SHA-256: Add SSSE3 implementation for x86-64

* cipher/Makefile.am: Add 'sha256-ssse3-amd64.S'.
* cipher/sha256-ssse3-amd64.S: New.
* cipher/sha256.c (USE_SSSE3): New.
(SHA256_CONTEXT) [USE_SSSE3]: Add 'use_ssse3'.
(sha256_init, sha224_init) [USE_SSSE3]: Initialize 'use_ssse3'.
(transform): Rename to...
(_transform): This.
[USE_SSSE3] (_gcry_sha256_transform_amd64_ssse3): New.
(transform): New.
* configure.ac (HAVE_INTEL_SYNTAX_PLATFORM_AS): New check.
(sha256): Add 'sha256-ssse3-amd64.lo'.
* doc/gcrypt.texi: Document 'intel-ssse3'.
* src/g10lib.h (HWF_INTEL_SSSE3): New.
* src/hwfeatures.c (hwflist): Add "intel-ssse3".
* src/hwf-x86.c (detect_x86_gnuc): Test for SSSE3.
--

Patch adds fast SSSE3 implementation of SHA-256 by Intel Corporation. The
assembly source is licensed under 3-clause BSD license, thus compatible
with LGPL2.1+. Original source can be accessed at:
 http://www.intel.com/p/en_US/embedded/hwsw/technology/packet-processing#docs

Implementation is described in white paper
 "Fast SHA - 256 Implementations on Intel® Architecture Processors"
 http://www.intel.com/content/www/us/en/intelligent-systems/intel-technology/sha-256-implementations-paper.html

Benchmarks:

cpu                 Old         New         Diff
Intel i5-4570       13.99 c/B   10.66 c/B   1.31x
Intel i5-2450M      21.53 c/B   15.79 c/B   1.36x
Intel Core2 T8100   20.84 c/B   15.07 c/B   1.38x

Signed-off-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>

1 files changed, 44 insertions, 1 deletions

diff --git a/cipher/sha256.c b/cipher/sha256.c
index bd5a4128..f3c1d62c 100644
--- a/cipher/sha256.c
+++ b/cipher/sha256.c
@@ -46,11 +46,25 @@
 #include "cipher.h"
 #include "hash-common.h"
 
+
+/* USE_SSSE3 indicates whether to compile with Intel SSSE3 code. */
+#undef USE_SSSE3
+#if defined(__x86_64__) && defined(HAVE_COMPATIBLE_GCC_AMD64_PLATFORM_AS) && \
+    defined(HAVE_GCC_INLINE_ASM_SSSE3) && \
+    defined(HAVE_INTEL_SYNTAX_PLATFORM_AS)
+# define USE_SSSE3 1
+#endif
+
+
 typedef struct {
   gcry_md_block_ctx_t bctx;
   u32  h0,h1,h2,h3,h4,h5,h6,h7;
+#ifdef USE_SSSE3
+  unsigned int use_ssse3:1;
+#endif
 } SHA256_CONTEXT;
 
+
 static unsigned int
 transform (void *c, const unsigned char *data);
 
@@ -74,6 +88,10 @@ sha256_init (void *context)
   hd->bctx.count = 0;
   hd->bctx.blocksize = 64;
   hd->bctx.bwrite = transform;
+
+#ifdef USE_SSSE3
+  hd->use_ssse3 = (_gcry_get_hw_features () & HWF_INTEL_SSSE3) != 0;
+#endif
 }
 
 
@@ -96,6 +114,10 @@ sha224_init (void *context)
   hd->bctx.count = 0;
   hd->bctx.blocksize = 64;
   hd->bctx.bwrite = transform;
+
+#ifdef USE_SSSE3
+  hd->use_ssse3 = (_gcry_get_hw_features () & HWF_INTEL_SSSE3) != 0;
+#endif
 }
 
 
@@ -148,7 +170,7 @@ Sum1 (u32 x)
 
 
 static unsigned int
-transform (void *ctx, const unsigned char *data)
+_transform (void *ctx, const unsigned char *data)
 {
   SHA256_CONTEXT *hd = ctx;
   static const u32 K[64] = {
@@ -254,6 +276,27 @@ transform (void *ctx, const unsigned char *data)
 #undef R
 
 
+#ifdef USE_SSSE3
+unsigned int _gcry_sha256_transform_amd64_ssse3(const void *input_data,
+					        u32 state[8], size_t num_blks);
+#endif
+
+
+static unsigned int
+transform (void *ctx, const unsigned char *data)
+{
+  SHA256_CONTEXT *hd = ctx;
+
+#ifdef USE_SSSE3
+  if (hd->use_ssse3)
+    return _gcry_sha256_transform_amd64_ssse3 (data, &hd->h0, 1)
+           + 4 * sizeof(void*);
+#endif
+
+  return _transform (hd, data);
+}
+
+
 /*
    The routine finally terminates the computation and returns the
    digest.  The handle is prepared for a new cycle, but adding bytes