Merge pull request #1 from monero-project/master

Attempting an online merge in my own repo

6 files changed, 434 insertions, 145 deletions

diff --git a/src/crypto/aesb.c b/src/crypto/aesb.c
new file mode 100644
index 000000000..ba48313da
--- /dev/null
+++ b/src/crypto/aesb.c
@@ -0,0 +1,177 @@
+/*
+---------------------------------------------------------------------------
+Copyright (c) 1998-2013, Brian Gladman, Worcester, UK. All rights reserved.
+
+The redistribution and use of this software (with or without changes)
+is allowed without the payment of fees or royalties provided that:
+
+  source code distributions include the above copyright notice, this
+  list of conditions and the following disclaimer;
+
+  binary distributions include the above copyright notice, this list
+  of conditions and the following disclaimer in their documentation.
+
+This software is provided 'as is' with no explicit or implied warranties
+in respect of its operation, including, but not limited to, correctness
+and fitness for purpose.
+---------------------------------------------------------------------------
+Issue Date: 20/12/2007
+*/
+
+#include <stdint.h>
+
+#if defined(__cplusplus)
+extern "C"
+{
+#endif
+
+#define TABLE_ALIGN		32
+#define WPOLY			0x011b
+#define N_COLS			4
+#define AES_BLOCK_SIZE	16
+#define RC_LENGTH		(5 * (AES_BLOCK_SIZE / 4 - 2))
+
+#if defined(_MSC_VER)
+#define ALIGN __declspec(align(TABLE_ALIGN))
+#elif defined(__GNUC__)
+#define ALIGN __attribute__ ((aligned(16)))
+#else
+#define ALIGN
+#endif
+
+#define rf1(r,c) (r)
+#define word_in(x,c) (*((uint32_t*)(x)+(c)))
+#define word_out(x,c,v) (*((uint32_t*)(x)+(c)) = (v))
+
+#define s(x,c) x[c]
+#define si(y,x,c) (s(y,c) = word_in(x, c))
+#define so(y,x,c) word_out(y, c, s(x,c))
+#define state_in(y,x) si(y,x,0); si(y,x,1); si(y,x,2); si(y,x,3)
+#define state_out(y,x)  so(y,x,0); so(y,x,1); so(y,x,2); so(y,x,3)
+#define round(rm,y,x,k) rm(y,x,k,0); rm(y,x,k,1); rm(y,x,k,2); rm(y,x,k,3)
+#define to_byte(x) ((x) & 0xff)
+#define bval(x,n) to_byte((x) >> (8 * (n)))
+
+#define fwd_var(x,r,c)\
+ ( r == 0 ? ( c == 0 ? s(x,0) : c == 1 ? s(x,1) : c == 2 ? s(x,2) : s(x,3))\
+ : r == 1 ? ( c == 0 ? s(x,1) : c == 1 ? s(x,2) : c == 2 ? s(x,3) : s(x,0))\
+ : r == 2 ? ( c == 0 ? s(x,2) : c == 1 ? s(x,3) : c == 2 ? s(x,0) : s(x,1))\
+ :          ( c == 0 ? s(x,3) : c == 1 ? s(x,0) : c == 2 ? s(x,1) : s(x,2)))
+
+#define fwd_rnd(y,x,k,c)  (s(y,c) = (k)[c] ^ four_tables(x,t_use(f,n),fwd_var,rf1,c))
+
+#define sb_data(w) {\
+	w(0x63), w(0x7c), w(0x77), w(0x7b), w(0xf2), w(0x6b), w(0x6f), w(0xc5),\
+	w(0x30), w(0x01), w(0x67), w(0x2b), w(0xfe), w(0xd7), w(0xab), w(0x76),\
+	w(0xca), w(0x82), w(0xc9), w(0x7d), w(0xfa), w(0x59), w(0x47), w(0xf0),\
+	w(0xad), w(0xd4), w(0xa2), w(0xaf), w(0x9c), w(0xa4), w(0x72), w(0xc0),\
+	w(0xb7), w(0xfd), w(0x93), w(0x26), w(0x36), w(0x3f), w(0xf7), w(0xcc),\
+	w(0x34), w(0xa5), w(0xe5), w(0xf1), w(0x71), w(0xd8), w(0x31), w(0x15),\
+	w(0x04), w(0xc7), w(0x23), w(0xc3), w(0x18), w(0x96), w(0x05), w(0x9a),\
+	w(0x07), w(0x12), w(0x80), w(0xe2), w(0xeb), w(0x27), w(0xb2), w(0x75),\
+	w(0x09), w(0x83), w(0x2c), w(0x1a), w(0x1b), w(0x6e), w(0x5a), w(0xa0),\
+	w(0x52), w(0x3b), w(0xd6), w(0xb3), w(0x29), w(0xe3), w(0x2f), w(0x84),\
+	w(0x53), w(0xd1), w(0x00), w(0xed), w(0x20), w(0xfc), w(0xb1), w(0x5b),\
+	w(0x6a), w(0xcb), w(0xbe), w(0x39), w(0x4a), w(0x4c), w(0x58), w(0xcf),\
+	w(0xd0), w(0xef), w(0xaa), w(0xfb), w(0x43), w(0x4d), w(0x33), w(0x85),\
+	w(0x45), w(0xf9), w(0x02), w(0x7f), w(0x50), w(0x3c), w(0x9f), w(0xa8),\
+	w(0x51), w(0xa3), w(0x40), w(0x8f), w(0x92), w(0x9d), w(0x38), w(0xf5),\
+	w(0xbc), w(0xb6), w(0xda), w(0x21), w(0x10), w(0xff), w(0xf3), w(0xd2),\
+	w(0xcd), w(0x0c), w(0x13), w(0xec), w(0x5f), w(0x97), w(0x44), w(0x17),\
+	w(0xc4), w(0xa7), w(0x7e), w(0x3d), w(0x64), w(0x5d), w(0x19), w(0x73),\
+	w(0x60), w(0x81), w(0x4f), w(0xdc), w(0x22), w(0x2a), w(0x90), w(0x88),\
+	w(0x46), w(0xee), w(0xb8), w(0x14), w(0xde), w(0x5e), w(0x0b), w(0xdb),\
+	w(0xe0), w(0x32), w(0x3a), w(0x0a), w(0x49), w(0x06), w(0x24), w(0x5c),\
+	w(0xc2), w(0xd3), w(0xac), w(0x62), w(0x91), w(0x95), w(0xe4), w(0x79),\
+	w(0xe7), w(0xc8), w(0x37), w(0x6d), w(0x8d), w(0xd5), w(0x4e), w(0xa9),\
+	w(0x6c), w(0x56), w(0xf4), w(0xea), w(0x65), w(0x7a), w(0xae), w(0x08),\
+	w(0xba), w(0x78), w(0x25), w(0x2e), w(0x1c), w(0xa6), w(0xb4), w(0xc6),\
+	w(0xe8), w(0xdd), w(0x74), w(0x1f), w(0x4b), w(0xbd), w(0x8b), w(0x8a),\
+	w(0x70), w(0x3e), w(0xb5), w(0x66), w(0x48), w(0x03), w(0xf6), w(0x0e),\
+	w(0x61), w(0x35), w(0x57), w(0xb9), w(0x86), w(0xc1), w(0x1d), w(0x9e),\
+	w(0xe1), w(0xf8), w(0x98), w(0x11), w(0x69), w(0xd9), w(0x8e), w(0x94),\
+	w(0x9b), w(0x1e), w(0x87), w(0xe9), w(0xce), w(0x55), w(0x28), w(0xdf),\
+	w(0x8c), w(0xa1), w(0x89), w(0x0d), w(0xbf), w(0xe6), w(0x42), w(0x68),\
+	w(0x41), w(0x99), w(0x2d), w(0x0f), w(0xb0), w(0x54), w(0xbb), w(0x16) }
+
+#define rc_data(w) {\
+	w(0x01), w(0x02), w(0x04), w(0x08), w(0x10),w(0x20), w(0x40), w(0x80),\
+	w(0x1b), w(0x36) }
+
+#define bytes2word(b0, b1, b2, b3) (((uint32_t)(b3) << 24) | \
+	((uint32_t)(b2) << 16) | ((uint32_t)(b1) << 8) | (b0))
+
+#define h0(x)   (x)
+#define w0(p)   bytes2word(p, 0, 0, 0)
+#define w1(p)   bytes2word(0, p, 0, 0)
+#define w2(p)   bytes2word(0, 0, p, 0)
+#define w3(p)   bytes2word(0, 0, 0, p)
+
+#define u0(p)   bytes2word(f2(p), p, p, f3(p))
+#define u1(p)   bytes2word(f3(p), f2(p), p, p)
+#define u2(p)   bytes2word(p, f3(p), f2(p), p)
+#define u3(p)   bytes2word(p, p, f3(p), f2(p))
+
+#define v0(p)   bytes2word(fe(p), f9(p), fd(p), fb(p))
+#define v1(p)   bytes2word(fb(p), fe(p), f9(p), fd(p))
+#define v2(p)   bytes2word(fd(p), fb(p), fe(p), f9(p))
+#define v3(p)   bytes2word(f9(p), fd(p), fb(p), fe(p))
+
+#define f2(x)   ((x<<1) ^ (((x>>7) & 1) * WPOLY))
+#define f4(x)   ((x<<2) ^ (((x>>6) & 1) * WPOLY) ^ (((x>>6) & 2) * WPOLY))
+#define f8(x)   ((x<<3) ^ (((x>>5) & 1) * WPOLY) ^ (((x>>5) & 2) * WPOLY) ^ (((x>>5) & 4) * WPOLY))
+#define f3(x)   (f2(x) ^ x)
+#define f9(x)   (f8(x) ^ x)
+#define fb(x)   (f8(x) ^ f2(x) ^ x)
+#define fd(x)   (f8(x) ^ f4(x) ^ x)
+#define fe(x)   (f8(x) ^ f4(x) ^ f2(x))
+
+#define t_dec(m,n) t_##m##n
+#define t_set(m,n) t_##m##n
+#define t_use(m,n) t_##m##n
+
+#define d_4(t,n,b,e,f,g,h) ALIGN const t n[4][256] = { b(e), b(f), b(g), b(h) }
+
+#define four_tables(x,tab,vf,rf,c) \
+	(tab[0][bval(vf(x,0,c),rf(0,c))] \
+	^ tab[1][bval(vf(x,1,c),rf(1,c))] \
+	^ tab[2][bval(vf(x,2,c),rf(2,c))] \
+	^ tab[3][bval(vf(x,3,c),rf(3,c))])
+
+d_4(uint32_t, t_dec(f,n), sb_data, u0, u1, u2, u3);
+
+void aesb_single_round(const uint8_t *in, uint8_t *out, uint8_t *expandedKey)
+{   
+	uint32_t b0[4], b1[4];
+	const uint32_t  *kp = (uint32_t *) expandedKey;
+	state_in(b0, in);
+
+	round(fwd_rnd,  b1, b0, kp);
+
+	state_out(out, b1);
+}
+
+void aesb_pseudo_round(const uint8_t *in, uint8_t *out, uint8_t *expandedKey)
+{   
+	uint32_t b0[4], b1[4];
+	const uint32_t  *kp = (uint32_t *) expandedKey;
+	state_in(b0, in);
+	
+	round(fwd_rnd,  b1, b0, kp);
+	round(fwd_rnd,  b0, b1, kp + 1 * N_COLS);
+	round(fwd_rnd,  b1, b0, kp + 2 * N_COLS);
+	round(fwd_rnd,  b0, b1, kp + 3 * N_COLS);
+	round(fwd_rnd,  b1, b0, kp + 4 * N_COLS);
+	round(fwd_rnd,  b0, b1, kp + 5 * N_COLS);
+	round(fwd_rnd,  b1, b0, kp + 6 * N_COLS);
+	round(fwd_rnd,  b0, b1, kp + 7 * N_COLS);
+	round(fwd_rnd,  b1, b0, kp + 8 * N_COLS);
+	round(fwd_rnd,  b0, b1, kp + 9 * N_COLS);
+
+	state_out(out, b0);
+}
+
+
+#if defined(__cplusplus)
+}
+#endif
diff --git a/src/crypto/oaes_config.h b/src/crypto/oaes_config.h
index 8a58c3cfc..3fc0e1be5 100644
--- a/src/crypto/oaes_config.h
+++ b/src/crypto/oaes_config.h
@@ -39,9 +39,9 @@ extern "C" {
 //#define OAES_HAVE_ISAAC 1
 //#endif // OAES_HAVE_ISAAC
 
-#ifndef OAES_DEBUG
-#define OAES_DEBUG 0
-#endif // OAES_DEBUG
+//#ifndef OAES_DEBUG
+//#define OAES_DEBUG 0
+//#endif // OAES_DEBUG
 
 #ifdef __cplusplus 
 }
diff --git a/src/crypto/oaes_lib.c b/src/crypto/oaes_lib.c
index 126f0a2f6..96f038600 100644
--- a/src/crypto/oaes_lib.c
+++ b/src/crypto/oaes_lib.c
@@ -64,30 +64,6 @@ static const char _NR[] = {
 # define min(a,b) (((a)<(b)) ? (a) : (b))
 #endif /* min */
 
-typedef struct _oaes_key
-{
-	size_t data_len;
-	uint8_t *data;
-	size_t exp_data_len;
-	uint8_t *exp_data;
-	size_t num_keys;
-	size_t key_base;
-} oaes_key;
-
-typedef struct _oaes_ctx
-{
-#ifdef OAES_HAVE_ISAAC
-  randctx * rctx;
-#endif // OAES_HAVE_ISAAC
-
-#ifdef OAES_DEBUG
-	oaes_step_cb step_cb;
-#endif // OAES_DEBUG
-
-	oaes_key * key;
-	OAES_OPTION options;
-	uint8_t iv[OAES_BLOCK_SIZE];
-} oaes_ctx;
 
 // "OAES<8-bit header version><8-bit type><16-bit options><8-bit flags><56-bit reserved>"
 static uint8_t oaes_header[OAES_BLOCK_SIZE] = {
diff --git a/src/crypto/oaes_lib.h b/src/crypto/oaes_lib.h
index 9155bce02..16b914c7a 100644
--- a/src/crypto/oaes_lib.h
+++ b/src/crypto/oaes_lib.h
@@ -101,6 +101,32 @@ typedef int ( * oaes_step_cb ) (
 
 typedef uint16_t OAES_OPTION;
 
+
+typedef struct _oaes_key
+{
+	size_t data_len;
+	uint8_t *data;
+	size_t exp_data_len;
+	uint8_t *exp_data;
+	size_t num_keys;
+	size_t key_base;
+} oaes_key;
+
+typedef struct _oaes_ctx
+{
+#ifdef OAES_HAVE_ISAAC
+  randctx * rctx;
+#endif // OAES_HAVE_ISAAC
+
+#ifdef OAES_DEBUG
+	oaes_step_cb step_cb;
+#endif // OAES_DEBUG
+
+	oaes_key * key;
+	OAES_OPTION options;
+	uint8_t iv[OAES_BLOCK_SIZE];
+} oaes_ctx;
+
 /*
  * // usage:
  * 
diff --git a/src/crypto/slow-hash.c b/src/crypto/slow-hash.c
index 6495e490e..35438dcab 100644
--- a/src/crypto/slow-hash.c
+++ b/src/crypto/slow-hash.c
@@ -11,141 +11,251 @@
 #include "hash-ops.h"
 #include "oaes_lib.h"
 
-static void (*const extra_hashes[4])(const void *, size_t, char *) = {
-  hash_extra_blake, hash_extra_groestl, hash_extra_jh, hash_extra_skein
-};
+#include <emmintrin.h>
+
+#if defined(_MSC_VER) || defined(__INTEL_COMPILER)
+#include <intrin.h>
+#define STATIC
+#define INLINE __inline
+#if !defined(RDATA_ALIGN16)
+#define RDATA_ALIGN16 __declspec(align(16))
+#endif
+#else
+#include <wmmintrin.h>
+#define STATIC static
+#define INLINE inline
+#if !defined(RDATA_ALIGN16)
+#define RDATA_ALIGN16 __attribute__ ((aligned(16)))
+#endif
+#endif
 
-#define MEMORY         (1 << 21) /* 2 MiB */
+#define MEMORY         (1 << 21) // 2MB scratchpad
 #define ITER           (1 << 20)
 #define AES_BLOCK_SIZE  16
-#define AES_KEY_SIZE    32 /*16*/
+#define AES_KEY_SIZE    32
 #define INIT_SIZE_BLK   8
 #define INIT_SIZE_BYTE (INIT_SIZE_BLK * AES_BLOCK_SIZE)
 
-static size_t e2i(const uint8_t* a, size_t count) { return (*((uint64_t*)a) / AES_BLOCK_SIZE) & (count - 1); }
+#define U64(x) ((uint64_t *) (x))
+#define R128(x) ((__m128i *) (x))
 
-static void mul(const uint8_t* a, const uint8_t* b, uint8_t* res) {
-  uint64_t a0, b0;
-  uint64_t hi, lo;
+extern int aesb_single_round(const uint8_t *in, uint8_t*out, const uint8_t *expandedKey);
+extern int aesb_pseudo_round(const uint8_t *in, uint8_t *out, const uint8_t *expandedKey);
 
-  a0 = SWAP64LE(((uint64_t*)a)[0]);
-  b0 = SWAP64LE(((uint64_t*)b)[0]);
-  lo = mul128(a0, b0, &hi);
-  ((uint64_t*)res)[0] = SWAP64LE(hi);
-  ((uint64_t*)res)[1] = SWAP64LE(lo);
+#pragma pack(push, 1)
+union cn_slow_hash_state
+{
+    union hash_state hs;
+    struct
+    {
+        uint8_t k[64];
+        uint8_t init[INIT_SIZE_BYTE];
+    };
+};
+#pragma pack(pop)
+
+#if defined(_MSC_VER) || defined(__INTEL_COMPILER)
+#define cpuid(info,x)    __cpuidex(info,x,0)
+#else
+void cpuid(int CPUInfo[4], int InfoType)
+{
+    __asm__ __volatile__
+    (
+        "cpuid":
+        "=a" (CPUInfo[0]),
+        "=b" (CPUInfo[1]),
+        "=c" (CPUInfo[2]),
+        "=d" (CPUInfo[3]) :
+        "a" (InfoType), "c" (0)
+    );
 }
+#endif
+
+STATIC INLINE void mul(const uint8_t *a, const uint8_t *b, uint8_t *res)
+{
+    uint64_t a0, b0;
+    uint64_t hi, lo;
 
-static void sum_half_blocks(uint8_t* a, const uint8_t* b) {
-  uint64_t a0, a1, b0, b1;
-
-  a0 = SWAP64LE(((uint64_t*)a)[0]);
-  a1 = SWAP64LE(((uint64_t*)a)[1]);
-  b0 = SWAP64LE(((uint64_t*)b)[0]);
-  b1 = SWAP64LE(((uint64_t*)b)[1]);
-  a0 += b0;
-  a1 += b1;
-  ((uint64_t*)a)[0] = SWAP64LE(a0);
-  ((uint64_t*)a)[1] = SWAP64LE(a1);
+    a0 = U64(a)[0];
+    b0 = U64(b)[0];
+    lo = mul128(a0, b0, &hi);
+    U64(res)[0] = hi;
+    U64(res)[1] = lo;
 }
 
-static void copy_block(uint8_t* dst, const uint8_t* src) {
-  memcpy(dst, src, AES_BLOCK_SIZE);
+STATIC INLINE void sum_half_blocks(uint8_t *a, const uint8_t *b)
+{
+    uint64_t a0, a1, b0, b1;
+    a0 = U64(a)[0];
+    a1 = U64(a)[1];
+    b0 = U64(b)[0];
+    b1 = U64(b)[1];
+    a0 += b0;
+    a1 += b1;
+    U64(a)[0] = a0;
+    U64(a)[1] = a1;
 }
 
-static void swap_blocks(uint8_t* a, uint8_t* b) {
-  size_t i;
-  uint8_t t;
-  for (i = 0; i < AES_BLOCK_SIZE; i++) {
-    t = a[i];
-    a[i] = b[i];
-    b[i] = t;
-  }
+STATIC INLINE void swap_blocks(uint8_t *a, uint8_t *b)
+{
+    uint64_t t[2];
+    U64(t)[0] = U64(a)[0];
+    U64(t)[1] = U64(a)[1];
+    U64(a)[0] = U64(b)[0];
+    U64(a)[1] = U64(b)[1];
+    U64(b)[0] = U64(t)[0];
+    U64(b)[1] = U64(t)[1];
 }
 
-static void xor_blocks(uint8_t* a, const uint8_t* b) {
-  size_t i;
-  for (i = 0; i < AES_BLOCK_SIZE; i++) {
-    a[i] ^= b[i];
-  }
+STATIC INLINE void xor_blocks(uint8_t *a, const uint8_t *b)
+{
+    U64(a)[0] ^= U64(b)[0];
+    U64(a)[1] ^= U64(b)[1];
 }
 
-#pragma pack(push, 1)
-union cn_slow_hash_state {
-  union hash_state hs;
-  struct {
-    uint8_t k[64];
-    uint8_t init[INIT_SIZE_BYTE];
-  };
-};
-#pragma pack(pop)
+STATIC INLINE int check_aes_hw(void)
+{
+    int cpuid_results[4];
+    static int supported = -1;
+
+    if(supported >= 0)
+        return supported;
+
+    cpuid(cpuid_results,1);
+    return supported = cpuid_results[2] & (1 << 25);
+}
+
+STATIC INLINE void aesni_pseudo_round(const uint8_t *in, uint8_t *out,
+                                      const uint8_t *expandedKey)
+{
+    __m128i *k = R128(expandedKey);
+    __m128i d;
+
+    d = _mm_loadu_si128(R128(in));
+    d = _mm_aesenc_si128(d, *R128(&k[0]));
+    d = _mm_aesenc_si128(d, *R128(&k[1]));
+    d = _mm_aesenc_si128(d, *R128(&k[2]));
+    d = _mm_aesenc_si128(d, *R128(&k[3]));
+    d = _mm_aesenc_si128(d, *R128(&k[4]));
+    d = _mm_aesenc_si128(d, *R128(&k[5]));
+    d = _mm_aesenc_si128(d, *R128(&k[6]));
+    d = _mm_aesenc_si128(d, *R128(&k[7]));
+    d = _mm_aesenc_si128(d, *R128(&k[8]));
+    d = _mm_aesenc_si128(d, *R128(&k[9]));
+    _mm_storeu_si128((R128(out)), d);
+}
+
+void cn_slow_hash(const void *data, size_t length, char *hash)
+{
+    uint8_t long_state[MEMORY];
+    uint8_t text[INIT_SIZE_BYTE];
+    uint8_t a[AES_BLOCK_SIZE];
+    uint8_t b[AES_BLOCK_SIZE];
+    uint8_t d[AES_BLOCK_SIZE];
+    uint8_t aes_key[AES_KEY_SIZE];
+    RDATA_ALIGN16 uint8_t expandedKey[256];
+
+    union cn_slow_hash_state state;
 
-void cn_slow_hash(const void *data, size_t length, char *hash) {
-  uint8_t long_state[MEMORY];
-  union cn_slow_hash_state state;
-  uint8_t text[INIT_SIZE_BYTE];
-  uint8_t a[AES_BLOCK_SIZE];
-  uint8_t b[AES_BLOCK_SIZE];
-  uint8_t c[AES_BLOCK_SIZE];
-  uint8_t d[AES_BLOCK_SIZE];
-  size_t i, j;
-  uint8_t aes_key[AES_KEY_SIZE];
-  OAES_CTX* aes_ctx;
-
-  hash_process(&state.hs, data, length);
-  memcpy(text, state.init, INIT_SIZE_BYTE);
-  memcpy(aes_key, state.hs.b, AES_KEY_SIZE);
-  aes_ctx = oaes_alloc();
-  
-  oaes_key_import_data(aes_ctx, aes_key, AES_KEY_SIZE);
-  for (i = 0; i < MEMORY / INIT_SIZE_BYTE; i++) {
-    for (j = 0; j < INIT_SIZE_BLK; j++) {    
-      oaes_pseudo_encrypt_ecb(aes_ctx, &text[AES_BLOCK_SIZE * j]);
+    size_t i, j;
+    uint8_t *p = NULL;
+    oaes_ctx *aes_ctx;
+
+    int useAes = check_aes_hw();
+    static void (*const extra_hashes[4])(const void *, size_t, char *) =
+    {
+        hash_extra_blake, hash_extra_groestl, hash_extra_jh, hash_extra_skein
+    };
+
+    hash_process(&state.hs, data, length);
+    memcpy(text, state.init, INIT_SIZE_BYTE);
+
+    aes_ctx = (oaes_ctx *) oaes_alloc();
+    oaes_key_import_data(aes_ctx, state.hs.b, AES_KEY_SIZE);
+
+    // use aligned data
+    memcpy(expandedKey, aes_ctx->key->exp_data, aes_ctx->key->exp_data_len);
+
+    if(useAes)
+    {
+        for(i = 0; i < MEMORY / INIT_SIZE_BYTE; i++)
+        {
+            for(j = 0; j < INIT_SIZE_BLK; j++)
+                aesni_pseudo_round(&text[AES_BLOCK_SIZE * j], &text[AES_BLOCK_SIZE * j], expandedKey);
+            memcpy(&long_state[i * INIT_SIZE_BYTE], text, INIT_SIZE_BYTE);
+        }
+    }
+    else
+    {
+        for(i = 0; i < MEMORY / INIT_SIZE_BYTE; i++)
+        {
+            for(j = 0; j < INIT_SIZE_BLK; j++)
+                aesb_pseudo_round(&text[AES_BLOCK_SIZE * j], &text[AES_BLOCK_SIZE * j], expandedKey);
+
+            memcpy(&long_state[i * INIT_SIZE_BYTE], text, INIT_SIZE_BYTE);
+        }
+    }
+
+    U64(a)[0] = U64(&state.k[0])[0] ^ U64(&state.k[32])[0];
+    U64(a)[1] = U64(&state.k[0])[1] ^ U64(&state.k[32])[1];
+    U64(b)[0] = U64(&state.k[16])[0] ^ U64(&state.k[48])[0];
+    U64(b)[1] = U64(&state.k[16])[1] ^ U64(&state.k[48])[1];
+
+    for(i = 0; i < ITER / 2; i++)
+    {
+				#define TOTALBLOCKS (MEMORY / AES_BLOCK_SIZE)
+				#define state_index(x) (((*((uint64_t *)x) >> 4) & (TOTALBLOCKS - 1)) << 4)
+
+        // Iteration 1
+        p = &long_state[state_index(a)];
+
+        if(useAes)
+            _mm_storeu_si128(R128(p), _mm_aesenc_si128(_mm_loadu_si128(R128(p)), _mm_loadu_si128(R128(a))));
+        else
+            aesb_single_round(p, p, a);
+
+        xor_blocks(b, p);
+        swap_blocks(b, p);
+        swap_blocks(a, b);
+
+        // Iteration 2
+        p = &long_state[state_index(a)];
+
+        mul(a, p, d);
+        sum_half_blocks(b, d);
+        swap_blocks(b, p);
+        xor_blocks(b, p);
+        swap_blocks(a, b);
+    }
+
+    memcpy(text, state.init, INIT_SIZE_BYTE);
+    oaes_key_import_data(aes_ctx, &state.hs.b[32], AES_KEY_SIZE);
+    memcpy(expandedKey, aes_ctx->key->exp_data, aes_ctx->key->exp_data_len);
+    if(useAes)
+    {
+        for(i = 0; i < MEMORY / INIT_SIZE_BYTE; i++)
+        {
+            for(j = 0; j < INIT_SIZE_BLK; j++)
+            {
+                xor_blocks(&text[j * AES_BLOCK_SIZE], &long_state[i * INIT_SIZE_BYTE + j * AES_BLOCK_SIZE]);
+                aesni_pseudo_round(&text[j * AES_BLOCK_SIZE], &text[j * AES_BLOCK_SIZE], expandedKey);
+            }
+        }
     }
-    memcpy(&long_state[i * INIT_SIZE_BYTE], text, INIT_SIZE_BYTE);
-  }
-
-  for (i = 0; i < 16; i++) {
-    a[i] = state.k[     i] ^ state.k[32 + i];
-    b[i] = state.k[16 + i] ^ state.k[48 + i];
-  }
-
-  for (i = 0; i < ITER / 2; i++) {
-    /* Dependency chain: address -> read value ------+
-     * written value <-+ hard function (AES or MUL) <+
-     * next address  <-+
-     */
-    /* Iteration 1 */
-    j = e2i(a, MEMORY / AES_BLOCK_SIZE);
-    copy_block(c, &long_state[j * AES_BLOCK_SIZE]);
-    oaes_encryption_round(a, c);
-    xor_blocks(b, c);
-    swap_blocks(b, c);
-    copy_block(&long_state[j * AES_BLOCK_SIZE], c);
-    assert(j == e2i(a, MEMORY / AES_BLOCK_SIZE));
-    swap_blocks(a, b);
-    /* Iteration 2 */
-    j = e2i(a, MEMORY / AES_BLOCK_SIZE);
-    copy_block(c, &long_state[j * AES_BLOCK_SIZE]);
-    mul(a, c, d);
-    sum_half_blocks(b, d);
-    swap_blocks(b, c);
-    xor_blocks(b, c);
-    copy_block(&long_state[j * AES_BLOCK_SIZE], c);
-    assert(j == e2i(a, MEMORY / AES_BLOCK_SIZE));
-    swap_blocks(a, b);
-  }
-
-  memcpy(text, state.init, INIT_SIZE_BYTE);
-  oaes_key_import_data(aes_ctx, &state.hs.b[32], AES_KEY_SIZE);
-  for (i = 0; i < MEMORY / INIT_SIZE_BYTE; i++) {
-    for (j = 0; j < INIT_SIZE_BLK; j++) {
-      xor_blocks(&text[j * AES_BLOCK_SIZE], &long_state[i * INIT_SIZE_BYTE + j * AES_BLOCK_SIZE]);
-      oaes_pseudo_encrypt_ecb(aes_ctx, &text[j * AES_BLOCK_SIZE]);
+    else
+    {
+        for(i = 0; i < MEMORY / INIT_SIZE_BYTE; i++)
+        {
+            for(j = 0; j < INIT_SIZE_BLK; j++)
+            {
+                xor_blocks(&text[j * AES_BLOCK_SIZE], &long_state[i * INIT_SIZE_BYTE + j * AES_BLOCK_SIZE]);
+                aesb_pseudo_round(&text[AES_BLOCK_SIZE * j], &text[AES_BLOCK_SIZE * j], expandedKey);
+            }
+        }
     }
-  }
-  memcpy(state.init, text, INIT_SIZE_BYTE);
-  hash_permutation(&state.hs);
-  /*memcpy(hash, &state, 32);*/
-  extra_hashes[state.hs.b[0] & 3](&state, 200, hash);
-  oaes_free(&aes_ctx);
+
+    oaes_free((OAES_CTX **) &aes_ctx);
+    memcpy(state.init, text, INIT_SIZE_BYTE);
+    hash_permutation(&state.hs);
+    extra_hashes[state.hs.b[0] & 3](&state, 200, hash);
 }
diff --git a/src/version.h.in b/src/version.h.in
index 2578ea635..01d2994f8 100644
--- a/src/version.h.in
+++ b/src/version.h.in
@@ -1,4 +1,4 @@
 #define BUILD_COMMIT_ID "@VERSION@"
-#define PROJECT_VERSION "0.8.6"
-#define PROJECT_VERSION_BUILD_NO "295"
+#define PROJECT_VERSION "0.8.8.2"
+#define PROJECT_VERSION_BUILD_NO "1"
 #define PROJECT_VERSION_LONG PROJECT_VERSION "." PROJECT_VERSION_BUILD_NO "(" BUILD_COMMIT_ID ")"