/****************
* Transform the message W which consists of 16 64-bit-words
*/
static void
transform (SHA512_CONTEXT *hd, const unsigned char *data)
{
u64 a, b, c, d, e, f, g, h;
u64 w[80];
int t;
static const u64 k[] =
{
U64_C(0x428a2f98d728ae22), U64_C(0x7137449123ef65cd),
U64_C(0xb5c0fbcfec4d3b2f), U64_C(0xe9b5dba58189dbbc),
U64_C(0x3956c25bf348b538), U64_C(0x59f111f1b605d019),
U64_C(0x923f82a4af194f9b), U64_C(0xab1c5ed5da6d8118),
U64_C(0xd807aa98a3030242), U64_C(0x12835b0145706fbe),
U64_C(0x243185be4ee4b28c), U64_C(0x550c7dc3d5ffb4e2),
U64_C(0x72be5d74f27b896f), U64_C(0x80deb1fe3b1696b1),
U64_C(0x9bdc06a725c71235), U64_C(0xc19bf174cf692694),
U64_C(0xe49b69c19ef14ad2), U64_C(0xefbe4786384f25e3),
U64_C(0x0fc19dc68b8cd5b5), U64_C(0x240ca1cc77ac9c65),
U64_C(0x2de92c6f592b0275), U64_C(0x4a7484aa6ea6e483),
U64_C(0x5cb0a9dcbd41fbd4), U64_C(0x76f988da831153b5),
U64_C(0x983e5152ee66dfab), U64_C(0xa831c66d2db43210),
U64_C(0xb00327c898fb213f), U64_C(0xbf597fc7beef0ee4),
U64_C(0xc6e00bf33da88fc2), U64_C(0xd5a79147930aa725),
U64_C(0x06ca6351e003826f), U64_C(0x142929670a0e6e70),
U64_C(0x27b70a8546d22ffc), U64_C(0x2e1b21385c26c926),
U64_C(0x4d2c6dfc5ac42aed), U64_C(0x53380d139d95b3df),
U64_C(0x650a73548baf63de), U64_C(0x766a0abb3c77b2a8),
U64_C(0x81c2c92e47edaee6), U64_C(0x92722c851482353b),
U64_C(0xa2bfe8a14cf10364), U64_C(0xa81a664bbc423001),
U64_C(0xc24b8b70d0f89791), U64_C(0xc76c51a30654be30),
U64_C(0xd192e819d6ef5218), U64_C(0xd69906245565a910),
U64_C(0xf40e35855771202a), U64_C(0x106aa07032bbd1b8),
U64_C(0x19a4c116b8d2d0c8), U64_C(0x1e376c085141ab53),
U64_C(0x2748774cdf8eeb99), U64_C(0x34b0bcb5e19b48a8),
U64_C(0x391c0cb3c5c95a63), U64_C(0x4ed8aa4ae3418acb),
U64_C(0x5b9cca4f7763e373), U64_C(0x682e6ff3d6b2b8a3),
U64_C(0x748f82ee5defb2fc), U64_C(0x78a5636f43172f60),
U64_C(0x84c87814a1f0ab72), U64_C(0x8cc702081a6439ec),
U64_C(0x90befffa23631e28), U64_C(0xa4506cebde82bde9),
U64_C(0xbef9a3f7b2c67915), U64_C(0xc67178f2e372532b),
U64_C(0xca273eceea26619c), U64_C(0xd186b8c721c0c207),
U64_C(0xeada7dd6cde0eb1e), U64_C(0xf57d4f7fee6ed178),
U64_C(0x06f067aa72176fba), U64_C(0x0a637dc5a2c898a6),
U64_C(0x113f9804bef90dae), U64_C(0x1b710b35131c471b),
U64_C(0x28db77f523047d84), U64_C(0x32caab7b40c72493),
U64_C(0x3c9ebe0a15c9bebc), U64_C(0x431d67c49c100d4c),
U64_C(0x4cc5d4becb3e42b6), U64_C(0x597f299cfc657e2a),
U64_C(0x5fcb6fab3ad6faec), U64_C(0x6c44198c4a475817)
};
/* get values from the chaining vars */
a = hd->h0;
b = hd->h1;
c = hd->h2;
d = hd->h3;
e = hd->h4;
f = hd->h5;
g = hd->h6;
h = hd->h7;
#ifdef WORDS_BIGENDIAN
memcpy (w, data, 128);
#else
{
int i;
byte *p2;
for (i = 0, p2 = (byte *) w; i < 16; i++, p2 += 8)
{
p2[7] = *data++;
p2[6] = *data++;
p2[5] = *data++;
p2[4] = *data++;
p2[3] = *data++;
p2[2] = *data++;
p2[1] = *data++;
p2[0] = *data++;
}
}
#endif
#define S0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7))
#define S1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
for (t = 16; t < 80; t++)
w[t] = S1 (w[t - 2]) + w[t - 7] + S0 (w[t - 15]) + w[t - 16];
for (t = 0; t < 80; )
{
u64 t1, t2;
/* Performance on a AMD Athlon(tm) Dual Core Processor 4050e
with gcc 4.3.3 using gcry_md_hash_buffer of each 10000 bytes
initialized to 0,1,2,3...255,0,... and 1000 iterations:
Not unrolled with macros: 440ms
Unrolled with macros: 350ms
Unrolled with inline: 330ms
*/
#if 1 /* Not unrolled. */
t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t];
t2 = Sum0 (a) + Maj (a, b, c);
h = g;
g = f;
f = e;
e = d + t1;
d = c;
c = b;
b = a;
a = t1 + t2;
t++;
#else /* Unrolled to interweave the chain variables. */
t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t];
t2 = Sum0 (a) + Maj (a, b, c);
d += t1;
h = t1 + t2;
t1 = g + Sum1 (d) + Ch (d, e, f) + k[t+1] + w[t+1];
t2 = Sum0 (h) + Maj (h, a, b);
c += t1;
g = t1 + t2;
t1 = f + Sum1 (c) + Ch (c, d, e) + k[t+2] + w[t+2];
t2 = Sum0 (g) + Maj (g, h, a);
b += t1;
f = t1 + t2;
t1 = e + Sum1 (b) + Ch (b, c, d) + k[t+3] + w[t+3];
t2 = Sum0 (f) + Maj (f, g, h);
a += t1;
e = t1 + t2;
t1 = d + Sum1 (a) + Ch (a, b, c) + k[t+4] + w[t+4];
t2 = Sum0 (e) + Maj (e, f, g);
h += t1;
d = t1 + t2;
t1 = c + Sum1 (h) + Ch (h, a, b) + k[t+5] + w[t+5];
t2 = Sum0 (d) + Maj (d, e, f);
g += t1;
c = t1 + t2;
t1 = b + Sum1 (g) + Ch (g, h, a) + k[t+6] + w[t+6];
t2 = Sum0 (c) + Maj (c, d, e);
f += t1;
b = t1 + t2;
t1 = a + Sum1 (f) + Ch (f, g, h) + k[t+7] + w[t+7];
t2 = Sum0 (b) + Maj (b, c, d);
e += t1;
a = t1 + t2;
t += 8;
#endif
}
/* Update chaining vars. */
hd->h0 += a;
hd->h1 += b;
hd->h2 += c;
hd->h3 += d;
hd->h4 += e;
hd->h5 += f;
hd->h6 += g;
hd->h7 += h;
}
/****************
* Transform the message W which consists of 16 64-bit-words
*/
static void
transform (SHA512_CONTEXT *hd, byte *data)
{
u64 a, b, c, d, e, f, g, h;
u64 w[80];
int t;
static const u64 k[] =
{
U64_C(0x428a2f98d728ae22), U64_C(0x7137449123ef65cd),
U64_C(0xb5c0fbcfec4d3b2f), U64_C(0xe9b5dba58189dbbc),
U64_C(0x3956c25bf348b538), U64_C(0x59f111f1b605d019),
U64_C(0x923f82a4af194f9b), U64_C(0xab1c5ed5da6d8118),
U64_C(0xd807aa98a3030242), U64_C(0x12835b0145706fbe),
U64_C(0x243185be4ee4b28c), U64_C(0x550c7dc3d5ffb4e2),
U64_C(0x72be5d74f27b896f), U64_C(0x80deb1fe3b1696b1),
U64_C(0x9bdc06a725c71235), U64_C(0xc19bf174cf692694),
U64_C(0xe49b69c19ef14ad2), U64_C(0xefbe4786384f25e3),
U64_C(0x0fc19dc68b8cd5b5), U64_C(0x240ca1cc77ac9c65),
U64_C(0x2de92c6f592b0275), U64_C(0x4a7484aa6ea6e483),
U64_C(0x5cb0a9dcbd41fbd4), U64_C(0x76f988da831153b5),
U64_C(0x983e5152ee66dfab), U64_C(0xa831c66d2db43210),
U64_C(0xb00327c898fb213f), U64_C(0xbf597fc7beef0ee4),
U64_C(0xc6e00bf33da88fc2), U64_C(0xd5a79147930aa725),
U64_C(0x06ca6351e003826f), U64_C(0x142929670a0e6e70),
U64_C(0x27b70a8546d22ffc), U64_C(0x2e1b21385c26c926),
U64_C(0x4d2c6dfc5ac42aed), U64_C(0x53380d139d95b3df),
U64_C(0x650a73548baf63de), U64_C(0x766a0abb3c77b2a8),
U64_C(0x81c2c92e47edaee6), U64_C(0x92722c851482353b),
U64_C(0xa2bfe8a14cf10364), U64_C(0xa81a664bbc423001),
U64_C(0xc24b8b70d0f89791), U64_C(0xc76c51a30654be30),
U64_C(0xd192e819d6ef5218), U64_C(0xd69906245565a910),
U64_C(0xf40e35855771202a), U64_C(0x106aa07032bbd1b8),
U64_C(0x19a4c116b8d2d0c8), U64_C(0x1e376c085141ab53),
U64_C(0x2748774cdf8eeb99), U64_C(0x34b0bcb5e19b48a8),
U64_C(0x391c0cb3c5c95a63), U64_C(0x4ed8aa4ae3418acb),
U64_C(0x5b9cca4f7763e373), U64_C(0x682e6ff3d6b2b8a3),
U64_C(0x748f82ee5defb2fc), U64_C(0x78a5636f43172f60),
U64_C(0x84c87814a1f0ab72), U64_C(0x8cc702081a6439ec),
U64_C(0x90befffa23631e28), U64_C(0xa4506cebde82bde9),
U64_C(0xbef9a3f7b2c67915), U64_C(0xc67178f2e372532b),
U64_C(0xca273eceea26619c), U64_C(0xd186b8c721c0c207),
U64_C(0xeada7dd6cde0eb1e), U64_C(0xf57d4f7fee6ed178),
U64_C(0x06f067aa72176fba), U64_C(0x0a637dc5a2c898a6),
U64_C(0x113f9804bef90dae), U64_C(0x1b710b35131c471b),
U64_C(0x28db77f523047d84), U64_C(0x32caab7b40c72493),
U64_C(0x3c9ebe0a15c9bebc), U64_C(0x431d67c49c100d4c),
U64_C(0x4cc5d4becb3e42b6), U64_C(0x597f299cfc657e2a),
U64_C(0x5fcb6fab3ad6faec), U64_C(0x6c44198c4a475817)
};
/* get values from the chaining vars */
a = hd->h0;
b = hd->h1;
c = hd->h2;
d = hd->h3;
e = hd->h4;
f = hd->h5;
g = hd->h6;
h = hd->h7;
#ifdef WORDS_BIGENDIAN
memcpy (w, data, 128);
#else
{
int i;
byte *p2;
for (i = 0, p2 = (byte *) w; i < 16; i++, p2 += 8)
{
p2[7] = *data++;
p2[6] = *data++;
p2[5] = *data++;
p2[4] = *data++;
p2[3] = *data++;
p2[2] = *data++;
p2[1] = *data++;
p2[0] = *data++;
}
}
#endif
#define ROTR(x,n) (((x)>>(n)) | ((x)<<(64-(n))))
#define Ch(x,y,z) (((x) & (y)) ^ ((~(x)) & (z)))
#define Maj(x,y,z) (((x) & (y)) ^ ((x) & (z)) ^ ((y) & (z)))
#define Sum0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
#define Sum1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
#define S0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7))
#define S1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
for (t = 16; t < 80; t++)
w[t] = S1 (w[t - 2]) + w[t - 7] + S0 (w[t - 15]) + w[t - 16];
for (t = 0; t < 80; t++)
{
u64 t1, t2;
t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t];
t2 = Sum0 (a) + Maj (a, b, c);
h = g;
g = f;
f = e;
e = d + t1;
d = c;
c = b;
b = a;
a = t1 + t2;
/* printf("t=%d a=%016llX b=%016llX c=%016llX d=%016llX "
"e=%016llX f=%016llX g=%016llX h=%016llX\n",t,a,b,c,d,e,f,g,h); */
}
/* update chaining vars */
hd->h0 += a;
hd->h1 += b;
hd->h2 += c;
hd->h3 += d;
hd->h4 += e;
hd->h5 += f;
hd->h6 += g;
hd->h7 += h;
}