generic-library/openssl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

"Monolithic" x86 assembler replacement for aes_core.c. Up to +15% better

Browse Source 
performance on recent microarchitectures.
This commit is contained in:
Andy Polyakov 2005-01-13 15:35:44 +00:00
parent 5d727078ac
commit e7e1150706
4 changed files with 1229 additions and 783 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
Configure
View File

@ -114,9 +114,9 @@ my $tlib="-lnsl -lsocket";
my $bits1="THIRTY_TWO_BIT ";
my $bits2="SIXTY_FOUR_BIT ";
my $x86_elf_asm="x86cpuid-elf.o:asm/bn86-elf.o asm/co86-elf.o:asm/dx86-elf.o asm/yx86-elf.o:aes_core.o asm/ax86-elf.o:asm/bx86-elf.o:asm/mx86-elf.o:asm/sx86-elf.o asm/s512sse2-elf.o:asm/cx86-elf.o:asm/rx86-elf.o:asm/rm86-elf.o:asm/r586-elf.o";
my $x86_coff_asm="x86cpuid-cof.o:asm/bn86-cof.o asm/co86-cof.o:asm/dx86-cof.o asm/yx86-cof.o:aes_core.o asm/ax86-cof.o:asm/bx86-cof.o:asm/mx86-cof.o:asm/sx86-cof.o asm/s512sse2-cof.o:asm/cx86-cof.o:asm/rx86-cof.o:asm/rm86-cof.o:asm/r586-cof.o";
my $x86_out_asm="x86cpuid-out.o:bn86-out.o co86-out.o:dx86-out.o yx86-out.o:aes_core.o ax86-out.o:bx86-out.o:mx86-out.o:sx86-out.o s512sse2-out.o:cx86-out.o:rx86-out.o:rm86-out.o:r586-out.o";
my $x86_elf_asm="x86cpuid-elf.o:asm/bn86-elf.o asm/co86-elf.o:asm/dx86-elf.o asm/yx86-elf.o:asm/ax86-elf.o:asm/bx86-elf.o:asm/mx86-elf.o:asm/sx86-elf.o asm/s512sse2-elf.o:asm/cx86-elf.o:asm/rx86-elf.o:asm/rm86-elf.o:asm/r586-elf.o";
my $x86_coff_asm="x86cpuid-cof.o:asm/bn86-cof.o asm/co86-cof.o:asm/dx86-cof.o asm/yx86-cof.o:asm/ax86-cof.o:asm/bx86-cof.o:asm/mx86-cof.o:asm/sx86-cof.o asm/s512sse2-cof.o:asm/cx86-cof.o:asm/rx86-cof.o:asm/rm86-cof.o:asm/r586-cof.o";
my $x86_out_asm="x86cpuid-out.o:bn86-out.o co86-out.o:dx86-out.o yx86-out.o:ax86-out.o:bx86-out.o:mx86-out.o:sx86-out.o s512sse2-out.o:cx86-out.o:rx86-out.o:rm86-out.o:r586-out.o";
my $ia64_asm=":asm/ia64.o::aes_core.o asm/aes-ia64.o:::asm/sha1-ia64.o asm/sha256-ia64.o asm/sha512-ia64.o::asm/rc4-ia64.o::";

62
TABLE
View File

@ -92,7 +92,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-cof.o
$bn_obj = asm/bn86-cof.o asm/co86-cof.o
$des_obj = asm/dx86-cof.o asm/yx86-cof.o
$aes_obj = aes_core.o asm/ax86-cof.o
$aes_obj = asm/ax86-cof.o
$bf_obj = asm/bx86-cof.o
$md5_obj = asm/mx86-cof.o
$sha1_obj = asm/sx86-cof.o asm/s512sse2-cof.o
@ -146,7 +146,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-out.o
$bn_obj = bn86-out.o co86-out.o
$des_obj = dx86-out.o yx86-out.o
$aes_obj = aes_core.o ax86-out.o
$aes_obj = ax86-out.o
$bf_obj = bx86-out.o
$md5_obj = mx86-out.o
$sha1_obj = sx86-out.o s512sse2-out.o
@ -173,7 +173,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-out.o
$bn_obj = bn86-out.o co86-out.o
$des_obj = dx86-out.o yx86-out.o
$aes_obj = aes_core.o ax86-out.o
$aes_obj = ax86-out.o
$bf_obj = bx86-out.o
$md5_obj = mx86-out.o
$sha1_obj = sx86-out.o s512sse2-out.o
@ -227,7 +227,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -551,7 +551,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-out.o
$bn_obj = bn86-out.o co86-out.o
$des_obj = dx86-out.o yx86-out.o
$aes_obj = aes_core.o ax86-out.o
$aes_obj = ax86-out.o
$bf_obj = bx86-out.o
$md5_obj = mx86-out.o
$sha1_obj = sx86-out.o s512sse2-out.o
@ -767,7 +767,7 @@ $bn_ops = BN_LLONG MD2_CHAR RC4_INDEX DES_PTR DES_RISC1 DES_UNROLL
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -794,7 +794,7 @@ $bn_ops = BN_LLONG MD2_CHAR RC4_INDEX DES_PTR DES_RISC1 DES_UNROLL
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -1334,7 +1334,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -1685,7 +1685,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -1739,7 +1739,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -1766,7 +1766,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -1847,7 +1847,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -1874,7 +1874,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -1901,7 +1901,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -1928,7 +1928,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -1955,7 +1955,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -2090,7 +2090,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -2279,7 +2279,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -2738,7 +2738,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -3035,7 +3035,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-out.o
$bn_obj = bn86-out.o co86-out.o
$des_obj = dx86-out.o yx86-out.o
$aes_obj = aes_core.o ax86-out.o
$aes_obj = ax86-out.o
$bf_obj = bx86-out.o
$md5_obj = mx86-out.o
$sha1_obj = sx86-out.o s512sse2-out.o
@ -3062,7 +3062,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -3116,7 +3116,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -3197,7 +3197,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -3332,7 +3332,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -3413,7 +3413,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -3629,7 +3629,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-cof.o
$bn_obj = asm/bn86-cof.o asm/co86-cof.o
$des_obj = asm/dx86-cof.o asm/yx86-cof.o
$aes_obj = aes_core.o asm/ax86-cof.o
$aes_obj = asm/ax86-cof.o
$bf_obj = asm/bx86-cof.o
$md5_obj = asm/mx86-cof.o
$sha1_obj = asm/sx86-cof.o asm/s512sse2-cof.o
@ -4034,7 +4034,7 @@ $bn_ops = DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -4061,7 +4061,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -4277,7 +4277,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -4547,7 +4547,7 @@ $bn_ops = BN_LLONG MD2_CHAR RC4_INDEX DES_PTR DES_RISC1 DES_UNROLL
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o
@ -4574,7 +4574,7 @@ $bn_ops = BN_LLONG DES_PTR DES_RISC1 DES_UNROLL RC4_INDEX MD2_INT
$cpuid_obj = x86cpuid-elf.o
$bn_obj = asm/bn86-elf.o asm/co86-elf.o
$des_obj = asm/dx86-elf.o asm/yx86-elf.o
$aes_obj = aes_core.o asm/ax86-elf.o
$aes_obj = asm/ax86-elf.o
$bf_obj = asm/bx86-elf.o
$md5_obj = asm/mx86-elf.o
$sha1_obj = asm/sx86-elf.o asm/s512sse2-elf.o

1938
crypto/aes/asm/aes-586.pl
View File

File diff suppressed because it is too large Load Diff

6
crypto/engine/eng_padlock.c
View File

@ -788,10 +788,10 @@ padlock_aes_init_key (EVP_CIPHER_CTX *ctx, const unsigned char *key,
AES_set_encrypt_key(key, key_len, &cdata->ks);
else
AES_set_decrypt_key(key, key_len, &cdata->ks);
/* OpenSSL internal functions use byte-swapped extended key. */
#ifndef AES_ASM
/* OpenSSL C functions use byte-swapped extended key. */
padlock_bswapl(&cdata->ks);
#endif
cdata->cword.b.keygen = 1;
break;