$($i$1)$ foo: fld f$0,0($x$1)$ ; load X$($i$)$ to Reg$($f$0)$

$($i$2)$ fmul.d f$4,$ f$0,$ f$2$ ; Reg$($f$4)=$ a$*$X$($i$)$

$($i$3)$ fld f$6,0($x$2)$ ; load Y$($i$)$ to Reg$($f$6)$

$($i$4)$ fadd.d f$6,$ f$4,$ f$6$ ; Reg$($f$6)=$ a$*$X$($i$)+$ Y$($i$)$

$($i$5)$ fsd f$6,0($x$2)$ ; store Reg$($f$6)$ to Y$($i$)$

$($i$6)$ addi x$1,$ x$1,8$ ; increase X index

$($i$7)$ addi x$2,$ x$2,8$ ; increase Y index

$($i$8)$ sltu x$4,$ x$1,$ x$3$ ; test: continue loop?

$($i$9)$ bnez x$4,$ foo ; loop if needed

Show how the loop would look both unscheduled by the compiler and after compiler scheduling, including any stalls or idle clock cycles. What is the execution time $($in cycles$)$ per element of the result vector Y$,$ unscheduled and scheduled?