device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
print("Device", device)

x = torch.randn(5000, 5000)

# CPU version
start_time = time.time()
_ = torch.matmul(x, x)
end_time = time.time()
print(f"CPU time: {(end_time - start_time):6.5f}s")

# GPU version
if torch.cuda.is_available():
    x = x.to(device)
    # CUDA is asynchronous, so we need to use different timing functions
    start = torch.cuda.Event(enable_timing=True)
    end = torch.cuda.Event(enable_timing=True)
    start.record()
    _ = torch.matmul(x, x)
    end.record()
    torch.cuda.synchronize()  # Waits for everything to finish running on the GPU
    print(f"GPU time: {0.001 * start.elapsed_time(end):6.5f}s")  # Milliseconds to seconds

import random
import numpy as np

import torch


def set_seed(seed=3407):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    if torch.cuda.is_available():
        torch.cuda.manual_seed(seed)
        torch.cuda.manual_seed_all(seed)

torch.backends.cudnn.determinstic = True
torch.backends.cudnn.benchmark = False