a$)$ What would be the baseline performance $($in cycles, per loop iteration$)$ of the code sequence in the table below, if no new instruction's execution could be initiated until the previous instruction's execution had completed? Ignore front$-$end fetch and decode. Assume for now that execution does not stall for lack of the next instruction, but only one instruction$/$cycle can be issued. Assume the branch is taken, and that there is a one cycle branch delay

$.$slot

Latencies beyond single cycle

$\backslash$table$[[$LD$,4],[$SD$,2],[$Integer$,0],[$Branch$,1],[$Add$.$D$,1],[$Mult$.$D$,5],[$Div$.$D$,10]]$

$\backslash$table$[[$Loop: $,$ LD$,$F$2,0($Rx$)],[$DIVD$,$F$8,$F$2,$F$0],[$MULTD$,$F$2,$F$6,$F$8],[$LD$,$F$4,0($Ry$)],[$ADDD$,$F$10,$F$8,$F$2],[$ADDD$,$F$4,$F$0,$F$4],[$ADDI$,$Rx$,$Rx$,$#$8],[$ADDI$,$Ry$,$Ry$,$H$8],[$SD$,$F$4,0($Ry$)],[$SUB$,$R$20,$R$4,$Rx$],[$BNZ$,$R$20,$Loop$]]$

b$)(10$ points$)$ Consider a multiple$-$issue design. Suppose you have Three execution pipelines, each capable of beginning execution of one instruction per cycle, and enough fetch$/$decode bandwidth in the front end so that it will not stall your execution. Assume results can be immediately forwarded from one execution unit to another, or to itself. Further assume that the only reason an execution pipeline would stall is to observe a true data dependency. Now how many cycles does the loop require? Do $.$schedule them showing the stalls

Execution Pipe $0$ Execution Pipe $1$ Execution Pipe $2$