torch device on cpu0 or cpu1 or mps0

I cannot find the bug ... but run this code (python) on torch device mps0 is slow quicker and cpu0 or cpu1 ... but where is the bug? or run it on neural engine with cpu1?

you need a setup like this:

#!/bin/bash
export HOMEBREW_BREW_GIT_REMOTE="https://github.com/Homebrew/brew"  # put your Git mirror of Homebrew/brew here
export HOMEBREW_CORE_GIT_REMOTE="https://github.com/Homebrew/homebrew-core"  # put your Git mirror of Homebrew/homebrew-core here
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install.sh)"
eval "$(/opt/homebrew/bin/brew shellenv)"
brew update --force --quiet
chmod -R go-w "$(brew --prefix)/share/zsh"
export OPENBLAS=$(/opt/homebrew/bin/brew --prefix openblas)
export CFLAGS="-falign-functions=8 ${CFLAGS}"

brew install wget
brew install unzip

conda init --all
conda create -n torch-gpu python=3.10
conda activate torch-gpu
conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 -c pytorch
conda install -c conda-forge jupyter jupyterlab
python3 -m pip install --upgrade pip
python3 -m pip install insightface==0.2.1 onnx imageio scikit-learn scikit-image moviepy
python3 -m pip install googledrivedownloader
python3 -m pip install imageio==2.4.1
python3 -m pip install Cython
python3 -m pip install --no-use-pep517 numpy
python3 -m pip install torch
python3 -m pip install image
python3 -m pip install timm
python3 -m pip install PlL
python3 -m pip install h5py

for i in `seq 1 6`; do
python3 test.py
done

conda deactivate

exit 0

test.py:

import torch
import math
# this ensures that the current MacOS version is at least 12.3+
print(torch.backends.mps.is_available())
# this ensures that the current current PyTorch installation was built with MPS activated.
print(torch.backends.mps.is_built())
dtype = torch.float
device = torch.device("cpu",0)
#device = torch.device("cpu",1)
#device = torch.device("mps",0)
# Create random input and output data
x = torch.linspace(-math.pi, math.pi, 2000, device=device, dtype=dtype)
y = torch.sin(x)

# Randomly initialize weights
a = torch.randn((), device=device, dtype=dtype)
b = torch.randn((), device=device, dtype=dtype)
c = torch.randn((), device=device, dtype=dtype)
d = torch.randn((), device=device, dtype=dtype)

learning_rate = 1e-6
for t in range(2000):
    # Forward pass: compute predicted y
    y_pred = a + b * x + c * x ** 2 + d * x ** 3

    # Compute and print loss
    loss = (y_pred - y).pow(2).sum().item()
    if t % 100 == 99:
        print(t, loss)

# Backprop to compute gradients of a, b, c, d with respect to loss
    grad_y_pred = 2.0 * (y_pred - y)
    grad_a = grad_y_pred.sum()
    grad_b = (grad_y_pred * x).sum()
    grad_c = (grad_y_pred * x ** 2).sum()
    grad_d = (grad_y_pred * x ** 3).sum()

    # Update weights using gradient descent
    a -= learning_rate * grad_a
    b -= learning_rate * grad_b
    c -= learning_rate * grad_c
    d -= learning_rate * grad_d


print(f'Result: y = {a.item()} + {b.item()} x + {c.item()} x^2 + {d.item()} x^3')