Add Intel PCLMUL implementations of CRC algorithms

* cipher/Makefile.am: Add 'crc-intel-pclmul.c'.
* cipher/crc-intel-pclmul.c: New.
* cipher/crc.c (USE_INTEL_PCLMUL): New macro.
(CRC_CONTEXT) [USE_INTEL_PCLMUL]: Add 'use_pclmul'.
[USE_INTEL_PCLMUL] (_gcry_crc32_intel_pclmul)
(gcry_crc24rfc2440_intel_pclmul): New.
(crc32_init, crc32rfc1510_init, crc24rfc2440_init)
[USE_INTEL_PCLMUL]: Select PCLMUL implementation if SSE4.1 and PCLMUL
HW features detected.
(crc32_write, crc24rfc2440_write) [USE_INTEL_PCLMUL]: Use PCLMUL
implementation if enabled.
(crc24_init): Document storage format of 24-bit CRC.
(crc24_next4): Use only 'data' for last table look-up.
* configure.ac: Add 'crc-intel-pclmul.lo'.
* src/g10lib.h (HWF_*, HWF_INTEL_SSE4_1): Update HWF flags to include
Intel SSE4.1.
* src/hwf-x86.c (detect_x86_gnuc): Add SSE4.1 detection.
* src/hwfeatures.c (hwflist): Add 'intel-sse4.1'.
* tests/basic.c (fillbuf_count): New.
(check_one_md): Add "?" check (million byte data-set with byte pattern
0x00,0x01,0x02,...); Test all buffer sizes 1 to 1000, for "!" and "?"
checks.
(check_one_md_multi): Skip "?".
(check_digests): Add "?" test-vectors for MD5, SHA1, SHA224, SHA256,
SHA384, SHA512, SHA3_224, SHA3_256, SHA3_384, SHA3_512, RIPEMD160,
CRC32, CRC32_RFC1510, CRC24_RFC2440, TIGER1 and WHIRLPOOL; Add "!"
test-vectors for CRC32_RFC1510 and CRC24_RFC2440.
--

Add Intel PCLMUL accelerated implmentations of CRC algorithms.
CRC performance is improved ~11x on x86_64 and i386 on Intel
Haswell, and ~2.7x on Intel Sandy-bridge.

Benchmark on Intel Core i5-4570 (x86_64, 3.2 Ghz):

 Before:
                 |  nanosecs/byte   mebibytes/sec   cycles/byte
  CRC32          |     0.865 ns/B    1103.0 MiB/s      2.77 c/B
  CRC32RFC1510   |     0.865 ns/B    1102.7 MiB/s      2.77 c/B
  CRC24RFC2440   |     0.865 ns/B    1103.0 MiB/s      2.77 c/B

 After:
                 |  nanosecs/byte   mebibytes/sec   cycles/byte
  CRC32          |     0.079 ns/B   12051.7 MiB/s     0.253 c/B
  CRC32RFC1510   |     0.079 ns/B   12050.6 MiB/s     0.253 c/B
  CRC24RFC2440   |     0.079 ns/B   12100.0 MiB/s     0.252 c/B

Benchmark on Intel Core i5-4570 (i386, 3.2 Ghz):

 Before:
                 |  nanosecs/byte   mebibytes/sec   cycles/byte
  CRC32          |     0.860 ns/B    1109.0 MiB/s      2.75 c/B
  CRC32RFC1510   |     0.861 ns/B    1108.3 MiB/s      2.75 c/B
  CRC24RFC2440   |     0.860 ns/B    1108.6 MiB/s      2.75 c/B

 After:
                 |  nanosecs/byte   mebibytes/sec   cycles/byte
  CRC32          |     0.078 ns/B   12207.0 MiB/s     0.250 c/B
  CRC32RFC1510   |     0.078 ns/B   12207.0 MiB/s     0.250 c/B
  CRC24RFC2440   |     0.080 ns/B   11925.6 MiB/s     0.256 c/B

Benchmark on Intel Core i5-2450M (x86_64, 2.5 Ghz):

 Before:
                 |  nanosecs/byte   mebibytes/sec   cycles/byte
  CRC32          |      1.25 ns/B     762.3 MiB/s      3.13 c/B
  CRC32RFC1510   |      1.26 ns/B     759.1 MiB/s      3.14 c/B
  CRC24RFC2440   |      1.25 ns/B     764.9 MiB/s      3.12 c/B

 After:
                 |  nanosecs/byte   mebibytes/sec   cycles/byte
  CRC32          |     0.451 ns/B    2114.3 MiB/s      1.13 c/B
  CRC32RFC1510   |     0.451 ns/B    2114.6 MiB/s      1.13 c/B
  CRC24RFC2440   |     0.457 ns/B    2085.0 MiB/s      1.14 c/B

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

1 files changed, 57 insertions, 2 deletions

diff --git a/cipher/crc.c b/cipher/crc.c
index 46a185a8..ee0e4e2e 100644
--- a/cipher/crc.c
+++ b/cipher/crc.c
@@ -31,14 +31,37 @@
 #include "bufhelp.h"
 
 
+/* USE_INTEL_PCLMUL indicates whether to compile CRC with Intel PCLMUL
+ * code.  */
+#undef USE_INTEL_PCLMUL
+#ifdef ENABLE_PCLMUL_SUPPORT
+# if ((defined(__i386__) && SIZEOF_UNSIGNED_LONG == 4) || defined(__x86_64__))
+#  if __GNUC__ >= 4
+#   define USE_INTEL_PCLMUL 1
+#  endif
+# endif
+#endif /* USE_INTEL_PCLMUL */
+
+
 typedef struct
 {
   u32 CRC;
+#ifdef USE_INTEL_PCLMUL
+  unsigned int use_pclmul:1;           /* Intel PCLMUL shall be used.  */
+#endif
   byte buf[4];
 }
 CRC_CONTEXT;
 
 
+#ifdef USE_INTEL_PCLMUL
+/*-- crc-intel-pclmul.c --*/
+void _gcry_crc32_intel_pclmul (u32 *pcrc, const byte *inbuf, size_t inlen);
+void _gcry_crc24rfc2440_intel_pclmul (u32 *pcrc, const byte *inbuf,
+				      size_t inlen);
+#endif
+
+
 /*
  * Code generated by universal_crc by Danjel McGougan
  *
@@ -338,6 +361,11 @@ static void
 crc32_init (void *context, unsigned int flags)
 {
   CRC_CONTEXT *ctx = (CRC_CONTEXT *) context;
+#ifdef USE_INTEL_PCLMUL
+  u32 hwf = _gcry_get_hw_features ();
+
+  ctx->use_pclmul = (hwf & HWF_INTEL_SSE4_1) && (hwf & HWF_INTEL_PCLMUL);
+#endif
 
   (void)flags;
 
@@ -351,6 +379,14 @@ crc32_write (void *context, const void *inbuf_arg, size_t inlen)
   const byte *inbuf = inbuf_arg;
   u32 crc;
 
+#ifdef USE_INTEL_PCLMUL
+  if (ctx->use_pclmul)
+    {
+      _gcry_crc32_intel_pclmul(&ctx->CRC, inbuf, inlen);
+      return;
+    }
+#endif
+
   if (!inbuf || !inlen)
     return;
 
@@ -403,6 +439,11 @@ static void
 crc32rfc1510_init (void *context, unsigned int flags)
 {
   CRC_CONTEXT *ctx = (CRC_CONTEXT *) context;
+#ifdef USE_INTEL_PCLMUL
+  u32 hwf = _gcry_get_hw_features ();
+
+  ctx->use_pclmul = (hwf & HWF_INTEL_SSE4_1) && (hwf & HWF_INTEL_PCLMUL);
+#endif
 
   (void)flags;
 
@@ -694,7 +735,8 @@ static const u32 crc24_table[1024] =
 static inline
 u32 crc24_init (void)
 {
-  return 0xce04b7;
+  /* Transformed to 32-bit CRC by multiplied by x⁸ and then byte swapped. */
+  return 0xce04b7; /* _gcry_bswap(0xb704ce << 8) */
 }
 
 static inline
@@ -713,7 +755,7 @@ u32 crc24_next4 (u32 crc, u32 data)
   crc = crc24_table[(crc & 0xff) + 0x300] ^
         crc24_table[((crc >> 8) & 0xff) + 0x200] ^
         crc24_table[((crc >> 16) & 0xff) + 0x100] ^
-        crc24_table[(crc >> 24) & 0xff];
+        crc24_table[(data >> 24) & 0xff];
   return crc;
 }
 
@@ -727,6 +769,11 @@ static void
 crc24rfc2440_init (void *context, unsigned int flags)
 {
   CRC_CONTEXT *ctx = (CRC_CONTEXT *) context;
+#ifdef USE_INTEL_PCLMUL
+  u32 hwf = _gcry_get_hw_features ();
+
+  ctx->use_pclmul = (hwf & HWF_INTEL_SSE4_1) && (hwf & HWF_INTEL_PCLMUL);
+#endif
 
   (void)flags;
 
@@ -740,6 +787,14 @@ crc24rfc2440_write (void *context, const void *inbuf_arg, size_t inlen)
   CRC_CONTEXT *ctx = (CRC_CONTEXT *) context;
   u32 crc;
 
+#ifdef USE_INTEL_PCLMUL
+  if (ctx->use_pclmul)
+    {
+      _gcry_crc24rfc2440_intel_pclmul(&ctx->CRC, inbuf, inlen);
+      return;
+    }
+#endif
+
   if (!inbuf || !inlen)
     return;