Speeding up build process with distutils

Try building with environment variable CC="ccache gcc", that will speed up build significantly when the source has not changed. (strangely, distutils uses CC also for c++ source files). Install the ccache package, of course.

Since you have a single extension which is assembled from multiple compiled object files, you can monkey-patch distutils to compile those in parallel (they are independent) – put this into your setup.py (adjust the N=2 as you wish):

# monkey-patch for parallel compilation
def parallelCCompile(self, sources, output_dir=None, macros=None, include_dirs=None, debug=0, extra_preargs=None, extra_postargs=None, depends=None):
    # those lines are copied from distutils.ccompiler.CCompiler directly
    macros, objects, extra_postargs, pp_opts, build = self._setup_compile(output_dir, macros, include_dirs, sources, depends, extra_postargs)
    cc_args = self._get_cc_args(pp_opts, debug, extra_preargs)
    # parallel code
    N=2 # number of parallel compilations
    import multiprocessing.pool
    def _single_compile(obj):
        try: src, ext = build[obj]
        except KeyError: return
        self._compile(obj, src, ext, cc_args, extra_postargs, pp_opts)
    # convert to list, imap is evaluated on-demand
    list(multiprocessing.pool.ThreadPool(N).imap(_single_compile,objects))
    return objects
import distutils.ccompiler
distutils.ccompiler.CCompiler.compile=parallelCCompile

For the sake of completeness, if you have multiple extensions, you can use the following solution:

import os
import multiprocessing
try:
    from concurrent.futures import ThreadPoolExecutor as Pool
except ImportError:
    from multiprocessing.pool import ThreadPool as LegacyPool

    # To ensure the with statement works. Required for some older 2.7.x releases
    class Pool(LegacyPool):
        def __enter__(self):
            return self

        def __exit__(self, *args):
            self.close()
            self.join()

def build_extensions(self):
    """Function to monkey-patch
    distutils.command.build_ext.build_ext.build_extensions

    """
    self.check_extensions_list(self.extensions)

    try:
        num_jobs = os.cpu_count()
    except AttributeError:
        num_jobs = multiprocessing.cpu_count()

    with Pool(num_jobs) as pool:
        pool.map(self.build_extension, self.extensions)

def compile(
    self, sources, output_dir=None, macros=None, include_dirs=None,
    debug=0, extra_preargs=None, extra_postargs=None, depends=None,
):
    """Function to monkey-patch distutils.ccompiler.CCompiler"""
    macros, objects, extra_postargs, pp_opts, build = self._setup_compile(
        output_dir, macros, include_dirs, sources, depends, extra_postargs
    )
    cc_args = self._get_cc_args(pp_opts, debug, extra_preargs)

    for obj in objects:
        try:
            src, ext = build[obj]
        except KeyError:
            continue
        self._compile(obj, src, ext, cc_args, extra_postargs, pp_opts)

    # Return *all* object filenames, not just the ones we just built.
    return objects


from distutils.ccompiler import CCompiler
from distutils.command.build_ext import build_ext
build_ext.build_extensions = build_extensions
CCompiler.compile = compile