From 466ce76ecaf1efeb18d20ed082818e9f54806d59 Mon Sep 17 00:00:00 2001
From: Linus Yang <laokongzi@gmail.com>
Date: Fri, 18 Aug 2017 17:38:24 +0800
Subject: [PATCH] Port OpenSSL asm code

---
 lib/aesacc.c       |  112 +-
 lib/aesacc.h       |    8 +
 lib/asm/arm.S      | 1194 ++++++++++++++++
 lib/asm/arm_arch.h |   83 ++
 lib/asm/mips.S     | 1835 +++++++++++++++++++++++++
 lib/asm/x86.S      | 3244 ++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 6461 insertions(+), 15 deletions(-)
 create mode 100644 lib/asm/arm.S
 create mode 100644 lib/asm/arm_arch.h
 create mode 100644 lib/asm/mips.S
 create mode 100644 lib/asm/x86.S

diff --git a/lib/aesacc.c b/lib/aesacc.c
index c845576..9939bc7 100644
--- a/lib/aesacc.c
+++ b/lib/aesacc.c
@@ -11,13 +11,19 @@
 
 #if defined(AES256) && (AES256 == 1)
 #define AES_KEYSIZE 256
-#define aes_setkey_enc aesni_setkey_enc_256
+#ifdef HAVE_AMD64
+  #define aes_setkey_enc aesni_setkey_enc_256
+#endif
 #elif defined(AES192) && (AES192 == 1)
 #define AES_KEYSIZE 192
-#define aes_setkey_enc aesni_setkey_enc_192
+#ifdef HAVE_AMD64
+  #define aes_setkey_enc aesni_setkey_enc_192
+#endif
 #else
 #define AES_KEYSIZE 128
-#define aes_setkey_enc aesni_setkey_enc_128
+#ifdef HAVE_AMD64
+  #define aes_setkey_enc aesni_setkey_enc_128
+#endif
 #endif
 
 #define AES_NR ((AES_KEYSIZE >> 5) + 6)
@@ -156,7 +162,87 @@ static void aes_inverse_key(uint8_t *invkey, const uint8_t *fwdkey)
 
 #endif /* HAVE_ARM64 */
 
+#ifdef HAVE_ASM
+
+#define AES_MAXNR 14
+
+typedef struct {
+  uint32_t rd_key[4 * (AES_MAXNR + 1)];
+  int rounds;
+} AES_KEY;
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+int AES_set_encrypt_key(const unsigned char *userKey, const int bits,
+                        AES_KEY *key);
+int AES_set_decrypt_key(const unsigned char *userKey, const int bits,
+                        AES_KEY *key);
+
+void AES_encrypt(const unsigned char *in, unsigned char *out,
+                 const AES_KEY *key);
+void AES_decrypt(const unsigned char *in, unsigned char *out,
+                 const AES_KEY *key);
+
+#ifdef __cplusplus
+}
+#endif
+
+static int aes_supported(void)
+{
+  return 2;
+}
+
+static void aes_crypt_ecb( int nr,
+                           unsigned char *rk,
+                           int mode,
+                           const unsigned char input[16],
+                           unsigned char output[16] )
+{
+  AES_KEY *ctx;
+  ctx = (AES_KEY *) rk;
+  ctx->rounds = nr;
+  if (mode == AES_DECRYPT) {
+    AES_decrypt(input, output, ctx);
+  } else {
+    AES_encrypt(input, output, ctx);
+  }
+}
+
+static void aes_setkey_enc(uint8_t *rk, const uint8_t *key)
+{
+  AES_KEY *ctx;
+  ctx = (AES_KEY *) rk;
+  ctx->rounds = AES_NR;
+  AES_set_encrypt_key(key, AES_KEYSIZE, ctx);
+}
+
+static void aes_setkey_dec(uint8_t *rk, const uint8_t *key)
+{
+  AES_KEY *ctx;
+  ctx = (AES_KEY *) rk;
+  ctx->rounds = AES_NR;
+  AES_set_decrypt_key(key, AES_KEYSIZE, ctx);
+}
+
+#endif
+
 #ifdef HAVE_HARDAES
+
+static void aes_setkey_dec(uint8_t *rk, const uint8_t *key)
+{
+  uint8_t rk_tmp[AES_RKSIZE];
+  aes_setkey_enc(rk_tmp, key);
+  aes_inverse_key(rk, rk_tmp);
+}
+
+#endif
+
+#if defined(HAVE_HARDAES) || defined(HAVE_ASM)
+
+#define HAVE_ACC 1
+
 /*
  * AESNI-CBC buffer encryption/decryption
  */
@@ -204,11 +290,11 @@ static void aes_crypt_cbc( int mode,
     }
 }
 
-#endif /* HAVE_HARDAES */
+#endif /* HAVE_HARDAES or HAVE_ASM */
 
 int AESACC_supported(void)
 {
-#if defined(HAVE_HARDAES)
+#if defined(HAVE_ACC)
   return aes_supported();
 #else
   return 0;
@@ -217,7 +303,7 @@ int AESACC_supported(void)
 
 void AESACC_CBC_encrypt_buffer(uint8_t* output, uint8_t* input, uint32_t length, const uint8_t* key, const uint8_t* iv)
 {
-#if defined(HAVE_HARDAES)
+#if defined(HAVE_ACC)
   uint8_t iv_tmp[16];
   uint8_t rk[AES_RKSIZE];
 
@@ -240,10 +326,9 @@ void AESACC_CBC_encrypt_buffer(uint8_t* output, uint8_t* input, uint32_t length,
 
 void AESACC_CBC_decrypt_buffer(uint8_t* output, uint8_t* input, uint32_t length, const uint8_t* key, const uint8_t* iv)
 {
-#if defined(HAVE_HARDAES)
+#if defined(HAVE_ACC)
   uint8_t iv_tmp[16];
   uint8_t rk[AES_RKSIZE];
-  uint8_t rk_tmp[AES_RKSIZE];
 
   if (aes_supported())
   {
@@ -252,8 +337,7 @@ void AESACC_CBC_decrypt_buffer(uint8_t* output, uint8_t* input, uint32_t length,
       return;
     }
     memcpy(iv_tmp, iv, 16);
-    aes_setkey_enc(rk_tmp, key);
-    aes_inverse_key(rk, rk_tmp);
+    aes_setkey_dec(rk, key);
     aes_crypt_cbc(AES_DECRYPT, rk, \
                   length, iv_tmp, input, output);
     return;
@@ -265,7 +349,7 @@ void AESACC_CBC_decrypt_buffer(uint8_t* output, uint8_t* input, uint32_t length,
 
 void AESACC_ECB_encrypt(const uint8_t* input, const uint8_t* key, uint8_t* output, const uint32_t length)
 {
-#if defined(HAVE_HARDAES)
+#if defined(HAVE_ACC)
   uint8_t rk[AES_RKSIZE];
 
   if (aes_supported())
@@ -285,9 +369,8 @@ void AESACC_ECB_encrypt(const uint8_t* input, const uint8_t* key, uint8_t* outpu
 
 void AESACC_ECB_decrypt(const uint8_t* input, const uint8_t* key, uint8_t *output, const uint32_t length)
 {
-#if defined(HAVE_HARDAES)
+#if defined(HAVE_ACC)
   uint8_t rk[AES_RKSIZE];
-  uint8_t rk_tmp[AES_RKSIZE];
 
   if (aes_supported())
   {
@@ -295,8 +378,7 @@ void AESACC_ECB_decrypt(const uint8_t* input, const uint8_t* key, uint8_t *outpu
     {
       return;
     }
-    aes_setkey_enc(rk_tmp, key);
-    aes_inverse_key(rk, rk_tmp);
+    aes_setkey_dec(rk, key);
     aes_crypt_ecb(AES_NR, rk, AES_DECRYPT, input, output);
     return;
   }
diff --git a/lib/aesacc.h b/lib/aesacc.h
index 61012e6..afc36d0 100644
--- a/lib/aesacc.h
+++ b/lib/aesacc.h
@@ -3,10 +3,18 @@
 
 #include <stdint.h>
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 int AESACC_supported(void);
 void AESACC_ECB_encrypt(const uint8_t* input, const uint8_t* key, uint8_t *output, const uint32_t length);
 void AESACC_ECB_decrypt(const uint8_t* input, const uint8_t* key, uint8_t *output, const uint32_t length);
 void AESACC_CBC_encrypt_buffer(uint8_t* output, uint8_t* input, uint32_t length, const uint8_t* key, const uint8_t* iv);
 void AESACC_CBC_decrypt_buffer(uint8_t* output, uint8_t* input, uint32_t length, const uint8_t* key, const uint8_t* iv);
 
+#ifdef __cplusplus
+}
+#endif
+
 #endif /* _AESACC_H_ */
diff --git a/lib/asm/arm.S b/lib/asm/arm.S
new file mode 100644
index 0000000..fd752ba
--- /dev/null
+++ b/lib/asm/arm.S
@@ -0,0 +1,1194 @@
+@ Copyright 2007-2016 The OpenSSL Project Authors. All Rights Reserved.
+@
+@ Licensed under the OpenSSL license (the "License").  You may not use
+@ this file except in compliance with the License.  You can obtain a copy
+@ in the file LICENSE in the source distribution or at
+@ https://www.openssl.org/source/license.html
+
+
+@ ====================================================================
+@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+@ project. The module is, however, dual licensed under OpenSSL and
+@ CRYPTOGAMS licenses depending on where you obtain it. For further
+@ details see http://www.openssl.org/~appro/cryptogams/.
+@ ====================================================================
+
+@ AES for ARMv4
+
+@ January 2007.
+@
+@ Code uses single 1K S-box and is >2 times faster than code generated
+@ by gcc-3.4.1. This is thanks to unique feature of ARMv4 ISA, which
+@ allows to merge logical or arithmetic operation with shift or rotate
+@ in one instruction and emit combined result every cycle. The module
+@ is endian-neutral. The performance is ~42 cycles/byte for 128-bit
+@ key [on single-issue Xscale PXA250 core].
+
+@ May 2007.
+@
+@ AES_set_[en|de]crypt_key is added.
+
+@ July 2010.
+@
+@ Rescheduling for dual-issue pipeline resulted in 12% improvement on
+@ Cortex A8 core and ~25 cycles per byte processed with 128-bit key.
+
+@ February 2011.
+@
+@ Profiler-assisted and platform-specific optimization resulted in 16%
+@ improvement on Cortex A8 core and ~21.5 cycles per byte.
+
+#ifndef __KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+#endif
+
+.text
+#if defined(__thumb2__) && !defined(__APPLE__)
+.syntax	unified
+.thumb
+#else
+.code	32
+#undef __thumb2__
+#endif
+
+
+.align	5
+AES_Te:
+.word	0xc66363a5, 0xf87c7c84, 0xee777799, 0xf67b7b8d
+.word	0xfff2f20d, 0xd66b6bbd, 0xde6f6fb1, 0x91c5c554
+.word	0x60303050, 0x02010103, 0xce6767a9, 0x562b2b7d
+.word	0xe7fefe19, 0xb5d7d762, 0x4dababe6, 0xec76769a
+.word	0x8fcaca45, 0x1f82829d, 0x89c9c940, 0xfa7d7d87
+.word	0xeffafa15, 0xb25959eb, 0x8e4747c9, 0xfbf0f00b
+.word	0x41adadec, 0xb3d4d467, 0x5fa2a2fd, 0x45afafea
+.word	0x239c9cbf, 0x53a4a4f7, 0xe4727296, 0x9bc0c05b
+.word	0x75b7b7c2, 0xe1fdfd1c, 0x3d9393ae, 0x4c26266a
+.word	0x6c36365a, 0x7e3f3f41, 0xf5f7f702, 0x83cccc4f
+.word	0x6834345c, 0x51a5a5f4, 0xd1e5e534, 0xf9f1f108
+.word	0xe2717193, 0xabd8d873, 0x62313153, 0x2a15153f
+.word	0x0804040c, 0x95c7c752, 0x46232365, 0x9dc3c35e
+.word	0x30181828, 0x379696a1, 0x0a05050f, 0x2f9a9ab5
+.word	0x0e070709, 0x24121236, 0x1b80809b, 0xdfe2e23d
+.word	0xcdebeb26, 0x4e272769, 0x7fb2b2cd, 0xea75759f
+.word	0x1209091b, 0x1d83839e, 0x582c2c74, 0x341a1a2e
+.word	0x361b1b2d, 0xdc6e6eb2, 0xb45a5aee, 0x5ba0a0fb
+.word	0xa45252f6, 0x763b3b4d, 0xb7d6d661, 0x7db3b3ce
+.word	0x5229297b, 0xdde3e33e, 0x5e2f2f71, 0x13848497
+.word	0xa65353f5, 0xb9d1d168, 0x00000000, 0xc1eded2c
+.word	0x40202060, 0xe3fcfc1f, 0x79b1b1c8, 0xb65b5bed
+.word	0xd46a6abe, 0x8dcbcb46, 0x67bebed9, 0x7239394b
+.word	0x944a4ade, 0x984c4cd4, 0xb05858e8, 0x85cfcf4a
+.word	0xbbd0d06b, 0xc5efef2a, 0x4faaaae5, 0xedfbfb16
+.word	0x864343c5, 0x9a4d4dd7, 0x66333355, 0x11858594
+.word	0x8a4545cf, 0xe9f9f910, 0x04020206, 0xfe7f7f81
+.word	0xa05050f0, 0x783c3c44, 0x259f9fba, 0x4ba8a8e3
+.word	0xa25151f3, 0x5da3a3fe, 0x804040c0, 0x058f8f8a
+.word	0x3f9292ad, 0x219d9dbc, 0x70383848, 0xf1f5f504
+.word	0x63bcbcdf, 0x77b6b6c1, 0xafdada75, 0x42212163
+.word	0x20101030, 0xe5ffff1a, 0xfdf3f30e, 0xbfd2d26d
+.word	0x81cdcd4c, 0x180c0c14, 0x26131335, 0xc3ecec2f
+.word	0xbe5f5fe1, 0x359797a2, 0x884444cc, 0x2e171739
+.word	0x93c4c457, 0x55a7a7f2, 0xfc7e7e82, 0x7a3d3d47
+.word	0xc86464ac, 0xba5d5de7, 0x3219192b, 0xe6737395
+.word	0xc06060a0, 0x19818198, 0x9e4f4fd1, 0xa3dcdc7f
+.word	0x44222266, 0x542a2a7e, 0x3b9090ab, 0x0b888883
+.word	0x8c4646ca, 0xc7eeee29, 0x6bb8b8d3, 0x2814143c
+.word	0xa7dede79, 0xbc5e5ee2, 0x160b0b1d, 0xaddbdb76
+.word	0xdbe0e03b, 0x64323256, 0x743a3a4e, 0x140a0a1e
+.word	0x924949db, 0x0c06060a, 0x4824246c, 0xb85c5ce4
+.word	0x9fc2c25d, 0xbdd3d36e, 0x43acacef, 0xc46262a6
+.word	0x399191a8, 0x319595a4, 0xd3e4e437, 0xf279798b
+.word	0xd5e7e732, 0x8bc8c843, 0x6e373759, 0xda6d6db7
+.word	0x018d8d8c, 0xb1d5d564, 0x9c4e4ed2, 0x49a9a9e0
+.word	0xd86c6cb4, 0xac5656fa, 0xf3f4f407, 0xcfeaea25
+.word	0xca6565af, 0xf47a7a8e, 0x47aeaee9, 0x10080818
+.word	0x6fbabad5, 0xf0787888, 0x4a25256f, 0x5c2e2e72
+.word	0x381c1c24, 0x57a6a6f1, 0x73b4b4c7, 0x97c6c651
+.word	0xcbe8e823, 0xa1dddd7c, 0xe874749c, 0x3e1f1f21
+.word	0x964b4bdd, 0x61bdbddc, 0x0d8b8b86, 0x0f8a8a85
+.word	0xe0707090, 0x7c3e3e42, 0x71b5b5c4, 0xcc6666aa
+.word	0x904848d8, 0x06030305, 0xf7f6f601, 0x1c0e0e12
+.word	0xc26161a3, 0x6a35355f, 0xae5757f9, 0x69b9b9d0
+.word	0x17868691, 0x99c1c158, 0x3a1d1d27, 0x279e9eb9
+.word	0xd9e1e138, 0xebf8f813, 0x2b9898b3, 0x22111133
+.word	0xd26969bb, 0xa9d9d970, 0x078e8e89, 0x339494a7
+.word	0x2d9b9bb6, 0x3c1e1e22, 0x15878792, 0xc9e9e920
+.word	0x87cece49, 0xaa5555ff, 0x50282878, 0xa5dfdf7a
+.word	0x038c8c8f, 0x59a1a1f8, 0x09898980, 0x1a0d0d17
+.word	0x65bfbfda, 0xd7e6e631, 0x844242c6, 0xd06868b8
+.word	0x824141c3, 0x299999b0, 0x5a2d2d77, 0x1e0f0f11
+.word	0x7bb0b0cb, 0xa85454fc, 0x6dbbbbd6, 0x2c16163a
+@ Te4[256]
+.byte	0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
+.byte	0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76
+.byte	0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0
+.byte	0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0
+.byte	0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc
+.byte	0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15
+.byte	0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a
+.byte	0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75
+.byte	0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0
+.byte	0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84
+.byte	0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b
+.byte	0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf
+.byte	0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85
+.byte	0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8
+.byte	0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5
+.byte	0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2
+.byte	0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17
+.byte	0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73
+.byte	0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88
+.byte	0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb
+.byte	0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c
+.byte	0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79
+.byte	0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9
+.byte	0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08
+.byte	0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6
+.byte	0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a
+.byte	0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e
+.byte	0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e
+.byte	0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94
+.byte	0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf
+.byte	0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68
+.byte	0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16
+@ rcon[]
+.word	0x01000000, 0x02000000, 0x04000000, 0x08000000
+.word	0x10000000, 0x20000000, 0x40000000, 0x80000000
+.word	0x1B000000, 0x36000000, 0, 0, 0, 0, 0, 0
+
+
+@ void AES_encrypt(const unsigned char *in, unsigned char *out,
+@ 		 const AES_KEY *key) {
+.globl	AES_encrypt
+
+.align	5
+AES_encrypt:
+#ifndef	__thumb2__
+	sub	r3,pc,#8		@ AES_encrypt
+#else
+	adr	r3,AES_encrypt
+#endif
+	stmdb	sp!,{r1,r4-r12,lr}
+#ifdef	__APPLE__
+	adr	r10,AES_Te
+#else
+	sub	r10,r3,#AES_encrypt-AES_Te	@ Te
+#endif
+	mov	r12,r0		@ inp
+	mov	r11,r2
+#if __ARM_ARCH__<7
+	ldrb	r0,[r12,#3]	@ load input data in endian-neutral
+	ldrb	r4,[r12,#2]	@ manner...
+	ldrb	r5,[r12,#1]
+	ldrb	r6,[r12,#0]
+	orr	r0,r0,r4,lsl#8
+	ldrb	r1,[r12,#7]
+	orr	r0,r0,r5,lsl#16
+	ldrb	r4,[r12,#6]
+	orr	r0,r0,r6,lsl#24
+	ldrb	r5,[r12,#5]
+	ldrb	r6,[r12,#4]
+	orr	r1,r1,r4,lsl#8
+	ldrb	r2,[r12,#11]
+	orr	r1,r1,r5,lsl#16
+	ldrb	r4,[r12,#10]
+	orr	r1,r1,r6,lsl#24
+	ldrb	r5,[r12,#9]
+	ldrb	r6,[r12,#8]
+	orr	r2,r2,r4,lsl#8
+	ldrb	r3,[r12,#15]
+	orr	r2,r2,r5,lsl#16
+	ldrb	r4,[r12,#14]
+	orr	r2,r2,r6,lsl#24
+	ldrb	r5,[r12,#13]
+	ldrb	r6,[r12,#12]
+	orr	r3,r3,r4,lsl#8
+	orr	r3,r3,r5,lsl#16
+	orr	r3,r3,r6,lsl#24
+#else
+	ldr	r0,[r12,#0]
+	ldr	r1,[r12,#4]
+	ldr	r2,[r12,#8]
+	ldr	r3,[r12,#12]
+#ifdef __ARMEL__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+#endif
+#endif
+	bl	_armv4_AES_encrypt
+
+	ldr	r12,[sp],#4		@ pop out
+#if __ARM_ARCH__>=7
+#ifdef __ARMEL__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+#endif
+	str	r0,[r12,#0]
+	str	r1,[r12,#4]
+	str	r2,[r12,#8]
+	str	r3,[r12,#12]
+#else
+	mov	r4,r0,lsr#24		@ write output in endian-neutral
+	mov	r5,r0,lsr#16		@ manner...
+	mov	r6,r0,lsr#8
+	strb	r4,[r12,#0]
+	strb	r5,[r12,#1]
+	mov	r4,r1,lsr#24
+	strb	r6,[r12,#2]
+	mov	r5,r1,lsr#16
+	strb	r0,[r12,#3]
+	mov	r6,r1,lsr#8
+	strb	r4,[r12,#4]
+	strb	r5,[r12,#5]
+	mov	r4,r2,lsr#24
+	strb	r6,[r12,#6]
+	mov	r5,r2,lsr#16
+	strb	r1,[r12,#7]
+	mov	r6,r2,lsr#8
+	strb	r4,[r12,#8]
+	strb	r5,[r12,#9]
+	mov	r4,r3,lsr#24
+	strb	r6,[r12,#10]
+	mov	r5,r3,lsr#16
+	strb	r2,[r12,#11]
+	mov	r6,r3,lsr#8
+	strb	r4,[r12,#12]
+	strb	r5,[r12,#13]
+	strb	r6,[r12,#14]
+	strb	r3,[r12,#15]
+#endif
+#if __ARM_ARCH__>=5
+	ldmia	sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,pc}
+#else
+	ldmia	sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+
+
+
+.align	2
+_armv4_AES_encrypt:
+	str	lr,[sp,#-4]!		@ push lr
+	ldmia	r11!,{r4,r5,r6,r7}
+	eor	r0,r0,r4
+	ldr	r12,[r11,#240-16]
+	eor	r1,r1,r5
+	eor	r2,r2,r6
+	eor	r3,r3,r7
+	sub	r12,r12,#1
+	mov	lr,#255
+
+	and	r7,lr,r0
+	and	r8,lr,r0,lsr#8
+	and	r9,lr,r0,lsr#16
+	mov	r0,r0,lsr#24
+Lenc_loop:
+	ldr	r4,[r10,r7,lsl#2]	@ Te3[s0>>0]
+	and	r7,lr,r1,lsr#16	@ i0
+	ldr	r5,[r10,r8,lsl#2]	@ Te2[s0>>8]
+	and	r8,lr,r1
+	ldr	r6,[r10,r9,lsl#2]	@ Te1[s0>>16]
+	and	r9,lr,r1,lsr#8
+	ldr	r0,[r10,r0,lsl#2]	@ Te0[s0>>24]
+	mov	r1,r1,lsr#24
+
+	ldr	r7,[r10,r7,lsl#2]	@ Te1[s1>>16]
+	ldr	r8,[r10,r8,lsl#2]	@ Te3[s1>>0]
+	ldr	r9,[r10,r9,lsl#2]	@ Te2[s1>>8]
+	eor	r0,r0,r7,ror#8
+	ldr	r1,[r10,r1,lsl#2]	@ Te0[s1>>24]
+	and	r7,lr,r2,lsr#8	@ i0
+	eor	r5,r5,r8,ror#8
+	and	r8,lr,r2,lsr#16	@ i1
+	eor	r6,r6,r9,ror#8
+	and	r9,lr,r2
+	ldr	r7,[r10,r7,lsl#2]	@ Te2[s2>>8]
+	eor	r1,r1,r4,ror#24
+	ldr	r8,[r10,r8,lsl#2]	@ Te1[s2>>16]
+	mov	r2,r2,lsr#24
+
+	ldr	r9,[r10,r9,lsl#2]	@ Te3[s2>>0]
+	eor	r0,r0,r7,ror#16
+	ldr	r2,[r10,r2,lsl#2]	@ Te0[s2>>24]
+	and	r7,lr,r3		@ i0
+	eor	r1,r1,r8,ror#8
+	and	r8,lr,r3,lsr#8	@ i1
+	eor	r6,r6,r9,ror#16
+	and	r9,lr,r3,lsr#16	@ i2
+	ldr	r7,[r10,r7,lsl#2]	@ Te3[s3>>0]
+	eor	r2,r2,r5,ror#16
+	ldr	r8,[r10,r8,lsl#2]	@ Te2[s3>>8]
+	mov	r3,r3,lsr#24
+
+	ldr	r9,[r10,r9,lsl#2]	@ Te1[s3>>16]
+	eor	r0,r0,r7,ror#24
+	ldr	r7,[r11],#16
+	eor	r1,r1,r8,ror#16
+	ldr	r3,[r10,r3,lsl#2]	@ Te0[s3>>24]
+	eor	r2,r2,r9,ror#8
+	ldr	r4,[r11,#-12]
+	eor	r3,r3,r6,ror#8
+
+	ldr	r5,[r11,#-8]
+	eor	r0,r0,r7
+	ldr	r6,[r11,#-4]
+	and	r7,lr,r0
+	eor	r1,r1,r4
+	and	r8,lr,r0,lsr#8
+	eor	r2,r2,r5
+	and	r9,lr,r0,lsr#16
+	eor	r3,r3,r6
+	mov	r0,r0,lsr#24
+
+	subs	r12,r12,#1
+	bne	Lenc_loop
+
+	add	r10,r10,#2
+
+	ldrb	r4,[r10,r7,lsl#2]	@ Te4[s0>>0]
+	and	r7,lr,r1,lsr#16	@ i0
+	ldrb	r5,[r10,r8,lsl#2]	@ Te4[s0>>8]
+	and	r8,lr,r1
+	ldrb	r6,[r10,r9,lsl#2]	@ Te4[s0>>16]
+	and	r9,lr,r1,lsr#8
+	ldrb	r0,[r10,r0,lsl#2]	@ Te4[s0>>24]
+	mov	r1,r1,lsr#24
+
+	ldrb	r7,[r10,r7,lsl#2]	@ Te4[s1>>16]
+	ldrb	r8,[r10,r8,lsl#2]	@ Te4[s1>>0]
+	ldrb	r9,[r10,r9,lsl#2]	@ Te4[s1>>8]
+	eor	r0,r7,r0,lsl#8
+	ldrb	r1,[r10,r1,lsl#2]	@ Te4[s1>>24]
+	and	r7,lr,r2,lsr#8	@ i0
+	eor	r5,r8,r5,lsl#8
+	and	r8,lr,r2,lsr#16	@ i1
+	eor	r6,r9,r6,lsl#8
+	and	r9,lr,r2
+	ldrb	r7,[r10,r7,lsl#2]	@ Te4[s2>>8]
+	eor	r1,r4,r1,lsl#24
+	ldrb	r8,[r10,r8,lsl#2]	@ Te4[s2>>16]
+	mov	r2,r2,lsr#24
+
+	ldrb	r9,[r10,r9,lsl#2]	@ Te4[s2>>0]
+	eor	r0,r7,r0,lsl#8
+	ldrb	r2,[r10,r2,lsl#2]	@ Te4[s2>>24]
+	and	r7,lr,r3		@ i0
+	eor	r1,r1,r8,lsl#16
+	and	r8,lr,r3,lsr#8	@ i1
+	eor	r6,r9,r6,lsl#8
+	and	r9,lr,r3,lsr#16	@ i2
+	ldrb	r7,[r10,r7,lsl#2]	@ Te4[s3>>0]
+	eor	r2,r5,r2,lsl#24
+	ldrb	r8,[r10,r8,lsl#2]	@ Te4[s3>>8]
+	mov	r3,r3,lsr#24
+
+	ldrb	r9,[r10,r9,lsl#2]	@ Te4[s3>>16]
+	eor	r0,r7,r0,lsl#8
+	ldr	r7,[r11,#0]
+	ldrb	r3,[r10,r3,lsl#2]	@ Te4[s3>>24]
+	eor	r1,r1,r8,lsl#8
+	ldr	r4,[r11,#4]
+	eor	r2,r2,r9,lsl#16
+	ldr	r5,[r11,#8]
+	eor	r3,r6,r3,lsl#24
+	ldr	r6,[r11,#12]
+
+	eor	r0,r0,r7
+	eor	r1,r1,r4
+	eor	r2,r2,r5
+	eor	r3,r3,r6
+
+	sub	r10,r10,#2
+	ldr	pc,[sp],#4		@ pop and return
+
+
+.globl	AES_set_encrypt_key
+
+.align	5
+AES_set_encrypt_key:
+_armv4_AES_set_encrypt_key:
+#ifndef	__thumb2__
+	sub	r3,pc,#8		@ AES_set_encrypt_key
+#else
+	adr	r3,AES_set_encrypt_key
+#endif
+	teq	r0,#0
+#ifdef	__thumb2__
+	itt	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	moveq	r0,#-1
+	beq	Labrt
+	teq	r2,#0
+#ifdef	__thumb2__
+	itt	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	moveq	r0,#-1
+	beq	Labrt
+
+	teq	r1,#128
+	beq	Lok
+	teq	r1,#192
+	beq	Lok
+	teq	r1,#256
+#ifdef	__thumb2__
+	itt	ne			@ Thumb2 thing, sanity check in ARM
+#endif
+	movne	r0,#-1
+	bne	Labrt
+
+Lok:	stmdb	sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr}
+	mov	r12,r0		@ inp
+	mov	lr,r1			@ bits
+	mov	r11,r2			@ key
+
+#ifdef	__APPLE__
+	adr	r10,AES_Te+1024				@ Te4
+#else
+	sub	r10,r3,#_armv4_AES_set_encrypt_key-AES_Te-1024	@ Te4
+#endif
+
+#if __ARM_ARCH__<7
+	ldrb	r0,[r12,#3]	@ load input data in endian-neutral
+	ldrb	r4,[r12,#2]	@ manner...
+	ldrb	r5,[r12,#1]
+	ldrb	r6,[r12,#0]
+	orr	r0,r0,r4,lsl#8
+	ldrb	r1,[r12,#7]
+	orr	r0,r0,r5,lsl#16
+	ldrb	r4,[r12,#6]
+	orr	r0,r0,r6,lsl#24
+	ldrb	r5,[r12,#5]
+	ldrb	r6,[r12,#4]
+	orr	r1,r1,r4,lsl#8
+	ldrb	r2,[r12,#11]
+	orr	r1,r1,r5,lsl#16
+	ldrb	r4,[r12,#10]
+	orr	r1,r1,r6,lsl#24
+	ldrb	r5,[r12,#9]
+	ldrb	r6,[r12,#8]
+	orr	r2,r2,r4,lsl#8
+	ldrb	r3,[r12,#15]
+	orr	r2,r2,r5,lsl#16
+	ldrb	r4,[r12,#14]
+	orr	r2,r2,r6,lsl#24
+	ldrb	r5,[r12,#13]
+	ldrb	r6,[r12,#12]
+	orr	r3,r3,r4,lsl#8
+	str	r0,[r11],#16
+	orr	r3,r3,r5,lsl#16
+	str	r1,[r11,#-12]
+	orr	r3,r3,r6,lsl#24
+	str	r2,[r11,#-8]
+	str	r3,[r11,#-4]
+#else
+	ldr	r0,[r12,#0]
+	ldr	r1,[r12,#4]
+	ldr	r2,[r12,#8]
+	ldr	r3,[r12,#12]
+#ifdef __ARMEL__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+#endif
+	str	r0,[r11],#16
+	str	r1,[r11,#-12]
+	str	r2,[r11,#-8]
+	str	r3,[r11,#-4]
+#endif
+
+	teq	lr,#128
+	bne	Lnot128
+	mov	r12,#10
+	str	r12,[r11,#240-16]
+	add	r6,r10,#256			@ rcon
+	mov	lr,#255
+
+L128_loop:
+	and	r5,lr,r3,lsr#24
+	and	r7,lr,r3,lsr#16
+	ldrb	r5,[r10,r5]
+	and	r8,lr,r3,lsr#8
+	ldrb	r7,[r10,r7]
+	and	r9,lr,r3
+	ldrb	r8,[r10,r8]
+	orr	r5,r5,r7,lsl#24
+	ldrb	r9,[r10,r9]
+	orr	r5,r5,r8,lsl#16
+	ldr	r4,[r6],#4			@ rcon[i++]
+	orr	r5,r5,r9,lsl#8
+	eor	r5,r5,r4
+	eor	r0,r0,r5			@ rk[4]=rk[0]^...
+	eor	r1,r1,r0			@ rk[5]=rk[1]^rk[4]
+	str	r0,[r11],#16
+	eor	r2,r2,r1			@ rk[6]=rk[2]^rk[5]
+	str	r1,[r11,#-12]
+	eor	r3,r3,r2			@ rk[7]=rk[3]^rk[6]
+	str	r2,[r11,#-8]
+	subs	r12,r12,#1
+	str	r3,[r11,#-4]
+	bne	L128_loop
+	sub	r2,r11,#176
+	b	Ldone
+
+Lnot128:
+#if __ARM_ARCH__<7
+	ldrb	r8,[r12,#19]
+	ldrb	r4,[r12,#18]
+	ldrb	r5,[r12,#17]
+	ldrb	r6,[r12,#16]
+	orr	r8,r8,r4,lsl#8
+	ldrb	r9,[r12,#23]
+	orr	r8,r8,r5,lsl#16
+	ldrb	r4,[r12,#22]
+	orr	r8,r8,r6,lsl#24
+	ldrb	r5,[r12,#21]
+	ldrb	r6,[r12,#20]
+	orr	r9,r9,r4,lsl#8
+	orr	r9,r9,r5,lsl#16
+	str	r8,[r11],#8
+	orr	r9,r9,r6,lsl#24
+	str	r9,[r11,#-4]
+#else
+	ldr	r8,[r12,#16]
+	ldr	r9,[r12,#20]
+#ifdef __ARMEL__
+	rev	r8,r8
+	rev	r9,r9
+#endif
+	str	r8,[r11],#8
+	str	r9,[r11,#-4]
+#endif
+
+	teq	lr,#192
+	bne	Lnot192
+	mov	r12,#12
+	str	r12,[r11,#240-24]
+	add	r6,r10,#256			@ rcon
+	mov	lr,#255
+	mov	r12,#8
+
+L192_loop:
+	and	r5,lr,r9,lsr#24
+	and	r7,lr,r9,lsr#16
+	ldrb	r5,[r10,r5]
+	and	r8,lr,r9,lsr#8
+	ldrb	r7,[r10,r7]
+	and	r9,lr,r9
+	ldrb	r8,[r10,r8]
+	orr	r5,r5,r7,lsl#24
+	ldrb	r9,[r10,r9]
+	orr	r5,r5,r8,lsl#16
+	ldr	r4,[r6],#4			@ rcon[i++]
+	orr	r5,r5,r9,lsl#8
+	eor	r9,r5,r4
+	eor	r0,r0,r9			@ rk[6]=rk[0]^...
+	eor	r1,r1,r0			@ rk[7]=rk[1]^rk[6]
+	str	r0,[r11],#24
+	eor	r2,r2,r1			@ rk[8]=rk[2]^rk[7]
+	str	r1,[r11,#-20]
+	eor	r3,r3,r2			@ rk[9]=rk[3]^rk[8]
+	str	r2,[r11,#-16]
+	subs	r12,r12,#1
+	str	r3,[r11,#-12]
+#ifdef	__thumb2__
+	itt	eq				@ Thumb2 thing, sanity check in ARM
+#endif
+	subeq	r2,r11,#216
+	beq	Ldone
+
+	ldr	r7,[r11,#-32]
+	ldr	r8,[r11,#-28]
+	eor	r7,r7,r3			@ rk[10]=rk[4]^rk[9]
+	eor	r9,r8,r7			@ rk[11]=rk[5]^rk[10]
+	str	r7,[r11,#-8]
+	str	r9,[r11,#-4]
+	b	L192_loop
+
+Lnot192:
+#if __ARM_ARCH__<7
+	ldrb	r8,[r12,#27]
+	ldrb	r4,[r12,#26]
+	ldrb	r5,[r12,#25]
+	ldrb	r6,[r12,#24]
+	orr	r8,r8,r4,lsl#8
+	ldrb	r9,[r12,#31]
+	orr	r8,r8,r5,lsl#16
+	ldrb	r4,[r12,#30]
+	orr	r8,r8,r6,lsl#24
+	ldrb	r5,[r12,#29]
+	ldrb	r6,[r12,#28]
+	orr	r9,r9,r4,lsl#8
+	orr	r9,r9,r5,lsl#16
+	str	r8,[r11],#8
+	orr	r9,r9,r6,lsl#24
+	str	r9,[r11,#-4]
+#else
+	ldr	r8,[r12,#24]
+	ldr	r9,[r12,#28]
+#ifdef __ARMEL__
+	rev	r8,r8
+	rev	r9,r9
+#endif
+	str	r8,[r11],#8
+	str	r9,[r11,#-4]
+#endif
+
+	mov	r12,#14
+	str	r12,[r11,#240-32]
+	add	r6,r10,#256			@ rcon
+	mov	lr,#255
+	mov	r12,#7
+
+L256_loop:
+	and	r5,lr,r9,lsr#24
+	and	r7,lr,r9,lsr#16
+	ldrb	r5,[r10,r5]
+	and	r8,lr,r9,lsr#8
+	ldrb	r7,[r10,r7]
+	and	r9,lr,r9
+	ldrb	r8,[r10,r8]
+	orr	r5,r5,r7,lsl#24
+	ldrb	r9,[r10,r9]
+	orr	r5,r5,r8,lsl#16
+	ldr	r4,[r6],#4			@ rcon[i++]
+	orr	r5,r5,r9,lsl#8
+	eor	r9,r5,r4
+	eor	r0,r0,r9			@ rk[8]=rk[0]^...
+	eor	r1,r1,r0			@ rk[9]=rk[1]^rk[8]
+	str	r0,[r11],#32
+	eor	r2,r2,r1			@ rk[10]=rk[2]^rk[9]
+	str	r1,[r11,#-28]
+	eor	r3,r3,r2			@ rk[11]=rk[3]^rk[10]
+	str	r2,[r11,#-24]
+	subs	r12,r12,#1
+	str	r3,[r11,#-20]
+#ifdef	__thumb2__
+	itt	eq				@ Thumb2 thing, sanity check in ARM
+#endif
+	subeq	r2,r11,#256
+	beq	Ldone
+
+	and	r5,lr,r3
+	and	r7,lr,r3,lsr#8
+	ldrb	r5,[r10,r5]
+	and	r8,lr,r3,lsr#16
+	ldrb	r7,[r10,r7]
+	and	r9,lr,r3,lsr#24
+	ldrb	r8,[r10,r8]
+	orr	r5,r5,r7,lsl#8
+	ldrb	r9,[r10,r9]
+	orr	r5,r5,r8,lsl#16
+	ldr	r4,[r11,#-48]
+	orr	r5,r5,r9,lsl#24
+
+	ldr	r7,[r11,#-44]
+	ldr	r8,[r11,#-40]
+	eor	r4,r4,r5			@ rk[12]=rk[4]^...
+	ldr	r9,[r11,#-36]
+	eor	r7,r7,r4			@ rk[13]=rk[5]^rk[12]
+	str	r4,[r11,#-16]
+	eor	r8,r8,r7			@ rk[14]=rk[6]^rk[13]
+	str	r7,[r11,#-12]
+	eor	r9,r9,r8			@ rk[15]=rk[7]^rk[14]
+	str	r8,[r11,#-8]
+	str	r9,[r11,#-4]
+	b	L256_loop
+
+.align	2
+Ldone:	mov	r0,#0
+	ldmia	sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr}
+Labrt:
+#if __ARM_ARCH__>=5
+	bx	lr				@ .word	0xe12fff1e
+#else
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+
+
+.globl	AES_set_decrypt_key
+
+.align	5
+AES_set_decrypt_key:
+	str	lr,[sp,#-4]!            @ push lr
+	bl	_armv4_AES_set_encrypt_key
+	teq	r0,#0
+	ldr	lr,[sp],#4              @ pop lr
+	bne	Labrt
+
+	mov	r0,r2			@ AES_set_encrypt_key preserves r2,
+	mov	r1,r2			@ which is AES_KEY *key
+	b	_armv4_AES_set_enc2dec_key
+
+
+@ void AES_set_enc2dec_key(const AES_KEY *inp,AES_KEY *out)
+.globl	AES_set_enc2dec_key
+
+.align	5
+AES_set_enc2dec_key:
+_armv4_AES_set_enc2dec_key:
+	stmdb	sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr}
+
+	ldr	r12,[r0,#240]
+	mov	r7,r0			@ input
+	add	r8,r0,r12,lsl#4
+	mov	r11,r1			@ output
+	add	r10,r1,r12,lsl#4
+	str	r12,[r1,#240]
+
+Linv:	ldr	r0,[r7],#16
+	ldr	r1,[r7,#-12]
+	ldr	r2,[r7,#-8]
+	ldr	r3,[r7,#-4]
+	ldr	r4,[r8],#-16
+	ldr	r5,[r8,#16+4]
+	ldr	r6,[r8,#16+8]
+	ldr	r9,[r8,#16+12]
+	str	r0,[r10],#-16
+	str	r1,[r10,#16+4]
+	str	r2,[r10,#16+8]
+	str	r3,[r10,#16+12]
+	str	r4,[r11],#16
+	str	r5,[r11,#-12]
+	str	r6,[r11,#-8]
+	str	r9,[r11,#-4]
+	teq	r7,r8
+	bne	Linv
+
+	ldr	r0,[r7]
+	ldr	r1,[r7,#4]
+	ldr	r2,[r7,#8]
+	ldr	r3,[r7,#12]
+	str	r0,[r11]
+	str	r1,[r11,#4]
+	str	r2,[r11,#8]
+	str	r3,[r11,#12]
+	sub	r11,r11,r12,lsl#3
+	ldr	r0,[r11,#16]!		@ prefetch tp1
+	mov	r7,#0x80
+	mov	r8,#0x1b
+	orr	r7,r7,#0x8000
+	orr	r8,r8,#0x1b00
+	orr	r7,r7,r7,lsl#16
+	orr	r8,r8,r8,lsl#16
+	sub	r12,r12,#1
+	mvn	r9,r7
+	mov	r12,r12,lsl#2	@ (rounds-1)*4
+
+Lmix:	and	r4,r0,r7
+	and	r1,r0,r9
+	sub	r4,r4,r4,lsr#7
+	and	r4,r4,r8
+	eor	r1,r4,r1,lsl#1	@ tp2
+
+	and	r4,r1,r7
+	and	r2,r1,r9
+	sub	r4,r4,r4,lsr#7
+	and	r4,r4,r8
+	eor	r2,r4,r2,lsl#1	@ tp4
+
+	and	r4,r2,r7
+	and	r3,r2,r9
+	sub	r4,r4,r4,lsr#7
+	and	r4,r4,r8
+	eor	r3,r4,r3,lsl#1	@ tp8
+
+	eor	r4,r1,r2
+	eor	r5,r0,r3		@ tp9
+	eor	r4,r4,r3		@ tpe
+	eor	r4,r4,r1,ror#24
+	eor	r4,r4,r5,ror#24	@ ^= ROTATE(tpb=tp9^tp2,8)
+	eor	r4,r4,r2,ror#16
+	eor	r4,r4,r5,ror#16	@ ^= ROTATE(tpd=tp9^tp4,16)
+	eor	r4,r4,r5,ror#8	@ ^= ROTATE(tp9,24)
+
+	ldr	r0,[r11,#4]		@ prefetch tp1
+	str	r4,[r11],#4
+	subs	r12,r12,#1
+	bne	Lmix
+
+	mov	r0,#0
+#if __ARM_ARCH__>=5
+	ldmia	sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,pc}
+#else
+	ldmia	sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+
+
+
+.align	5
+AES_Td:
+.word	0x51f4a750, 0x7e416553, 0x1a17a4c3, 0x3a275e96
+.word	0x3bab6bcb, 0x1f9d45f1, 0xacfa58ab, 0x4be30393
+.word	0x2030fa55, 0xad766df6, 0x88cc7691, 0xf5024c25
+.word	0x4fe5d7fc, 0xc52acbd7, 0x26354480, 0xb562a38f
+.word	0xdeb15a49, 0x25ba1b67, 0x45ea0e98, 0x5dfec0e1
+.word	0xc32f7502, 0x814cf012, 0x8d4697a3, 0x6bd3f9c6
+.word	0x038f5fe7, 0x15929c95, 0xbf6d7aeb, 0x955259da
+.word	0xd4be832d, 0x587421d3, 0x49e06929, 0x8ec9c844
+.word	0x75c2896a, 0xf48e7978, 0x99583e6b, 0x27b971dd
+.word	0xbee14fb6, 0xf088ad17, 0xc920ac66, 0x7dce3ab4
+.word	0x63df4a18, 0xe51a3182, 0x97513360, 0x62537f45
+.word	0xb16477e0, 0xbb6bae84, 0xfe81a01c, 0xf9082b94
+.word	0x70486858, 0x8f45fd19, 0x94de6c87, 0x527bf8b7
+.word	0xab73d323, 0x724b02e2, 0xe31f8f57, 0x6655ab2a
+.word	0xb2eb2807, 0x2fb5c203, 0x86c57b9a, 0xd33708a5
+.word	0x302887f2, 0x23bfa5b2, 0x02036aba, 0xed16825c
+.word	0x8acf1c2b, 0xa779b492, 0xf307f2f0, 0x4e69e2a1
+.word	0x65daf4cd, 0x0605bed5, 0xd134621f, 0xc4a6fe8a
+.word	0x342e539d, 0xa2f355a0, 0x058ae132, 0xa4f6eb75
+.word	0x0b83ec39, 0x4060efaa, 0x5e719f06, 0xbd6e1051
+.word	0x3e218af9, 0x96dd063d, 0xdd3e05ae, 0x4de6bd46
+.word	0x91548db5, 0x71c45d05, 0x0406d46f, 0x605015ff
+.word	0x1998fb24, 0xd6bde997, 0x894043cc, 0x67d99e77
+.word	0xb0e842bd, 0x07898b88, 0xe7195b38, 0x79c8eedb
+.word	0xa17c0a47, 0x7c420fe9, 0xf8841ec9, 0x00000000
+.word	0x09808683, 0x322bed48, 0x1e1170ac, 0x6c5a724e
+.word	0xfd0efffb, 0x0f853856, 0x3daed51e, 0x362d3927
+.word	0x0a0fd964, 0x685ca621, 0x9b5b54d1, 0x24362e3a
+.word	0x0c0a67b1, 0x9357e70f, 0xb4ee96d2, 0x1b9b919e
+.word	0x80c0c54f, 0x61dc20a2, 0x5a774b69, 0x1c121a16
+.word	0xe293ba0a, 0xc0a02ae5, 0x3c22e043, 0x121b171d
+.word	0x0e090d0b, 0xf28bc7ad, 0x2db6a8b9, 0x141ea9c8
+.word	0x57f11985, 0xaf75074c, 0xee99ddbb, 0xa37f60fd
+.word	0xf701269f, 0x5c72f5bc, 0x44663bc5, 0x5bfb7e34
+.word	0x8b432976, 0xcb23c6dc, 0xb6edfc68, 0xb8e4f163
+.word	0xd731dcca, 0x42638510, 0x13972240, 0x84c61120
+.word	0x854a247d, 0xd2bb3df8, 0xaef93211, 0xc729a16d
+.word	0x1d9e2f4b, 0xdcb230f3, 0x0d8652ec, 0x77c1e3d0
+.word	0x2bb3166c, 0xa970b999, 0x119448fa, 0x47e96422
+.word	0xa8fc8cc4, 0xa0f03f1a, 0x567d2cd8, 0x223390ef
+.word	0x87494ec7, 0xd938d1c1, 0x8ccaa2fe, 0x98d40b36
+.word	0xa6f581cf, 0xa57ade28, 0xdab78e26, 0x3fadbfa4
+.word	0x2c3a9de4, 0x5078920d, 0x6a5fcc9b, 0x547e4662
+.word	0xf68d13c2, 0x90d8b8e8, 0x2e39f75e, 0x82c3aff5
+.word	0x9f5d80be, 0x69d0937c, 0x6fd52da9, 0xcf2512b3
+.word	0xc8ac993b, 0x10187da7, 0xe89c636e, 0xdb3bbb7b
+.word	0xcd267809, 0x6e5918f4, 0xec9ab701, 0x834f9aa8
+.word	0xe6956e65, 0xaaffe67e, 0x21bccf08, 0xef15e8e6
+.word	0xbae79bd9, 0x4a6f36ce, 0xea9f09d4, 0x29b07cd6
+.word	0x31a4b2af, 0x2a3f2331, 0xc6a59430, 0x35a266c0
+.word	0x744ebc37, 0xfc82caa6, 0xe090d0b0, 0x33a7d815
+.word	0xf104984a, 0x41ecdaf7, 0x7fcd500e, 0x1791f62f
+.word	0x764dd68d, 0x43efb04d, 0xccaa4d54, 0xe49604df
+.word	0x9ed1b5e3, 0x4c6a881b, 0xc12c1fb8, 0x4665517f
+.word	0x9d5eea04, 0x018c355d, 0xfa877473, 0xfb0b412e
+.word	0xb3671d5a, 0x92dbd252, 0xe9105633, 0x6dd64713
+.word	0x9ad7618c, 0x37a10c7a, 0x59f8148e, 0xeb133c89
+.word	0xcea927ee, 0xb761c935, 0xe11ce5ed, 0x7a47b13c
+.word	0x9cd2df59, 0x55f2733f, 0x1814ce79, 0x73c737bf
+.word	0x53f7cdea, 0x5ffdaa5b, 0xdf3d6f14, 0x7844db86
+.word	0xcaaff381, 0xb968c43e, 0x3824342c, 0xc2a3405f
+.word	0x161dc372, 0xbce2250c, 0x283c498b, 0xff0d9541
+.word	0x39a80171, 0x080cb3de, 0xd8b4e49c, 0x6456c190
+.word	0x7bcb8461, 0xd532b670, 0x486c5c74, 0xd0b85742
+@ Td4[256]
+.byte	0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
+.byte	0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
+.byte	0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
+.byte	0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
+.byte	0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
+.byte	0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
+.byte	0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
+.byte	0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
+.byte	0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
+.byte	0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
+.byte	0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
+.byte	0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
+.byte	0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
+.byte	0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
+.byte	0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
+.byte	0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
+.byte	0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
+.byte	0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
+.byte	0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
+.byte	0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
+.byte	0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
+.byte	0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
+.byte	0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
+.byte	0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
+.byte	0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
+.byte	0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
+.byte	0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
+.byte	0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
+.byte	0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
+.byte	0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
+.byte	0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
+.byte	0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
+
+
+@ void AES_decrypt(const unsigned char *in, unsigned char *out,
+@ 		 const AES_KEY *key) {
+.globl	AES_decrypt
+
+.align	5
+AES_decrypt:
+#ifndef	__thumb2__
+	sub	r3,pc,#8		@ AES_decrypt
+#else
+	adr	r3,AES_decrypt
+#endif
+	stmdb	sp!,{r1,r4-r12,lr}
+#ifdef	__APPLE__
+	adr	r10,AES_Td
+#else
+	sub	r10,r3,#AES_decrypt-AES_Td	@ Td
+#endif
+	mov	r12,r0		@ inp
+	mov	r11,r2
+#if __ARM_ARCH__<7
+	ldrb	r0,[r12,#3]	@ load input data in endian-neutral
+	ldrb	r4,[r12,#2]	@ manner...
+	ldrb	r5,[r12,#1]
+	ldrb	r6,[r12,#0]
+	orr	r0,r0,r4,lsl#8
+	ldrb	r1,[r12,#7]
+	orr	r0,r0,r5,lsl#16
+	ldrb	r4,[r12,#6]
+	orr	r0,r0,r6,lsl#24
+	ldrb	r5,[r12,#5]
+	ldrb	r6,[r12,#4]
+	orr	r1,r1,r4,lsl#8
+	ldrb	r2,[r12,#11]
+	orr	r1,r1,r5,lsl#16
+	ldrb	r4,[r12,#10]
+	orr	r1,r1,r6,lsl#24
+	ldrb	r5,[r12,#9]
+	ldrb	r6,[r12,#8]
+	orr	r2,r2,r4,lsl#8
+	ldrb	r3,[r12,#15]
+	orr	r2,r2,r5,lsl#16
+	ldrb	r4,[r12,#14]
+	orr	r2,r2,r6,lsl#24
+	ldrb	r5,[r12,#13]
+	ldrb	r6,[r12,#12]
+	orr	r3,r3,r4,lsl#8
+	orr	r3,r3,r5,lsl#16
+	orr	r3,r3,r6,lsl#24
+#else
+	ldr	r0,[r12,#0]
+	ldr	r1,[r12,#4]
+	ldr	r2,[r12,#8]
+	ldr	r3,[r12,#12]
+#ifdef __ARMEL__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+#endif
+#endif
+	bl	_armv4_AES_decrypt
+
+	ldr	r12,[sp],#4		@ pop out
+#if __ARM_ARCH__>=7
+#ifdef __ARMEL__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+#endif
+	str	r0,[r12,#0]
+	str	r1,[r12,#4]
+	str	r2,[r12,#8]
+	str	r3,[r12,#12]
+#else
+	mov	r4,r0,lsr#24		@ write output in endian-neutral
+	mov	r5,r0,lsr#16		@ manner...
+	mov	r6,r0,lsr#8
+	strb	r4,[r12,#0]
+	strb	r5,[r12,#1]
+	mov	r4,r1,lsr#24
+	strb	r6,[r12,#2]
+	mov	r5,r1,lsr#16
+	strb	r0,[r12,#3]
+	mov	r6,r1,lsr#8
+	strb	r4,[r12,#4]
+	strb	r5,[r12,#5]
+	mov	r4,r2,lsr#24
+	strb	r6,[r12,#6]
+	mov	r5,r2,lsr#16
+	strb	r1,[r12,#7]
+	mov	r6,r2,lsr#8
+	strb	r4,[r12,#8]
+	strb	r5,[r12,#9]
+	mov	r4,r3,lsr#24
+	strb	r6,[r12,#10]
+	mov	r5,r3,lsr#16
+	strb	r2,[r12,#11]
+	mov	r6,r3,lsr#8
+	strb	r4,[r12,#12]
+	strb	r5,[r12,#13]
+	strb	r6,[r12,#14]
+	strb	r3,[r12,#15]
+#endif
+#if __ARM_ARCH__>=5
+	ldmia	sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,pc}
+#else
+	ldmia	sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+
+
+
+.align	2
+_armv4_AES_decrypt:
+	str	lr,[sp,#-4]!		@ push lr
+	ldmia	r11!,{r4,r5,r6,r7}
+	eor	r0,r0,r4
+	ldr	r12,[r11,#240-16]
+	eor	r1,r1,r5
+	eor	r2,r2,r6
+	eor	r3,r3,r7
+	sub	r12,r12,#1
+	mov	lr,#255
+
+	and	r7,lr,r0,lsr#16
+	and	r8,lr,r0,lsr#8
+	and	r9,lr,r0
+	mov	r0,r0,lsr#24
+Ldec_loop:
+	ldr	r4,[r10,r7,lsl#2]	@ Td1[s0>>16]
+	and	r7,lr,r1		@ i0
+	ldr	r5,[r10,r8,lsl#2]	@ Td2[s0>>8]
+	and	r8,lr,r1,lsr#16
+	ldr	r6,[r10,r9,lsl#2]	@ Td3[s0>>0]
+	and	r9,lr,r1,lsr#8
+	ldr	r0,[r10,r0,lsl#2]	@ Td0[s0>>24]
+	mov	r1,r1,lsr#24
+
+	ldr	r7,[r10,r7,lsl#2]	@ Td3[s1>>0]
+	ldr	r8,[r10,r8,lsl#2]	@ Td1[s1>>16]
+	ldr	r9,[r10,r9,lsl#2]	@ Td2[s1>>8]
+	eor	r0,r0,r7,ror#24
+	ldr	r1,[r10,r1,lsl#2]	@ Td0[s1>>24]
+	and	r7,lr,r2,lsr#8	@ i0
+	eor	r5,r8,r5,ror#8
+	and	r8,lr,r2		@ i1
+	eor	r6,r9,r6,ror#8
+	and	r9,lr,r2,lsr#16
+	ldr	r7,[r10,r7,lsl#2]	@ Td2[s2>>8]
+	eor	r1,r1,r4,ror#8
+	ldr	r8,[r10,r8,lsl#2]	@ Td3[s2>>0]
+	mov	r2,r2,lsr#24
+
+	ldr	r9,[r10,r9,lsl#2]	@ Td1[s2>>16]
+	eor	r0,r0,r7,ror#16
+	ldr	r2,[r10,r2,lsl#2]	@ Td0[s2>>24]
+	and	r7,lr,r3,lsr#16	@ i0
+	eor	r1,r1,r8,ror#24
+	and	r8,lr,r3,lsr#8	@ i1
+	eor	r6,r9,r6,ror#8
+	and	r9,lr,r3		@ i2
+	ldr	r7,[r10,r7,lsl#2]	@ Td1[s3>>16]
+	eor	r2,r2,r5,ror#8
+	ldr	r8,[r10,r8,lsl#2]	@ Td2[s3>>8]
+	mov	r3,r3,lsr#24
+
+	ldr	r9,[r10,r9,lsl#2]	@ Td3[s3>>0]
+	eor	r0,r0,r7,ror#8
+	ldr	r7,[r11],#16
+	eor	r1,r1,r8,ror#16
+	ldr	r3,[r10,r3,lsl#2]	@ Td0[s3>>24]
+	eor	r2,r2,r9,ror#24
+
+	ldr	r4,[r11,#-12]
+	eor	r0,r0,r7
+	ldr	r5,[r11,#-8]
+	eor	r3,r3,r6,ror#8
+	ldr	r6,[r11,#-4]
+	and	r7,lr,r0,lsr#16
+	eor	r1,r1,r4
+	and	r8,lr,r0,lsr#8
+	eor	r2,r2,r5
+	and	r9,lr,r0
+	eor	r3,r3,r6
+	mov	r0,r0,lsr#24
+
+	subs	r12,r12,#1
+	bne	Ldec_loop
+
+	add	r10,r10,#1024
+
+	ldr	r5,[r10,#0]		@ prefetch Td4
+	ldr	r6,[r10,#32]
+	ldr	r4,[r10,#64]
+	ldr	r5,[r10,#96]
+	ldr	r6,[r10,#128]
+	ldr	r4,[r10,#160]
+	ldr	r5,[r10,#192]
+	ldr	r6,[r10,#224]
+
+	ldrb	r0,[r10,r0]		@ Td4[s0>>24]
+	ldrb	r4,[r10,r7]		@ Td4[s0>>16]
+	and	r7,lr,r1		@ i0
+	ldrb	r5,[r10,r8]		@ Td4[s0>>8]
+	and	r8,lr,r1,lsr#16
+	ldrb	r6,[r10,r9]		@ Td4[s0>>0]
+	and	r9,lr,r1,lsr#8
+
+	add	r1,r10,r1,lsr#24
+	ldrb	r7,[r10,r7]		@ Td4[s1>>0]
+	ldrb	r1,[r1]		@ Td4[s1>>24]
+	ldrb	r8,[r10,r8]		@ Td4[s1>>16]
+	eor	r0,r7,r0,lsl#24
+	ldrb	r9,[r10,r9]		@ Td4[s1>>8]
+	eor	r1,r4,r1,lsl#8
+	and	r7,lr,r2,lsr#8	@ i0
+	eor	r5,r5,r8,lsl#8
+	and	r8,lr,r2		@ i1
+	ldrb	r7,[r10,r7]		@ Td4[s2>>8]
+	eor	r6,r6,r9,lsl#8
+	ldrb	r8,[r10,r8]		@ Td4[s2>>0]
+	and	r9,lr,r2,lsr#16
+
+	add	r2,r10,r2,lsr#24
+	ldrb	r2,[r2]		@ Td4[s2>>24]
+	eor	r0,r0,r7,lsl#8
+	ldrb	r9,[r10,r9]		@ Td4[s2>>16]
+	eor	r1,r8,r1,lsl#16
+	and	r7,lr,r3,lsr#16	@ i0
+	eor	r2,r5,r2,lsl#16
+	and	r8,lr,r3,lsr#8	@ i1
+	ldrb	r7,[r10,r7]		@ Td4[s3>>16]
+	eor	r6,r6,r9,lsl#16
+	ldrb	r8,[r10,r8]		@ Td4[s3>>8]
+	and	r9,lr,r3		@ i2
+
+	add	r3,r10,r3,lsr#24
+	ldrb	r9,[r10,r9]		@ Td4[s3>>0]
+	ldrb	r3,[r3]		@ Td4[s3>>24]
+	eor	r0,r0,r7,lsl#16
+	ldr	r7,[r11,#0]
+	eor	r1,r1,r8,lsl#8
+	ldr	r4,[r11,#4]
+	eor	r2,r9,r2,lsl#8
+	ldr	r5,[r11,#8]
+	eor	r3,r6,r3,lsl#24
+	ldr	r6,[r11,#12]
+
+	eor	r0,r0,r7
+	eor	r1,r1,r4
+	eor	r2,r2,r5
+	eor	r3,r3,r6
+
+	sub	r10,r10,#1024
+	ldr	pc,[sp],#4		@ pop and return
+
+.byte	65,69,83,32,102,111,114,32,65,82,77,118,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
+.align	2
+.align	2
diff --git a/lib/asm/arm_arch.h b/lib/asm/arm_arch.h
new file mode 100644
index 0000000..3fc9e69
--- /dev/null
+++ b/lib/asm/arm_arch.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright 2011-2016 The OpenSSL Project Authors. All Rights Reserved.
+ *
+ * Licensed under the OpenSSL license (the "License").  You may not use
+ * this file except in compliance with the License.  You can obtain a copy
+ * in the file LICENSE in the source distribution or at
+ * https://www.openssl.org/source/license.html
+ */
+
+#ifndef __ARM_ARCH_H__
+# define __ARM_ARCH_H__
+
+# if !defined(__ARM_ARCH__)
+#  if defined(__CC_ARM)
+#   define __ARM_ARCH__ __TARGET_ARCH_ARM
+#   if defined(__BIG_ENDIAN)
+#    define __ARMEB__
+#   else
+#    define __ARMEL__
+#   endif
+#  elif defined(__GNUC__)
+#   if   defined(__aarch64__)
+#    define __ARM_ARCH__ 8
+#    if __BYTE_ORDER__==__ORDER_BIG_ENDIAN__
+#     define __ARMEB__
+#    else
+#     define __ARMEL__
+#    endif
+  /*
+   * Why doesn't gcc define __ARM_ARCH__? Instead it defines
+   * bunch of below macros. See all_architectires[] table in
+   * gcc/config/arm/arm.c. On a side note it defines
+   * __ARMEL__/__ARMEB__ for little-/big-endian.
+   */
+#   elif defined(__ARM_ARCH)
+#    define __ARM_ARCH__ __ARM_ARCH
+#   elif defined(__ARM_ARCH_8A__)
+#    define __ARM_ARCH__ 8
+#   elif defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__)     || \
+        defined(__ARM_ARCH_7R__)|| defined(__ARM_ARCH_7M__)     || \
+        defined(__ARM_ARCH_7EM__)
+#    define __ARM_ARCH__ 7
+#   elif defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__)     || \
+        defined(__ARM_ARCH_6K__)|| defined(__ARM_ARCH_6M__)     || \
+        defined(__ARM_ARCH_6Z__)|| defined(__ARM_ARCH_6ZK__)    || \
+        defined(__ARM_ARCH_6T2__)
+#    define __ARM_ARCH__ 6
+#   elif defined(__ARM_ARCH_5__) || defined(__ARM_ARCH_5T__)     || \
+        defined(__ARM_ARCH_5E__)|| defined(__ARM_ARCH_5TE__)    || \
+        defined(__ARM_ARCH_5TEJ__)
+#    define __ARM_ARCH__ 5
+#   elif defined(__ARM_ARCH_4__) || defined(__ARM_ARCH_4T__)
+#    define __ARM_ARCH__ 4
+#   else
+#    error "unsupported ARM architecture"
+#   endif
+#  endif
+# endif
+
+# if !defined(__ARM_MAX_ARCH__)
+#  define __ARM_MAX_ARCH__ __ARM_ARCH__
+# endif
+
+# if __ARM_MAX_ARCH__<__ARM_ARCH__
+#  error "__ARM_MAX_ARCH__ can't be less than __ARM_ARCH__"
+# elif __ARM_MAX_ARCH__!=__ARM_ARCH__
+#  if __ARM_ARCH__<7 && __ARM_MAX_ARCH__>=7 && defined(__ARMEB__)
+#   error "can't build universal big-endian binary"
+#  endif
+# endif
+
+# if !__ASSEMBLER__
+extern unsigned int OPENSSL_armcap_P;
+# endif
+
+# define ARMV7_NEON      (1<<0)
+# define ARMV7_TICK      (1<<1)
+# define ARMV8_AES       (1<<2)
+# define ARMV8_SHA1      (1<<3)
+# define ARMV8_SHA256    (1<<4)
+# define ARMV8_PMULL     (1<<5)
+
+#endif
diff --git a/lib/asm/mips.S b/lib/asm/mips.S
new file mode 100644
index 0000000..4aa0e4c
--- /dev/null
+++ b/lib/asm/mips.S
@@ -0,0 +1,1835 @@
+.text
+#ifdef OPENSSL_FIPSCANISTER
+# include <openssl/fipssyms.h>
+#endif
+
+#if defined(__mips_smartmips) && !defined(_MIPS_ARCH_MIPS32R2)
+#define _MIPS_ARCH_MIPS32R2
+#endif
+
+#if !defined(__mips_eabi) && (!defined(__vxworks) || defined(__pic__))
+.option	pic2
+#endif
+.set	noat
+.align	5
+.ent	_mips_AES_encrypt
+_mips_AES_encrypt:
+	.frame	$29,0,$31
+	.set	reorder
+	lw	$12,0($6)
+	lw	$13,4($6)
+	lw	$14,8($6)
+	lw	$15,12($6)
+	lw	$30,240($6)
+	add $3,$6,16
+
+	xor	$8,$12
+	xor	$9,$13
+	xor	$10,$14
+	xor	$11,$15
+
+	sub	$30,1
+#if defined(__mips_smartmips)
+	ext	$1,$9,8,8
+.Loop_enc:
+	ext	$2,$10,8,8
+	ext	$24,$11,8,8
+	ext	$25,$8,8,8
+	lwxs	$12,$1($7)		# Te1[s1>>16]
+	ext	$1,$10,16,8
+	lwxs	$13,$2($7)		# Te1[s2>>16]
+	ext	$2,$11,16,8
+	lwxs	$14,$24($7)		# Te1[s3>>16]
+	ext	$24,$8,16,8
+	lwxs	$15,$25($7)		# Te1[s0>>16]
+	ext	$25,$9,16,8
+
+	lwxs	$16,$1($7)		# Te2[s2>>8]
+	ext	$1,$11,24,8
+	lwxs	$17,$2($7)		# Te2[s3>>8]
+	ext	$2,$8,24,8
+	lwxs	$18,$24($7)		# Te2[s0>>8]
+	ext	$24,$9,24,8
+	lwxs	$19,$25($7)		# Te2[s1>>8]
+	ext	$25,$10,24,8
+
+	lwxs	$20,$1($7)		# Te3[s3]
+	ext	$1,$8,0,8
+	lwxs	$21,$2($7)		# Te3[s0]
+	ext	$2,$9,0,8
+	lwxs	$22,$24($7)		# Te3[s1]
+	ext	$24,$10,0,8
+	lwxs	$23,$25($7)		# Te3[s2]
+	ext	$25,$11,0,8
+
+	rotr	$12,$12,24
+	rotr	$13,$13,24
+	rotr	$14,$14,24
+	rotr	$15,$15,24
+
+	rotr	$16,$16,16
+	rotr	$17,$17,16
+	rotr	$18,$18,16
+	rotr	$19,$19,16
+
+	xor	$12,$16
+	lwxs	$16,$1($7)		# Te0[s0>>24]
+	xor	$13,$17
+	lwxs	$17,$2($7)		# Te0[s1>>24]
+	xor	$14,$18
+	lwxs	$18,$24($7)		# Te0[s2>>24]
+	xor	$15,$19
+	lwxs	$19,$25($7)		# Te0[s3>>24]
+
+	rotr	$20,$20,8
+	lw	$8,0($3)
+	rotr	$21,$21,8
+	lw	$9,4($3)
+	rotr	$22,$22,8
+	lw	$10,8($3)
+	rotr	$23,$23,8
+	lw	$11,12($3)
+
+	xor	$12,$20
+	xor	$13,$21
+	xor	$14,$22
+	xor	$15,$23
+
+	xor	$12,$16
+	xor	$13,$17
+	xor	$14,$18
+	xor	$15,$19
+
+	sub	$30,1
+	add $3,16
+	xor	$8,$12
+	xor	$9,$13
+	xor	$10,$14
+	xor	$11,$15
+	.set	noreorder
+	bnez	$30,.Loop_enc
+	ext	$1,$9,8,8
+
+	srl	$1,$9,6
+#else
+	srl	$1,$9,6
+.Loop_enc:
+	srl	$2,$10,6
+	srl	$24,$11,6
+	srl	$25,$8,6
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+#if defined(_MIPS_ARCH_MIPS32R2) || defined(_MIPS_ARCH_MIPS64R2)
+	lw	$12,0($1)		# Te1[s1>>16]
+	srl	$1,$10,14
+	lw	$13,0($2)		# Te1[s2>>16]
+	srl	$2,$11,14
+	lw	$14,0($24)		# Te1[s3>>16]
+	srl	$24,$8,14
+	lw	$15,0($25)		# Te1[s0>>16]
+	srl	$25,$9,14
+#else
+	lwl	$12,2($1)		# Te1[s1>>16]
+	lwl	$13,2($2)		# Te1[s2>>16]
+	lwl	$14,2($24)		# Te1[s3>>16]
+	lwl	$15,2($25)		# Te1[s0>>16]
+	lwr	$12,3($1)		# Te1[s1>>16]
+	srl	$1,$10,14
+	lwr	$13,3($2)		# Te1[s2>>16]
+	srl	$2,$11,14
+	lwr	$14,3($24)		# Te1[s3>>16]
+	srl	$24,$8,14
+	lwr	$15,3($25)		# Te1[s0>>16]
+	srl	$25,$9,14
+#endif
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+#if defined(_MIPS_ARCH_MIPS32R2) || defined(_MIPS_ARCH_MIPS64R2)
+	rotr	$12,$12,24
+	rotr	$13,$13,24
+	rotr	$14,$14,24
+	rotr	$15,$15,24
+# if defined(_MIPSEL)
+	lw	$16,0($1)		# Te2[s2>>8]
+	srl	$1,$11,22
+	lw	$17,0($2)		# Te2[s3>>8]
+	srl	$2,$8,22
+	lw	$18,0($24)		# Te2[s0>>8]
+	srl	$24,$9,22
+	lw	$19,0($25)		# Te2[s1>>8]
+	srl	$25,$10,22
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lw	$20,0($1)		# Te3[s3]
+	ins $1,$8,2,8
+	lw	$21,0($2)		# Te3[s0]
+	ins $2,$9,2,8
+	lw	$22,0($24)		# Te3[s1]
+	ins $24,$10,2,8
+	lw	$23,0($25)		# Te3[s2]
+	ins $25,$11,2,8
+# else
+	lw	$16,0($1)		# Te2[s2>>8]
+	ins $1,$11,2,8
+	lw	$17,0($2)		# Te2[s3>>8]
+	ins $2,$8,2,8
+	lw	$18,0($24)		# Te2[s0>>8]
+	ins $24,$9,2,8
+	lw	$19,0($25)		# Te2[s1>>8]
+	ins $25,$10,2,8
+
+	lw	$20,0($1)		# Te3[s3]
+	sll	$1,$8,2
+	lw	$21,0($2)		# Te3[s0]
+	sll	$2,$9,2
+	lw	$22,0($24)		# Te3[s1]
+	sll	$24,$10,2
+	lw	$23,0($25)		# Te3[s2]
+	sll	$25,$11,2
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+# endif
+	rotr	$16,$16,16
+	rotr	$17,$17,16
+	rotr	$18,$18,16
+	rotr	$19,$19,16
+
+	rotr	$20,$20,8
+	rotr	$21,$21,8
+	rotr	$22,$22,8
+	rotr	$23,$23,8
+#else
+	lwl	$16,1($1)		# Te2[s2>>8]
+	lwl	$17,1($2)		# Te2[s3>>8]
+	lwl	$18,1($24)		# Te2[s0>>8]
+	lwl	$19,1($25)		# Te2[s1>>8]
+	lwr	$16,2($1)		# Te2[s2>>8]
+	srl	$1,$11,22
+	lwr	$17,2($2)		# Te2[s3>>8]
+	srl	$2,$8,22
+	lwr	$18,2($24)		# Te2[s0>>8]
+	srl	$24,$9,22
+	lwr	$19,2($25)		# Te2[s1>>8]
+	srl	$25,$10,22
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lwl	$20,0($1)		# Te3[s3]
+	lwl	$21,0($2)		# Te3[s0]
+	lwl	$22,0($24)		# Te3[s1]
+	lwl	$23,0($25)		# Te3[s2]
+	lwr	$20,1($1)		# Te3[s3]
+	sll	$1,$8,2
+	lwr	$21,1($2)		# Te3[s0]
+	sll	$2,$9,2
+	lwr	$22,1($24)		# Te3[s1]
+	sll	$24,$10,2
+	lwr	$23,1($25)		# Te3[s2]
+	sll	$25,$11,2
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+#endif
+	xor	$12,$16
+	lw	$16,0($1)		# Te0[s0>>24]
+	xor	$13,$17
+	lw	$17,0($2)		# Te0[s1>>24]
+	xor	$14,$18
+	lw	$18,0($24)		# Te0[s2>>24]
+	xor	$15,$19
+	lw	$19,0($25)		# Te0[s3>>24]
+
+	xor	$12,$20
+	lw	$8,0($3)
+	xor	$13,$21
+	lw	$9,4($3)
+	xor	$14,$22
+	lw	$10,8($3)
+	xor	$15,$23
+	lw	$11,12($3)
+
+	xor	$12,$16
+	xor	$13,$17
+	xor	$14,$18
+	xor	$15,$19
+
+	sub	$30,1
+	add $3,16
+	xor	$8,$12
+	xor	$9,$13
+	xor	$10,$14
+	xor	$11,$15
+	.set	noreorder
+	bnez	$30,.Loop_enc
+	srl	$1,$9,6
+#endif
+
+	.set	reorder
+	srl	$2,$10,6
+	srl	$24,$11,6
+	srl	$25,$8,6
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lbu	$12,2($1)		# Te4[s1>>16]
+	srl	$1,$10,14
+	lbu	$13,2($2)		# Te4[s2>>16]
+	srl	$2,$11,14
+	lbu	$14,2($24)		# Te4[s3>>16]
+	srl	$24,$8,14
+	lbu	$15,2($25)		# Te4[s0>>16]
+	srl	$25,$9,14
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+#if defined(_MIPS_ARCH_MIPS32R2) || defined(_MIPS_ARCH_MIPS64R2)
+# if defined(_MIPSEL)
+	lbu	$16,2($1)		# Te4[s2>>8]
+	ins $1,$8,2,8
+	lbu	$17,2($2)		# Te4[s3>>8]
+	ins $2,$9,2,8
+	lbu	$18,2($24)		# Te4[s0>>8]
+	ins $24,$10,2,8
+	lbu	$19,2($25)		# Te4[s1>>8]
+	ins $25,$11,2,8
+
+	lbu	$20,2($1)		# Te4[s0>>24]
+	srl	$1,$11,22
+	lbu	$21,2($2)		# Te4[s1>>24]
+	srl	$2,$8,22
+	lbu	$22,2($24)		# Te4[s2>>24]
+	srl	$24,$9,22
+	lbu	$23,2($25)		# Te4[s3>>24]
+	srl	$25,$10,22
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+# else
+	lbu	$16,2($1)		# Te4[s2>>8]
+	sll	$1,$8,2
+	lbu	$17,2($2)		# Te4[s3>>8]
+	sll	$2,$9,2
+	lbu	$18,2($24)		# Te4[s0>>8]
+	sll	$24,$10,2
+	lbu	$19,2($25)		# Te4[s1>>8]
+	sll	$25,$11,2
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lbu	$20,2($1)		# Te4[s0>>24]
+	ins $1,$11,2,8
+	lbu	$21,2($2)		# Te4[s1>>24]
+	ins $2,$8,2,8
+	lbu	$22,2($24)		# Te4[s2>>24]
+	ins $24,$9,2,8
+	lbu	$23,2($25)		# Te4[s3>>24]
+	ins $25,$10,2,8
+# endif
+	sll	$12,$12,8
+	sll	$13,$13,8
+	sll	$14,$14,8
+	sll	$15,$15,8
+
+	ins	$12,$16,16,8
+	lbu	$16,2($1)		# Te4[s3]
+	ins	$13,$17,16,8
+	lbu	$17,2($2)		# Te4[s0]
+	ins	$14,$18,16,8
+	lbu	$18,2($24)		# Te4[s1]
+	ins	$15,$19,16,8
+	lbu	$19,2($25)		# Te4[s2]
+
+	ins	$12,$20,0,8
+	lw	$8,0($3)
+	ins	$13,$21,0,8
+	lw	$9,4($3)
+	ins	$14,$22,0,8
+	lw	$10,8($3)
+	ins	$15,$23,0,8
+	lw	$11,12($3)
+
+	ins	$12,$16,24,8
+	ins	$13,$17,24,8
+	ins	$14,$18,24,8
+	ins	$15,$19,24,8
+#else
+	lbu	$16,2($1)		# Te4[s2>>8]
+	sll	$1,$8,2
+	lbu	$17,2($2)		# Te4[s3>>8]
+	sll	$2,$9,2
+	lbu	$18,2($24)		# Te4[s0>>8]
+	sll	$24,$10,2
+	lbu	$19,2($25)		# Te4[s1>>8]
+	sll	$25,$11,2
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lbu	$20,2($1)		# Te4[s0>>24]
+	srl	$1,$11,22
+	lbu	$21,2($2)		# Te4[s1>>24]
+	srl	$2,$8,22
+	lbu	$22,2($24)		# Te4[s2>>24]
+	srl	$24,$9,22
+	lbu	$23,2($25)		# Te4[s3>>24]
+	srl	$25,$10,22
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+
+	sll	$12,$12,8
+	sll	$13,$13,8
+	sll	$14,$14,8
+	sll	$15,$15,8
+
+	sll	$16,$16,16
+	sll	$17,$17,16
+	sll	$18,$18,16
+	sll	$19,$19,16
+
+	xor	$12,$16
+	lbu	$16,2($1)		# Te4[s3]
+	xor	$13,$17
+	lbu	$17,2($2)		# Te4[s0]
+	xor	$14,$18
+	lbu	$18,2($24)		# Te4[s1]
+	xor	$15,$19
+	lbu	$19,2($25)		# Te4[s2]
+
+	#sll	$20,$20,0
+	lw	$8,0($3)
+	#sll	$21,$21,0
+	lw	$9,4($3)
+	#sll	$22,$22,0
+	lw	$10,8($3)
+	#sll	$23,$23,0
+	lw	$11,12($3)
+
+	xor	$12,$20
+	xor	$13,$21
+	xor	$14,$22
+	xor	$15,$23
+
+	sll	$16,$16,24
+	sll	$17,$17,24
+	sll	$18,$18,24
+	sll	$19,$19,24
+
+	xor	$12,$16
+	xor	$13,$17
+	xor	$14,$18
+	xor	$15,$19
+#endif
+	xor	$8,$12
+	xor	$9,$13
+	xor	$10,$14
+	xor	$11,$15
+
+	jr	$31
+.end	_mips_AES_encrypt
+
+.align	5
+.globl	AES_encrypt
+.ent	AES_encrypt
+AES_encrypt:
+	.frame	$29,64,$31
+	.mask	0xc0ff0000,-4
+	.set	noreorder
+	sub $29,64
+	sw	$31,64-1*4($29)
+	sw	$30,64-2*4($29)
+	sw	$23,64-3*4($29)
+	sw	$22,64-4*4($29)
+	sw	$21,64-5*4($29)
+	sw	$20,64-6*4($29)
+	sw	$19,64-7*4($29)
+	sw	$18,64-8*4($29)
+	sw	$17,64-9*4($29)
+	sw	$16,64-10*4($29)
+	.cplocal	$7
+	.cpsetup	$25,$0,AES_encrypt
+	.set	reorder
+	la	$7,AES_Te		# PIC-ified 'load address'
+
+	lwl	$8,0+3($4)
+	lwl	$9,4+3($4)
+	lwl	$10,8+3($4)
+	lwl	$11,12+3($4)
+	lwr	$8,0+0($4)
+	lwr	$9,4+0($4)
+	lwr	$10,8+0($4)
+	lwr	$11,12+0($4)
+
+	bal	_mips_AES_encrypt
+
+	swr	$8,0+0($5)
+	swr	$9,4+0($5)
+	swr	$10,8+0($5)
+	swr	$11,12+0($5)
+	swl	$8,0+3($5)
+	swl	$9,4+3($5)
+	swl	$10,8+3($5)
+	swl	$11,12+3($5)
+
+	.set	noreorder
+	lw	$31,64-1*4($29)
+	lw	$30,64-2*4($29)
+	lw	$23,64-3*4($29)
+	lw	$22,64-4*4($29)
+	lw	$21,64-5*4($29)
+	lw	$20,64-6*4($29)
+	lw	$19,64-7*4($29)
+	lw	$18,64-8*4($29)
+	lw	$17,64-9*4($29)
+	lw	$16,64-10*4($29)
+	jr	$31
+	add $29,64
+.end	AES_encrypt
+.align	5
+.ent	_mips_AES_decrypt
+_mips_AES_decrypt:
+	.frame	$29,0,$31
+	.set	reorder
+	lw	$12,0($6)
+	lw	$13,4($6)
+	lw	$14,8($6)
+	lw	$15,12($6)
+	lw	$30,240($6)
+	add $3,$6,16
+
+	xor	$8,$12
+	xor	$9,$13
+	xor	$10,$14
+	xor	$11,$15
+
+	sub	$30,1
+#if defined(__mips_smartmips)
+	ext	$1,$11,8,8
+.Loop_dec:
+	ext	$2,$8,8,8
+	ext	$24,$9,8,8
+	ext	$25,$10,8,8
+	lwxs	$12,$1($7)		# Td1[s3>>16]
+	ext	$1,$10,16,8
+	lwxs	$13,$2($7)		# Td1[s0>>16]
+	ext	$2,$11,16,8
+	lwxs	$14,$24($7)		# Td1[s1>>16]
+	ext	$24,$8,16,8
+	lwxs	$15,$25($7)		# Td1[s2>>16]
+	ext	$25,$9,16,8
+
+	lwxs	$16,$1($7)		# Td2[s2>>8]
+	ext	$1,$9,24,8
+	lwxs	$17,$2($7)		# Td2[s3>>8]
+	ext	$2,$10,24,8
+	lwxs	$18,$24($7)		# Td2[s0>>8]
+	ext	$24,$11,24,8
+	lwxs	$19,$25($7)		# Td2[s1>>8]
+	ext	$25,$8,24,8
+
+	lwxs	$20,$1($7)		# Td3[s1]
+	ext	$1,$8,0,8
+	lwxs	$21,$2($7)		# Td3[s2]
+	ext	$2,$9,0,8
+	lwxs	$22,$24($7)		# Td3[s3]
+	ext	$24,$10,0,8
+	lwxs	$23,$25($7)		# Td3[s0]
+	ext	$25,$11,0,8
+
+	rotr	$12,$12,24
+	rotr	$13,$13,24
+	rotr	$14,$14,24
+	rotr	$15,$15,24
+
+	rotr	$16,$16,16
+	rotr	$17,$17,16
+	rotr	$18,$18,16
+	rotr	$19,$19,16
+
+	xor	$12,$16
+	lwxs	$16,$1($7)		# Td0[s0>>24]
+	xor	$13,$17
+	lwxs	$17,$2($7)		# Td0[s1>>24]
+	xor	$14,$18
+	lwxs	$18,$24($7)		# Td0[s2>>24]
+	xor	$15,$19
+	lwxs	$19,$25($7)		# Td0[s3>>24]
+
+	rotr	$20,$20,8
+	lw	$8,0($3)
+	rotr	$21,$21,8
+	lw	$9,4($3)
+	rotr	$22,$22,8
+	lw	$10,8($3)
+	rotr	$23,$23,8
+	lw	$11,12($3)
+
+	xor	$12,$20
+	xor	$13,$21
+	xor	$14,$22
+	xor	$15,$23
+
+	xor	$12,$16
+	xor	$13,$17
+	xor	$14,$18
+	xor	$15,$19
+
+	sub	$30,1
+	add $3,16
+	xor	$8,$12
+	xor	$9,$13
+	xor	$10,$14
+	xor	$11,$15
+	.set	noreorder
+	bnez	$30,.Loop_dec
+	ext	$1,$11,8,8
+
+	srl	$1,$11,6
+#else
+	srl	$1,$11,6
+.Loop_dec:
+	srl	$2,$8,6
+	srl	$24,$9,6
+	srl	$25,$10,6
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+#if defined(_MIPS_ARCH_MIPS32R2) || defined(_MIPS_ARCH_MIPS64R2)
+	lw	$12,0($1)		# Td1[s3>>16]
+	srl	$1,$10,14
+	lw	$13,0($2)		# Td1[s0>>16]
+	srl	$2,$11,14
+	lw	$14,0($24)		# Td1[s1>>16]
+	srl	$24,$8,14
+	lw	$15,0($25)		# Td1[s2>>16]
+	srl	$25,$9,14
+#else
+	lwl	$12,2($1)		# Td1[s3>>16]
+	lwl	$13,2($2)		# Td1[s0>>16]
+	lwl	$14,2($24)		# Td1[s1>>16]
+	lwl	$15,2($25)		# Td1[s2>>16]
+	lwr	$12,3($1)		# Td1[s3>>16]
+	srl	$1,$10,14
+	lwr	$13,3($2)		# Td1[s0>>16]
+	srl	$2,$11,14
+	lwr	$14,3($24)		# Td1[s1>>16]
+	srl	$24,$8,14
+	lwr	$15,3($25)		# Td1[s2>>16]
+	srl	$25,$9,14
+#endif
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+#if defined(_MIPS_ARCH_MIPS32R2) || defined(_MIPS_ARCH_MIPS64R2)
+	rotr	$12,$12,24
+	rotr	$13,$13,24
+	rotr	$14,$14,24
+	rotr	$15,$15,24
+# if defined(_MIPSEL)
+	lw	$16,0($1)		# Td2[s2>>8]
+	srl	$1,$9,22
+	lw	$17,0($2)		# Td2[s3>>8]
+	srl	$2,$10,22
+	lw	$18,0($24)		# Td2[s0>>8]
+	srl	$24,$11,22
+	lw	$19,0($25)		# Td2[s1>>8]
+	srl	$25,$8,22
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lw	$20,0($1)		# Td3[s1]
+	ins $1,$8,2,8
+	lw	$21,0($2)		# Td3[s2]
+	ins $2,$9,2,8
+	lw	$22,0($24)		# Td3[s3]
+	ins $24,$10,2,8
+	lw	$23,0($25)		# Td3[s0]
+	ins $25,$11,2,8
+#else
+	lw	$16,0($1)		# Td2[s2>>8]
+	ins $1,$9,2,8
+	lw	$17,0($2)		# Td2[s3>>8]
+	ins $2,$10,2,8
+	lw	$18,0($24)		# Td2[s0>>8]
+	ins $24,$11,2,8
+	lw	$19,0($25)		# Td2[s1>>8]
+	ins $25,$8,2,8
+
+	lw	$20,0($1)		# Td3[s1]
+	sll	$1,$8,2
+	lw	$21,0($2)		# Td3[s2]
+	sll	$2,$9,2
+	lw	$22,0($24)		# Td3[s3]
+	sll	$24,$10,2
+	lw	$23,0($25)		# Td3[s0]
+	sll	$25,$11,2
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+#endif
+	rotr	$16,$16,16
+	rotr	$17,$17,16
+	rotr	$18,$18,16
+	rotr	$19,$19,16
+
+	rotr	$20,$20,8
+	rotr	$21,$21,8
+	rotr	$22,$22,8
+	rotr	$23,$23,8
+#else
+	lwl	$16,1($1)		# Td2[s2>>8]
+	lwl	$17,1($2)		# Td2[s3>>8]
+	lwl	$18,1($24)		# Td2[s0>>8]
+	lwl	$19,1($25)		# Td2[s1>>8]
+	lwr	$16,2($1)		# Td2[s2>>8]
+	srl	$1,$9,22
+	lwr	$17,2($2)		# Td2[s3>>8]
+	srl	$2,$10,22
+	lwr	$18,2($24)		# Td2[s0>>8]
+	srl	$24,$11,22
+	lwr	$19,2($25)		# Td2[s1>>8]
+	srl	$25,$8,22
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lwl	$20,0($1)		# Td3[s1]
+	lwl	$21,0($2)		# Td3[s2]
+	lwl	$22,0($24)		# Td3[s3]
+	lwl	$23,0($25)		# Td3[s0]
+	lwr	$20,1($1)		# Td3[s1]
+	sll	$1,$8,2
+	lwr	$21,1($2)		# Td3[s2]
+	sll	$2,$9,2
+	lwr	$22,1($24)		# Td3[s3]
+	sll	$24,$10,2
+	lwr	$23,1($25)		# Td3[s0]
+	sll	$25,$11,2
+
+	and	$1,0x3fc
+	and	$2,0x3fc
+	and	$24,0x3fc
+	and	$25,0x3fc
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+#endif
+
+	xor	$12,$16
+	lw	$16,0($1)		# Td0[s0>>24]
+	xor	$13,$17
+	lw	$17,0($2)		# Td0[s1>>24]
+	xor	$14,$18
+	lw	$18,0($24)		# Td0[s2>>24]
+	xor	$15,$19
+	lw	$19,0($25)		# Td0[s3>>24]
+
+	xor	$12,$20
+	lw	$8,0($3)
+	xor	$13,$21
+	lw	$9,4($3)
+	xor	$14,$22
+	lw	$10,8($3)
+	xor	$15,$23
+	lw	$11,12($3)
+
+	xor	$12,$16
+	xor	$13,$17
+	xor	$14,$18
+	xor	$15,$19
+
+	sub	$30,1
+	add $3,16
+	xor	$8,$12
+	xor	$9,$13
+	xor	$10,$14
+	xor	$11,$15
+	.set	noreorder
+	bnez	$30,.Loop_dec
+	srl	$1,$11,6
+#endif
+
+	.set	reorder
+	lw	$16,1024($7)		# prefetch Td4
+	srl	$1,$11,8
+	lw	$17,1024+32($7)
+	srl	$2,$8,8
+	lw	$18,1024+64($7)
+	srl	$24,$9,8
+	lw	$19,1024+96($7)
+	srl	$25,$10,8
+	lw	$20,1024+128($7)
+	and	$1,0xff
+	lw	$21,1024+160($7)
+	and	$2,0xff
+	lw	$22,1024+192($7)
+	and	$24,0xff
+	lw	$23,1024+224($7)
+	and	$25,0xff
+
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lbu	$12,1024($1)		# Td4[s3>>16]
+	srl	$1,$10,16
+	lbu	$13,1024($2)		# Td4[s0>>16]
+	srl	$2,$11,16
+	lbu	$14,1024($24)		# Td4[s1>>16]
+	srl	$24,$8,16
+	lbu	$15,1024($25)		# Td4[s2>>16]
+	srl	$25,$9,16
+
+	and	$1,0xff
+	and	$2,0xff
+	and	$24,0xff
+	and	$25,0xff
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+#if defined(_MIPS_ARCH_MIPS32R2) || defined(_MIPS_ARCH_MIPS64R2)
+# if defined(_MIPSEL)
+	lbu	$16,1024($1)		# Td4[s2>>8]
+	ins $1,$8,0,8
+	lbu	$17,1024($2)		# Td4[s3>>8]
+	ins $2,$9,0,8
+	lbu	$18,1024($24)		# Td4[s0>>8]
+	ins $24,$10,0,8
+	lbu	$19,1024($25)		# Td4[s1>>8]
+	ins $25,$11,0,8
+
+	lbu	$20,1024($1)		# Td4[s0>>24]
+	srl	$1,$9,24
+	lbu	$21,1024($2)		# Td4[s1>>24]
+	srl	$2,$10,24
+	lbu	$22,1024($24)		# Td4[s2>>24]
+	srl	$24,$11,24
+	lbu	$23,1024($25)		# Td4[s3>>24]
+	srl	$25,$8,24
+
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+# else
+	lbu	$16,1024($1)		# Td4[s2>>8]
+	and	$1,$8,0xff
+	lbu	$17,1024($2)		# Td4[s3>>8]
+	and	$2,$9,0xff
+	lbu	$18,1024($24)		# Td4[s0>>8]
+	and	$24,$10,0xff
+	lbu	$19,1024($25)		# Td4[s1>>8]
+	and	$25,$11,0xff
+
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lbu	$20,1024($1)		# Td4[s0>>24]
+	ins $1,$9,0,8
+	lbu	$21,1024($2)		# Td4[s1>>24]
+	ins $2,$10,0,8
+	lbu	$22,1024($24)		# Td4[s2>>24]
+	ins $24,$11,0,8
+	lbu	$23,1024($25)		# Td4[s3>>24]
+	ins $25,$8,0,8
+# endif
+	sll	$12,$12,8
+	sll	$13,$13,8
+	sll	$14,$14,8
+	sll	$15,$15,8
+
+	ins	$12,$16,16,8
+	lbu	$16,1024($1)		# Td4[s1]
+	ins	$13,$17,16,8
+	lbu	$17,1024($2)		# Td4[s2]
+	ins	$14,$18,16,8
+	lbu	$18,1024($24)		# Td4[s3]
+	ins	$15,$19,16,8
+	lbu	$19,1024($25)		# Td4[s0]
+
+	ins	$12,$20,0,8
+	lw	$8,0($3)
+	ins	$13,$21,0,8
+	lw	$9,4($3)
+	ins	$14,$22,0,8
+	lw	$10,8($3)
+	ins	$15,$23,0,8
+	lw	$11,12($3)
+
+	ins	$12,$16,24,8
+	ins	$13,$17,24,8
+	ins	$14,$18,24,8
+	ins	$15,$19,24,8
+#else
+	lbu	$16,1024($1)		# Td4[s2>>8]
+	and	$1,$8,0xff
+	lbu	$17,1024($2)		# Td4[s3>>8]
+	and	$2,$9,0xff
+	lbu	$18,1024($24)		# Td4[s0>>8]
+	and	$24,$10,0xff
+	lbu	$19,1024($25)		# Td4[s1>>8]
+	and	$25,$11,0xff
+
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lbu	$20,1024($1)		# Td4[s0>>24]
+	srl	$1,$9,24
+	lbu	$21,1024($2)		# Td4[s1>>24]
+	srl	$2,$10,24
+	lbu	$22,1024($24)		# Td4[s2>>24]
+	srl	$24,$11,24
+	lbu	$23,1024($25)		# Td4[s3>>24]
+	srl	$25,$8,24
+
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+
+	sll	$12,$12,8
+	sll	$13,$13,8
+	sll	$14,$14,8
+	sll	$15,$15,8
+
+	sll	$16,$16,16
+	sll	$17,$17,16
+	sll	$18,$18,16
+	sll	$19,$19,16
+
+	xor	$12,$16
+	lbu	$16,1024($1)		# Td4[s1]
+	xor	$13,$17
+	lbu	$17,1024($2)		# Td4[s2]
+	xor	$14,$18
+	lbu	$18,1024($24)		# Td4[s3]
+	xor	$15,$19
+	lbu	$19,1024($25)		# Td4[s0]
+
+	#sll	$20,$20,0
+	lw	$8,0($3)
+	#sll	$21,$21,0
+	lw	$9,4($3)
+	#sll	$22,$22,0
+	lw	$10,8($3)
+	#sll	$23,$23,0
+	lw	$11,12($3)
+
+	xor	$12,$20
+	xor	$13,$21
+	xor	$14,$22
+	xor	$15,$23
+
+	sll	$16,$16,24
+	sll	$17,$17,24
+	sll	$18,$18,24
+	sll	$19,$19,24
+
+	xor	$12,$16
+	xor	$13,$17
+	xor	$14,$18
+	xor	$15,$19
+#endif
+
+	xor	$8,$12
+	xor	$9,$13
+	xor	$10,$14
+	xor	$11,$15
+
+	jr	$31
+.end	_mips_AES_decrypt
+
+.align	5
+.globl	AES_decrypt
+.ent	AES_decrypt
+AES_decrypt:
+	.frame	$29,64,$31
+	.mask	0xc0ff0000,-4
+	.set	noreorder
+	sub $29,64
+	sw	$31,64-1*4($29)
+	sw	$30,64-2*4($29)
+	sw	$23,64-3*4($29)
+	sw	$22,64-4*4($29)
+	sw	$21,64-5*4($29)
+	sw	$20,64-6*4($29)
+	sw	$19,64-7*4($29)
+	sw	$18,64-8*4($29)
+	sw	$17,64-9*4($29)
+	sw	$16,64-10*4($29)
+	.cplocal	$7
+	.cpsetup	$25,$0,AES_decrypt
+	.set	reorder
+	la	$7,AES_Td		# PIC-ified 'load address'
+
+	lwl	$8,0+3($4)
+	lwl	$9,4+3($4)
+	lwl	$10,8+3($4)
+	lwl	$11,12+3($4)
+	lwr	$8,0+0($4)
+	lwr	$9,4+0($4)
+	lwr	$10,8+0($4)
+	lwr	$11,12+0($4)
+
+	bal	_mips_AES_decrypt
+
+	swr	$8,0+0($5)
+	swr	$9,4+0($5)
+	swr	$10,8+0($5)
+	swr	$11,12+0($5)
+	swl	$8,0+3($5)
+	swl	$9,4+3($5)
+	swl	$10,8+3($5)
+	swl	$11,12+3($5)
+
+	.set	noreorder
+	lw	$31,64-1*4($29)
+	lw	$30,64-2*4($29)
+	lw	$23,64-3*4($29)
+	lw	$22,64-4*4($29)
+	lw	$21,64-5*4($29)
+	lw	$20,64-6*4($29)
+	lw	$19,64-7*4($29)
+	lw	$18,64-8*4($29)
+	lw	$17,64-9*4($29)
+	lw	$16,64-10*4($29)
+	jr	$31
+	add $29,64
+.end	AES_decrypt
+.align	5
+.ent	_mips_AES_set_encrypt_key
+_mips_AES_set_encrypt_key:
+	.frame	$29,0,$31
+	.set	noreorder
+	beqz	$4,.Lekey_done
+	li	$2,-1
+	beqz	$6,.Lekey_done
+	add $3,$7,256
+
+	.set	reorder
+	lwl	$8,0+3($4)	# load 128 bits
+	lwl	$9,4+3($4)
+	lwl	$10,8+3($4)
+	lwl	$11,12+3($4)
+	li	$1,128
+	lwr	$8,0+0($4)
+	lwr	$9,4+0($4)
+	lwr	$10,8+0($4)
+	lwr	$11,12+0($4)
+	.set	noreorder
+	beq	$5,$1,.L128bits
+	li	$30,10
+
+	.set	reorder
+	lwl	$12,16+3($4)	# load 192 bits
+	lwl	$13,20+3($4)
+	li	$1,192
+	lwr	$12,16+0($4)
+	lwr	$13,20+0($4)
+	.set	noreorder
+	beq	$5,$1,.L192bits
+	li	$30,8
+
+	.set	reorder
+	lwl	$14,24+3($4)	# load 256 bits
+	lwl	$15,28+3($4)
+	li	$1,256
+	lwr	$14,24+0($4)
+	lwr	$15,28+0($4)
+	.set	noreorder
+	beq	$5,$1,.L256bits
+	li	$30,7
+
+	b	.Lekey_done
+	li	$2,-2
+
+.align	4
+.L128bits:
+	.set	reorder
+	srl	$1,$11,16
+	srl	$2,$11,8
+	and	$1,0xff
+	and	$2,0xff
+	and	$24,$11,0xff
+	srl	$25,$11,24
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lbu	$1,0($1)
+	lbu	$2,0($2)
+	lbu	$24,0($24)
+	lbu	$25,0($25)
+
+	sw	$8,0($6)
+	sw	$9,4($6)
+	sw	$10,8($6)
+	sw	$11,12($6)
+	sub	$30,1
+	add $6,16
+
+	sll	$1,$1,8
+	#sll	$2,$2,0
+	sll	$24,$24,24
+	sll	$25,$25,16
+
+	xor	$8,$1
+	lw	$1,0($3)
+	xor	$8,$2
+	xor	$8,$24
+	xor	$8,$25
+	xor	$8,$1
+
+	xor	$9,$8
+	xor	$10,$9
+	xor	$11,$10
+
+	.set	noreorder
+	bnez	$30,.L128bits
+	add $3,4
+
+	sw	$8,0($6)
+	sw	$9,4($6)
+	sw	$10,8($6)
+	li	$30,10
+	sw	$11,12($6)
+	li	$2,0
+	sw	$30,80($6)
+	b	.Lekey_done
+	sub $6,10*16
+
+.align	4
+.L192bits:
+	.set	reorder
+	srl	$1,$13,16
+	srl	$2,$13,8
+	and	$1,0xff
+	and	$2,0xff
+	and	$24,$13,0xff
+	srl	$25,$13,24
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lbu	$1,0($1)
+	lbu	$2,0($2)
+	lbu	$24,0($24)
+	lbu	$25,0($25)
+
+	sw	$8,0($6)
+	sw	$9,4($6)
+	sw	$10,8($6)
+	sw	$11,12($6)
+	sw	$12,16($6)
+	sw	$13,20($6)
+	sub	$30,1
+	add $6,24
+
+	sll	$1,$1,8
+	#sll	$2,$2,0
+	sll	$24,$24,24
+	sll	$25,$25,16
+
+	xor	$8,$1
+	lw	$1,0($3)
+	xor	$8,$2
+	xor	$8,$24
+	xor	$8,$25
+	xor	$8,$1
+
+	xor	$9,$8
+	xor	$10,$9
+	xor	$11,$10
+	xor	$12,$11
+	xor	$13,$12
+
+	.set	noreorder
+	bnez	$30,.L192bits
+	add $3,4
+
+	sw	$8,0($6)
+	sw	$9,4($6)
+	sw	$10,8($6)
+	li	$30,12
+	sw	$11,12($6)
+	li	$2,0
+	sw	$30,48($6)
+	b	.Lekey_done
+	sub $6,12*16
+
+.align	4
+.L256bits:
+	.set	reorder
+	srl	$1,$15,16
+	srl	$2,$15,8
+	and	$1,0xff
+	and	$2,0xff
+	and	$24,$15,0xff
+	srl	$25,$15,24
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lbu	$1,0($1)
+	lbu	$2,0($2)
+	lbu	$24,0($24)
+	lbu	$25,0($25)
+
+	sw	$8,0($6)
+	sw	$9,4($6)
+	sw	$10,8($6)
+	sw	$11,12($6)
+	sw	$12,16($6)
+	sw	$13,20($6)
+	sw	$14,24($6)
+	sw	$15,28($6)
+	sub	$30,1
+
+	sll	$1,$1,8
+	#sll	$2,$2,0
+	sll	$24,$24,24
+	sll	$25,$25,16
+
+	xor	$8,$1
+	lw	$1,0($3)
+	xor	$8,$2
+	xor	$8,$24
+	xor	$8,$25
+	xor	$8,$1
+
+	xor	$9,$8
+	xor	$10,$9
+	xor	$11,$10
+	beqz	$30,.L256bits_done
+
+	srl	$1,$11,24
+	srl	$2,$11,16
+	srl	$24,$11,8
+	and	$25,$11,0xff
+	and	$2,0xff
+	and	$24,0xff
+	add $1,$7
+	add $2,$7
+	add $24,$7
+	add $25,$7
+	lbu	$1,0($1)
+	lbu	$2,0($2)
+	lbu	$24,0($24)
+	lbu	$25,0($25)
+	sll	$1,24
+	sll	$2,16
+	sll	$24,8
+
+	xor	$12,$1
+	xor	$12,$2
+	xor	$12,$24
+	xor	$12,$25
+
+	xor	$13,$12
+	xor	$14,$13
+	xor	$15,$14
+
+	add $6,32
+	.set	noreorder
+	b	.L256bits
+	add $3,4
+
+.L256bits_done:
+	sw	$8,32($6)
+	sw	$9,36($6)
+	sw	$10,40($6)
+	li	$30,14
+	sw	$11,44($6)
+	li	$2,0
+	sw	$30,48($6)
+	sub $6,12*16
+
+.Lekey_done:
+	jr	$31
+	nop
+.end	_mips_AES_set_encrypt_key
+
+.globl	AES_set_encrypt_key
+.ent	AES_set_encrypt_key
+AES_set_encrypt_key:
+	.frame	$29,32,$31
+	.mask	0xc0000000,-4
+	.set	noreorder
+	sub $29,32
+	sw	$31,32-1*4($29)
+	sw	$30,32-2*4($29)
+	.cplocal	$7
+	.cpsetup	$25,$0,AES_set_encrypt_key
+	.set	reorder
+	la	$7,AES_Te4		# PIC-ified 'load address'
+
+	bal	_mips_AES_set_encrypt_key
+
+	.set	noreorder
+	move	$4,$2
+	lw	$31,32-1*4($29)
+	lw	$30,32-2*4($29)
+	jr	$31
+	add $29,32
+.end	AES_set_encrypt_key
+.align	5
+.globl	AES_set_decrypt_key
+.ent	AES_set_decrypt_key
+AES_set_decrypt_key:
+	.frame	$29,32,$31
+	.mask	0xc0000000,-4
+	.set	noreorder
+	sub $29,32
+	sw	$31,32-1*4($29)
+	sw	$30,32-2*4($29)
+	.cplocal	$7
+	.cpsetup	$25,$0,AES_set_decrypt_key
+	.set	reorder
+	la	$7,AES_Te4		# PIC-ified 'load address'
+
+	bal	_mips_AES_set_encrypt_key
+
+	bltz	$2,.Ldkey_done
+
+	sll	$1,$30,4
+	add $4,$6,0
+	add $5,$6,$1
+.align	4
+.Lswap:
+	lw	$8,0($4)
+	lw	$9,4($4)
+	lw	$10,8($4)
+	lw	$11,12($4)
+	lw	$12,0($5)
+	lw	$13,4($5)
+	lw	$14,8($5)
+	lw	$15,12($5)
+	sw	$8,0($5)
+	sw	$9,4($5)
+	sw	$10,8($5)
+	sw	$11,12($5)
+	add $4,16
+	sub $5,16
+	sw	$12,-16($4)
+	sw	$13,-12($4)
+	sw	$14,-8($4)
+	sw	$15,-4($4)
+	bne	$4,$5,.Lswap
+
+	lw	$8,16($6)		# modulo-scheduled
+	lui	$2,0x8080
+	sub	$30,1
+	or	$2,0x8080
+	sll	$30,2
+	add $6,16
+	lui	$25,0x1b1b
+	nor	$24,$0,$2
+	or	$25,0x1b1b
+.align	4
+.Lmix:
+	and	$1,$8,$2
+	and	$9,$8,$24
+	srl	$10,$1,7
+	addu	$9,$9		# tp2<<1
+	subu	$1,$10
+	and	$1,$25
+	xor	$9,$1
+
+	and	$1,$9,$2
+	and	$10,$9,$24
+	srl	$11,$1,7
+	addu	$10,$10		# tp4<<1
+	subu	$1,$11
+	and	$1,$25
+	xor	$10,$1
+
+	and	$1,$10,$2
+	and	$11,$10,$24
+	srl	$12,$1,7
+	addu	$11,$11		# tp8<<1
+	subu	$1,$12
+	and	$1,$25
+	xor	$11,$1
+
+	xor	$12,$11,$8
+	xor	$15,$11,$10
+	xor	$13,$12,$9
+	xor	$14,$12,$10
+
+#if defined(_MIPS_ARCH_MIPS32R2) || defined(_MIPS_ARCH_MIPS64R2)
+	rotr	$8,$14,16
+	 xor	$15,$9
+	rotr	$9,$12,24
+	xor	$15,$8
+	rotr	$10,$13,8
+	xor	$15,$9
+	lw	$8,4($6)		# modulo-scheduled
+	xor	$15,$10
+#else
+	sll	$8,$14,16
+	 xor	$15,$9
+	srl	$9,$14,16
+	xor	$15,$8
+	sll	$8,$12,8
+	xor	$15,$9
+	srl	$9,$12,24
+	xor	$15,$8
+	sll	$8,$13,24
+	xor	$15,$9
+	srl	$9,$13,8
+	xor	$15,$8
+	lw	$8,4($6)		# modulo-scheduled
+	xor	$15,$9
+#endif
+	sub	$30,1
+	sw	$15,0($6)
+	add $6,4
+	bnez	$30,.Lmix
+
+	li	$2,0
+.Ldkey_done:
+	.set	noreorder
+	move	$4,$2
+	lw	$31,32-1*4($29)
+	lw	$30,32-2*4($29)
+	jr	$31
+	add $29,32
+.end	AES_set_decrypt_key
+.rdata
+.align	10
+AES_Te:
+.byte	0xc6,0x63,0x63,0xa5,	0xf8,0x7c,0x7c,0x84	# Te0
+.byte	0xee,0x77,0x77,0x99,	0xf6,0x7b,0x7b,0x8d
+.byte	0xff,0xf2,0xf2,0x0d,	0xd6,0x6b,0x6b,0xbd
+.byte	0xde,0x6f,0x6f,0xb1,	0x91,0xc5,0xc5,0x54
+.byte	0x60,0x30,0x30,0x50,	0x02,0x01,0x01,0x03
+.byte	0xce,0x67,0x67,0xa9,	0x56,0x2b,0x2b,0x7d
+.byte	0xe7,0xfe,0xfe,0x19,	0xb5,0xd7,0xd7,0x62
+.byte	0x4d,0xab,0xab,0xe6,	0xec,0x76,0x76,0x9a
+.byte	0x8f,0xca,0xca,0x45,	0x1f,0x82,0x82,0x9d
+.byte	0x89,0xc9,0xc9,0x40,	0xfa,0x7d,0x7d,0x87
+.byte	0xef,0xfa,0xfa,0x15,	0xb2,0x59,0x59,0xeb
+.byte	0x8e,0x47,0x47,0xc9,	0xfb,0xf0,0xf0,0x0b
+.byte	0x41,0xad,0xad,0xec,	0xb3,0xd4,0xd4,0x67
+.byte	0x5f,0xa2,0xa2,0xfd,	0x45,0xaf,0xaf,0xea
+.byte	0x23,0x9c,0x9c,0xbf,	0x53,0xa4,0xa4,0xf7
+.byte	0xe4,0x72,0x72,0x96,	0x9b,0xc0,0xc0,0x5b
+.byte	0x75,0xb7,0xb7,0xc2,	0xe1,0xfd,0xfd,0x1c
+.byte	0x3d,0x93,0x93,0xae,	0x4c,0x26,0x26,0x6a
+.byte	0x6c,0x36,0x36,0x5a,	0x7e,0x3f,0x3f,0x41
+.byte	0xf5,0xf7,0xf7,0x02,	0x83,0xcc,0xcc,0x4f
+.byte	0x68,0x34,0x34,0x5c,	0x51,0xa5,0xa5,0xf4
+.byte	0xd1,0xe5,0xe5,0x34,	0xf9,0xf1,0xf1,0x08
+.byte	0xe2,0x71,0x71,0x93,	0xab,0xd8,0xd8,0x73
+.byte	0x62,0x31,0x31,0x53,	0x2a,0x15,0x15,0x3f
+.byte	0x08,0x04,0x04,0x0c,	0x95,0xc7,0xc7,0x52
+.byte	0x46,0x23,0x23,0x65,	0x9d,0xc3,0xc3,0x5e
+.byte	0x30,0x18,0x18,0x28,	0x37,0x96,0x96,0xa1
+.byte	0x0a,0x05,0x05,0x0f,	0x2f,0x9a,0x9a,0xb5
+.byte	0x0e,0x07,0x07,0x09,	0x24,0x12,0x12,0x36
+.byte	0x1b,0x80,0x80,0x9b,	0xdf,0xe2,0xe2,0x3d
+.byte	0xcd,0xeb,0xeb,0x26,	0x4e,0x27,0x27,0x69
+.byte	0x7f,0xb2,0xb2,0xcd,	0xea,0x75,0x75,0x9f
+.byte	0x12,0x09,0x09,0x1b,	0x1d,0x83,0x83,0x9e
+.byte	0x58,0x2c,0x2c,0x74,	0x34,0x1a,0x1a,0x2e
+.byte	0x36,0x1b,0x1b,0x2d,	0xdc,0x6e,0x6e,0xb2
+.byte	0xb4,0x5a,0x5a,0xee,	0x5b,0xa0,0xa0,0xfb
+.byte	0xa4,0x52,0x52,0xf6,	0x76,0x3b,0x3b,0x4d
+.byte	0xb7,0xd6,0xd6,0x61,	0x7d,0xb3,0xb3,0xce
+.byte	0x52,0x29,0x29,0x7b,	0xdd,0xe3,0xe3,0x3e
+.byte	0x5e,0x2f,0x2f,0x71,	0x13,0x84,0x84,0x97
+.byte	0xa6,0x53,0x53,0xf5,	0xb9,0xd1,0xd1,0x68
+.byte	0x00,0x00,0x00,0x00,	0xc1,0xed,0xed,0x2c
+.byte	0x40,0x20,0x20,0x60,	0xe3,0xfc,0xfc,0x1f
+.byte	0x79,0xb1,0xb1,0xc8,	0xb6,0x5b,0x5b,0xed
+.byte	0xd4,0x6a,0x6a,0xbe,	0x8d,0xcb,0xcb,0x46
+.byte	0x67,0xbe,0xbe,0xd9,	0x72,0x39,0x39,0x4b
+.byte	0x94,0x4a,0x4a,0xde,	0x98,0x4c,0x4c,0xd4
+.byte	0xb0,0x58,0x58,0xe8,	0x85,0xcf,0xcf,0x4a
+.byte	0xbb,0xd0,0xd0,0x6b,	0xc5,0xef,0xef,0x2a
+.byte	0x4f,0xaa,0xaa,0xe5,	0xed,0xfb,0xfb,0x16
+.byte	0x86,0x43,0x43,0xc5,	0x9a,0x4d,0x4d,0xd7
+.byte	0x66,0x33,0x33,0x55,	0x11,0x85,0x85,0x94
+.byte	0x8a,0x45,0x45,0xcf,	0xe9,0xf9,0xf9,0x10
+.byte	0x04,0x02,0x02,0x06,	0xfe,0x7f,0x7f,0x81
+.byte	0xa0,0x50,0x50,0xf0,	0x78,0x3c,0x3c,0x44
+.byte	0x25,0x9f,0x9f,0xba,	0x4b,0xa8,0xa8,0xe3
+.byte	0xa2,0x51,0x51,0xf3,	0x5d,0xa3,0xa3,0xfe
+.byte	0x80,0x40,0x40,0xc0,	0x05,0x8f,0x8f,0x8a
+.byte	0x3f,0x92,0x92,0xad,	0x21,0x9d,0x9d,0xbc
+.byte	0x70,0x38,0x38,0x48,	0xf1,0xf5,0xf5,0x04
+.byte	0x63,0xbc,0xbc,0xdf,	0x77,0xb6,0xb6,0xc1
+.byte	0xaf,0xda,0xda,0x75,	0x42,0x21,0x21,0x63
+.byte	0x20,0x10,0x10,0x30,	0xe5,0xff,0xff,0x1a
+.byte	0xfd,0xf3,0xf3,0x0e,	0xbf,0xd2,0xd2,0x6d
+.byte	0x81,0xcd,0xcd,0x4c,	0x18,0x0c,0x0c,0x14
+.byte	0x26,0x13,0x13,0x35,	0xc3,0xec,0xec,0x2f
+.byte	0xbe,0x5f,0x5f,0xe1,	0x35,0x97,0x97,0xa2
+.byte	0x88,0x44,0x44,0xcc,	0x2e,0x17,0x17,0x39
+.byte	0x93,0xc4,0xc4,0x57,	0x55,0xa7,0xa7,0xf2
+.byte	0xfc,0x7e,0x7e,0x82,	0x7a,0x3d,0x3d,0x47
+.byte	0xc8,0x64,0x64,0xac,	0xba,0x5d,0x5d,0xe7
+.byte	0x32,0x19,0x19,0x2b,	0xe6,0x73,0x73,0x95
+.byte	0xc0,0x60,0x60,0xa0,	0x19,0x81,0x81,0x98
+.byte	0x9e,0x4f,0x4f,0xd1,	0xa3,0xdc,0xdc,0x7f
+.byte	0x44,0x22,0x22,0x66,	0x54,0x2a,0x2a,0x7e
+.byte	0x3b,0x90,0x90,0xab,	0x0b,0x88,0x88,0x83
+.byte	0x8c,0x46,0x46,0xca,	0xc7,0xee,0xee,0x29
+.byte	0x6b,0xb8,0xb8,0xd3,	0x28,0x14,0x14,0x3c
+.byte	0xa7,0xde,0xde,0x79,	0xbc,0x5e,0x5e,0xe2
+.byte	0x16,0x0b,0x0b,0x1d,	0xad,0xdb,0xdb,0x76
+.byte	0xdb,0xe0,0xe0,0x3b,	0x64,0x32,0x32,0x56
+.byte	0x74,0x3a,0x3a,0x4e,	0x14,0x0a,0x0a,0x1e
+.byte	0x92,0x49,0x49,0xdb,	0x0c,0x06,0x06,0x0a
+.byte	0x48,0x24,0x24,0x6c,	0xb8,0x5c,0x5c,0xe4
+.byte	0x9f,0xc2,0xc2,0x5d,	0xbd,0xd3,0xd3,0x6e
+.byte	0x43,0xac,0xac,0xef,	0xc4,0x62,0x62,0xa6
+.byte	0x39,0x91,0x91,0xa8,	0x31,0x95,0x95,0xa4
+.byte	0xd3,0xe4,0xe4,0x37,	0xf2,0x79,0x79,0x8b
+.byte	0xd5,0xe7,0xe7,0x32,	0x8b,0xc8,0xc8,0x43
+.byte	0x6e,0x37,0x37,0x59,	0xda,0x6d,0x6d,0xb7
+.byte	0x01,0x8d,0x8d,0x8c,	0xb1,0xd5,0xd5,0x64
+.byte	0x9c,0x4e,0x4e,0xd2,	0x49,0xa9,0xa9,0xe0
+.byte	0xd8,0x6c,0x6c,0xb4,	0xac,0x56,0x56,0xfa
+.byte	0xf3,0xf4,0xf4,0x07,	0xcf,0xea,0xea,0x25
+.byte	0xca,0x65,0x65,0xaf,	0xf4,0x7a,0x7a,0x8e
+.byte	0x47,0xae,0xae,0xe9,	0x10,0x08,0x08,0x18
+.byte	0x6f,0xba,0xba,0xd5,	0xf0,0x78,0x78,0x88
+.byte	0x4a,0x25,0x25,0x6f,	0x5c,0x2e,0x2e,0x72
+.byte	0x38,0x1c,0x1c,0x24,	0x57,0xa6,0xa6,0xf1
+.byte	0x73,0xb4,0xb4,0xc7,	0x97,0xc6,0xc6,0x51
+.byte	0xcb,0xe8,0xe8,0x23,	0xa1,0xdd,0xdd,0x7c
+.byte	0xe8,0x74,0x74,0x9c,	0x3e,0x1f,0x1f,0x21
+.byte	0x96,0x4b,0x4b,0xdd,	0x61,0xbd,0xbd,0xdc
+.byte	0x0d,0x8b,0x8b,0x86,	0x0f,0x8a,0x8a,0x85
+.byte	0xe0,0x70,0x70,0x90,	0x7c,0x3e,0x3e,0x42
+.byte	0x71,0xb5,0xb5,0xc4,	0xcc,0x66,0x66,0xaa
+.byte	0x90,0x48,0x48,0xd8,	0x06,0x03,0x03,0x05
+.byte	0xf7,0xf6,0xf6,0x01,	0x1c,0x0e,0x0e,0x12
+.byte	0xc2,0x61,0x61,0xa3,	0x6a,0x35,0x35,0x5f
+.byte	0xae,0x57,0x57,0xf9,	0x69,0xb9,0xb9,0xd0
+.byte	0x17,0x86,0x86,0x91,	0x99,0xc1,0xc1,0x58
+.byte	0x3a,0x1d,0x1d,0x27,	0x27,0x9e,0x9e,0xb9
+.byte	0xd9,0xe1,0xe1,0x38,	0xeb,0xf8,0xf8,0x13
+.byte	0x2b,0x98,0x98,0xb3,	0x22,0x11,0x11,0x33
+.byte	0xd2,0x69,0x69,0xbb,	0xa9,0xd9,0xd9,0x70
+.byte	0x07,0x8e,0x8e,0x89,	0x33,0x94,0x94,0xa7
+.byte	0x2d,0x9b,0x9b,0xb6,	0x3c,0x1e,0x1e,0x22
+.byte	0x15,0x87,0x87,0x92,	0xc9,0xe9,0xe9,0x20
+.byte	0x87,0xce,0xce,0x49,	0xaa,0x55,0x55,0xff
+.byte	0x50,0x28,0x28,0x78,	0xa5,0xdf,0xdf,0x7a
+.byte	0x03,0x8c,0x8c,0x8f,	0x59,0xa1,0xa1,0xf8
+.byte	0x09,0x89,0x89,0x80,	0x1a,0x0d,0x0d,0x17
+.byte	0x65,0xbf,0xbf,0xda,	0xd7,0xe6,0xe6,0x31
+.byte	0x84,0x42,0x42,0xc6,	0xd0,0x68,0x68,0xb8
+.byte	0x82,0x41,0x41,0xc3,	0x29,0x99,0x99,0xb0
+.byte	0x5a,0x2d,0x2d,0x77,	0x1e,0x0f,0x0f,0x11
+.byte	0x7b,0xb0,0xb0,0xcb,	0xa8,0x54,0x54,0xfc
+.byte	0x6d,0xbb,0xbb,0xd6,	0x2c,0x16,0x16,0x3a
+
+AES_Td:
+.byte	0x51,0xf4,0xa7,0x50,	0x7e,0x41,0x65,0x53	# Td0
+.byte	0x1a,0x17,0xa4,0xc3,	0x3a,0x27,0x5e,0x96
+.byte	0x3b,0xab,0x6b,0xcb,	0x1f,0x9d,0x45,0xf1
+.byte	0xac,0xfa,0x58,0xab,	0x4b,0xe3,0x03,0x93
+.byte	0x20,0x30,0xfa,0x55,	0xad,0x76,0x6d,0xf6
+.byte	0x88,0xcc,0x76,0x91,	0xf5,0x02,0x4c,0x25
+.byte	0x4f,0xe5,0xd7,0xfc,	0xc5,0x2a,0xcb,0xd7
+.byte	0x26,0x35,0x44,0x80,	0xb5,0x62,0xa3,0x8f
+.byte	0xde,0xb1,0x5a,0x49,	0x25,0xba,0x1b,0x67
+.byte	0x45,0xea,0x0e,0x98,	0x5d,0xfe,0xc0,0xe1
+.byte	0xc3,0x2f,0x75,0x02,	0x81,0x4c,0xf0,0x12
+.byte	0x8d,0x46,0x97,0xa3,	0x6b,0xd3,0xf9,0xc6
+.byte	0x03,0x8f,0x5f,0xe7,	0x15,0x92,0x9c,0x95
+.byte	0xbf,0x6d,0x7a,0xeb,	0x95,0x52,0x59,0xda
+.byte	0xd4,0xbe,0x83,0x2d,	0x58,0x74,0x21,0xd3
+.byte	0x49,0xe0,0x69,0x29,	0x8e,0xc9,0xc8,0x44
+.byte	0x75,0xc2,0x89,0x6a,	0xf4,0x8e,0x79,0x78
+.byte	0x99,0x58,0x3e,0x6b,	0x27,0xb9,0x71,0xdd
+.byte	0xbe,0xe1,0x4f,0xb6,	0xf0,0x88,0xad,0x17
+.byte	0xc9,0x20,0xac,0x66,	0x7d,0xce,0x3a,0xb4
+.byte	0x63,0xdf,0x4a,0x18,	0xe5,0x1a,0x31,0x82
+.byte	0x97,0x51,0x33,0x60,	0x62,0x53,0x7f,0x45
+.byte	0xb1,0x64,0x77,0xe0,	0xbb,0x6b,0xae,0x84
+.byte	0xfe,0x81,0xa0,0x1c,	0xf9,0x08,0x2b,0x94
+.byte	0x70,0x48,0x68,0x58,	0x8f,0x45,0xfd,0x19
+.byte	0x94,0xde,0x6c,0x87,	0x52,0x7b,0xf8,0xb7
+.byte	0xab,0x73,0xd3,0x23,	0x72,0x4b,0x02,0xe2
+.byte	0xe3,0x1f,0x8f,0x57,	0x66,0x55,0xab,0x2a
+.byte	0xb2,0xeb,0x28,0x07,	0x2f,0xb5,0xc2,0x03
+.byte	0x86,0xc5,0x7b,0x9a,	0xd3,0x37,0x08,0xa5
+.byte	0x30,0x28,0x87,0xf2,	0x23,0xbf,0xa5,0xb2
+.byte	0x02,0x03,0x6a,0xba,	0xed,0x16,0x82,0x5c
+.byte	0x8a,0xcf,0x1c,0x2b,	0xa7,0x79,0xb4,0x92
+.byte	0xf3,0x07,0xf2,0xf0,	0x4e,0x69,0xe2,0xa1
+.byte	0x65,0xda,0xf4,0xcd,	0x06,0x05,0xbe,0xd5
+.byte	0xd1,0x34,0x62,0x1f,	0xc4,0xa6,0xfe,0x8a
+.byte	0x34,0x2e,0x53,0x9d,	0xa2,0xf3,0x55,0xa0
+.byte	0x05,0x8a,0xe1,0x32,	0xa4,0xf6,0xeb,0x75
+.byte	0x0b,0x83,0xec,0x39,	0x40,0x60,0xef,0xaa
+.byte	0x5e,0x71,0x9f,0x06,	0xbd,0x6e,0x10,0x51
+.byte	0x3e,0x21,0x8a,0xf9,	0x96,0xdd,0x06,0x3d
+.byte	0xdd,0x3e,0x05,0xae,	0x4d,0xe6,0xbd,0x46
+.byte	0x91,0x54,0x8d,0xb5,	0x71,0xc4,0x5d,0x05
+.byte	0x04,0x06,0xd4,0x6f,	0x60,0x50,0x15,0xff
+.byte	0x19,0x98,0xfb,0x24,	0xd6,0xbd,0xe9,0x97
+.byte	0x89,0x40,0x43,0xcc,	0x67,0xd9,0x9e,0x77
+.byte	0xb0,0xe8,0x42,0xbd,	0x07,0x89,0x8b,0x88
+.byte	0xe7,0x19,0x5b,0x38,	0x79,0xc8,0xee,0xdb
+.byte	0xa1,0x7c,0x0a,0x47,	0x7c,0x42,0x0f,0xe9
+.byte	0xf8,0x84,0x1e,0xc9,	0x00,0x00,0x00,0x00
+.byte	0x09,0x80,0x86,0x83,	0x32,0x2b,0xed,0x48
+.byte	0x1e,0x11,0x70,0xac,	0x6c,0x5a,0x72,0x4e
+.byte	0xfd,0x0e,0xff,0xfb,	0x0f,0x85,0x38,0x56
+.byte	0x3d,0xae,0xd5,0x1e,	0x36,0x2d,0x39,0x27
+.byte	0x0a,0x0f,0xd9,0x64,	0x68,0x5c,0xa6,0x21
+.byte	0x9b,0x5b,0x54,0xd1,	0x24,0x36,0x2e,0x3a
+.byte	0x0c,0x0a,0x67,0xb1,	0x93,0x57,0xe7,0x0f
+.byte	0xb4,0xee,0x96,0xd2,	0x1b,0x9b,0x91,0x9e
+.byte	0x80,0xc0,0xc5,0x4f,	0x61,0xdc,0x20,0xa2
+.byte	0x5a,0x77,0x4b,0x69,	0x1c,0x12,0x1a,0x16
+.byte	0xe2,0x93,0xba,0x0a,	0xc0,0xa0,0x2a,0xe5
+.byte	0x3c,0x22,0xe0,0x43,	0x12,0x1b,0x17,0x1d
+.byte	0x0e,0x09,0x0d,0x0b,	0xf2,0x8b,0xc7,0xad
+.byte	0x2d,0xb6,0xa8,0xb9,	0x14,0x1e,0xa9,0xc8
+.byte	0x57,0xf1,0x19,0x85,	0xaf,0x75,0x07,0x4c
+.byte	0xee,0x99,0xdd,0xbb,	0xa3,0x7f,0x60,0xfd
+.byte	0xf7,0x01,0x26,0x9f,	0x5c,0x72,0xf5,0xbc
+.byte	0x44,0x66,0x3b,0xc5,	0x5b,0xfb,0x7e,0x34
+.byte	0x8b,0x43,0x29,0x76,	0xcb,0x23,0xc6,0xdc
+.byte	0xb6,0xed,0xfc,0x68,	0xb8,0xe4,0xf1,0x63
+.byte	0xd7,0x31,0xdc,0xca,	0x42,0x63,0x85,0x10
+.byte	0x13,0x97,0x22,0x40,	0x84,0xc6,0x11,0x20
+.byte	0x85,0x4a,0x24,0x7d,	0xd2,0xbb,0x3d,0xf8
+.byte	0xae,0xf9,0x32,0x11,	0xc7,0x29,0xa1,0x6d
+.byte	0x1d,0x9e,0x2f,0x4b,	0xdc,0xb2,0x30,0xf3
+.byte	0x0d,0x86,0x52,0xec,	0x77,0xc1,0xe3,0xd0
+.byte	0x2b,0xb3,0x16,0x6c,	0xa9,0x70,0xb9,0x99
+.byte	0x11,0x94,0x48,0xfa,	0x47,0xe9,0x64,0x22
+.byte	0xa8,0xfc,0x8c,0xc4,	0xa0,0xf0,0x3f,0x1a
+.byte	0x56,0x7d,0x2c,0xd8,	0x22,0x33,0x90,0xef
+.byte	0x87,0x49,0x4e,0xc7,	0xd9,0x38,0xd1,0xc1
+.byte	0x8c,0xca,0xa2,0xfe,	0x98,0xd4,0x0b,0x36
+.byte	0xa6,0xf5,0x81,0xcf,	0xa5,0x7a,0xde,0x28
+.byte	0xda,0xb7,0x8e,0x26,	0x3f,0xad,0xbf,0xa4
+.byte	0x2c,0x3a,0x9d,0xe4,	0x50,0x78,0x92,0x0d
+.byte	0x6a,0x5f,0xcc,0x9b,	0x54,0x7e,0x46,0x62
+.byte	0xf6,0x8d,0x13,0xc2,	0x90,0xd8,0xb8,0xe8
+.byte	0x2e,0x39,0xf7,0x5e,	0x82,0xc3,0xaf,0xf5
+.byte	0x9f,0x5d,0x80,0xbe,	0x69,0xd0,0x93,0x7c
+.byte	0x6f,0xd5,0x2d,0xa9,	0xcf,0x25,0x12,0xb3
+.byte	0xc8,0xac,0x99,0x3b,	0x10,0x18,0x7d,0xa7
+.byte	0xe8,0x9c,0x63,0x6e,	0xdb,0x3b,0xbb,0x7b
+.byte	0xcd,0x26,0x78,0x09,	0x6e,0x59,0x18,0xf4
+.byte	0xec,0x9a,0xb7,0x01,	0x83,0x4f,0x9a,0xa8
+.byte	0xe6,0x95,0x6e,0x65,	0xaa,0xff,0xe6,0x7e
+.byte	0x21,0xbc,0xcf,0x08,	0xef,0x15,0xe8,0xe6
+.byte	0xba,0xe7,0x9b,0xd9,	0x4a,0x6f,0x36,0xce
+.byte	0xea,0x9f,0x09,0xd4,	0x29,0xb0,0x7c,0xd6
+.byte	0x31,0xa4,0xb2,0xaf,	0x2a,0x3f,0x23,0x31
+.byte	0xc6,0xa5,0x94,0x30,	0x35,0xa2,0x66,0xc0
+.byte	0x74,0x4e,0xbc,0x37,	0xfc,0x82,0xca,0xa6
+.byte	0xe0,0x90,0xd0,0xb0,	0x33,0xa7,0xd8,0x15
+.byte	0xf1,0x04,0x98,0x4a,	0x41,0xec,0xda,0xf7
+.byte	0x7f,0xcd,0x50,0x0e,	0x17,0x91,0xf6,0x2f
+.byte	0x76,0x4d,0xd6,0x8d,	0x43,0xef,0xb0,0x4d
+.byte	0xcc,0xaa,0x4d,0x54,	0xe4,0x96,0x04,0xdf
+.byte	0x9e,0xd1,0xb5,0xe3,	0x4c,0x6a,0x88,0x1b
+.byte	0xc1,0x2c,0x1f,0xb8,	0x46,0x65,0x51,0x7f
+.byte	0x9d,0x5e,0xea,0x04,	0x01,0x8c,0x35,0x5d
+.byte	0xfa,0x87,0x74,0x73,	0xfb,0x0b,0x41,0x2e
+.byte	0xb3,0x67,0x1d,0x5a,	0x92,0xdb,0xd2,0x52
+.byte	0xe9,0x10,0x56,0x33,	0x6d,0xd6,0x47,0x13
+.byte	0x9a,0xd7,0x61,0x8c,	0x37,0xa1,0x0c,0x7a
+.byte	0x59,0xf8,0x14,0x8e,	0xeb,0x13,0x3c,0x89
+.byte	0xce,0xa9,0x27,0xee,	0xb7,0x61,0xc9,0x35
+.byte	0xe1,0x1c,0xe5,0xed,	0x7a,0x47,0xb1,0x3c
+.byte	0x9c,0xd2,0xdf,0x59,	0x55,0xf2,0x73,0x3f
+.byte	0x18,0x14,0xce,0x79,	0x73,0xc7,0x37,0xbf
+.byte	0x53,0xf7,0xcd,0xea,	0x5f,0xfd,0xaa,0x5b
+.byte	0xdf,0x3d,0x6f,0x14,	0x78,0x44,0xdb,0x86
+.byte	0xca,0xaf,0xf3,0x81,	0xb9,0x68,0xc4,0x3e
+.byte	0x38,0x24,0x34,0x2c,	0xc2,0xa3,0x40,0x5f
+.byte	0x16,0x1d,0xc3,0x72,	0xbc,0xe2,0x25,0x0c
+.byte	0x28,0x3c,0x49,0x8b,	0xff,0x0d,0x95,0x41
+.byte	0x39,0xa8,0x01,0x71,	0x08,0x0c,0xb3,0xde
+.byte	0xd8,0xb4,0xe4,0x9c,	0x64,0x56,0xc1,0x90
+.byte	0x7b,0xcb,0x84,0x61,	0xd5,0x32,0xb6,0x70
+.byte	0x48,0x6c,0x5c,0x74,	0xd0,0xb8,0x57,0x42
+
+.byte	0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38	# Td4
+.byte	0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
+.byte	0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
+.byte	0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
+.byte	0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
+.byte	0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
+.byte	0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
+.byte	0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
+.byte	0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
+.byte	0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
+.byte	0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
+.byte	0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
+.byte	0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
+.byte	0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
+.byte	0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
+.byte	0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
+.byte	0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
+.byte	0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
+.byte	0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
+.byte	0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
+.byte	0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
+.byte	0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
+.byte	0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
+.byte	0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
+.byte	0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
+.byte	0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
+.byte	0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
+.byte	0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
+.byte	0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
+.byte	0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
+.byte	0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
+.byte	0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
+
+AES_Te4:
+.byte	0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5	# Te4
+.byte	0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76
+.byte	0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0
+.byte	0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0
+.byte	0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc
+.byte	0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15
+.byte	0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a
+.byte	0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75
+.byte	0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0
+.byte	0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84
+.byte	0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b
+.byte	0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf
+.byte	0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85
+.byte	0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8
+.byte	0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5
+.byte	0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2
+.byte	0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17
+.byte	0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73
+.byte	0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88
+.byte	0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb
+.byte	0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c
+.byte	0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79
+.byte	0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9
+.byte	0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08
+.byte	0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6
+.byte	0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a
+.byte	0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e
+.byte	0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e
+.byte	0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94
+.byte	0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf
+.byte	0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68
+.byte	0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16
+
+.byte	0x01,0x00,0x00,0x00,	0x02,0x00,0x00,0x00	# rcon
+.byte	0x04,0x00,0x00,0x00,	0x08,0x00,0x00,0x00
+.byte	0x10,0x00,0x00,0x00,	0x20,0x00,0x00,0x00
+.byte	0x40,0x00,0x00,0x00,	0x80,0x00,0x00,0x00
+.byte	0x1B,0x00,0x00,0x00,	0x36,0x00,0x00,0x00
diff --git a/lib/asm/x86.S b/lib/asm/x86.S
new file mode 100644
index 0000000..2e89193
--- /dev/null
+++ b/lib/asm/x86.S
@@ -0,0 +1,3244 @@
+.file	"aes-586.s"
+.text
+.type	_x86_AES_encrypt_compact,@function
+.align	16
+_x86_AES_encrypt_compact:
+	movl	%edi,20(%esp)
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	movl	240(%edi),%esi
+	leal	-2(%esi,%esi,1),%esi
+	leal	(%edi,%esi,8),%esi
+	movl	%esi,24(%esp)
+	movl	-128(%ebp),%edi
+	movl	-96(%ebp),%esi
+	movl	-64(%ebp),%edi
+	movl	-32(%ebp),%esi
+	movl	(%ebp),%edi
+	movl	32(%ebp),%esi
+	movl	64(%ebp),%edi
+	movl	96(%ebp),%esi
+.align	16
+.L000loop:
+	movl	%eax,%esi
+	andl	$255,%esi
+	movzbl	-128(%ebp,%esi,1),%esi
+	movzbl	%bh,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%ecx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	shrl	$24,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	movl	%esi,4(%esp)
+
+	movl	%ebx,%esi
+	andl	$255,%esi
+	shrl	$16,%ebx
+	movzbl	-128(%ebp,%esi,1),%esi
+	movzbl	%ch,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%eax,%edi
+	shrl	$24,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	movl	%esi,8(%esp)
+
+	movl	%ecx,%esi
+	andl	$255,%esi
+	shrl	$24,%ecx
+	movzbl	-128(%ebp,%esi,1),%esi
+	movzbl	%dh,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%eax,%edi
+	shrl	$16,%edi
+	andl	$255,%edx
+	andl	$255,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movzbl	%bh,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+
+	andl	$255,%edx
+	movzbl	-128(%ebp,%edx,1),%edx
+	movzbl	%ah,%eax
+	movzbl	-128(%ebp,%eax,1),%eax
+	shll	$8,%eax
+	xorl	%eax,%edx
+	movl	4(%esp),%eax
+	andl	$255,%ebx
+	movzbl	-128(%ebp,%ebx,1),%ebx
+	shll	$16,%ebx
+	xorl	%ebx,%edx
+	movl	8(%esp),%ebx
+	movzbl	-128(%ebp,%ecx,1),%ecx
+	shll	$24,%ecx
+	xorl	%ecx,%edx
+	movl	%esi,%ecx
+
+	movl	$2155905152,%ebp
+	andl	%ecx,%ebp
+	leal	(%ecx,%ecx,1),%edi
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	andl	$4278124286,%edi
+	subl	%ebp,%esi
+	movl	%ecx,%ebp
+	andl	$454761243,%esi
+	rorl	$16,%ebp
+	xorl	%edi,%esi
+	movl	%ecx,%edi
+	xorl	%esi,%ecx
+	rorl	$24,%edi
+	xorl	%ebp,%esi
+	roll	$24,%ecx
+	xorl	%edi,%esi
+	movl	$2155905152,%ebp
+	xorl	%esi,%ecx
+	andl	%edx,%ebp
+	leal	(%edx,%edx,1),%edi
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	andl	$4278124286,%edi
+	subl	%ebp,%esi
+	movl	%edx,%ebp
+	andl	$454761243,%esi
+	rorl	$16,%ebp
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	xorl	%esi,%edx
+	rorl	$24,%edi
+	xorl	%ebp,%esi
+	roll	$24,%edx
+	xorl	%edi,%esi
+	movl	$2155905152,%ebp
+	xorl	%esi,%edx
+	andl	%eax,%ebp
+	leal	(%eax,%eax,1),%edi
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	andl	$4278124286,%edi
+	subl	%ebp,%esi
+	movl	%eax,%ebp
+	andl	$454761243,%esi
+	rorl	$16,%ebp
+	xorl	%edi,%esi
+	movl	%eax,%edi
+	xorl	%esi,%eax
+	rorl	$24,%edi
+	xorl	%ebp,%esi
+	roll	$24,%eax
+	xorl	%edi,%esi
+	movl	$2155905152,%ebp
+	xorl	%esi,%eax
+	andl	%ebx,%ebp
+	leal	(%ebx,%ebx,1),%edi
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	andl	$4278124286,%edi
+	subl	%ebp,%esi
+	movl	%ebx,%ebp
+	andl	$454761243,%esi
+	rorl	$16,%ebp
+	xorl	%edi,%esi
+	movl	%ebx,%edi
+	xorl	%esi,%ebx
+	rorl	$24,%edi
+	xorl	%ebp,%esi
+	roll	$24,%ebx
+	xorl	%edi,%esi
+	xorl	%esi,%ebx
+	movl	20(%esp),%edi
+	movl	28(%esp),%ebp
+	addl	$16,%edi
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	cmpl	24(%esp),%edi
+	movl	%edi,20(%esp)
+	jb	.L000loop
+	movl	%eax,%esi
+	andl	$255,%esi
+	movzbl	-128(%ebp,%esi,1),%esi
+	movzbl	%bh,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%ecx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	shrl	$24,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	movl	%esi,4(%esp)
+
+	movl	%ebx,%esi
+	andl	$255,%esi
+	shrl	$16,%ebx
+	movzbl	-128(%ebp,%esi,1),%esi
+	movzbl	%ch,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%eax,%edi
+	shrl	$24,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	movl	%esi,8(%esp)
+
+	movl	%ecx,%esi
+	andl	$255,%esi
+	shrl	$24,%ecx
+	movzbl	-128(%ebp,%esi,1),%esi
+	movzbl	%dh,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%eax,%edi
+	shrl	$16,%edi
+	andl	$255,%edx
+	andl	$255,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movzbl	%bh,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+
+	movl	20(%esp),%edi
+	andl	$255,%edx
+	movzbl	-128(%ebp,%edx,1),%edx
+	movzbl	%ah,%eax
+	movzbl	-128(%ebp,%eax,1),%eax
+	shll	$8,%eax
+	xorl	%eax,%edx
+	movl	4(%esp),%eax
+	andl	$255,%ebx
+	movzbl	-128(%ebp,%ebx,1),%ebx
+	shll	$16,%ebx
+	xorl	%ebx,%edx
+	movl	8(%esp),%ebx
+	movzbl	-128(%ebp,%ecx,1),%ecx
+	shll	$24,%ecx
+	xorl	%ecx,%edx
+	movl	%esi,%ecx
+
+	xorl	16(%edi),%eax
+	xorl	20(%edi),%ebx
+	xorl	24(%edi),%ecx
+	xorl	28(%edi),%edx
+	ret
+.size	_x86_AES_encrypt_compact,.-_x86_AES_encrypt_compact
+.type	_sse_AES_encrypt_compact,@function
+.align	16
+_sse_AES_encrypt_compact:
+	pxor	(%edi),%mm0
+	pxor	8(%edi),%mm4
+	movl	240(%edi),%esi
+	leal	-2(%esi,%esi,1),%esi
+	leal	(%edi,%esi,8),%esi
+	movl	%esi,24(%esp)
+	movl	$454761243,%eax
+	movl	%eax,8(%esp)
+	movl	%eax,12(%esp)
+	movl	-128(%ebp),%eax
+	movl	-96(%ebp),%ebx
+	movl	-64(%ebp),%ecx
+	movl	-32(%ebp),%edx
+	movl	(%ebp),%eax
+	movl	32(%ebp),%ebx
+	movl	64(%ebp),%ecx
+	movl	96(%ebp),%edx
+.align	16
+.L001loop:
+	pshufw	$8,%mm0,%mm1
+	pshufw	$13,%mm4,%mm5
+	movd	%mm1,%eax
+	movd	%mm5,%ebx
+	movl	%edi,20(%esp)
+	movzbl	%al,%esi
+	movzbl	%ah,%edx
+	pshufw	$13,%mm0,%mm2
+	movzbl	-128(%ebp,%esi,1),%ecx
+	movzbl	%bl,%edi
+	movzbl	-128(%ebp,%edx,1),%edx
+	shrl	$16,%eax
+	shll	$8,%edx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%bh,%edi
+	shll	$16,%esi
+	pshufw	$8,%mm4,%mm6
+	orl	%esi,%ecx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%ah,%edi
+	shll	$24,%esi
+	shrl	$16,%ebx
+	orl	%esi,%edx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%bh,%edi
+	shll	$8,%esi
+	orl	%esi,%ecx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%al,%edi
+	shll	$24,%esi
+	orl	%esi,%ecx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%bl,%edi
+	movd	%mm2,%eax
+	movd	%ecx,%mm0
+	movzbl	-128(%ebp,%edi,1),%ecx
+	movzbl	%ah,%edi
+	shll	$16,%ecx
+	movd	%mm6,%ebx
+	orl	%esi,%ecx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%bh,%edi
+	shll	$24,%esi
+	orl	%esi,%ecx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%bl,%edi
+	shll	$8,%esi
+	shrl	$16,%ebx
+	orl	%esi,%ecx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%al,%edi
+	shrl	$16,%eax
+	movd	%ecx,%mm1
+	movzbl	-128(%ebp,%edi,1),%ecx
+	movzbl	%ah,%edi
+	shll	$16,%ecx
+	andl	$255,%eax
+	orl	%esi,%ecx
+	punpckldq	%mm1,%mm0
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%bh,%edi
+	shll	$24,%esi
+	andl	$255,%ebx
+	movzbl	-128(%ebp,%eax,1),%eax
+	orl	%esi,%ecx
+	shll	$16,%eax
+	movzbl	-128(%ebp,%edi,1),%esi
+	orl	%eax,%edx
+	shll	$8,%esi
+	movzbl	-128(%ebp,%ebx,1),%ebx
+	orl	%esi,%ecx
+	orl	%ebx,%edx
+	movl	20(%esp),%edi
+	movd	%ecx,%mm4
+	movd	%edx,%mm5
+	punpckldq	%mm5,%mm4
+	addl	$16,%edi
+	cmpl	24(%esp),%edi
+	ja	.L002out
+	movq	8(%esp),%mm2
+	pxor	%mm3,%mm3
+	pxor	%mm7,%mm7
+	movq	%mm0,%mm1
+	movq	%mm4,%mm5
+	pcmpgtb	%mm0,%mm3
+	pcmpgtb	%mm4,%mm7
+	pand	%mm2,%mm3
+	pand	%mm2,%mm7
+	pshufw	$177,%mm0,%mm2
+	pshufw	$177,%mm4,%mm6
+	paddb	%mm0,%mm0
+	paddb	%mm4,%mm4
+	pxor	%mm3,%mm0
+	pxor	%mm7,%mm4
+	pshufw	$177,%mm2,%mm3
+	pshufw	$177,%mm6,%mm7
+	pxor	%mm0,%mm1
+	pxor	%mm4,%mm5
+	pxor	%mm2,%mm0
+	pxor	%mm6,%mm4
+	movq	%mm3,%mm2
+	movq	%mm7,%mm6
+	pslld	$8,%mm3
+	pslld	$8,%mm7
+	psrld	$24,%mm2
+	psrld	$24,%mm6
+	pxor	%mm3,%mm0
+	pxor	%mm7,%mm4
+	pxor	%mm2,%mm0
+	pxor	%mm6,%mm4
+	movq	%mm1,%mm3
+	movq	%mm5,%mm7
+	movq	(%edi),%mm2
+	movq	8(%edi),%mm6
+	psrld	$8,%mm1
+	psrld	$8,%mm5
+	movl	-128(%ebp),%eax
+	pslld	$24,%mm3
+	pslld	$24,%mm7
+	movl	-64(%ebp),%ebx
+	pxor	%mm1,%mm0
+	pxor	%mm5,%mm4
+	movl	(%ebp),%ecx
+	pxor	%mm3,%mm0
+	pxor	%mm7,%mm4
+	movl	64(%ebp),%edx
+	pxor	%mm2,%mm0
+	pxor	%mm6,%mm4
+	jmp	.L001loop
+.align	16
+.L002out:
+	pxor	(%edi),%mm0
+	pxor	8(%edi),%mm4
+	ret
+.size	_sse_AES_encrypt_compact,.-_sse_AES_encrypt_compact
+.type	_x86_AES_encrypt,@function
+.align	16
+_x86_AES_encrypt:
+	movl	%edi,20(%esp)
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	movl	240(%edi),%esi
+	leal	-2(%esi,%esi,1),%esi
+	leal	(%edi,%esi,8),%esi
+	movl	%esi,24(%esp)
+.align	16
+.L003loop:
+	movl	%eax,%esi
+	andl	$255,%esi
+	movl	(%ebp,%esi,8),%esi
+	movzbl	%bh,%edi
+	xorl	3(%ebp,%edi,8),%esi
+	movl	%ecx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	xorl	2(%ebp,%edi,8),%esi
+	movl	%edx,%edi
+	shrl	$24,%edi
+	xorl	1(%ebp,%edi,8),%esi
+	movl	%esi,4(%esp)
+
+	movl	%ebx,%esi
+	andl	$255,%esi
+	shrl	$16,%ebx
+	movl	(%ebp,%esi,8),%esi
+	movzbl	%ch,%edi
+	xorl	3(%ebp,%edi,8),%esi
+	movl	%edx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	xorl	2(%ebp,%edi,8),%esi
+	movl	%eax,%edi
+	shrl	$24,%edi
+	xorl	1(%ebp,%edi,8),%esi
+	movl	%esi,8(%esp)
+
+	movl	%ecx,%esi
+	andl	$255,%esi
+	shrl	$24,%ecx
+	movl	(%ebp,%esi,8),%esi
+	movzbl	%dh,%edi
+	xorl	3(%ebp,%edi,8),%esi
+	movl	%eax,%edi
+	shrl	$16,%edi
+	andl	$255,%edx
+	andl	$255,%edi
+	xorl	2(%ebp,%edi,8),%esi
+	movzbl	%bh,%edi
+	xorl	1(%ebp,%edi,8),%esi
+
+	movl	20(%esp),%edi
+	movl	(%ebp,%edx,8),%edx
+	movzbl	%ah,%eax
+	xorl	3(%ebp,%eax,8),%edx
+	movl	4(%esp),%eax
+	andl	$255,%ebx
+	xorl	2(%ebp,%ebx,8),%edx
+	movl	8(%esp),%ebx
+	xorl	1(%ebp,%ecx,8),%edx
+	movl	%esi,%ecx
+
+	addl	$16,%edi
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	cmpl	24(%esp),%edi
+	movl	%edi,20(%esp)
+	jb	.L003loop
+	movl	%eax,%esi
+	andl	$255,%esi
+	movl	2(%ebp,%esi,8),%esi
+	andl	$255,%esi
+	movzbl	%bh,%edi
+	movl	(%ebp,%edi,8),%edi
+	andl	$65280,%edi
+	xorl	%edi,%esi
+	movl	%ecx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movl	(%ebp,%edi,8),%edi
+	andl	$16711680,%edi
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	shrl	$24,%edi
+	movl	2(%ebp,%edi,8),%edi
+	andl	$4278190080,%edi
+	xorl	%edi,%esi
+	movl	%esi,4(%esp)
+	movl	%ebx,%esi
+	andl	$255,%esi
+	shrl	$16,%ebx
+	movl	2(%ebp,%esi,8),%esi
+	andl	$255,%esi
+	movzbl	%ch,%edi
+	movl	(%ebp,%edi,8),%edi
+	andl	$65280,%edi
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movl	(%ebp,%edi,8),%edi
+	andl	$16711680,%edi
+	xorl	%edi,%esi
+	movl	%eax,%edi
+	shrl	$24,%edi
+	movl	2(%ebp,%edi,8),%edi
+	andl	$4278190080,%edi
+	xorl	%edi,%esi
+	movl	%esi,8(%esp)
+	movl	%ecx,%esi
+	andl	$255,%esi
+	shrl	$24,%ecx
+	movl	2(%ebp,%esi,8),%esi
+	andl	$255,%esi
+	movzbl	%dh,%edi
+	movl	(%ebp,%edi,8),%edi
+	andl	$65280,%edi
+	xorl	%edi,%esi
+	movl	%eax,%edi
+	shrl	$16,%edi
+	andl	$255,%edx
+	andl	$255,%edi
+	movl	(%ebp,%edi,8),%edi
+	andl	$16711680,%edi
+	xorl	%edi,%esi
+	movzbl	%bh,%edi
+	movl	2(%ebp,%edi,8),%edi
+	andl	$4278190080,%edi
+	xorl	%edi,%esi
+	movl	20(%esp),%edi
+	andl	$255,%edx
+	movl	2(%ebp,%edx,8),%edx
+	andl	$255,%edx
+	movzbl	%ah,%eax
+	movl	(%ebp,%eax,8),%eax
+	andl	$65280,%eax
+	xorl	%eax,%edx
+	movl	4(%esp),%eax
+	andl	$255,%ebx
+	movl	(%ebp,%ebx,8),%ebx
+	andl	$16711680,%ebx
+	xorl	%ebx,%edx
+	movl	8(%esp),%ebx
+	movl	2(%ebp,%ecx,8),%ecx
+	andl	$4278190080,%ecx
+	xorl	%ecx,%edx
+	movl	%esi,%ecx
+	addl	$16,%edi
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	ret
+.align	64
+.LAES_Te:
+.long	2774754246,2774754246
+.long	2222750968,2222750968
+.long	2574743534,2574743534
+.long	2373680118,2373680118
+.long	234025727,234025727
+.long	3177933782,3177933782
+.long	2976870366,2976870366
+.long	1422247313,1422247313
+.long	1345335392,1345335392
+.long	50397442,50397442
+.long	2842126286,2842126286
+.long	2099981142,2099981142
+.long	436141799,436141799
+.long	1658312629,1658312629
+.long	3870010189,3870010189
+.long	2591454956,2591454956
+.long	1170918031,1170918031
+.long	2642575903,2642575903
+.long	1086966153,1086966153
+.long	2273148410,2273148410
+.long	368769775,368769775
+.long	3948501426,3948501426
+.long	3376891790,3376891790
+.long	200339707,200339707
+.long	3970805057,3970805057
+.long	1742001331,1742001331
+.long	4255294047,4255294047
+.long	3937382213,3937382213
+.long	3214711843,3214711843
+.long	4154762323,4154762323
+.long	2524082916,2524082916
+.long	1539358875,1539358875
+.long	3266819957,3266819957
+.long	486407649,486407649
+.long	2928907069,2928907069
+.long	1780885068,1780885068
+.long	1513502316,1513502316
+.long	1094664062,1094664062
+.long	49805301,49805301
+.long	1338821763,1338821763
+.long	1546925160,1546925160
+.long	4104496465,4104496465
+.long	887481809,887481809
+.long	150073849,150073849
+.long	2473685474,2473685474
+.long	1943591083,1943591083
+.long	1395732834,1395732834
+.long	1058346282,1058346282
+.long	201589768,201589768
+.long	1388824469,1388824469
+.long	1696801606,1696801606
+.long	1589887901,1589887901
+.long	672667696,672667696
+.long	2711000631,2711000631
+.long	251987210,251987210
+.long	3046808111,3046808111
+.long	151455502,151455502
+.long	907153956,907153956
+.long	2608889883,2608889883
+.long	1038279391,1038279391
+.long	652995533,652995533
+.long	1764173646,1764173646
+.long	3451040383,3451040383
+.long	2675275242,2675275242
+.long	453576978,453576978
+.long	2659418909,2659418909
+.long	1949051992,1949051992
+.long	773462580,773462580
+.long	756751158,756751158
+.long	2993581788,2993581788
+.long	3998898868,3998898868
+.long	4221608027,4221608027
+.long	4132590244,4132590244
+.long	1295727478,1295727478
+.long	1641469623,1641469623
+.long	3467883389,3467883389
+.long	2066295122,2066295122
+.long	1055122397,1055122397
+.long	1898917726,1898917726
+.long	2542044179,2542044179
+.long	4115878822,4115878822
+.long	1758581177,1758581177
+.long	0,0
+.long	753790401,753790401
+.long	1612718144,1612718144
+.long	536673507,536673507
+.long	3367088505,3367088505
+.long	3982187446,3982187446
+.long	3194645204,3194645204
+.long	1187761037,1187761037
+.long	3653156455,3653156455
+.long	1262041458,1262041458
+.long	3729410708,3729410708
+.long	3561770136,3561770136
+.long	3898103984,3898103984
+.long	1255133061,1255133061
+.long	1808847035,1808847035
+.long	720367557,720367557
+.long	3853167183,3853167183
+.long	385612781,385612781
+.long	3309519750,3309519750
+.long	3612167578,3612167578
+.long	1429418854,1429418854
+.long	2491778321,2491778321
+.long	3477423498,3477423498
+.long	284817897,284817897
+.long	100794884,100794884
+.long	2172616702,2172616702
+.long	4031795360,4031795360
+.long	1144798328,1144798328
+.long	3131023141,3131023141
+.long	3819481163,3819481163
+.long	4082192802,4082192802
+.long	4272137053,4272137053
+.long	3225436288,3225436288
+.long	2324664069,2324664069
+.long	2912064063,2912064063
+.long	3164445985,3164445985
+.long	1211644016,1211644016
+.long	83228145,83228145
+.long	3753688163,3753688163
+.long	3249976951,3249976951
+.long	1977277103,1977277103
+.long	1663115586,1663115586
+.long	806359072,806359072
+.long	452984805,452984805
+.long	250868733,250868733
+.long	1842533055,1842533055
+.long	1288555905,1288555905
+.long	336333848,336333848
+.long	890442534,890442534
+.long	804056259,804056259
+.long	3781124030,3781124030
+.long	2727843637,2727843637
+.long	3427026056,3427026056
+.long	957814574,957814574
+.long	1472513171,1472513171
+.long	4071073621,4071073621
+.long	2189328124,2189328124
+.long	1195195770,1195195770
+.long	2892260552,2892260552
+.long	3881655738,3881655738
+.long	723065138,723065138
+.long	2507371494,2507371494
+.long	2690670784,2690670784
+.long	2558624025,2558624025
+.long	3511635870,3511635870
+.long	2145180835,2145180835
+.long	1713513028,1713513028
+.long	2116692564,2116692564
+.long	2878378043,2878378043
+.long	2206763019,2206763019
+.long	3393603212,3393603212
+.long	703524551,703524551
+.long	3552098411,3552098411
+.long	1007948840,1007948840
+.long	2044649127,2044649127
+.long	3797835452,3797835452
+.long	487262998,487262998
+.long	1994120109,1994120109
+.long	1004593371,1004593371
+.long	1446130276,1446130276
+.long	1312438900,1312438900
+.long	503974420,503974420
+.long	3679013266,3679013266
+.long	168166924,168166924
+.long	1814307912,1814307912
+.long	3831258296,3831258296
+.long	1573044895,1573044895
+.long	1859376061,1859376061
+.long	4021070915,4021070915
+.long	2791465668,2791465668
+.long	2828112185,2828112185
+.long	2761266481,2761266481
+.long	937747667,937747667
+.long	2339994098,2339994098
+.long	854058965,854058965
+.long	1137232011,1137232011
+.long	1496790894,1496790894
+.long	3077402074,3077402074
+.long	2358086913,2358086913
+.long	1691735473,1691735473
+.long	3528347292,3528347292
+.long	3769215305,3769215305
+.long	3027004632,3027004632
+.long	4199962284,4199962284
+.long	133494003,133494003
+.long	636152527,636152527
+.long	2942657994,2942657994
+.long	2390391540,2390391540
+.long	3920539207,3920539207
+.long	403179536,403179536
+.long	3585784431,3585784431
+.long	2289596656,2289596656
+.long	1864705354,1864705354
+.long	1915629148,1915629148
+.long	605822008,605822008
+.long	4054230615,4054230615
+.long	3350508659,3350508659
+.long	1371981463,1371981463
+.long	602466507,602466507
+.long	2094914977,2094914977
+.long	2624877800,2624877800
+.long	555687742,555687742
+.long	3712699286,3712699286
+.long	3703422305,3703422305
+.long	2257292045,2257292045
+.long	2240449039,2240449039
+.long	2423288032,2423288032
+.long	1111375484,1111375484
+.long	3300242801,3300242801
+.long	2858837708,2858837708
+.long	3628615824,3628615824
+.long	84083462,84083462
+.long	32962295,32962295
+.long	302911004,302911004
+.long	2741068226,2741068226
+.long	1597322602,1597322602
+.long	4183250862,4183250862
+.long	3501832553,3501832553
+.long	2441512471,2441512471
+.long	1489093017,1489093017
+.long	656219450,656219450
+.long	3114180135,3114180135
+.long	954327513,954327513
+.long	335083755,335083755
+.long	3013122091,3013122091
+.long	856756514,856756514
+.long	3144247762,3144247762
+.long	1893325225,1893325225
+.long	2307821063,2307821063
+.long	2811532339,2811532339
+.long	3063651117,3063651117
+.long	572399164,572399164
+.long	2458355477,2458355477
+.long	552200649,552200649
+.long	1238290055,1238290055
+.long	4283782570,4283782570
+.long	2015897680,2015897680
+.long	2061492133,2061492133
+.long	2408352771,2408352771
+.long	4171342169,4171342169
+.long	2156497161,2156497161
+.long	386731290,386731290
+.long	3669999461,3669999461
+.long	837215959,837215959
+.long	3326231172,3326231172
+.long	3093850320,3093850320
+.long	3275833730,3275833730
+.long	2962856233,2962856233
+.long	1999449434,1999449434
+.long	286199582,286199582
+.long	3417354363,3417354363
+.long	4233385128,4233385128
+.long	3602627437,3602627437
+.long	974525996,974525996
+.byte	99,124,119,123,242,107,111,197
+.byte	48,1,103,43,254,215,171,118
+.byte	202,130,201,125,250,89,71,240
+.byte	173,212,162,175,156,164,114,192
+.byte	183,253,147,38,54,63,247,204
+.byte	52,165,229,241,113,216,49,21
+.byte	4,199,35,195,24,150,5,154
+.byte	7,18,128,226,235,39,178,117
+.byte	9,131,44,26,27,110,90,160
+.byte	82,59,214,179,41,227,47,132
+.byte	83,209,0,237,32,252,177,91
+.byte	106,203,190,57,74,76,88,207
+.byte	208,239,170,251,67,77,51,133
+.byte	69,249,2,127,80,60,159,168
+.byte	81,163,64,143,146,157,56,245
+.byte	188,182,218,33,16,255,243,210
+.byte	205,12,19,236,95,151,68,23
+.byte	196,167,126,61,100,93,25,115
+.byte	96,129,79,220,34,42,144,136
+.byte	70,238,184,20,222,94,11,219
+.byte	224,50,58,10,73,6,36,92
+.byte	194,211,172,98,145,149,228,121
+.byte	231,200,55,109,141,213,78,169
+.byte	108,86,244,234,101,122,174,8
+.byte	186,120,37,46,28,166,180,198
+.byte	232,221,116,31,75,189,139,138
+.byte	112,62,181,102,72,3,246,14
+.byte	97,53,87,185,134,193,29,158
+.byte	225,248,152,17,105,217,142,148
+.byte	155,30,135,233,206,85,40,223
+.byte	140,161,137,13,191,230,66,104
+.byte	65,153,45,15,176,84,187,22
+.byte	99,124,119,123,242,107,111,197
+.byte	48,1,103,43,254,215,171,118
+.byte	202,130,201,125,250,89,71,240
+.byte	173,212,162,175,156,164,114,192
+.byte	183,253,147,38,54,63,247,204
+.byte	52,165,229,241,113,216,49,21
+.byte	4,199,35,195,24,150,5,154
+.byte	7,18,128,226,235,39,178,117
+.byte	9,131,44,26,27,110,90,160
+.byte	82,59,214,179,41,227,47,132
+.byte	83,209,0,237,32,252,177,91
+.byte	106,203,190,57,74,76,88,207
+.byte	208,239,170,251,67,77,51,133
+.byte	69,249,2,127,80,60,159,168
+.byte	81,163,64,143,146,157,56,245
+.byte	188,182,218,33,16,255,243,210
+.byte	205,12,19,236,95,151,68,23
+.byte	196,167,126,61,100,93,25,115
+.byte	96,129,79,220,34,42,144,136
+.byte	70,238,184,20,222,94,11,219
+.byte	224,50,58,10,73,6,36,92
+.byte	194,211,172,98,145,149,228,121
+.byte	231,200,55,109,141,213,78,169
+.byte	108,86,244,234,101,122,174,8
+.byte	186,120,37,46,28,166,180,198
+.byte	232,221,116,31,75,189,139,138
+.byte	112,62,181,102,72,3,246,14
+.byte	97,53,87,185,134,193,29,158
+.byte	225,248,152,17,105,217,142,148
+.byte	155,30,135,233,206,85,40,223
+.byte	140,161,137,13,191,230,66,104
+.byte	65,153,45,15,176,84,187,22
+.byte	99,124,119,123,242,107,111,197
+.byte	48,1,103,43,254,215,171,118
+.byte	202,130,201,125,250,89,71,240
+.byte	173,212,162,175,156,164,114,192
+.byte	183,253,147,38,54,63,247,204
+.byte	52,165,229,241,113,216,49,21
+.byte	4,199,35,195,24,150,5,154
+.byte	7,18,128,226,235,39,178,117
+.byte	9,131,44,26,27,110,90,160
+.byte	82,59,214,179,41,227,47,132
+.byte	83,209,0,237,32,252,177,91
+.byte	106,203,190,57,74,76,88,207
+.byte	208,239,170,251,67,77,51,133
+.byte	69,249,2,127,80,60,159,168
+.byte	81,163,64,143,146,157,56,245
+.byte	188,182,218,33,16,255,243,210
+.byte	205,12,19,236,95,151,68,23
+.byte	196,167,126,61,100,93,25,115
+.byte	96,129,79,220,34,42,144,136
+.byte	70,238,184,20,222,94,11,219
+.byte	224,50,58,10,73,6,36,92
+.byte	194,211,172,98,145,149,228,121
+.byte	231,200,55,109,141,213,78,169
+.byte	108,86,244,234,101,122,174,8
+.byte	186,120,37,46,28,166,180,198
+.byte	232,221,116,31,75,189,139,138
+.byte	112,62,181,102,72,3,246,14
+.byte	97,53,87,185,134,193,29,158
+.byte	225,248,152,17,105,217,142,148
+.byte	155,30,135,233,206,85,40,223
+.byte	140,161,137,13,191,230,66,104
+.byte	65,153,45,15,176,84,187,22
+.byte	99,124,119,123,242,107,111,197
+.byte	48,1,103,43,254,215,171,118
+.byte	202,130,201,125,250,89,71,240
+.byte	173,212,162,175,156,164,114,192
+.byte	183,253,147,38,54,63,247,204
+.byte	52,165,229,241,113,216,49,21
+.byte	4,199,35,195,24,150,5,154
+.byte	7,18,128,226,235,39,178,117
+.byte	9,131,44,26,27,110,90,160
+.byte	82,59,214,179,41,227,47,132
+.byte	83,209,0,237,32,252,177,91
+.byte	106,203,190,57,74,76,88,207
+.byte	208,239,170,251,67,77,51,133
+.byte	69,249,2,127,80,60,159,168
+.byte	81,163,64,143,146,157,56,245
+.byte	188,182,218,33,16,255,243,210
+.byte	205,12,19,236,95,151,68,23
+.byte	196,167,126,61,100,93,25,115
+.byte	96,129,79,220,34,42,144,136
+.byte	70,238,184,20,222,94,11,219
+.byte	224,50,58,10,73,6,36,92
+.byte	194,211,172,98,145,149,228,121
+.byte	231,200,55,109,141,213,78,169
+.byte	108,86,244,234,101,122,174,8
+.byte	186,120,37,46,28,166,180,198
+.byte	232,221,116,31,75,189,139,138
+.byte	112,62,181,102,72,3,246,14
+.byte	97,53,87,185,134,193,29,158
+.byte	225,248,152,17,105,217,142,148
+.byte	155,30,135,233,206,85,40,223
+.byte	140,161,137,13,191,230,66,104
+.byte	65,153,45,15,176,84,187,22
+.long	1,2,4,8
+.long	16,32,64,128
+.long	27,54,0,0
+.long	0,0,0,0
+.size	_x86_AES_encrypt,.-_x86_AES_encrypt
+.globl	AES_encrypt
+.type	AES_encrypt,@function
+.align	16
+AES_encrypt:
+.L_AES_encrypt_begin:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	movl	20(%esp),%esi
+	movl	28(%esp),%edi
+	movl	%esp,%eax
+	subl	$36,%esp
+	andl	$-64,%esp
+	leal	-127(%edi),%ebx
+	subl	%esp,%ebx
+	negl	%ebx
+	andl	$960,%ebx
+	subl	%ebx,%esp
+	addl	$4,%esp
+	movl	%eax,28(%esp)
+	call	.L004pic_point
+.L004pic_point:
+	popl	%ebp
+	leal	OPENSSL_ia32cap_P,%eax
+	leal	.LAES_Te-.L004pic_point(%ebp),%ebp
+	leal	764(%esp),%ebx
+	subl	%ebp,%ebx
+	andl	$768,%ebx
+	leal	2176(%ebp,%ebx,1),%ebp
+	btl	$25,(%eax)
+	jnc	.L005x86
+	movq	(%esi),%mm0
+	movq	8(%esi),%mm4
+	call	_sse_AES_encrypt_compact
+	movl	28(%esp),%esp
+	movl	24(%esp),%esi
+	movq	%mm0,(%esi)
+	movq	%mm4,8(%esi)
+	emms
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.align	16
+.L005x86:
+	movl	%ebp,24(%esp)
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	call	_x86_AES_encrypt_compact
+	movl	28(%esp),%esp
+	movl	24(%esp),%esi
+	movl	%eax,(%esi)
+	movl	%ebx,4(%esi)
+	movl	%ecx,8(%esi)
+	movl	%edx,12(%esi)
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.size	AES_encrypt,.-.L_AES_encrypt_begin
+.type	_x86_AES_decrypt_compact,@function
+.align	16
+_x86_AES_decrypt_compact:
+	movl	%edi,20(%esp)
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	movl	240(%edi),%esi
+	leal	-2(%esi,%esi,1),%esi
+	leal	(%edi,%esi,8),%esi
+	movl	%esi,24(%esp)
+	movl	-128(%ebp),%edi
+	movl	-96(%ebp),%esi
+	movl	-64(%ebp),%edi
+	movl	-32(%ebp),%esi
+	movl	(%ebp),%edi
+	movl	32(%ebp),%esi
+	movl	64(%ebp),%edi
+	movl	96(%ebp),%esi
+.align	16
+.L006loop:
+	movl	%eax,%esi
+	andl	$255,%esi
+	movzbl	-128(%ebp,%esi,1),%esi
+	movzbl	%dh,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%ecx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%ebx,%edi
+	shrl	$24,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	movl	%esi,4(%esp)
+	movl	%ebx,%esi
+	andl	$255,%esi
+	movzbl	-128(%ebp,%esi,1),%esi
+	movzbl	%ah,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%ecx,%edi
+	shrl	$24,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	movl	%esi,8(%esp)
+	movl	%ecx,%esi
+	andl	$255,%esi
+	movzbl	-128(%ebp,%esi,1),%esi
+	movzbl	%bh,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%eax,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	shrl	$24,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	andl	$255,%edx
+	movzbl	-128(%ebp,%edx,1),%edx
+	movzbl	%ch,%ecx
+	movzbl	-128(%ebp,%ecx,1),%ecx
+	shll	$8,%ecx
+	xorl	%ecx,%edx
+	movl	%esi,%ecx
+	shrl	$16,%ebx
+	andl	$255,%ebx
+	movzbl	-128(%ebp,%ebx,1),%ebx
+	shll	$16,%ebx
+	xorl	%ebx,%edx
+	shrl	$24,%eax
+	movzbl	-128(%ebp,%eax,1),%eax
+	shll	$24,%eax
+	xorl	%eax,%edx
+	movl	$2155905152,%edi
+	andl	%ecx,%edi
+	movl	%edi,%esi
+	shrl	$7,%edi
+	leal	(%ecx,%ecx,1),%eax
+	subl	%edi,%esi
+	andl	$4278124286,%eax
+	andl	$454761243,%esi
+	xorl	%esi,%eax
+	movl	$2155905152,%edi
+	andl	%eax,%edi
+	movl	%edi,%esi
+	shrl	$7,%edi
+	leal	(%eax,%eax,1),%ebx
+	subl	%edi,%esi
+	andl	$4278124286,%ebx
+	andl	$454761243,%esi
+	xorl	%ecx,%eax
+	xorl	%esi,%ebx
+	movl	$2155905152,%edi
+	andl	%ebx,%edi
+	movl	%edi,%esi
+	shrl	$7,%edi
+	leal	(%ebx,%ebx,1),%ebp
+	subl	%edi,%esi
+	andl	$4278124286,%ebp
+	andl	$454761243,%esi
+	xorl	%ecx,%ebx
+	roll	$8,%ecx
+	xorl	%esi,%ebp
+	xorl	%eax,%ecx
+	xorl	%ebp,%eax
+	xorl	%ebx,%ecx
+	xorl	%ebp,%ebx
+	roll	$24,%eax
+	xorl	%ebp,%ecx
+	roll	$16,%ebx
+	xorl	%eax,%ecx
+	roll	$8,%ebp
+	xorl	%ebx,%ecx
+	movl	4(%esp),%eax
+	xorl	%ebp,%ecx
+	movl	%ecx,12(%esp)
+	movl	$2155905152,%edi
+	andl	%edx,%edi
+	movl	%edi,%esi
+	shrl	$7,%edi
+	leal	(%edx,%edx,1),%ebx
+	subl	%edi,%esi
+	andl	$4278124286,%ebx
+	andl	$454761243,%esi
+	xorl	%esi,%ebx
+	movl	$2155905152,%edi
+	andl	%ebx,%edi
+	movl	%edi,%esi
+	shrl	$7,%edi
+	leal	(%ebx,%ebx,1),%ecx
+	subl	%edi,%esi
+	andl	$4278124286,%ecx
+	andl	$454761243,%esi
+	xorl	%edx,%ebx
+	xorl	%esi,%ecx
+	movl	$2155905152,%edi
+	andl	%ecx,%edi
+	movl	%edi,%esi
+	shrl	$7,%edi
+	leal	(%ecx,%ecx,1),%ebp
+	subl	%edi,%esi
+	andl	$4278124286,%ebp
+	andl	$454761243,%esi
+	xorl	%edx,%ecx
+	roll	$8,%edx
+	xorl	%esi,%ebp
+	xorl	%ebx,%edx
+	xorl	%ebp,%ebx
+	xorl	%ecx,%edx
+	xorl	%ebp,%ecx
+	roll	$24,%ebx
+	xorl	%ebp,%edx
+	roll	$16,%ecx
+	xorl	%ebx,%edx
+	roll	$8,%ebp
+	xorl	%ecx,%edx
+	movl	8(%esp),%ebx
+	xorl	%ebp,%edx
+	movl	%edx,16(%esp)
+	movl	$2155905152,%edi
+	andl	%eax,%edi
+	movl	%edi,%esi
+	shrl	$7,%edi
+	leal	(%eax,%eax,1),%ecx
+	subl	%edi,%esi
+	andl	$4278124286,%ecx
+	andl	$454761243,%esi
+	xorl	%esi,%ecx
+	movl	$2155905152,%edi
+	andl	%ecx,%edi
+	movl	%edi,%esi
+	shrl	$7,%edi
+	leal	(%ecx,%ecx,1),%edx
+	subl	%edi,%esi
+	andl	$4278124286,%edx
+	andl	$454761243,%esi
+	xorl	%eax,%ecx
+	xorl	%esi,%edx
+	movl	$2155905152,%edi
+	andl	%edx,%edi
+	movl	%edi,%esi
+	shrl	$7,%edi
+	leal	(%edx,%edx,1),%ebp
+	subl	%edi,%esi
+	andl	$4278124286,%ebp
+	andl	$454761243,%esi
+	xorl	%eax,%edx
+	roll	$8,%eax
+	xorl	%esi,%ebp
+	xorl	%ecx,%eax
+	xorl	%ebp,%ecx
+	xorl	%edx,%eax
+	xorl	%ebp,%edx
+	roll	$24,%ecx
+	xorl	%ebp,%eax
+	roll	$16,%edx
+	xorl	%ecx,%eax
+	roll	$8,%ebp
+	xorl	%edx,%eax
+	xorl	%ebp,%eax
+	movl	$2155905152,%edi
+	andl	%ebx,%edi
+	movl	%edi,%esi
+	shrl	$7,%edi
+	leal	(%ebx,%ebx,1),%ecx
+	subl	%edi,%esi
+	andl	$4278124286,%ecx
+	andl	$454761243,%esi
+	xorl	%esi,%ecx
+	movl	$2155905152,%edi
+	andl	%ecx,%edi
+	movl	%edi,%esi
+	shrl	$7,%edi
+	leal	(%ecx,%ecx,1),%edx
+	subl	%edi,%esi
+	andl	$4278124286,%edx
+	andl	$454761243,%esi
+	xorl	%ebx,%ecx
+	xorl	%esi,%edx
+	movl	$2155905152,%edi
+	andl	%edx,%edi
+	movl	%edi,%esi
+	shrl	$7,%edi
+	leal	(%edx,%edx,1),%ebp
+	subl	%edi,%esi
+	andl	$4278124286,%ebp
+	andl	$454761243,%esi
+	xorl	%ebx,%edx
+	roll	$8,%ebx
+	xorl	%esi,%ebp
+	xorl	%ecx,%ebx
+	xorl	%ebp,%ecx
+	xorl	%edx,%ebx
+	xorl	%ebp,%edx
+	roll	$24,%ecx
+	xorl	%ebp,%ebx
+	roll	$16,%edx
+	xorl	%ecx,%ebx
+	roll	$8,%ebp
+	xorl	%edx,%ebx
+	movl	12(%esp),%ecx
+	xorl	%ebp,%ebx
+	movl	16(%esp),%edx
+	movl	20(%esp),%edi
+	movl	28(%esp),%ebp
+	addl	$16,%edi
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	cmpl	24(%esp),%edi
+	movl	%edi,20(%esp)
+	jb	.L006loop
+	movl	%eax,%esi
+	andl	$255,%esi
+	movzbl	-128(%ebp,%esi,1),%esi
+	movzbl	%dh,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%ecx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%ebx,%edi
+	shrl	$24,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	movl	%esi,4(%esp)
+	movl	%ebx,%esi
+	andl	$255,%esi
+	movzbl	-128(%ebp,%esi,1),%esi
+	movzbl	%ah,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%ecx,%edi
+	shrl	$24,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	movl	%esi,8(%esp)
+	movl	%ecx,%esi
+	andl	$255,%esi
+	movzbl	-128(%ebp,%esi,1),%esi
+	movzbl	%bh,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%eax,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	shrl	$24,%edi
+	movzbl	-128(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	movl	20(%esp),%edi
+	andl	$255,%edx
+	movzbl	-128(%ebp,%edx,1),%edx
+	movzbl	%ch,%ecx
+	movzbl	-128(%ebp,%ecx,1),%ecx
+	shll	$8,%ecx
+	xorl	%ecx,%edx
+	movl	%esi,%ecx
+	shrl	$16,%ebx
+	andl	$255,%ebx
+	movzbl	-128(%ebp,%ebx,1),%ebx
+	shll	$16,%ebx
+	xorl	%ebx,%edx
+	movl	8(%esp),%ebx
+	shrl	$24,%eax
+	movzbl	-128(%ebp,%eax,1),%eax
+	shll	$24,%eax
+	xorl	%eax,%edx
+	movl	4(%esp),%eax
+	xorl	16(%edi),%eax
+	xorl	20(%edi),%ebx
+	xorl	24(%edi),%ecx
+	xorl	28(%edi),%edx
+	ret
+.size	_x86_AES_decrypt_compact,.-_x86_AES_decrypt_compact
+.type	_sse_AES_decrypt_compact,@function
+.align	16
+_sse_AES_decrypt_compact:
+	pxor	(%edi),%mm0
+	pxor	8(%edi),%mm4
+	movl	240(%edi),%esi
+	leal	-2(%esi,%esi,1),%esi
+	leal	(%edi,%esi,8),%esi
+	movl	%esi,24(%esp)
+	movl	$454761243,%eax
+	movl	%eax,8(%esp)
+	movl	%eax,12(%esp)
+	movl	-128(%ebp),%eax
+	movl	-96(%ebp),%ebx
+	movl	-64(%ebp),%ecx
+	movl	-32(%ebp),%edx
+	movl	(%ebp),%eax
+	movl	32(%ebp),%ebx
+	movl	64(%ebp),%ecx
+	movl	96(%ebp),%edx
+.align	16
+.L007loop:
+	pshufw	$12,%mm0,%mm1
+	pshufw	$9,%mm4,%mm5
+	movd	%mm1,%eax
+	movd	%mm5,%ebx
+	movl	%edi,20(%esp)
+	movzbl	%al,%esi
+	movzbl	%ah,%edx
+	pshufw	$6,%mm0,%mm2
+	movzbl	-128(%ebp,%esi,1),%ecx
+	movzbl	%bl,%edi
+	movzbl	-128(%ebp,%edx,1),%edx
+	shrl	$16,%eax
+	shll	$8,%edx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%bh,%edi
+	shll	$16,%esi
+	pshufw	$3,%mm4,%mm6
+	orl	%esi,%ecx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%ah,%edi
+	shll	$24,%esi
+	shrl	$16,%ebx
+	orl	%esi,%edx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%bh,%edi
+	shll	$24,%esi
+	orl	%esi,%ecx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%al,%edi
+	shll	$8,%esi
+	movd	%mm2,%eax
+	orl	%esi,%ecx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%bl,%edi
+	shll	$16,%esi
+	movd	%mm6,%ebx
+	movd	%ecx,%mm0
+	movzbl	-128(%ebp,%edi,1),%ecx
+	movzbl	%al,%edi
+	orl	%esi,%ecx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%bl,%edi
+	orl	%esi,%edx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%ah,%edi
+	shll	$16,%esi
+	shrl	$16,%eax
+	orl	%esi,%edx
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%bh,%edi
+	shrl	$16,%ebx
+	shll	$8,%esi
+	movd	%edx,%mm1
+	movzbl	-128(%ebp,%edi,1),%edx
+	movzbl	%bh,%edi
+	shll	$24,%edx
+	andl	$255,%ebx
+	orl	%esi,%edx
+	punpckldq	%mm1,%mm0
+	movzbl	-128(%ebp,%edi,1),%esi
+	movzbl	%al,%edi
+	shll	$8,%esi
+	movzbl	%ah,%eax
+	movzbl	-128(%ebp,%ebx,1),%ebx
+	orl	%esi,%ecx
+	movzbl	-128(%ebp,%edi,1),%esi
+	orl	%ebx,%edx
+	shll	$16,%esi
+	movzbl	-128(%ebp,%eax,1),%eax
+	orl	%esi,%edx
+	shll	$24,%eax
+	orl	%eax,%ecx
+	movl	20(%esp),%edi
+	movd	%edx,%mm4
+	movd	%ecx,%mm5
+	punpckldq	%mm5,%mm4
+	addl	$16,%edi
+	cmpl	24(%esp),%edi
+	ja	.L008out
+	movq	%mm0,%mm3
+	movq	%mm4,%mm7
+	pshufw	$228,%mm0,%mm2
+	pshufw	$228,%mm4,%mm6
+	movq	%mm0,%mm1
+	movq	%mm4,%mm5
+	pshufw	$177,%mm0,%mm0
+	pshufw	$177,%mm4,%mm4
+	pslld	$8,%mm2
+	pslld	$8,%mm6
+	psrld	$8,%mm3
+	psrld	$8,%mm7
+	pxor	%mm2,%mm0
+	pxor	%mm6,%mm4
+	pxor	%mm3,%mm0
+	pxor	%mm7,%mm4
+	pslld	$16,%mm2
+	pslld	$16,%mm6
+	psrld	$16,%mm3
+	psrld	$16,%mm7
+	pxor	%mm2,%mm0
+	pxor	%mm6,%mm4
+	pxor	%mm3,%mm0
+	pxor	%mm7,%mm4
+	movq	8(%esp),%mm3
+	pxor	%mm2,%mm2
+	pxor	%mm6,%mm6
+	pcmpgtb	%mm1,%mm2
+	pcmpgtb	%mm5,%mm6
+	pand	%mm3,%mm2
+	pand	%mm3,%mm6
+	paddb	%mm1,%mm1
+	paddb	%mm5,%mm5
+	pxor	%mm2,%mm1
+	pxor	%mm6,%mm5
+	movq	%mm1,%mm3
+	movq	%mm5,%mm7
+	movq	%mm1,%mm2
+	movq	%mm5,%mm6
+	pxor	%mm1,%mm0
+	pxor	%mm5,%mm4
+	pslld	$24,%mm3
+	pslld	$24,%mm7
+	psrld	$8,%mm2
+	psrld	$8,%mm6
+	pxor	%mm3,%mm0
+	pxor	%mm7,%mm4
+	pxor	%mm2,%mm0
+	pxor	%mm6,%mm4
+	movq	8(%esp),%mm2
+	pxor	%mm3,%mm3
+	pxor	%mm7,%mm7
+	pcmpgtb	%mm1,%mm3
+	pcmpgtb	%mm5,%mm7
+	pand	%mm2,%mm3
+	pand	%mm2,%mm7
+	paddb	%mm1,%mm1
+	paddb	%mm5,%mm5
+	pxor	%mm3,%mm1
+	pxor	%mm7,%mm5
+	pshufw	$177,%mm1,%mm3
+	pshufw	$177,%mm5,%mm7
+	pxor	%mm1,%mm0
+	pxor	%mm5,%mm4
+	pxor	%mm3,%mm0
+	pxor	%mm7,%mm4
+	pxor	%mm3,%mm3
+	pxor	%mm7,%mm7
+	pcmpgtb	%mm1,%mm3
+	pcmpgtb	%mm5,%mm7
+	pand	%mm2,%mm3
+	pand	%mm2,%mm7
+	paddb	%mm1,%mm1
+	paddb	%mm5,%mm5
+	pxor	%mm3,%mm1
+	pxor	%mm7,%mm5
+	pxor	%mm1,%mm0
+	pxor	%mm5,%mm4
+	movq	%mm1,%mm3
+	movq	%mm5,%mm7
+	pshufw	$177,%mm1,%mm2
+	pshufw	$177,%mm5,%mm6
+	pxor	%mm2,%mm0
+	pxor	%mm6,%mm4
+	pslld	$8,%mm1
+	pslld	$8,%mm5
+	psrld	$8,%mm3
+	psrld	$8,%mm7
+	movq	(%edi),%mm2
+	movq	8(%edi),%mm6
+	pxor	%mm1,%mm0
+	pxor	%mm5,%mm4
+	pxor	%mm3,%mm0
+	pxor	%mm7,%mm4
+	movl	-128(%ebp),%eax
+	pslld	$16,%mm1
+	pslld	$16,%mm5
+	movl	-64(%ebp),%ebx
+	psrld	$16,%mm3
+	psrld	$16,%mm7
+	movl	(%ebp),%ecx
+	pxor	%mm1,%mm0
+	pxor	%mm5,%mm4
+	movl	64(%ebp),%edx
+	pxor	%mm3,%mm0
+	pxor	%mm7,%mm4
+	pxor	%mm2,%mm0
+	pxor	%mm6,%mm4
+	jmp	.L007loop
+.align	16
+.L008out:
+	pxor	(%edi),%mm0
+	pxor	8(%edi),%mm4
+	ret
+.size	_sse_AES_decrypt_compact,.-_sse_AES_decrypt_compact
+.type	_x86_AES_decrypt,@function
+.align	16
+_x86_AES_decrypt:
+	movl	%edi,20(%esp)
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	movl	240(%edi),%esi
+	leal	-2(%esi,%esi,1),%esi
+	leal	(%edi,%esi,8),%esi
+	movl	%esi,24(%esp)
+.align	16
+.L009loop:
+	movl	%eax,%esi
+	andl	$255,%esi
+	movl	(%ebp,%esi,8),%esi
+	movzbl	%dh,%edi
+	xorl	3(%ebp,%edi,8),%esi
+	movl	%ecx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	xorl	2(%ebp,%edi,8),%esi
+	movl	%ebx,%edi
+	shrl	$24,%edi
+	xorl	1(%ebp,%edi,8),%esi
+	movl	%esi,4(%esp)
+
+	movl	%ebx,%esi
+	andl	$255,%esi
+	movl	(%ebp,%esi,8),%esi
+	movzbl	%ah,%edi
+	xorl	3(%ebp,%edi,8),%esi
+	movl	%edx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	xorl	2(%ebp,%edi,8),%esi
+	movl	%ecx,%edi
+	shrl	$24,%edi
+	xorl	1(%ebp,%edi,8),%esi
+	movl	%esi,8(%esp)
+
+	movl	%ecx,%esi
+	andl	$255,%esi
+	movl	(%ebp,%esi,8),%esi
+	movzbl	%bh,%edi
+	xorl	3(%ebp,%edi,8),%esi
+	movl	%eax,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	xorl	2(%ebp,%edi,8),%esi
+	movl	%edx,%edi
+	shrl	$24,%edi
+	xorl	1(%ebp,%edi,8),%esi
+
+	movl	20(%esp),%edi
+	andl	$255,%edx
+	movl	(%ebp,%edx,8),%edx
+	movzbl	%ch,%ecx
+	xorl	3(%ebp,%ecx,8),%edx
+	movl	%esi,%ecx
+	shrl	$16,%ebx
+	andl	$255,%ebx
+	xorl	2(%ebp,%ebx,8),%edx
+	movl	8(%esp),%ebx
+	shrl	$24,%eax
+	xorl	1(%ebp,%eax,8),%edx
+	movl	4(%esp),%eax
+
+	addl	$16,%edi
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	cmpl	24(%esp),%edi
+	movl	%edi,20(%esp)
+	jb	.L009loop
+	leal	2176(%ebp),%ebp
+	movl	-128(%ebp),%edi
+	movl	-96(%ebp),%esi
+	movl	-64(%ebp),%edi
+	movl	-32(%ebp),%esi
+	movl	(%ebp),%edi
+	movl	32(%ebp),%esi
+	movl	64(%ebp),%edi
+	movl	96(%ebp),%esi
+	leal	-128(%ebp),%ebp
+	movl	%eax,%esi
+	andl	$255,%esi
+	movzbl	(%ebp,%esi,1),%esi
+	movzbl	%dh,%edi
+	movzbl	(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%ecx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%ebx,%edi
+	shrl	$24,%edi
+	movzbl	(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	movl	%esi,4(%esp)
+	movl	%ebx,%esi
+	andl	$255,%esi
+	movzbl	(%ebp,%esi,1),%esi
+	movzbl	%ah,%edi
+	movzbl	(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%ecx,%edi
+	shrl	$24,%edi
+	movzbl	(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	movl	%esi,8(%esp)
+	movl	%ecx,%esi
+	andl	$255,%esi
+	movzbl	(%ebp,%esi,1),%esi
+	movzbl	%bh,%edi
+	movzbl	(%ebp,%edi,1),%edi
+	shll	$8,%edi
+	xorl	%edi,%esi
+	movl	%eax,%edi
+	shrl	$16,%edi
+	andl	$255,%edi
+	movzbl	(%ebp,%edi,1),%edi
+	shll	$16,%edi
+	xorl	%edi,%esi
+	movl	%edx,%edi
+	shrl	$24,%edi
+	movzbl	(%ebp,%edi,1),%edi
+	shll	$24,%edi
+	xorl	%edi,%esi
+	movl	20(%esp),%edi
+	andl	$255,%edx
+	movzbl	(%ebp,%edx,1),%edx
+	movzbl	%ch,%ecx
+	movzbl	(%ebp,%ecx,1),%ecx
+	shll	$8,%ecx
+	xorl	%ecx,%edx
+	movl	%esi,%ecx
+	shrl	$16,%ebx
+	andl	$255,%ebx
+	movzbl	(%ebp,%ebx,1),%ebx
+	shll	$16,%ebx
+	xorl	%ebx,%edx
+	movl	8(%esp),%ebx
+	shrl	$24,%eax
+	movzbl	(%ebp,%eax,1),%eax
+	shll	$24,%eax
+	xorl	%eax,%edx
+	movl	4(%esp),%eax
+	leal	-2048(%ebp),%ebp
+	addl	$16,%edi
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	ret
+.align	64
+.LAES_Td:
+.long	1353184337,1353184337
+.long	1399144830,1399144830
+.long	3282310938,3282310938
+.long	2522752826,2522752826
+.long	3412831035,3412831035
+.long	4047871263,4047871263
+.long	2874735276,2874735276
+.long	2466505547,2466505547
+.long	1442459680,1442459680
+.long	4134368941,4134368941
+.long	2440481928,2440481928
+.long	625738485,625738485
+.long	4242007375,4242007375
+.long	3620416197,3620416197
+.long	2151953702,2151953702
+.long	2409849525,2409849525
+.long	1230680542,1230680542
+.long	1729870373,1729870373
+.long	2551114309,2551114309
+.long	3787521629,3787521629
+.long	41234371,41234371
+.long	317738113,317738113
+.long	2744600205,2744600205
+.long	3338261355,3338261355
+.long	3881799427,3881799427
+.long	2510066197,2510066197
+.long	3950669247,3950669247
+.long	3663286933,3663286933
+.long	763608788,763608788
+.long	3542185048,3542185048
+.long	694804553,694804553
+.long	1154009486,1154009486
+.long	1787413109,1787413109
+.long	2021232372,2021232372
+.long	1799248025,1799248025
+.long	3715217703,3715217703
+.long	3058688446,3058688446
+.long	397248752,397248752
+.long	1722556617,1722556617
+.long	3023752829,3023752829
+.long	407560035,407560035
+.long	2184256229,2184256229
+.long	1613975959,1613975959
+.long	1165972322,1165972322
+.long	3765920945,3765920945
+.long	2226023355,2226023355
+.long	480281086,480281086
+.long	2485848313,2485848313
+.long	1483229296,1483229296
+.long	436028815,436028815
+.long	2272059028,2272059028
+.long	3086515026,3086515026
+.long	601060267,601060267
+.long	3791801202,3791801202
+.long	1468997603,1468997603
+.long	715871590,715871590
+.long	120122290,120122290
+.long	63092015,63092015
+.long	2591802758,2591802758
+.long	2768779219,2768779219
+.long	4068943920,4068943920
+.long	2997206819,2997206819
+.long	3127509762,3127509762
+.long	1552029421,1552029421
+.long	723308426,723308426
+.long	2461301159,2461301159
+.long	4042393587,4042393587
+.long	2715969870,2715969870
+.long	3455375973,3455375973
+.long	3586000134,3586000134
+.long	526529745,526529745
+.long	2331944644,2331944644
+.long	2639474228,2639474228
+.long	2689987490,2689987490
+.long	853641733,853641733
+.long	1978398372,1978398372
+.long	971801355,971801355
+.long	2867814464,2867814464
+.long	111112542,111112542
+.long	1360031421,1360031421
+.long	4186579262,4186579262
+.long	1023860118,1023860118
+.long	2919579357,2919579357
+.long	1186850381,1186850381
+.long	3045938321,3045938321
+.long	90031217,90031217
+.long	1876166148,1876166148
+.long	4279586912,4279586912
+.long	620468249,620468249
+.long	2548678102,2548678102
+.long	3426959497,3426959497
+.long	2006899047,2006899047
+.long	3175278768,3175278768
+.long	2290845959,2290845959
+.long	945494503,945494503
+.long	3689859193,3689859193
+.long	1191869601,1191869601
+.long	3910091388,3910091388
+.long	3374220536,3374220536
+.long	0,0
+.long	2206629897,2206629897
+.long	1223502642,1223502642
+.long	2893025566,2893025566
+.long	1316117100,1316117100
+.long	4227796733,4227796733
+.long	1446544655,1446544655
+.long	517320253,517320253
+.long	658058550,658058550
+.long	1691946762,1691946762
+.long	564550760,564550760
+.long	3511966619,3511966619
+.long	976107044,976107044
+.long	2976320012,2976320012
+.long	266819475,266819475
+.long	3533106868,3533106868
+.long	2660342555,2660342555
+.long	1338359936,1338359936
+.long	2720062561,2720062561
+.long	1766553434,1766553434
+.long	370807324,370807324
+.long	179999714,179999714
+.long	3844776128,3844776128
+.long	1138762300,1138762300
+.long	488053522,488053522
+.long	185403662,185403662
+.long	2915535858,2915535858
+.long	3114841645,3114841645
+.long	3366526484,3366526484
+.long	2233069911,2233069911
+.long	1275557295,1275557295
+.long	3151862254,3151862254
+.long	4250959779,4250959779
+.long	2670068215,2670068215
+.long	3170202204,3170202204
+.long	3309004356,3309004356
+.long	880737115,880737115
+.long	1982415755,1982415755
+.long	3703972811,3703972811
+.long	1761406390,1761406390
+.long	1676797112,1676797112
+.long	3403428311,3403428311
+.long	277177154,277177154
+.long	1076008723,1076008723
+.long	538035844,538035844
+.long	2099530373,2099530373
+.long	4164795346,4164795346
+.long	288553390,288553390
+.long	1839278535,1839278535
+.long	1261411869,1261411869
+.long	4080055004,4080055004
+.long	3964831245,3964831245
+.long	3504587127,3504587127
+.long	1813426987,1813426987
+.long	2579067049,2579067049
+.long	4199060497,4199060497
+.long	577038663,577038663
+.long	3297574056,3297574056
+.long	440397984,440397984
+.long	3626794326,3626794326
+.long	4019204898,4019204898
+.long	3343796615,3343796615
+.long	3251714265,3251714265
+.long	4272081548,4272081548
+.long	906744984,906744984
+.long	3481400742,3481400742
+.long	685669029,685669029
+.long	646887386,646887386
+.long	2764025151,2764025151
+.long	3835509292,3835509292
+.long	227702864,227702864
+.long	2613862250,2613862250
+.long	1648787028,1648787028
+.long	3256061430,3256061430
+.long	3904428176,3904428176
+.long	1593260334,1593260334
+.long	4121936770,4121936770
+.long	3196083615,3196083615
+.long	2090061929,2090061929
+.long	2838353263,2838353263
+.long	3004310991,3004310991
+.long	999926984,999926984
+.long	2809993232,2809993232
+.long	1852021992,1852021992
+.long	2075868123,2075868123
+.long	158869197,158869197
+.long	4095236462,4095236462
+.long	28809964,28809964
+.long	2828685187,2828685187
+.long	1701746150,1701746150
+.long	2129067946,2129067946
+.long	147831841,147831841
+.long	3873969647,3873969647
+.long	3650873274,3650873274
+.long	3459673930,3459673930
+.long	3557400554,3557400554
+.long	3598495785,3598495785
+.long	2947720241,2947720241
+.long	824393514,824393514
+.long	815048134,815048134
+.long	3227951669,3227951669
+.long	935087732,935087732
+.long	2798289660,2798289660
+.long	2966458592,2966458592
+.long	366520115,366520115
+.long	1251476721,1251476721
+.long	4158319681,4158319681
+.long	240176511,240176511
+.long	804688151,804688151
+.long	2379631990,2379631990
+.long	1303441219,1303441219
+.long	1414376140,1414376140
+.long	3741619940,3741619940
+.long	3820343710,3820343710
+.long	461924940,461924940
+.long	3089050817,3089050817
+.long	2136040774,2136040774
+.long	82468509,82468509
+.long	1563790337,1563790337
+.long	1937016826,1937016826
+.long	776014843,776014843
+.long	1511876531,1511876531
+.long	1389550482,1389550482
+.long	861278441,861278441
+.long	323475053,323475053
+.long	2355222426,2355222426
+.long	2047648055,2047648055
+.long	2383738969,2383738969
+.long	2302415851,2302415851
+.long	3995576782,3995576782
+.long	902390199,902390199
+.long	3991215329,3991215329
+.long	1018251130,1018251130
+.long	1507840668,1507840668
+.long	1064563285,1064563285
+.long	2043548696,2043548696
+.long	3208103795,3208103795
+.long	3939366739,3939366739
+.long	1537932639,1537932639
+.long	342834655,342834655
+.long	2262516856,2262516856
+.long	2180231114,2180231114
+.long	1053059257,1053059257
+.long	741614648,741614648
+.long	1598071746,1598071746
+.long	1925389590,1925389590
+.long	203809468,203809468
+.long	2336832552,2336832552
+.long	1100287487,1100287487
+.long	1895934009,1895934009
+.long	3736275976,3736275976
+.long	2632234200,2632234200
+.long	2428589668,2428589668
+.long	1636092795,1636092795
+.long	1890988757,1890988757
+.long	1952214088,1952214088
+.long	1113045200,1113045200
+.byte	82,9,106,213,48,54,165,56
+.byte	191,64,163,158,129,243,215,251
+.byte	124,227,57,130,155,47,255,135
+.byte	52,142,67,68,196,222,233,203
+.byte	84,123,148,50,166,194,35,61
+.byte	238,76,149,11,66,250,195,78
+.byte	8,46,161,102,40,217,36,178
+.byte	118,91,162,73,109,139,209,37
+.byte	114,248,246,100,134,104,152,22
+.byte	212,164,92,204,93,101,182,146
+.byte	108,112,72,80,253,237,185,218
+.byte	94,21,70,87,167,141,157,132
+.byte	144,216,171,0,140,188,211,10
+.byte	247,228,88,5,184,179,69,6
+.byte	208,44,30,143,202,63,15,2
+.byte	193,175,189,3,1,19,138,107
+.byte	58,145,17,65,79,103,220,234
+.byte	151,242,207,206,240,180,230,115
+.byte	150,172,116,34,231,173,53,133
+.byte	226,249,55,232,28,117,223,110
+.byte	71,241,26,113,29,41,197,137
+.byte	111,183,98,14,170,24,190,27
+.byte	252,86,62,75,198,210,121,32
+.byte	154,219,192,254,120,205,90,244
+.byte	31,221,168,51,136,7,199,49
+.byte	177,18,16,89,39,128,236,95
+.byte	96,81,127,169,25,181,74,13
+.byte	45,229,122,159,147,201,156,239
+.byte	160,224,59,77,174,42,245,176
+.byte	200,235,187,60,131,83,153,97
+.byte	23,43,4,126,186,119,214,38
+.byte	225,105,20,99,85,33,12,125
+.byte	82,9,106,213,48,54,165,56
+.byte	191,64,163,158,129,243,215,251
+.byte	124,227,57,130,155,47,255,135
+.byte	52,142,67,68,196,222,233,203
+.byte	84,123,148,50,166,194,35,61
+.byte	238,76,149,11,66,250,195,78
+.byte	8,46,161,102,40,217,36,178
+.byte	118,91,162,73,109,139,209,37
+.byte	114,248,246,100,134,104,152,22
+.byte	212,164,92,204,93,101,182,146
+.byte	108,112,72,80,253,237,185,218
+.byte	94,21,70,87,167,141,157,132
+.byte	144,216,171,0,140,188,211,10
+.byte	247,228,88,5,184,179,69,6
+.byte	208,44,30,143,202,63,15,2
+.byte	193,175,189,3,1,19,138,107
+.byte	58,145,17,65,79,103,220,234
+.byte	151,242,207,206,240,180,230,115
+.byte	150,172,116,34,231,173,53,133
+.byte	226,249,55,232,28,117,223,110
+.byte	71,241,26,113,29,41,197,137
+.byte	111,183,98,14,170,24,190,27
+.byte	252,86,62,75,198,210,121,32
+.byte	154,219,192,254,120,205,90,244
+.byte	31,221,168,51,136,7,199,49
+.byte	177,18,16,89,39,128,236,95
+.byte	96,81,127,169,25,181,74,13
+.byte	45,229,122,159,147,201,156,239
+.byte	160,224,59,77,174,42,245,176
+.byte	200,235,187,60,131,83,153,97
+.byte	23,43,4,126,186,119,214,38
+.byte	225,105,20,99,85,33,12,125
+.byte	82,9,106,213,48,54,165,56
+.byte	191,64,163,158,129,243,215,251
+.byte	124,227,57,130,155,47,255,135
+.byte	52,142,67,68,196,222,233,203
+.byte	84,123,148,50,166,194,35,61
+.byte	238,76,149,11,66,250,195,78
+.byte	8,46,161,102,40,217,36,178
+.byte	118,91,162,73,109,139,209,37
+.byte	114,248,246,100,134,104,152,22
+.byte	212,164,92,204,93,101,182,146
+.byte	108,112,72,80,253,237,185,218
+.byte	94,21,70,87,167,141,157,132
+.byte	144,216,171,0,140,188,211,10
+.byte	247,228,88,5,184,179,69,6
+.byte	208,44,30,143,202,63,15,2
+.byte	193,175,189,3,1,19,138,107
+.byte	58,145,17,65,79,103,220,234
+.byte	151,242,207,206,240,180,230,115
+.byte	150,172,116,34,231,173,53,133
+.byte	226,249,55,232,28,117,223,110
+.byte	71,241,26,113,29,41,197,137
+.byte	111,183,98,14,170,24,190,27
+.byte	252,86,62,75,198,210,121,32
+.byte	154,219,192,254,120,205,90,244
+.byte	31,221,168,51,136,7,199,49
+.byte	177,18,16,89,39,128,236,95
+.byte	96,81,127,169,25,181,74,13
+.byte	45,229,122,159,147,201,156,239
+.byte	160,224,59,77,174,42,245,176
+.byte	200,235,187,60,131,83,153,97
+.byte	23,43,4,126,186,119,214,38
+.byte	225,105,20,99,85,33,12,125
+.byte	82,9,106,213,48,54,165,56
+.byte	191,64,163,158,129,243,215,251
+.byte	124,227,57,130,155,47,255,135
+.byte	52,142,67,68,196,222,233,203
+.byte	84,123,148,50,166,194,35,61
+.byte	238,76,149,11,66,250,195,78
+.byte	8,46,161,102,40,217,36,178
+.byte	118,91,162,73,109,139,209,37
+.byte	114,248,246,100,134,104,152,22
+.byte	212,164,92,204,93,101,182,146
+.byte	108,112,72,80,253,237,185,218
+.byte	94,21,70,87,167,141,157,132
+.byte	144,216,171,0,140,188,211,10
+.byte	247,228,88,5,184,179,69,6
+.byte	208,44,30,143,202,63,15,2
+.byte	193,175,189,3,1,19,138,107
+.byte	58,145,17,65,79,103,220,234
+.byte	151,242,207,206,240,180,230,115
+.byte	150,172,116,34,231,173,53,133
+.byte	226,249,55,232,28,117,223,110
+.byte	71,241,26,113,29,41,197,137
+.byte	111,183,98,14,170,24,190,27
+.byte	252,86,62,75,198,210,121,32
+.byte	154,219,192,254,120,205,90,244
+.byte	31,221,168,51,136,7,199,49
+.byte	177,18,16,89,39,128,236,95
+.byte	96,81,127,169,25,181,74,13
+.byte	45,229,122,159,147,201,156,239
+.byte	160,224,59,77,174,42,245,176
+.byte	200,235,187,60,131,83,153,97
+.byte	23,43,4,126,186,119,214,38
+.byte	225,105,20,99,85,33,12,125
+.size	_x86_AES_decrypt,.-_x86_AES_decrypt
+.globl	AES_decrypt
+.type	AES_decrypt,@function
+.align	16
+AES_decrypt:
+.L_AES_decrypt_begin:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	movl	20(%esp),%esi
+	movl	28(%esp),%edi
+	movl	%esp,%eax
+	subl	$36,%esp
+	andl	$-64,%esp
+	leal	-127(%edi),%ebx
+	subl	%esp,%ebx
+	negl	%ebx
+	andl	$960,%ebx
+	subl	%ebx,%esp
+	addl	$4,%esp
+	movl	%eax,28(%esp)
+	call	.L010pic_point
+.L010pic_point:
+	popl	%ebp
+	leal	OPENSSL_ia32cap_P,%eax
+	leal	.LAES_Td-.L010pic_point(%ebp),%ebp
+	leal	764(%esp),%ebx
+	subl	%ebp,%ebx
+	andl	$768,%ebx
+	leal	2176(%ebp,%ebx,1),%ebp
+	btl	$25,(%eax)
+	jnc	.L011x86
+	movq	(%esi),%mm0
+	movq	8(%esi),%mm4
+	call	_sse_AES_decrypt_compact
+	movl	28(%esp),%esp
+	movl	24(%esp),%esi
+	movq	%mm0,(%esi)
+	movq	%mm4,8(%esi)
+	emms
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.align	16
+.L011x86:
+	movl	%ebp,24(%esp)
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	call	_x86_AES_decrypt_compact
+	movl	28(%esp),%esp
+	movl	24(%esp),%esi
+	movl	%eax,(%esi)
+	movl	%ebx,4(%esi)
+	movl	%ecx,8(%esi)
+	movl	%edx,12(%esi)
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.size	AES_decrypt,.-.L_AES_decrypt_begin
+.globl	AES_cbc_encrypt
+.type	AES_cbc_encrypt,@function
+.align	16
+AES_cbc_encrypt:
+.L_AES_cbc_encrypt_begin:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	movl	28(%esp),%ecx
+	cmpl	$0,%ecx
+	je	.L012drop_out
+	call	.L013pic_point
+.L013pic_point:
+	popl	%ebp
+	leal	OPENSSL_ia32cap_P,%eax
+	cmpl	$0,40(%esp)
+	leal	.LAES_Te-.L013pic_point(%ebp),%ebp
+	jne	.L014picked_te
+	leal	.LAES_Td-.LAES_Te(%ebp),%ebp
+.L014picked_te:
+	pushfl
+	cld
+	cmpl	$512,%ecx
+	jb	.L015slow_way
+	testl	$15,%ecx
+	jnz	.L015slow_way
+	btl	$28,(%eax)
+	jc	.L015slow_way
+	leal	-324(%esp),%esi
+	andl	$-64,%esi
+	movl	%ebp,%eax
+	leal	2304(%ebp),%ebx
+	movl	%esi,%edx
+	andl	$4095,%eax
+	andl	$4095,%ebx
+	andl	$4095,%edx
+	cmpl	%ebx,%edx
+	jb	.L016tbl_break_out
+	subl	%ebx,%edx
+	subl	%edx,%esi
+	jmp	.L017tbl_ok
+.align	4
+.L016tbl_break_out:
+	subl	%eax,%edx
+	andl	$4095,%edx
+	addl	$384,%edx
+	subl	%edx,%esi
+.align	4
+.L017tbl_ok:
+	leal	24(%esp),%edx
+	xchgl	%esi,%esp
+	addl	$4,%esp
+	movl	%ebp,24(%esp)
+	movl	%esi,28(%esp)
+	movl	(%edx),%eax
+	movl	4(%edx),%ebx
+	movl	12(%edx),%edi
+	movl	16(%edx),%esi
+	movl	20(%edx),%edx
+	movl	%eax,32(%esp)
+	movl	%ebx,36(%esp)
+	movl	%ecx,40(%esp)
+	movl	%edi,44(%esp)
+	movl	%esi,48(%esp)
+	movl	$0,316(%esp)
+	movl	%edi,%ebx
+	movl	$61,%ecx
+	subl	%ebp,%ebx
+	movl	%edi,%esi
+	andl	$4095,%ebx
+	leal	76(%esp),%edi
+	cmpl	$2304,%ebx
+	jb	.L018do_copy
+	cmpl	$3852,%ebx
+	jb	.L019skip_copy
+.align	4
+.L018do_copy:
+	movl	%edi,44(%esp)
+.long	2784229001
+.L019skip_copy:
+	movl	$16,%edi
+.align	4
+.L020prefetch_tbl:
+	movl	(%ebp),%eax
+	movl	32(%ebp),%ebx
+	movl	64(%ebp),%ecx
+	movl	96(%ebp),%esi
+	leal	128(%ebp),%ebp
+	subl	$1,%edi
+	jnz	.L020prefetch_tbl
+	subl	$2048,%ebp
+	movl	32(%esp),%esi
+	movl	48(%esp),%edi
+	cmpl	$0,%edx
+	je	.L021fast_decrypt
+	movl	(%edi),%eax
+	movl	4(%edi),%ebx
+.align	16
+.L022fast_enc_loop:
+	movl	8(%edi),%ecx
+	movl	12(%edi),%edx
+	xorl	(%esi),%eax
+	xorl	4(%esi),%ebx
+	xorl	8(%esi),%ecx
+	xorl	12(%esi),%edx
+	movl	44(%esp),%edi
+	call	_x86_AES_encrypt
+	movl	32(%esp),%esi
+	movl	36(%esp),%edi
+	movl	%eax,(%edi)
+	movl	%ebx,4(%edi)
+	movl	%ecx,8(%edi)
+	movl	%edx,12(%edi)
+	leal	16(%esi),%esi
+	movl	40(%esp),%ecx
+	movl	%esi,32(%esp)
+	leal	16(%edi),%edx
+	movl	%edx,36(%esp)
+	subl	$16,%ecx
+	movl	%ecx,40(%esp)
+	jnz	.L022fast_enc_loop
+	movl	48(%esp),%esi
+	movl	8(%edi),%ecx
+	movl	12(%edi),%edx
+	movl	%eax,(%esi)
+	movl	%ebx,4(%esi)
+	movl	%ecx,8(%esi)
+	movl	%edx,12(%esi)
+	cmpl	$0,316(%esp)
+	movl	44(%esp),%edi
+	je	.L023skip_ezero
+	movl	$60,%ecx
+	xorl	%eax,%eax
+.align	4
+.long	2884892297
+.L023skip_ezero:
+	movl	28(%esp),%esp
+	popfl
+.L012drop_out:
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+	pushfl
+.align	16
+.L021fast_decrypt:
+	cmpl	36(%esp),%esi
+	je	.L024fast_dec_in_place
+	movl	%edi,52(%esp)
+.align	4
+.align	16
+.L025fast_dec_loop:
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	movl	44(%esp),%edi
+	call	_x86_AES_decrypt
+	movl	52(%esp),%edi
+	movl	40(%esp),%esi
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	movl	36(%esp),%edi
+	movl	32(%esp),%esi
+	movl	%eax,(%edi)
+	movl	%ebx,4(%edi)
+	movl	%ecx,8(%edi)
+	movl	%edx,12(%edi)
+	movl	40(%esp),%ecx
+	movl	%esi,52(%esp)
+	leal	16(%esi),%esi
+	movl	%esi,32(%esp)
+	leal	16(%edi),%edi
+	movl	%edi,36(%esp)
+	subl	$16,%ecx
+	movl	%ecx,40(%esp)
+	jnz	.L025fast_dec_loop
+	movl	52(%esp),%edi
+	movl	48(%esp),%esi
+	movl	(%edi),%eax
+	movl	4(%edi),%ebx
+	movl	8(%edi),%ecx
+	movl	12(%edi),%edx
+	movl	%eax,(%esi)
+	movl	%ebx,4(%esi)
+	movl	%ecx,8(%esi)
+	movl	%edx,12(%esi)
+	jmp	.L026fast_dec_out
+.align	16
+.L024fast_dec_in_place:
+.L027fast_dec_in_place_loop:
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	leal	60(%esp),%edi
+	movl	%eax,(%edi)
+	movl	%ebx,4(%edi)
+	movl	%ecx,8(%edi)
+	movl	%edx,12(%edi)
+	movl	44(%esp),%edi
+	call	_x86_AES_decrypt
+	movl	48(%esp),%edi
+	movl	36(%esp),%esi
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	movl	%eax,(%esi)
+	movl	%ebx,4(%esi)
+	movl	%ecx,8(%esi)
+	movl	%edx,12(%esi)
+	leal	16(%esi),%esi
+	movl	%esi,36(%esp)
+	leal	60(%esp),%esi
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	movl	%eax,(%edi)
+	movl	%ebx,4(%edi)
+	movl	%ecx,8(%edi)
+	movl	%edx,12(%edi)
+	movl	32(%esp),%esi
+	movl	40(%esp),%ecx
+	leal	16(%esi),%esi
+	movl	%esi,32(%esp)
+	subl	$16,%ecx
+	movl	%ecx,40(%esp)
+	jnz	.L027fast_dec_in_place_loop
+.align	4
+.L026fast_dec_out:
+	cmpl	$0,316(%esp)
+	movl	44(%esp),%edi
+	je	.L028skip_dzero
+	movl	$60,%ecx
+	xorl	%eax,%eax
+.align	4
+.long	2884892297
+.L028skip_dzero:
+	movl	28(%esp),%esp
+	popfl
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+	pushfl
+.align	16
+.L015slow_way:
+	movl	(%eax),%eax
+	movl	36(%esp),%edi
+	leal	-80(%esp),%esi
+	andl	$-64,%esi
+	leal	-143(%edi),%ebx
+	subl	%esi,%ebx
+	negl	%ebx
+	andl	$960,%ebx
+	subl	%ebx,%esi
+	leal	768(%esi),%ebx
+	subl	%ebp,%ebx
+	andl	$768,%ebx
+	leal	2176(%ebp,%ebx,1),%ebp
+	leal	24(%esp),%edx
+	xchgl	%esi,%esp
+	addl	$4,%esp
+	movl	%ebp,24(%esp)
+	movl	%esi,28(%esp)
+	movl	%eax,52(%esp)
+	movl	(%edx),%eax
+	movl	4(%edx),%ebx
+	movl	16(%edx),%esi
+	movl	20(%edx),%edx
+	movl	%eax,32(%esp)
+	movl	%ebx,36(%esp)
+	movl	%ecx,40(%esp)
+	movl	%edi,44(%esp)
+	movl	%esi,48(%esp)
+	movl	%esi,%edi
+	movl	%eax,%esi
+	cmpl	$0,%edx
+	je	.L029slow_decrypt
+	cmpl	$16,%ecx
+	movl	%ebx,%edx
+	jb	.L030slow_enc_tail
+	btl	$25,52(%esp)
+	jnc	.L031slow_enc_x86
+	movq	(%edi),%mm0
+	movq	8(%edi),%mm4
+.align	16
+.L032slow_enc_loop_sse:
+	pxor	(%esi),%mm0
+	pxor	8(%esi),%mm4
+	movl	44(%esp),%edi
+	call	_sse_AES_encrypt_compact
+	movl	32(%esp),%esi
+	movl	36(%esp),%edi
+	movl	40(%esp),%ecx
+	movq	%mm0,(%edi)
+	movq	%mm4,8(%edi)
+	leal	16(%esi),%esi
+	movl	%esi,32(%esp)
+	leal	16(%edi),%edx
+	movl	%edx,36(%esp)
+	subl	$16,%ecx
+	cmpl	$16,%ecx
+	movl	%ecx,40(%esp)
+	jae	.L032slow_enc_loop_sse
+	testl	$15,%ecx
+	jnz	.L030slow_enc_tail
+	movl	48(%esp),%esi
+	movq	%mm0,(%esi)
+	movq	%mm4,8(%esi)
+	emms
+	movl	28(%esp),%esp
+	popfl
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+	pushfl
+.align	16
+.L031slow_enc_x86:
+	movl	(%edi),%eax
+	movl	4(%edi),%ebx
+.align	4
+.L033slow_enc_loop_x86:
+	movl	8(%edi),%ecx
+	movl	12(%edi),%edx
+	xorl	(%esi),%eax
+	xorl	4(%esi),%ebx
+	xorl	8(%esi),%ecx
+	xorl	12(%esi),%edx
+	movl	44(%esp),%edi
+	call	_x86_AES_encrypt_compact
+	movl	32(%esp),%esi
+	movl	36(%esp),%edi
+	movl	%eax,(%edi)
+	movl	%ebx,4(%edi)
+	movl	%ecx,8(%edi)
+	movl	%edx,12(%edi)
+	movl	40(%esp),%ecx
+	leal	16(%esi),%esi
+	movl	%esi,32(%esp)
+	leal	16(%edi),%edx
+	movl	%edx,36(%esp)
+	subl	$16,%ecx
+	cmpl	$16,%ecx
+	movl	%ecx,40(%esp)
+	jae	.L033slow_enc_loop_x86
+	testl	$15,%ecx
+	jnz	.L030slow_enc_tail
+	movl	48(%esp),%esi
+	movl	8(%edi),%ecx
+	movl	12(%edi),%edx
+	movl	%eax,(%esi)
+	movl	%ebx,4(%esi)
+	movl	%ecx,8(%esi)
+	movl	%edx,12(%esi)
+	movl	28(%esp),%esp
+	popfl
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+	pushfl
+.align	16
+.L030slow_enc_tail:
+	emms
+	movl	%edx,%edi
+	movl	$16,%ebx
+	subl	%ecx,%ebx
+	cmpl	%esi,%edi
+	je	.L034enc_in_place
+.align	4
+.long	2767451785
+	jmp	.L035enc_skip_in_place
+.L034enc_in_place:
+	leal	(%edi,%ecx,1),%edi
+.L035enc_skip_in_place:
+	movl	%ebx,%ecx
+	xorl	%eax,%eax
+.align	4
+.long	2868115081
+	movl	48(%esp),%edi
+	movl	%edx,%esi
+	movl	(%edi),%eax
+	movl	4(%edi),%ebx
+	movl	$16,40(%esp)
+	jmp	.L033slow_enc_loop_x86
+.align	16
+.L029slow_decrypt:
+	btl	$25,52(%esp)
+	jnc	.L036slow_dec_loop_x86
+.align	4
+.L037slow_dec_loop_sse:
+	movq	(%esi),%mm0
+	movq	8(%esi),%mm4
+	movl	44(%esp),%edi
+	call	_sse_AES_decrypt_compact
+	movl	32(%esp),%esi
+	leal	60(%esp),%eax
+	movl	36(%esp),%ebx
+	movl	40(%esp),%ecx
+	movl	48(%esp),%edi
+	movq	(%esi),%mm1
+	movq	8(%esi),%mm5
+	pxor	(%edi),%mm0
+	pxor	8(%edi),%mm4
+	movq	%mm1,(%edi)
+	movq	%mm5,8(%edi)
+	subl	$16,%ecx
+	jc	.L038slow_dec_partial_sse
+	movq	%mm0,(%ebx)
+	movq	%mm4,8(%ebx)
+	leal	16(%ebx),%ebx
+	movl	%ebx,36(%esp)
+	leal	16(%esi),%esi
+	movl	%esi,32(%esp)
+	movl	%ecx,40(%esp)
+	jnz	.L037slow_dec_loop_sse
+	emms
+	movl	28(%esp),%esp
+	popfl
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+	pushfl
+.align	16
+.L038slow_dec_partial_sse:
+	movq	%mm0,(%eax)
+	movq	%mm4,8(%eax)
+	emms
+	addl	$16,%ecx
+	movl	%ebx,%edi
+	movl	%eax,%esi
+.align	4
+.long	2767451785
+	movl	28(%esp),%esp
+	popfl
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+	pushfl
+.align	16
+.L036slow_dec_loop_x86:
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	leal	60(%esp),%edi
+	movl	%eax,(%edi)
+	movl	%ebx,4(%edi)
+	movl	%ecx,8(%edi)
+	movl	%edx,12(%edi)
+	movl	44(%esp),%edi
+	call	_x86_AES_decrypt_compact
+	movl	48(%esp),%edi
+	movl	40(%esp),%esi
+	xorl	(%edi),%eax
+	xorl	4(%edi),%ebx
+	xorl	8(%edi),%ecx
+	xorl	12(%edi),%edx
+	subl	$16,%esi
+	jc	.L039slow_dec_partial_x86
+	movl	%esi,40(%esp)
+	movl	36(%esp),%esi
+	movl	%eax,(%esi)
+	movl	%ebx,4(%esi)
+	movl	%ecx,8(%esi)
+	movl	%edx,12(%esi)
+	leal	16(%esi),%esi
+	movl	%esi,36(%esp)
+	leal	60(%esp),%esi
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	movl	%eax,(%edi)
+	movl	%ebx,4(%edi)
+	movl	%ecx,8(%edi)
+	movl	%edx,12(%edi)
+	movl	32(%esp),%esi
+	leal	16(%esi),%esi
+	movl	%esi,32(%esp)
+	jnz	.L036slow_dec_loop_x86
+	movl	28(%esp),%esp
+	popfl
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+	pushfl
+.align	16
+.L039slow_dec_partial_x86:
+	leal	60(%esp),%esi
+	movl	%eax,(%esi)
+	movl	%ebx,4(%esi)
+	movl	%ecx,8(%esi)
+	movl	%edx,12(%esi)
+	movl	32(%esp),%esi
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	movl	%eax,(%edi)
+	movl	%ebx,4(%edi)
+	movl	%ecx,8(%edi)
+	movl	%edx,12(%edi)
+	movl	40(%esp),%ecx
+	movl	36(%esp),%edi
+	leal	60(%esp),%esi
+.align	4
+.long	2767451785
+	movl	28(%esp),%esp
+	popfl
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.size	AES_cbc_encrypt,.-.L_AES_cbc_encrypt_begin
+.type	_x86_AES_set_encrypt_key,@function
+.align	16
+_x86_AES_set_encrypt_key:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	movl	24(%esp),%esi
+	movl	32(%esp),%edi
+	testl	$-1,%esi
+	jz	.L040badpointer
+	testl	$-1,%edi
+	jz	.L040badpointer
+	call	.L041pic_point
+.L041pic_point:
+	popl	%ebp
+	leal	.LAES_Te-.L041pic_point(%ebp),%ebp
+	leal	2176(%ebp),%ebp
+	movl	-128(%ebp),%eax
+	movl	-96(%ebp),%ebx
+	movl	-64(%ebp),%ecx
+	movl	-32(%ebp),%edx
+	movl	(%ebp),%eax
+	movl	32(%ebp),%ebx
+	movl	64(%ebp),%ecx
+	movl	96(%ebp),%edx
+	movl	28(%esp),%ecx
+	cmpl	$128,%ecx
+	je	.L04210rounds
+	cmpl	$192,%ecx
+	je	.L04312rounds
+	cmpl	$256,%ecx
+	je	.L04414rounds
+	movl	$-2,%eax
+	jmp	.L045exit
+.L04210rounds:
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	movl	%eax,(%edi)
+	movl	%ebx,4(%edi)
+	movl	%ecx,8(%edi)
+	movl	%edx,12(%edi)
+	xorl	%ecx,%ecx
+	jmp	.L04610shortcut
+.align	4
+.L04710loop:
+	movl	(%edi),%eax
+	movl	12(%edi),%edx
+.L04610shortcut:
+	movzbl	%dl,%esi
+	movzbl	-128(%ebp,%esi,1),%ebx
+	movzbl	%dh,%esi
+	shll	$24,%ebx
+	xorl	%ebx,%eax
+	movzbl	-128(%ebp,%esi,1),%ebx
+	shrl	$16,%edx
+	movzbl	%dl,%esi
+	xorl	%ebx,%eax
+	movzbl	-128(%ebp,%esi,1),%ebx
+	movzbl	%dh,%esi
+	shll	$8,%ebx
+	xorl	%ebx,%eax
+	movzbl	-128(%ebp,%esi,1),%ebx
+	shll	$16,%ebx
+	xorl	%ebx,%eax
+	xorl	896(%ebp,%ecx,4),%eax
+	movl	%eax,16(%edi)
+	xorl	4(%edi),%eax
+	movl	%eax,20(%edi)
+	xorl	8(%edi),%eax
+	movl	%eax,24(%edi)
+	xorl	12(%edi),%eax
+	movl	%eax,28(%edi)
+	incl	%ecx
+	addl	$16,%edi
+	cmpl	$10,%ecx
+	jl	.L04710loop
+	movl	$10,80(%edi)
+	xorl	%eax,%eax
+	jmp	.L045exit
+.L04312rounds:
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	movl	%eax,(%edi)
+	movl	%ebx,4(%edi)
+	movl	%ecx,8(%edi)
+	movl	%edx,12(%edi)
+	movl	16(%esi),%ecx
+	movl	20(%esi),%edx
+	movl	%ecx,16(%edi)
+	movl	%edx,20(%edi)
+	xorl	%ecx,%ecx
+	jmp	.L04812shortcut
+.align	4
+.L04912loop:
+	movl	(%edi),%eax
+	movl	20(%edi),%edx
+.L04812shortcut:
+	movzbl	%dl,%esi
+	movzbl	-128(%ebp,%esi,1),%ebx
+	movzbl	%dh,%esi
+	shll	$24,%ebx
+	xorl	%ebx,%eax
+	movzbl	-128(%ebp,%esi,1),%ebx
+	shrl	$16,%edx
+	movzbl	%dl,%esi
+	xorl	%ebx,%eax
+	movzbl	-128(%ebp,%esi,1),%ebx
+	movzbl	%dh,%esi
+	shll	$8,%ebx
+	xorl	%ebx,%eax
+	movzbl	-128(%ebp,%esi,1),%ebx
+	shll	$16,%ebx
+	xorl	%ebx,%eax
+	xorl	896(%ebp,%ecx,4),%eax
+	movl	%eax,24(%edi)
+	xorl	4(%edi),%eax
+	movl	%eax,28(%edi)
+	xorl	8(%edi),%eax
+	movl	%eax,32(%edi)
+	xorl	12(%edi),%eax
+	movl	%eax,36(%edi)
+	cmpl	$7,%ecx
+	je	.L05012break
+	incl	%ecx
+	xorl	16(%edi),%eax
+	movl	%eax,40(%edi)
+	xorl	20(%edi),%eax
+	movl	%eax,44(%edi)
+	addl	$24,%edi
+	jmp	.L04912loop
+.L05012break:
+	movl	$12,72(%edi)
+	xorl	%eax,%eax
+	jmp	.L045exit
+.L04414rounds:
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	movl	%eax,(%edi)
+	movl	%ebx,4(%edi)
+	movl	%ecx,8(%edi)
+	movl	%edx,12(%edi)
+	movl	16(%esi),%eax
+	movl	20(%esi),%ebx
+	movl	24(%esi),%ecx
+	movl	28(%esi),%edx
+	movl	%eax,16(%edi)
+	movl	%ebx,20(%edi)
+	movl	%ecx,24(%edi)
+	movl	%edx,28(%edi)
+	xorl	%ecx,%ecx
+	jmp	.L05114shortcut
+.align	4
+.L05214loop:
+	movl	28(%edi),%edx
+.L05114shortcut:
+	movl	(%edi),%eax
+	movzbl	%dl,%esi
+	movzbl	-128(%ebp,%esi,1),%ebx
+	movzbl	%dh,%esi
+	shll	$24,%ebx
+	xorl	%ebx,%eax
+	movzbl	-128(%ebp,%esi,1),%ebx
+	shrl	$16,%edx
+	movzbl	%dl,%esi
+	xorl	%ebx,%eax
+	movzbl	-128(%ebp,%esi,1),%ebx
+	movzbl	%dh,%esi
+	shll	$8,%ebx
+	xorl	%ebx,%eax
+	movzbl	-128(%ebp,%esi,1),%ebx
+	shll	$16,%ebx
+	xorl	%ebx,%eax
+	xorl	896(%ebp,%ecx,4),%eax
+	movl	%eax,32(%edi)
+	xorl	4(%edi),%eax
+	movl	%eax,36(%edi)
+	xorl	8(%edi),%eax
+	movl	%eax,40(%edi)
+	xorl	12(%edi),%eax
+	movl	%eax,44(%edi)
+	cmpl	$6,%ecx
+	je	.L05314break
+	incl	%ecx
+	movl	%eax,%edx
+	movl	16(%edi),%eax
+	movzbl	%dl,%esi
+	movzbl	-128(%ebp,%esi,1),%ebx
+	movzbl	%dh,%esi
+	xorl	%ebx,%eax
+	movzbl	-128(%ebp,%esi,1),%ebx
+	shrl	$16,%edx
+	shll	$8,%ebx
+	movzbl	%dl,%esi
+	xorl	%ebx,%eax
+	movzbl	-128(%ebp,%esi,1),%ebx
+	movzbl	%dh,%esi
+	shll	$16,%ebx
+	xorl	%ebx,%eax
+	movzbl	-128(%ebp,%esi,1),%ebx
+	shll	$24,%ebx
+	xorl	%ebx,%eax
+	movl	%eax,48(%edi)
+	xorl	20(%edi),%eax
+	movl	%eax,52(%edi)
+	xorl	24(%edi),%eax
+	movl	%eax,56(%edi)
+	xorl	28(%edi),%eax
+	movl	%eax,60(%edi)
+	addl	$32,%edi
+	jmp	.L05214loop
+.L05314break:
+	movl	$14,48(%edi)
+	xorl	%eax,%eax
+	jmp	.L045exit
+.L040badpointer:
+	movl	$-1,%eax
+.L045exit:
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.size	_x86_AES_set_encrypt_key,.-_x86_AES_set_encrypt_key
+.globl	AES_set_encrypt_key
+.type	AES_set_encrypt_key,@function
+.align	16
+AES_set_encrypt_key:
+.L_AES_set_encrypt_key_begin:
+	call	_x86_AES_set_encrypt_key
+	ret
+.size	AES_set_encrypt_key,.-.L_AES_set_encrypt_key_begin
+.globl	AES_set_decrypt_key
+.type	AES_set_decrypt_key,@function
+.align	16
+AES_set_decrypt_key:
+.L_AES_set_decrypt_key_begin:
+	call	_x86_AES_set_encrypt_key
+	cmpl	$0,%eax
+	je	.L054proceed
+	ret
+.L054proceed:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	movl	28(%esp),%esi
+	movl	240(%esi),%ecx
+	leal	(,%ecx,4),%ecx
+	leal	(%esi,%ecx,4),%edi
+.align	4
+.L055invert:
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	(%edi),%ecx
+	movl	4(%edi),%edx
+	movl	%eax,(%edi)
+	movl	%ebx,4(%edi)
+	movl	%ecx,(%esi)
+	movl	%edx,4(%esi)
+	movl	8(%esi),%eax
+	movl	12(%esi),%ebx
+	movl	8(%edi),%ecx
+	movl	12(%edi),%edx
+	movl	%eax,8(%edi)
+	movl	%ebx,12(%edi)
+	movl	%ecx,8(%esi)
+	movl	%edx,12(%esi)
+	addl	$16,%esi
+	subl	$16,%edi
+	cmpl	%edi,%esi
+	jne	.L055invert
+	movl	28(%esp),%edi
+	movl	240(%edi),%esi
+	leal	-2(%esi,%esi,1),%esi
+	leal	(%edi,%esi,8),%esi
+	movl	%esi,28(%esp)
+	movl	16(%edi),%eax
+.align	4
+.L056permute:
+	addl	$16,%edi
+	movl	$2155905152,%ebp
+	andl	%eax,%ebp
+	leal	(%eax,%eax,1),%ebx
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	subl	%ebp,%esi
+	andl	$4278124286,%ebx
+	andl	$454761243,%esi
+	xorl	%esi,%ebx
+	movl	$2155905152,%ebp
+	andl	%ebx,%ebp
+	leal	(%ebx,%ebx,1),%ecx
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	subl	%ebp,%esi
+	andl	$4278124286,%ecx
+	andl	$454761243,%esi
+	xorl	%eax,%ebx
+	xorl	%esi,%ecx
+	movl	$2155905152,%ebp
+	andl	%ecx,%ebp
+	leal	(%ecx,%ecx,1),%edx
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	xorl	%eax,%ecx
+	subl	%ebp,%esi
+	andl	$4278124286,%edx
+	andl	$454761243,%esi
+	roll	$8,%eax
+	xorl	%esi,%edx
+	movl	4(%edi),%ebp
+	xorl	%ebx,%eax
+	xorl	%edx,%ebx
+	xorl	%ecx,%eax
+	roll	$24,%ebx
+	xorl	%edx,%ecx
+	xorl	%edx,%eax
+	roll	$16,%ecx
+	xorl	%ebx,%eax
+	roll	$8,%edx
+	xorl	%ecx,%eax
+	movl	%ebp,%ebx
+	xorl	%edx,%eax
+	movl	%eax,(%edi)
+	movl	$2155905152,%ebp
+	andl	%ebx,%ebp
+	leal	(%ebx,%ebx,1),%ecx
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	subl	%ebp,%esi
+	andl	$4278124286,%ecx
+	andl	$454761243,%esi
+	xorl	%esi,%ecx
+	movl	$2155905152,%ebp
+	andl	%ecx,%ebp
+	leal	(%ecx,%ecx,1),%edx
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	subl	%ebp,%esi
+	andl	$4278124286,%edx
+	andl	$454761243,%esi
+	xorl	%ebx,%ecx
+	xorl	%esi,%edx
+	movl	$2155905152,%ebp
+	andl	%edx,%ebp
+	leal	(%edx,%edx,1),%eax
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	xorl	%ebx,%edx
+	subl	%ebp,%esi
+	andl	$4278124286,%eax
+	andl	$454761243,%esi
+	roll	$8,%ebx
+	xorl	%esi,%eax
+	movl	8(%edi),%ebp
+	xorl	%ecx,%ebx
+	xorl	%eax,%ecx
+	xorl	%edx,%ebx
+	roll	$24,%ecx
+	xorl	%eax,%edx
+	xorl	%eax,%ebx
+	roll	$16,%edx
+	xorl	%ecx,%ebx
+	roll	$8,%eax
+	xorl	%edx,%ebx
+	movl	%ebp,%ecx
+	xorl	%eax,%ebx
+	movl	%ebx,4(%edi)
+	movl	$2155905152,%ebp
+	andl	%ecx,%ebp
+	leal	(%ecx,%ecx,1),%edx
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	subl	%ebp,%esi
+	andl	$4278124286,%edx
+	andl	$454761243,%esi
+	xorl	%esi,%edx
+	movl	$2155905152,%ebp
+	andl	%edx,%ebp
+	leal	(%edx,%edx,1),%eax
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	subl	%ebp,%esi
+	andl	$4278124286,%eax
+	andl	$454761243,%esi
+	xorl	%ecx,%edx
+	xorl	%esi,%eax
+	movl	$2155905152,%ebp
+	andl	%eax,%ebp
+	leal	(%eax,%eax,1),%ebx
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	xorl	%ecx,%eax
+	subl	%ebp,%esi
+	andl	$4278124286,%ebx
+	andl	$454761243,%esi
+	roll	$8,%ecx
+	xorl	%esi,%ebx
+	movl	12(%edi),%ebp
+	xorl	%edx,%ecx
+	xorl	%ebx,%edx
+	xorl	%eax,%ecx
+	roll	$24,%edx
+	xorl	%ebx,%eax
+	xorl	%ebx,%ecx
+	roll	$16,%eax
+	xorl	%edx,%ecx
+	roll	$8,%ebx
+	xorl	%eax,%ecx
+	movl	%ebp,%edx
+	xorl	%ebx,%ecx
+	movl	%ecx,8(%edi)
+	movl	$2155905152,%ebp
+	andl	%edx,%ebp
+	leal	(%edx,%edx,1),%eax
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	subl	%ebp,%esi
+	andl	$4278124286,%eax
+	andl	$454761243,%esi
+	xorl	%esi,%eax
+	movl	$2155905152,%ebp
+	andl	%eax,%ebp
+	leal	(%eax,%eax,1),%ebx
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	subl	%ebp,%esi
+	andl	$4278124286,%ebx
+	andl	$454761243,%esi
+	xorl	%edx,%eax
+	xorl	%esi,%ebx
+	movl	$2155905152,%ebp
+	andl	%ebx,%ebp
+	leal	(%ebx,%ebx,1),%ecx
+	movl	%ebp,%esi
+	shrl	$7,%ebp
+	xorl	%edx,%ebx
+	subl	%ebp,%esi
+	andl	$4278124286,%ecx
+	andl	$454761243,%esi
+	roll	$8,%edx
+	xorl	%esi,%ecx
+	movl	16(%edi),%ebp
+	xorl	%eax,%edx
+	xorl	%ecx,%eax
+	xorl	%ebx,%edx
+	roll	$24,%eax
+	xorl	%ecx,%ebx
+	xorl	%ecx,%edx
+	roll	$16,%ebx
+	xorl	%eax,%edx
+	roll	$8,%ecx
+	xorl	%ebx,%edx
+	movl	%ebp,%eax
+	xorl	%ecx,%edx
+	movl	%edx,12(%edi)
+	cmpl	28(%esp),%edi
+	jb	.L056permute
+	xorl	%eax,%eax
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.size	AES_set_decrypt_key,.-.L_AES_set_decrypt_key_begin
+.byte	65,69,83,32,102,111,114,32,120,56,54,44,32,67,82,89
+.byte	80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114
+.byte	111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
+.comm	OPENSSL_ia32cap_P,16,4