into four 64-bit words: // // 255 204 153 102 51 0 // ├──l4──┼──l3──┼──l2──┼──l1──┼──l0──┤ // ├───u3───┼───u2───┼───u1───┼───u0───┤ // 256 192 128 64 0 u0 := t.l1<<51 | t.l0 u1 := t.l2<<(102-64) | t.l1>>(64-51) u2 := t.l3<<(153-128) | t.l2>>(128-102) u3 := t.l4<<(204-192) | t.l3>>(192-153) byteorder.LEPutUint64(out[0*8:], u0) byteorder.LEPutUint64(out[1*8:], u1) byteorder.LEPutUint64(out[2*8:], u2) byteorder.LEPutUint64(out[3*8:], u3) return out[:] } // Equal returns 1 if v and u are equal, and 0 otherwise....

const1, x3, t3 ORR t0, t1, t0 ORR x2, t3, t1 ORR t1, t0, t0 CMP $0, t0 CSEL EQ, t2, hlp1, hlp1 LDx(z2sqr) LDy(x1in) CALL p256MulInternal<>(SB) // u1 = x1 * z2藛2 STy(u1) LDx(z1sqr) LDy(x2in) CALL p256MulInternal<>(SB) // u2 = x2 * z1藛2 STy(u2) LDx(u1) CALL p256SubInternal<>(SB) // h = u2 - u1 STx(h) MOVD $1, t2 ORR x0, x1, t0 // Check if zero mod p256 ORR x2, x3, t1 ORR t1, t0, t0 CMP $0, t0 CSEL EQ, t2, ZR, hlp0 EOR $-1, x0, t0 EOR const0, x1, t1 EOR const1, x3, t3 ORR t0, t1, t0 ORR x2, t3, t1 ORR t1,...