rbnacl-libsodium 0.5.0.1 → 0.6.0

data/vendor/libsodium/src/libsodium/crypto_scalarmult/curve25519/ref10/fe_sub_curve25519_ref10.c

@@ -0,0 +1,61 @@
+#include "fe.h"
+
+#ifndef HAVE_TI_MODE
+
+/*
+h = f - g
+Can overlap h with f or g.
+
+Preconditions:
+   |f| bounded by 1.1*2^25,1.1*2^24,1.1*2^25,1.1*2^24,etc.
+   |g| bounded by 1.1*2^25,1.1*2^24,1.1*2^25,1.1*2^24,etc.
+
+Postconditions:
+   |h| bounded by 1.1*2^26,1.1*2^25,1.1*2^26,1.1*2^25,etc.
+*/
+
+void fe_sub(fe h,fe f,fe g)
+{
+  crypto_int32 f0 = f[0];
+  crypto_int32 f1 = f[1];
+  crypto_int32 f2 = f[2];
+  crypto_int32 f3 = f[3];
+  crypto_int32 f4 = f[4];
+  crypto_int32 f5 = f[5];
+  crypto_int32 f6 = f[6];
+  crypto_int32 f7 = f[7];
+  crypto_int32 f8 = f[8];
+  crypto_int32 f9 = f[9];
+  crypto_int32 g0 = g[0];
+  crypto_int32 g1 = g[1];
+  crypto_int32 g2 = g[2];
+  crypto_int32 g3 = g[3];
+  crypto_int32 g4 = g[4];
+  crypto_int32 g5 = g[5];
+  crypto_int32 g6 = g[6];
+  crypto_int32 g7 = g[7];
+  crypto_int32 g8 = g[8];
+  crypto_int32 g9 = g[9];
+  crypto_int32 h0 = f0 - g0;
+  crypto_int32 h1 = f1 - g1;
+  crypto_int32 h2 = f2 - g2;
+  crypto_int32 h3 = f3 - g3;
+  crypto_int32 h4 = f4 - g4;
+  crypto_int32 h5 = f5 - g5;
+  crypto_int32 h6 = f6 - g6;
+  crypto_int32 h7 = f7 - g7;
+  crypto_int32 h8 = f8 - g8;
+  crypto_int32 h9 = f9 - g9;
+  h[0] = h0;
+  h[1] = h1;
+  h[2] = h2;
+  h[3] = h3;
+  h[4] = h4;
+  h[5] = h5;
+  h[6] = h6;
+  h[7] = h7;
+  h[8] = h8;
+  h[9] = h9;
+}
+
+#endif

data/vendor/libsodium/src/libsodium/crypto_scalarmult/curve25519/ref10/fe_tobytes_curve25519_ref10.c

@@ -0,0 +1,123 @@
+#include "fe.h"
+
+#ifndef HAVE_TI_MODE
+
+/*
+Preconditions:
+  |h| bounded by 1.1*2^25,1.1*2^24,1.1*2^25,1.1*2^24,etc.
+
+Write p=2^255-19; q=floor(h/p).
+Basic claim: q = floor(2^(-255)(h + 19 2^(-25)h9 + 2^(-1))).
+
+Proof:
+  Have |h|<=p so |q|<=1 so |19^2 2^(-255) q|<1/4.
+  Also have |h-2^230 h9|<2^230 so |19 2^(-255)(h-2^230 h9)|<1/4.
+
+  Write y=2^(-1)-19^2 2^(-255)q-19 2^(-255)(h-2^230 h9).
+  Then 0<y<1.
+
+  Write r=h-pq.
+  Have 0<=r<=p-1=2^255-20.
+  Thus 0<=r+19(2^-255)r<r+19(2^-255)2^255<=2^255-1.
+
+  Write x=r+19(2^-255)r+y.
+  Then 0<x<2^255 so floor(2^(-255)x) = 0 so floor(q+2^(-255)x) = q.
+
+  Have q+2^(-255)x = 2^(-255)(h + 19 2^(-25) h9 + 2^(-1))
+  so floor(2^(-255)(h + 19 2^(-25) h9 + 2^(-1))) = q.
+*/
+
+void fe_tobytes(unsigned char *s,fe h)
+{
+  crypto_int32 h0 = h[0];
+  crypto_int32 h1 = h[1];
+  crypto_int32 h2 = h[2];
+  crypto_int32 h3 = h[3];
+  crypto_int32 h4 = h[4];
+  crypto_int32 h5 = h[5];
+  crypto_int32 h6 = h[6];
+  crypto_int32 h7 = h[7];
+  crypto_int32 h8 = h[8];
+  crypto_int32 h9 = h[9];
+  crypto_int32 q;
+  crypto_int32 carry0;
+  crypto_int32 carry1;
+  crypto_int32 carry2;
+  crypto_int32 carry3;
+  crypto_int32 carry4;
+  crypto_int32 carry5;
+  crypto_int32 carry6;
+  crypto_int32 carry7;
+  crypto_int32 carry8;
+  crypto_int32 carry9;
+
+  q = (19 * h9 + (((crypto_int32) 1) << 24)) >> 25;
+  q = (h0 + q) >> 26;
+  q = (h1 + q) >> 25;
+  q = (h2 + q) >> 26;
+  q = (h3 + q) >> 25;
+  q = (h4 + q) >> 26;
+  q = (h5 + q) >> 25;
+  q = (h6 + q) >> 26;
+  q = (h7 + q) >> 25;
+  q = (h8 + q) >> 26;
+  q = (h9 + q) >> 25;
+
+  /* Goal: Output h-(2^255-19)q, which is between 0 and 2^255-20. */
+  h0 += 19 * q;
+  /* Goal: Output h-2^255 q, which is between 0 and 2^255-20. */
+
+  carry0 = h0 >> 26; h1 += carry0; h0 -= carry0 << 26;
+  carry1 = h1 >> 25; h2 += carry1; h1 -= carry1 << 25;
+  carry2 = h2 >> 26; h3 += carry2; h2 -= carry2 << 26;
+  carry3 = h3 >> 25; h4 += carry3; h3 -= carry3 << 25;
+  carry4 = h4 >> 26; h5 += carry4; h4 -= carry4 << 26;
+  carry5 = h5 >> 25; h6 += carry5; h5 -= carry5 << 25;
+  carry6 = h6 >> 26; h7 += carry6; h6 -= carry6 << 26;
+  carry7 = h7 >> 25; h8 += carry7; h7 -= carry7 << 25;
+  carry8 = h8 >> 26; h9 += carry8; h8 -= carry8 << 26;
+  carry9 = h9 >> 25;               h9 -= carry9 << 25;
+                  /* h10 = carry9 */
+
+  /*
+  Goal: Output h0+...+2^255 h10-2^255 q, which is between 0 and 2^255-20.
+  Have h0+...+2^230 h9 between 0 and 2^255-1;
+  evidently 2^255 h10-2^255 q = 0.
+  Goal: Output h0+...+2^230 h9.
+  */
+
+  s[0] = h0 >> 0;
+  s[1] = h0 >> 8;
+  s[2] = h0 >> 16;
+  s[3] = (h0 >> 24) | (h1 << 2);
+  s[4] = h1 >> 6;
+  s[5] = h1 >> 14;
+  s[6] = (h1 >> 22) | (h2 << 3);
+  s[7] = h2 >> 5;
+  s[8] = h2 >> 13;
+  s[9] = (h2 >> 21) | (h3 << 5);
+  s[10] = h3 >> 3;
+  s[11] = h3 >> 11;
+  s[12] = (h3 >> 19) | (h4 << 6);
+  s[13] = h4 >> 2;
+  s[14] = h4 >> 10;
+  s[15] = h4 >> 18;
+  s[16] = h5 >> 0;
+  s[17] = h5 >> 8;
+  s[18] = h5 >> 16;
+  s[19] = (h5 >> 24) | (h6 << 1);
+  s[20] = h6 >> 7;
+  s[21] = h6 >> 15;
+  s[22] = (h6 >> 23) | (h7 << 3);
+  s[23] = h7 >> 5;
+  s[24] = h7 >> 13;
+  s[25] = (h7 >> 21) | (h8 << 4);
+  s[26] = h8 >> 4;
+  s[27] = h8 >> 12;
+  s[28] = (h8 >> 20) | (h9 << 6);
+  s[29] = h9 >> 2;
+  s[30] = h9 >> 10;
+  s[31] = h9 >> 18;
+}
+
+#endif

data/vendor/libsodium/src/libsodium/crypto_scalarmult/curve25519/ref10/montgomery.h

@@ -0,0 +1,140 @@
+
+/* qhasm: fe X2 */
+
+/* qhasm: fe Z2 */
+
+/* qhasm: fe X3 */
+
+/* qhasm: fe Z3 */
+
+/* qhasm: fe X4 */
+
+/* qhasm: fe Z4 */
+
+/* qhasm: fe X5 */
+
+/* qhasm: fe Z5 */
+
+/* qhasm: fe A */
+
+/* qhasm: fe B */
+
+/* qhasm: fe C */
+
+/* qhasm: fe D */
+
+/* qhasm: fe E */
+
+/* qhasm: fe AA */
+
+/* qhasm: fe BB */
+
+/* qhasm: fe DA */
+
+/* qhasm: fe CB */
+
+/* qhasm: fe t0 */
+
+/* qhasm: fe t1 */
+
+/* qhasm: fe t2 */
+
+/* qhasm: fe t3 */
+
+/* qhasm: fe t4 */
+
+/* qhasm: enter ladder */
+
+/* qhasm: D = X3-Z3 */
+/* asm 1: fe_sub(>D=fe#5,<X3=fe#3,<Z3=fe#4); */
+/* asm 2: fe_sub(>D=tmp0,<X3=x3,<Z3=z3); */
+fe_sub(tmp0,x3,z3);
+
+/* qhasm: B = X2-Z2 */
+/* asm 1: fe_sub(>B=fe#6,<X2=fe#1,<Z2=fe#2); */
+/* asm 2: fe_sub(>B=tmp1,<X2=x2,<Z2=z2); */
+fe_sub(tmp1,x2,z2);
+
+/* qhasm: A = X2+Z2 */
+/* asm 1: fe_add(>A=fe#1,<X2=fe#1,<Z2=fe#2); */
+/* asm 2: fe_add(>A=x2,<X2=x2,<Z2=z2); */
+fe_add(x2,x2,z2);
+
+/* qhasm: C = X3+Z3 */
+/* asm 1: fe_add(>C=fe#2,<X3=fe#3,<Z3=fe#4); */
+/* asm 2: fe_add(>C=z2,<X3=x3,<Z3=z3); */
+fe_add(z2,x3,z3);
+
+/* qhasm: DA = D*A */
+/* asm 1: fe_mul(>DA=fe#4,<D=fe#5,<A=fe#1); */
+/* asm 2: fe_mul(>DA=z3,<D=tmp0,<A=x2); */
+fe_mul(z3,tmp0,x2);
+
+/* qhasm: CB = C*B */
+/* asm 1: fe_mul(>CB=fe#2,<C=fe#2,<B=fe#6); */
+/* asm 2: fe_mul(>CB=z2,<C=z2,<B=tmp1); */
+fe_mul(z2,z2,tmp1);
+
+/* qhasm: BB = B^2 */
+/* asm 1: fe_sq(>BB=fe#5,<B=fe#6); */
+/* asm 2: fe_sq(>BB=tmp0,<B=tmp1); */
+fe_sq(tmp0,tmp1);
+
+/* qhasm: AA = A^2 */
+/* asm 1: fe_sq(>AA=fe#6,<A=fe#1); */
+/* asm 2: fe_sq(>AA=tmp1,<A=x2); */
+fe_sq(tmp1,x2);
+
+/* qhasm: t0 = DA+CB */
+/* asm 1: fe_add(>t0=fe#3,<DA=fe#4,<CB=fe#2); */
+/* asm 2: fe_add(>t0=x3,<DA=z3,<CB=z2); */
+fe_add(x3,z3,z2);
+
+/* qhasm: assign x3 to t0 */
+
+/* qhasm: t1 = DA-CB */
+/* asm 1: fe_sub(>t1=fe#2,<DA=fe#4,<CB=fe#2); */
+/* asm 2: fe_sub(>t1=z2,<DA=z3,<CB=z2); */
+fe_sub(z2,z3,z2);
+
+/* qhasm: X4 = AA*BB */
+/* asm 1: fe_mul(>X4=fe#1,<AA=fe#6,<BB=fe#5); */
+/* asm 2: fe_mul(>X4=x2,<AA=tmp1,<BB=tmp0); */
+fe_mul(x2,tmp1,tmp0);
+
+/* qhasm: E = AA-BB */
+/* asm 1: fe_sub(>E=fe#6,<AA=fe#6,<BB=fe#5); */
+/* asm 2: fe_sub(>E=tmp1,<AA=tmp1,<BB=tmp0); */
+fe_sub(tmp1,tmp1,tmp0);
+
+/* qhasm: t2 = t1^2 */
+/* asm 1: fe_sq(>t2=fe#2,<t1=fe#2); */
+/* asm 2: fe_sq(>t2=z2,<t1=z2); */
+fe_sq(z2,z2);
+
+/* qhasm: t3 = a24*E */
+/* asm 1: fe_mul121666(>t3=fe#4,<E=fe#6); */
+/* asm 2: fe_mul121666(>t3=z3,<E=tmp1); */
+fe_mul121666(z3,tmp1);
+
+/* qhasm: X5 = t0^2 */
+/* asm 1: fe_sq(>X5=fe#3,<t0=fe#3); */
+/* asm 2: fe_sq(>X5=x3,<t0=x3); */
+fe_sq(x3,x3);
+
+/* qhasm: t4 = BB+t3 */
+/* asm 1: fe_add(>t4=fe#5,<BB=fe#5,<t3=fe#4); */
+/* asm 2: fe_add(>t4=tmp0,<BB=tmp0,<t3=z3); */
+fe_add(tmp0,tmp0,z3);
+
+/* qhasm: Z5 = X1*t2 */
+/* asm 1: fe_mul(>Z5=fe#4,x1,<t2=fe#2); */
+/* asm 2: fe_mul(>Z5=z3,x1,<t2=z2); */
+fe_mul(z3,x1,z2);
+
+/* qhasm: Z4 = E*t4 */
+/* asm 1: fe_mul(>Z4=fe#2,<E=fe#6,<t4=fe#5); */
+/* asm 2: fe_mul(>Z4=z2,<E=tmp1,<t4=tmp0); */
+fe_mul(z2,tmp1,tmp0);
+
+/* qhasm: return */

data/vendor/libsodium/src/libsodium/crypto_scalarmult/curve25519/ref10/pow225521.h

@@ -0,0 +1,160 @@
+
+/* qhasm: fe z1 */
+
+/* qhasm: fe z2 */
+
+/* qhasm: fe z8 */
+
+/* qhasm: fe z9 */
+
+/* qhasm: fe z11 */
+
+/* qhasm: fe z22 */
+
+/* qhasm: fe z_5_0 */
+
+/* qhasm: fe z_10_5 */
+
+/* qhasm: fe z_10_0 */
+
+/* qhasm: fe z_20_10 */
+
+/* qhasm: fe z_20_0 */
+
+/* qhasm: fe z_40_20 */
+
+/* qhasm: fe z_40_0 */
+
+/* qhasm: fe z_50_10 */
+
+/* qhasm: fe z_50_0 */
+
+/* qhasm: fe z_100_50 */
+
+/* qhasm: fe z_100_0 */
+
+/* qhasm: fe z_200_100 */
+
+/* qhasm: fe z_200_0 */
+
+/* qhasm: fe z_250_50 */
+
+/* qhasm: fe z_250_0 */
+
+/* qhasm: fe z_255_5 */
+
+/* qhasm: fe z_255_21 */
+
+/* qhasm: enter pow225521 */
+
+/* qhasm: z2 = z1^2^1 */
+/* asm 1: fe_sq(>z2=fe#1,<z1=fe#11); for (i = 1;i < 1;++i) fe_sq(>z2=fe#1,>z2=fe#1); */
+/* asm 2: fe_sq(>z2=t0,<z1=z); for (i = 1;i < 1;++i) fe_sq(>z2=t0,>z2=t0); */
+fe_sq(t0,z); for (i = 1;i < 1;++i) fe_sq(t0,t0);
+
+/* qhasm: z8 = z2^2^2 */
+/* asm 1: fe_sq(>z8=fe#2,<z2=fe#1); for (i = 1;i < 2;++i) fe_sq(>z8=fe#2,>z8=fe#2); */
+/* asm 2: fe_sq(>z8=t1,<z2=t0); for (i = 1;i < 2;++i) fe_sq(>z8=t1,>z8=t1); */
+fe_sq(t1,t0); for (i = 1;i < 2;++i) fe_sq(t1,t1);
+
+/* qhasm: z9 = z1*z8 */
+/* asm 1: fe_mul(>z9=fe#2,<z1=fe#11,<z8=fe#2); */
+/* asm 2: fe_mul(>z9=t1,<z1=z,<z8=t1); */
+fe_mul(t1,z,t1);
+
+/* qhasm: z11 = z2*z9 */
+/* asm 1: fe_mul(>z11=fe#1,<z2=fe#1,<z9=fe#2); */
+/* asm 2: fe_mul(>z11=t0,<z2=t0,<z9=t1); */
+fe_mul(t0,t0,t1);
+
+/* qhasm: z22 = z11^2^1 */
+/* asm 1: fe_sq(>z22=fe#3,<z11=fe#1); for (i = 1;i < 1;++i) fe_sq(>z22=fe#3,>z22=fe#3); */
+/* asm 2: fe_sq(>z22=t2,<z11=t0); for (i = 1;i < 1;++i) fe_sq(>z22=t2,>z22=t2); */
+fe_sq(t2,t0); for (i = 1;i < 1;++i) fe_sq(t2,t2);
+
+/* qhasm: z_5_0 = z9*z22 */
+/* asm 1: fe_mul(>z_5_0=fe#2,<z9=fe#2,<z22=fe#3); */
+/* asm 2: fe_mul(>z_5_0=t1,<z9=t1,<z22=t2); */
+fe_mul(t1,t1,t2);
+
+/* qhasm: z_10_5 = z_5_0^2^5 */
+/* asm 1: fe_sq(>z_10_5=fe#3,<z_5_0=fe#2); for (i = 1;i < 5;++i) fe_sq(>z_10_5=fe#3,>z_10_5=fe#3); */
+/* asm 2: fe_sq(>z_10_5=t2,<z_5_0=t1); for (i = 1;i < 5;++i) fe_sq(>z_10_5=t2,>z_10_5=t2); */
+fe_sq(t2,t1); for (i = 1;i < 5;++i) fe_sq(t2,t2);
+
+/* qhasm: z_10_0 = z_10_5*z_5_0 */
+/* asm 1: fe_mul(>z_10_0=fe#2,<z_10_5=fe#3,<z_5_0=fe#2); */
+/* asm 2: fe_mul(>z_10_0=t1,<z_10_5=t2,<z_5_0=t1); */
+fe_mul(t1,t2,t1);
+
+/* qhasm: z_20_10 = z_10_0^2^10 */
+/* asm 1: fe_sq(>z_20_10=fe#3,<z_10_0=fe#2); for (i = 1;i < 10;++i) fe_sq(>z_20_10=fe#3,>z_20_10=fe#3); */
+/* asm 2: fe_sq(>z_20_10=t2,<z_10_0=t1); for (i = 1;i < 10;++i) fe_sq(>z_20_10=t2,>z_20_10=t2); */
+fe_sq(t2,t1); for (i = 1;i < 10;++i) fe_sq(t2,t2);
+
+/* qhasm: z_20_0 = z_20_10*z_10_0 */
+/* asm 1: fe_mul(>z_20_0=fe#3,<z_20_10=fe#3,<z_10_0=fe#2); */
+/* asm 2: fe_mul(>z_20_0=t2,<z_20_10=t2,<z_10_0=t1); */
+fe_mul(t2,t2,t1);
+
+/* qhasm: z_40_20 = z_20_0^2^20 */
+/* asm 1: fe_sq(>z_40_20=fe#4,<z_20_0=fe#3); for (i = 1;i < 20;++i) fe_sq(>z_40_20=fe#4,>z_40_20=fe#4); */
+/* asm 2: fe_sq(>z_40_20=t3,<z_20_0=t2); for (i = 1;i < 20;++i) fe_sq(>z_40_20=t3,>z_40_20=t3); */
+fe_sq(t3,t2); for (i = 1;i < 20;++i) fe_sq(t3,t3);
+
+/* qhasm: z_40_0 = z_40_20*z_20_0 */
+/* asm 1: fe_mul(>z_40_0=fe#3,<z_40_20=fe#4,<z_20_0=fe#3); */
+/* asm 2: fe_mul(>z_40_0=t2,<z_40_20=t3,<z_20_0=t2); */
+fe_mul(t2,t3,t2);
+
+/* qhasm: z_50_10 = z_40_0^2^10 */
+/* asm 1: fe_sq(>z_50_10=fe#3,<z_40_0=fe#3); for (i = 1;i < 10;++i) fe_sq(>z_50_10=fe#3,>z_50_10=fe#3); */
+/* asm 2: fe_sq(>z_50_10=t2,<z_40_0=t2); for (i = 1;i < 10;++i) fe_sq(>z_50_10=t2,>z_50_10=t2); */
+fe_sq(t2,t2); for (i = 1;i < 10;++i) fe_sq(t2,t2);
+
+/* qhasm: z_50_0 = z_50_10*z_10_0 */
+/* asm 1: fe_mul(>z_50_0=fe#2,<z_50_10=fe#3,<z_10_0=fe#2); */
+/* asm 2: fe_mul(>z_50_0=t1,<z_50_10=t2,<z_10_0=t1); */
+fe_mul(t1,t2,t1);
+
+/* qhasm: z_100_50 = z_50_0^2^50 */
+/* asm 1: fe_sq(>z_100_50=fe#3,<z_50_0=fe#2); for (i = 1;i < 50;++i) fe_sq(>z_100_50=fe#3,>z_100_50=fe#3); */
+/* asm 2: fe_sq(>z_100_50=t2,<z_50_0=t1); for (i = 1;i < 50;++i) fe_sq(>z_100_50=t2,>z_100_50=t2); */
+fe_sq(t2,t1); for (i = 1;i < 50;++i) fe_sq(t2,t2);
+
+/* qhasm: z_100_0 = z_100_50*z_50_0 */
+/* asm 1: fe_mul(>z_100_0=fe#3,<z_100_50=fe#3,<z_50_0=fe#2); */
+/* asm 2: fe_mul(>z_100_0=t2,<z_100_50=t2,<z_50_0=t1); */
+fe_mul(t2,t2,t1);
+
+/* qhasm: z_200_100 = z_100_0^2^100 */
+/* asm 1: fe_sq(>z_200_100=fe#4,<z_100_0=fe#3); for (i = 1;i < 100;++i) fe_sq(>z_200_100=fe#4,>z_200_100=fe#4); */
+/* asm 2: fe_sq(>z_200_100=t3,<z_100_0=t2); for (i = 1;i < 100;++i) fe_sq(>z_200_100=t3,>z_200_100=t3); */
+fe_sq(t3,t2); for (i = 1;i < 100;++i) fe_sq(t3,t3);
+
+/* qhasm: z_200_0 = z_200_100*z_100_0 */
+/* asm 1: fe_mul(>z_200_0=fe#3,<z_200_100=fe#4,<z_100_0=fe#3); */
+/* asm 2: fe_mul(>z_200_0=t2,<z_200_100=t3,<z_100_0=t2); */
+fe_mul(t2,t3,t2);
+
+/* qhasm: z_250_50 = z_200_0^2^50 */
+/* asm 1: fe_sq(>z_250_50=fe#3,<z_200_0=fe#3); for (i = 1;i < 50;++i) fe_sq(>z_250_50=fe#3,>z_250_50=fe#3); */
+/* asm 2: fe_sq(>z_250_50=t2,<z_200_0=t2); for (i = 1;i < 50;++i) fe_sq(>z_250_50=t2,>z_250_50=t2); */
+fe_sq(t2,t2); for (i = 1;i < 50;++i) fe_sq(t2,t2);
+
+/* qhasm: z_250_0 = z_250_50*z_50_0 */
+/* asm 1: fe_mul(>z_250_0=fe#2,<z_250_50=fe#3,<z_50_0=fe#2); */
+/* asm 2: fe_mul(>z_250_0=t1,<z_250_50=t2,<z_50_0=t1); */
+fe_mul(t1,t2,t1);
+
+/* qhasm: z_255_5 = z_250_0^2^5 */
+/* asm 1: fe_sq(>z_255_5=fe#2,<z_250_0=fe#2); for (i = 1;i < 5;++i) fe_sq(>z_255_5=fe#2,>z_255_5=fe#2); */
+/* asm 2: fe_sq(>z_255_5=t1,<z_250_0=t1); for (i = 1;i < 5;++i) fe_sq(>z_255_5=t1,>z_255_5=t1); */
+fe_sq(t1,t1); for (i = 1;i < 5;++i) fe_sq(t1,t1);
+
+/* qhasm: z_255_21 = z_255_5*z11 */
+/* asm 1: fe_mul(>z_255_21=fe#12,<z_255_5=fe#2,<z11=fe#1); */
+/* asm 2: fe_mul(>z_255_21=out,<z_255_5=t1,<z11=t0); */
+fe_mul(out,t1,t0);
+
+/* qhasm: return */