diff --git a/MANIFEST.in b/MANIFEST.in
index 2625063..297d1f7 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -4,6 +4,7 @@ include ksw2_dispatch.c
 include getopt.c
 include main.c
 include README.md
+include sse2neon/emmintrin.h
 include python/mappy.c
 include python/cmappy.h
 include python/cmappy.pxd
diff --git a/setup.py b/setup.py
index 7f52909..87dcc2f 100644
--- a/setup.py
+++ b/setup.py
@@ -14,12 +14,22 @@ else: # with Cython
 	module_src = 'python/mappy.pyx'
 	cmdclass['build_ext'] = build_ext
 
-import sys
+import sys, platform
+
 sys.path.append('python')
 
+extra_compile_args = ['-DHAVE_KALLOC']
+include_dirs = ["."]
+
+if platform.machine() in ["aarch64", "arm64"]:
+	include_dirs.append("sse2neon/")
+	extra_compile_args.extend(['-ftree-vectorize', '-DKSW_SSE2_ONLY', '-D__SSE2__'])
+else:
+	extra_compile_args.append('-msse4.1') # WARNING: ancient x86_64 CPUs don't have SSE4
+
 def readme():
-    with open('python/README.rst') as f:
-        return f.read()
+	with open('python/README.rst') as f:
+		return f.read()
 
 setup(
 	name = 'mappy',
@@ -39,8 +49,8 @@ setup(
 		depends = ['minimap.h', 'bseq.h', 'kalloc.h', 'kdq.h', 'khash.h', 'kseq.h', 'ksort.h',
 				   'ksw2.h', 'kthread.h', 'kvec.h', 'mmpriv.h', 'sdust.h',
 				   'python/cmappy.h', 'python/cmappy.pxd'],
-		extra_compile_args = ['-DHAVE_KALLOC', '-msse4.1'], # WARNING: ancient x86_64 CPUs don't have SSE4
-		include_dirs = ['.'],
+		extra_compile_args = extra_compile_args,
+		include_dirs = include_dirs,
 		libraries = ['z', 'm', 'pthread'])],
 	classifiers = [
 		'Development Status :: 5 - Production/Stable',