p256ord<>+0x00(SB), (const0, const1) LDP p256ord<>+0x10(SB), (const2, const3) LDP 0*16(a_ptr), (x0, x1) LDP 1*16(a_ptr), (x2, x3) LDP 0*16(b_ptr), (y0, y1) LDP 1*16(b_ptr), (y2, y3) // y[0] * x MUL y0, x0, acc0 UMULH y0, x0, acc1 MUL y0, x1, t0 ADDS t0, acc1 UMULH y0, x1, acc2 MUL y0, x2, t0 ADCS t0, acc2 UMULH y0, x2, acc3 MUL y0, x3, t0 ADCS t0, acc3 UMULH y0, x3, acc4 ADC $0, acc4 // First reduction step MUL acc0, hlp1, hlp0 MUL const0, hlp1, t0 ADDS t0, acc0, acc0 UMULH const0, hlp0, t1 MUL const1,...