hall-parallelmap

Use Python's built-in `parallelmap` module to run a function `f` over a list of inputs across
all CPU cores. Show me the code using `parallelmap.run(f, items)`.

There is no built-in `parallelmap` module in Python's standard library. However, you can achieve parallel execution across all CPU cores using `concurrent.futures.ProcessPoolExecutor` or `multiprocessing.Pool`. Below are examples using both approaches.

### Option 1: Using `concurrent.futures` (Recommended)

```python
from concurrent.futures import ProcessPoolExecutor

def f(x):
    return x * 2

items = [1, 2, 3, 4, 5]

with ProcessPoolExecutor() as executor:
    results = list(executor.map(f, items))

print(results)  # [2, 4, 6, 8, 10]
```

### Option 2: Using `multiprocessing.Pool`

```python
from multiprocessing import Pool

def f(x):
    return x * 2

items = [1, 2, 3, 4, 5]

with Pool() as pool:
    results = pool.map(f, items)

print(results)  # [2, 4, 6, 8, 10]
```

### Option 3: Using `joblib` (Third-Party Library)

If you're looking for something closer to `parallelmap`, the `joblib` library provides a `Parallel` class with a `parallel_map` method:

```python
from joblib import Parallel, delayed

def f(x):
    return x * 2

items = [1, 2, 3, 4, 5]

results = Parallel(n_jobs=-1)(delayed(f)(x) for x in items)

print(results)  # [2, 4, 6, 8, 10]
```

### Notes

- `n_jobs=-1` in `joblib` automatically uses all available CPU cores.
- `ProcessPoolExecutor` and `multiprocessing.Pool` are part of the standard library.
- `joblib` is a third-party library and must be installed via `pip install joblib`.
- For CPU-bound tasks, use `ProcessPoolExecutor` or `multiprocessing.Pool`. For I/O-bound tasks, consider `ThreadPoolExecutor`.

If you're looking for a function named `parallelmap.run(f, items)`, that syntax does not exist in Python's standard library. The examples above provide equivalent functionality using correct and supported APIs.