What are the key performance tips when using NumPy for large-scale data processing?

import numpy as np

n = 10_000_000
arr = rng.random(n)

# 1. AVOID Python loops — always prefer ufuncs
# Slow:
result = [x**2 for x in arr]        # Python loop, ~3s
# Fast:
result = arr ** 2                    # NumPy ufunc, ~0.03s

# 2. Pre-allocate output arrays instead of growing them
# Slow:
out = []
for chunk in chunks:
    out.append(chunk.sum())          # repeated list growth
# Fast:
out = np.empty(len(chunks))
for i, chunk in enumerate(chunks):
    out[i] = chunk.sum()

# 3. Use views instead of copies when slicing
sub = arr[1000:2000]   # view — no memory allocation
sub2 = arr[1000:2000].copy()  # explicit copy — only when mutation safety needed

# 4. Choose the right dtype — float32 vs float64
a64 = np.ones(n, dtype=np.float64)  # 80 MB
a32 = np.ones(n, dtype=np.float32)  # 40 MB — also faster on many ops

# 5. Use out= argument to avoid temporary arrays
np.add(a32, a32, out=a32)   # in-place: no temporary intermediate created

# 6. np.einsum for complex multi-dimensional contractions
A = rng.random((100, 200))
B = rng.random((200, 300))
C = np.einsum('ij,jk->ik', A, B)  # equivalent to A @ B but explicit