_dotp2: .cproc   a_0, b_0
        .reg    a_4, b_4, sum0, sum1, I
        .reg    val1, val2, prod1, prod2
        ADD     4,a_0,a_4
        ADD     4,b_0,b_4
        MVK     25,i    ; I = 100/4
        ZERO    sum0    ; multiply result = 0
        ZERO    sum1    ; multiply result = 0
        .mptr   a_0,a+0,8
        .mptr   a_4,a+4,8
        .mptr   b_0,b+0,8
        .mptr   b_4,b+4,8
 
loop:   .trip   25
        LDW     *a_0++[2],val1  ; load a[0-1] bankx
        LDW     *b_0++[2],val2  ; load b[0-1] banky
        MPY     val1,val2,prod1 ; a[0] * b[0]
        MPYH    val1,val2,prod2 ; a[1] * b[1]
        ADD     prod1,sum0,sum0 ; sum0 += a[0] * b[0]
        ADD     prod2,sum1,sum1 ; sum1 += a[1] * b[1]
        LDW     *a_4++[2],val1  ; load a[2-3] bankx+2
        LDW     *b_4++[2],val2  ; load b[2-3] banky+2
        MPY     val1,val2,prod1 ; a[2] * b[2]
        MPYH    val1,val2,prod2 ; a[3] * b[3]
        ADD     prod1,sum0,sum0 ; sum0 += a[2] * b[2]
        ADD     prod2,sum1,sum1 ; sum1 += a[3] * b[3]
    [I] ADD     -1,i,i          ; I--
    [I] B       loop            ; if (!0) goto loop
         ADD     sum0,sum1,A4    ; compute final result
        .return A4
        .endproc