Function batch_norm_simd 

pub fn batch_norm_simd(
    input: &[f32],
    output: &mut [f32],
    gamma: &[f32],
    beta: &[f32],
    mean: &[f32],
    var: &[f32],
    epsilon: f32,
    channels: usize,
)

SIMD-accelerated batch normalization with automatic architecture dispatch