Optimizing x64 assembler MUL loop
void muladd(unsigned* r, const unsigned* a, unsigned len, unsigned b) {
   unsigned __int64 of = 0;  // overflow
   unsigned i = 0;  // loop variable
   while (i < len) {
      of += (unsigned __int64)a[i] * b + r[i];
      r[i] = (unsigned)of;
      of >>= 32;
      ++i;
   }
   r[i] = (unsigned)of;  // save overflow
}

mov   rax, rdi                             ; rdi = b
mul   QWORD PTR [rbx+r10*8-64]             ; rdx:rax = a[i] * b; r10 = i
mov   rsi, QWORD PTR [r14+r10*8-64]        ; r14 = r; rsi = r[i]
add   rax, rsi
adc   rdx, 0
add   rax, r11                             ; r11 = of (low part)
adc   rdx, 0
mov   QWORD PTR [r14+r10*8-64], rax        ; save result
mov   r11, rdx

; this repeats itself 8 times with different offsets