fixes bpo-31834: Use optimized code for BLAKE2 only with SSSE3+ (#4066)

Rework the code choosing BLAKE2 code paths from using the optimized
variant on all x86_64 machines to using it when SSSE3 or better
supported instructions sets are available.

Firstly, this solves the problem of using pure SSE2 code path on x86_64
machines. As reported in the bug, this code is slower than the reference
code on all tested x86_64 machines. Furthermore, on Athlon64 that lacks
SSSE3, it is even 2.5 times slower than the reference code! Checking
for SSSE3 therefore ensures that the optimized implementation will only
be used when it has a chance of performing better.

Secondly, this makes it possible to use SSSE3+ optimizations on 32-bit
x86 systems. This allows for even 2 times speed gain on modern 32-bit
x86 systems (tested in a 32-bit chroot).

diff --git a/Misc/NEWS.d/next/Library/2017-10-23-23-27-52.bpo-31834.InwC6O.rst b/Misc/NEWS.d/next/Library/2017-10-23-23-27-52.bpo-31834.InwC6O.rst
new file mode 100644 (file)
index 0000000..0fe3950
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2017-10-23-23-27-52.bpo-31834.InwC6O.rst
@@ -0,0 +1,2 @@
+Use optimized code for BLAKE2 only with SSSE3+. The pure SSE2 implementation
+is slower than the pure C reference implementation.

diff --git a/Modules/_blake2/blake2b_impl.c b/Modules/_blake2/blake2b_impl.c
index b1ae3e9b6281087429712f72dd07cc9c17dba319..3c2a035f3d72f21abc100c1d7ce97c5b54d9cc56 100644 (file)
--- a/Modules/_blake2/blake2b_impl.c
+++ b/Modules/_blake2/blake2b_impl.c
@@ -26,7 +26,9 @@
 #include "impl/blake2.h"
 #include "impl/blake2-impl.h" /* for secure_zero_memory() and store48() */
 
-#ifdef BLAKE2_USE_SSE
+/* pure SSE2 implementation is very slow, so only use the more optimized SSSE3+
+ * https://bugs.python.org/issue31834 */
+#if defined(__SSSE3__) || defined(__SSE4_1__) || defined(__AVX__) || defined(__XOP__)
 #include "impl/blake2b.c"
 #else
 #include "impl/blake2b-ref.c"

diff --git a/Modules/_blake2/blake2s_impl.c b/Modules/_blake2/blake2s_impl.c
index 3615a383db33f5cc0b77804eaa8dacbbd493c4a0..2c5697299fcd91c3d035e6a134a712490eaf0054 100644 (file)
--- a/Modules/_blake2/blake2s_impl.c
+++ b/Modules/_blake2/blake2s_impl.c
@@ -26,7 +26,9 @@
 #include "impl/blake2.h"
 #include "impl/blake2-impl.h" /* for secure_zero_memory() and store48() */
 
-#ifdef BLAKE2_USE_SSE
+/* pure SSE2 implementation is very slow, so only use the more optimized SSSE3+
+ * https://bugs.python.org/issue31834 */
+#if defined(__SSSE3__) || defined(__SSE4_1__) || defined(__AVX__) || defined(__XOP__)
 #include "impl/blake2s.c"
 #else
 #include "impl/blake2s-ref.c"

diff --git a/setup.py b/setup.py
index 11c4ec67f43f8b973be784f53e2ace271283033a..51e5d7eff7fed823093f3800c6d16297e31a6e73 100644 (file)
--- a/setup.py
+++ b/setup.py
@@ -922,19 +922,10 @@ class PyBuildExt(build_ext):
                                         'Modules/_blake2/impl/*'))
         blake2_deps.append('hashlib.h')
 
-        blake2_macros = []
-        if (not cross_compiling and
-                os.uname().machine == "x86_64" and
-                sys.maxsize >  2**32):
-            # Every x86_64 machine has at least SSE2.  Check for sys.maxsize
-            # in case that kernel is 64-bit but userspace is 32-bit.
-            blake2_macros.append(('BLAKE2_USE_SSE', '1'))
-
         exts.append( Extension('_blake2',
                                ['_blake2/blake2module.c',
                                 '_blake2/blake2b_impl.c',
                                 '_blake2/blake2s_impl.c'],
-                               define_macros=blake2_macros,
                                depends=blake2_deps) )
 
         sha3_deps = glob(os.path.join(os.getcwd(), srcdir,