This commit completes recent modular exponentiation optimizations on

x86_64 platform. It targets specifically RSA1024 sign (using ideas
from http://eprint.iacr.org/2011/239) and adds more than 10% on most
platforms. Overall performance improvement relative to 1.0.0 is ~40%
in average, with best result of 54% on Westmere. Incidentally ~40%
is average improvement even for longer key lengths.

1 files changed, 12 insertions, 12 deletions

diff --git a/TABLE b/TABLE
index f520d7116b..b5aea36d97 100644
--- a/TABLE
+++ b/TABLE
@@ -297,7 +297,7 @@ $sys_id       =
 $lflags       = 
 $bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_INT DES_UNROLL
 $cpuid_obj    = x86_64cpuid.o
-$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-gf2m.o modexp512-x86_64.o
+$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-mont5.o x86_64-gf2m.o modexp512-x86_64.o
 $des_obj      = 
 $aes_obj      = aes-x86_64.o aesni-x86_64.o
 $bf_obj       = 
@@ -777,7 +777,7 @@ $sys_id       = WIN64A
 $lflags       = 
 $bn_ops       = SIXTY_FOUR_BIT RC4_CHUNK_LL DES_INT EXPORT_VAR_AS_FN
 $cpuid_obj    = x86_64cpuid.o
-$bn_obj       = bn_asm.o x86_64-mont.o
+$bn_obj       = bn_asm.o x86_64-mont.o x86_64-mont5.o x86_64-gf2m.o modexp512-x86_64.o
 $des_obj      = 
 $aes_obj      = aes-x86_64.o aesni-x86_64.o
 $bf_obj       = 
@@ -1385,7 +1385,7 @@ $sys_id       = MACOSX
 $lflags       = -Wl,-search_paths_first%
 $bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHAR RC4_CHUNK DES_INT DES_UNROLL
 $cpuid_obj    = x86_64cpuid.o
-$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-gf2m.o modexp512-x86_64.o
+$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-mont5.o x86_64-gf2m.o modexp512-x86_64.o
 $des_obj      = 
 $aes_obj      = aes-x86_64.o aesni-x86_64.o
 $bf_obj       = 
@@ -1545,9 +1545,9 @@ $sys_id       = WIN64A
 $lflags       = 
 $bn_ops       = SIXTY_FOUR_BIT RC4_CHUNK_LL DES_INT EXPORT_VAR_AS_FN
 $cpuid_obj    = x86_64cpuid.o
-$bn_obj       = bn_asm.o x86_64-mont.o
+$bn_obj       = bn_asm.o x86_64-mont.o x86_64-mont5.o x86_64-gf2m.o modexp512-x86_64.o
 $des_obj      = 
-$aes_obj      = aes-x86_64.o
+$aes_obj      = aes-x86_64.o aesni-x86_64.o
 $bf_obj       = 
 $md5_obj      = md5-x86_64.o
 $sha1_obj     = sha1-x86_64.o sha256-x86_64.o sha512-x86_64.o
@@ -2313,7 +2313,7 @@ $sys_id       =
 $lflags       = -ldl
 $bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_INT DES_UNROLL
 $cpuid_obj    = x86_64cpuid.o
-$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-gf2m.o modexp512-x86_64.o
+$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-mont5.o x86_64-gf2m.o modexp512-x86_64.o
 $des_obj      = 
 $aes_obj      = aes-x86_64.o aesni-x86_64.o
 $bf_obj       = 
@@ -2505,7 +2505,7 @@ $sys_id       =
 $lflags       = -ldl
 $bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_INT DES_UNROLL
 $cpuid_obj    = x86_64cpuid.o
-$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-gf2m.o modexp512-x86_64.o
+$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-mont5.o x86_64-gf2m.o modexp512-x86_64.o
 $des_obj      = 
 $aes_obj      = aes-x86_64.o aesni-x86_64.o
 $bf_obj       = 
@@ -2569,7 +2569,7 @@ $sys_id       =
 $lflags       = -ldl
 $bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_INT DES_UNROLL
 $cpuid_obj    = x86_64cpuid.o
-$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-gf2m.o modexp512-x86_64.o
+$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-mont5.o x86_64-gf2m.o modexp512-x86_64.o
 $des_obj      = 
 $aes_obj      = aes-x86_64.o aesni-x86_64.o
 $bf_obj       = 
@@ -4073,7 +4073,7 @@ $sys_id       =
 $lflags       = -ldl
 $bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_INT DES_UNROLL
 $cpuid_obj    = x86_64cpuid.o
-$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-gf2m.o modexp512-x86_64.o
+$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-mont5.o x86_64-gf2m.o modexp512-x86_64.o
 $des_obj      = 
 $aes_obj      = aes-x86_64.o aesni-x86_64.o
 $bf_obj       = 
@@ -4233,7 +4233,7 @@ $sys_id       = MINGW64
 $lflags       = -lws2_32 -lgdi32 -lcrypt32
 $bn_ops       = SIXTY_FOUR_BIT RC4_CHUNK_LL DES_INT EXPORT_VAR_AS_FN
 $cpuid_obj    = x86_64cpuid.o
-$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-gf2m.o modexp512-x86_64.o
+$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-mont5.o x86_64-gf2m.o modexp512-x86_64.o
 $des_obj      = 
 $aes_obj      = aes-x86_64.o aesni-x86_64.o
 $bf_obj       = 
@@ -5193,7 +5193,7 @@ $sys_id       =
 $lflags       = -lsocket -lnsl -ldl
 $bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_INT DES_UNROLL
 $cpuid_obj    = x86_64cpuid.o
-$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-gf2m.o modexp512-x86_64.o
+$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-mont5.o x86_64-gf2m.o modexp512-x86_64.o
 $des_obj      = 
 $aes_obj      = aes-x86_64.o aesni-x86_64.o
 $bf_obj       = 
@@ -5225,7 +5225,7 @@ $sys_id       =
 $lflags       = -lsocket -lnsl -ldl
 $bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHUNK DES_INT DES_UNROLL
 $cpuid_obj    = x86_64cpuid.o
-$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-gf2m.o modexp512-x86_64.o
+$bn_obj       = x86_64-gcc.o x86_64-mont.o x86_64-mont5.o x86_64-gf2m.o modexp512-x86_64.o
 $des_obj      = 
 $aes_obj      = aes-x86_64.o aesni-x86_64.o
 $bf_obj       =