+ F[0] = A;
+ F[4] = E;
+ F[8] = T;
+ T += F[7] + Sigma1(E) + Ch(E, F[5], F[6]) + K512[i];
+ E = F[3] + T;
+ A = T + Sigma0(A) + Maj(A, F[1], F[2]);
+ }
+
+ for (; i < 80; i++, F--) {
+ T = sigma0(F[8 + 16 - 1]);
+ T += sigma1(F[8 + 16 - 14]);
+ T += F[8 + 16] + F[8 + 16 - 9];
+
+ F[0] = A;
+ F[4] = E;
+ F[8] = T;
+ T += F[7] + Sigma1(E) + Ch(E, F[5], F[6]) + K512[i];
+ E = F[3] + T;
+ A = T + Sigma0(A) + Maj(A, F[1], F[2]);
+ }
+
+ ctx->h[0] += A;
+ ctx->h[1] += F[1];
+ ctx->h[2] += F[2];
+ ctx->h[3] += F[3];
+ ctx->h[4] += E;
+ ctx->h[5] += F[5];
+ ctx->h[6] += F[6];
+ ctx->h[7] += F[7];
+
+ W += SHA_LBLOCK;
+ }
+}
+
+# elif defined(OPENSSL_SMALL_FOOTPRINT)
+static void sha512_block_data_order(SHA512_CTX *ctx, const void *in,
+ size_t num)
+{
+ const SHA_LONG64 *W = in;
+ SHA_LONG64 a, b, c, d, e, f, g, h, s0, s1, T1, T2;
+ SHA_LONG64 X[16];
+ int i;
+
+ while (num--) {
+
+ a = ctx->h[0];
+ b = ctx->h[1];
+ c = ctx->h[2];
+ d = ctx->h[3];
+ e = ctx->h[4];
+ f = ctx->h[5];
+ g = ctx->h[6];
+ h = ctx->h[7];
+
+ for (i = 0; i < 16; i++) {
+# ifdef B_ENDIAN
+ T1 = X[i] = W[i];
+# else
+ T1 = X[i] = PULL64(W[i]);
+# endif
+ T1 += h + Sigma1(e) + Ch(e, f, g) + K512[i];
+ T2 = Sigma0(a) + Maj(a, b, c);
+ h = g;
+ g = f;
+ f = e;
+ e = d + T1;
+ d = c;
+ c = b;
+ b = a;
+ a = T1 + T2;
+ }
+
+ for (; i < 80; i++) {
+ s0 = X[(i + 1) & 0x0f];
+ s0 = sigma0(s0);
+ s1 = X[(i + 14) & 0x0f];
+ s1 = sigma1(s1);
+
+ T1 = X[i & 0xf] += s0 + s1 + X[(i + 9) & 0xf];
+ T1 += h + Sigma1(e) + Ch(e, f, g) + K512[i];
+ T2 = Sigma0(a) + Maj(a, b, c);
+ h = g;
+ g = f;
+ f = e;
+ e = d + T1;
+ d = c;
+ c = b;
+ b = a;
+ a = T1 + T2;
+ }
+
+ ctx->h[0] += a;
+ ctx->h[1] += b;
+ ctx->h[2] += c;
+ ctx->h[3] += d;
+ ctx->h[4] += e;
+ ctx->h[5] += f;
+ ctx->h[6] += g;
+ ctx->h[7] += h;
+
+ W += SHA_LBLOCK;
+ }
+}
+
+# else
+# define ROUND_00_15(i,a,b,c,d,e,f,g,h) do { \
+ T1 += h + Sigma1(e) + Ch(e,f,g) + K512[i]; \
+ h = Sigma0(a) + Maj(a,b,c); \
+ d += T1; h += T1; } while (0)
+# define ROUND_16_80(i,j,a,b,c,d,e,f,g,h,X) do { \
+ s0 = X[(j+1)&0x0f]; s0 = sigma0(s0); \
+ s1 = X[(j+14)&0x0f]; s1 = sigma1(s1); \
+ T1 = X[(j)&0x0f] += s0 + s1 + X[(j+9)&0x0f]; \
+ ROUND_00_15(i+j,a,b,c,d,e,f,g,h); } while (0)
+static void sha512_block_data_order(SHA512_CTX *ctx, const void *in,
+ size_t num)
+{
+ const SHA_LONG64 *W = in;
+ SHA_LONG64 a, b, c, d, e, f, g, h, s0, s1, T1;
+ SHA_LONG64 X[16];
+ int i;
+
+ while (num--) {
+
+ a = ctx->h[0];
+ b = ctx->h[1];
+ c = ctx->h[2];
+ d = ctx->h[3];
+ e = ctx->h[4];
+ f = ctx->h[5];
+ g = ctx->h[6];
+ h = ctx->h[7];
+
+# ifdef B_ENDIAN
+ T1 = X[0] = W[0];
+ ROUND_00_15(0, a, b, c, d, e, f, g, h);
+ T1 = X[1] = W[1];
+ ROUND_00_15(1, h, a, b, c, d, e, f, g);
+ T1 = X[2] = W[2];
+ ROUND_00_15(2, g, h, a, b, c, d, e, f);
+ T1 = X[3] = W[3];
+ ROUND_00_15(3, f, g, h, a, b, c, d, e);
+ T1 = X[4] = W[4];
+ ROUND_00_15(4, e, f, g, h, a, b, c, d);
+ T1 = X[5] = W[5];
+ ROUND_00_15(5, d, e, f, g, h, a, b, c);
+ T1 = X[6] = W[6];
+ ROUND_00_15(6, c, d, e, f, g, h, a, b);
+ T1 = X[7] = W[7];
+ ROUND_00_15(7, b, c, d, e, f, g, h, a);
+ T1 = X[8] = W[8];
+ ROUND_00_15(8, a, b, c, d, e, f, g, h);
+ T1 = X[9] = W[9];
+ ROUND_00_15(9, h, a, b, c, d, e, f, g);
+ T1 = X[10] = W[10];
+ ROUND_00_15(10, g, h, a, b, c, d, e, f);
+ T1 = X[11] = W[11];
+ ROUND_00_15(11, f, g, h, a, b, c, d, e);
+ T1 = X[12] = W[12];
+ ROUND_00_15(12, e, f, g, h, a, b, c, d);
+ T1 = X[13] = W[13];
+ ROUND_00_15(13, d, e, f, g, h, a, b, c);
+ T1 = X[14] = W[14];
+ ROUND_00_15(14, c, d, e, f, g, h, a, b);
+ T1 = X[15] = W[15];
+ ROUND_00_15(15, b, c, d, e, f, g, h, a);
+# else
+ T1 = X[0] = PULL64(W[0]);
+ ROUND_00_15(0, a, b, c, d, e, f, g, h);
+ T1 = X[1] = PULL64(W[1]);
+ ROUND_00_15(1, h, a, b, c, d, e, f, g);
+ T1 = X[2] = PULL64(W[2]);
+ ROUND_00_15(2, g, h, a, b, c, d, e, f);
+ T1 = X[3] = PULL64(W[3]);
+ ROUND_00_15(3, f, g, h, a, b, c, d, e);
+ T1 = X[4] = PULL64(W[4]);
+ ROUND_00_15(4, e, f, g, h, a, b, c, d);
+ T1 = X[5] = PULL64(W[5]);
+ ROUND_00_15(5, d, e, f, g, h, a, b, c);
+ T1 = X[6] = PULL64(W[6]);
+ ROUND_00_15(6, c, d, e, f, g, h, a, b);
+ T1 = X[7] = PULL64(W[7]);
+ ROUND_00_15(7, b, c, d, e, f, g, h, a);
+ T1 = X[8] = PULL64(W[8]);
+ ROUND_00_15(8, a, b, c, d, e, f, g, h);
+ T1 = X[9] = PULL64(W[9]);
+ ROUND_00_15(9, h, a, b, c, d, e, f, g);
+ T1 = X[10] = PULL64(W[10]);
+ ROUND_00_15(10, g, h, a, b, c, d, e, f);
+ T1 = X[11] = PULL64(W[11]);
+ ROUND_00_15(11, f, g, h, a, b, c, d, e);
+ T1 = X[12] = PULL64(W[12]);
+ ROUND_00_15(12, e, f, g, h, a, b, c, d);
+ T1 = X[13] = PULL64(W[13]);
+ ROUND_00_15(13, d, e, f, g, h, a, b, c);
+ T1 = X[14] = PULL64(W[14]);
+ ROUND_00_15(14, c, d, e, f, g, h, a, b);
+ T1 = X[15] = PULL64(W[15]);
+ ROUND_00_15(15, b, c, d, e, f, g, h, a);