a RuntimeException Error.

Urgency
None.

System information

• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): macOS Mojave
• ONNX Runtime installed from (source or binary): Binary
• ONNX Runtime version: 1.10.0
• Python version: 3.9.7
• Visual Studio version (if applicable): n/a
• GCC/Compiler version (if compiling from source): n/a
• CUDA/cuDNN version: n/a
• GPU model and memory: n/a
• PyTorch version: 1.10.2

To Reproduce

• Describe steps/code to reproduce the behavior.

import torch
import onnx.checker
import onnxruntime as ort
class Model(torch.nn.Module):
    @torch.no_grad()
    def forward(self, i1):
        x=torch.relu(i1)
        o0=torch.clip(x,-1,1)
        return o0


model = Model()
inputs = (torch.randn((2, 2, 2, 1, 2),dtype=torch.float64),)
output_names = ["o0"]
torch.onnx.export(model, inputs, "1.onnx", verbose=False,
                  input_names=["i1"], output_names=output_names, opset_version=14)

onnx_model = onnx.load("1.onnx")
onnx.checker.check_model(onnx_model,full_check=True)
sess = ort.InferenceSession(
     onnx._serialize(onnx_model))
res = sess.run(output_names, {"input": inputs[0].numpy()})

• Attach the ONNX model to the issue (where applicable) to expedite investigation.
  1.onnx.zip

Expected behavior
Not crash.

Screenshots

• Error message