Consider the following loop, which calculates Y,- aX, + bY,. Assume the pipeline latencies given below Latency Instruction producing result FP ALU op FP ALU op Load double Load double Instruction using result (clock cycles) 3 2 Another FP ALU op Store double FP ALU op Store double 0 loop: L.D F0,0 (R1) load Xi] F4,0(R2 ) F4,F4,F6 ;load Y[i] ;b*Y[i] L.D MUL.D S.D 0 (R2),FO ;store Y[i] DSUBUl R1, R1, #8 ;decrement X index DSUBUl R2, R2, #8 ;decrement Y index BNE R1, R3, loop ;stopping address in R3 Assume a single-issue pipeline. (Both the integer and .D floating point instructions are in the same pipeline.) Unroll the loop as many times as necessary to schedule it without any delays. What is the execution time per element? Consider the following loop, which calculates Y,- aX, + bY,. Assume the pipeline latencies given below Latency Instruction producing result FP ALU op FP ALU op Load double Load double Instruction using result (clock cycles) 3 2 Another FP ALU op Store double FP ALU op Store double 0 loop: L.D F0,0 (R1) load Xi] F4,0(R2 ) F4,F4,F6 ;load Y[i] ;b*Y[i] L.D MUL.D S.D 0 (R2),FO ;store Y[i] DSUBUl R1, R1, #8 ;decrement X index DSUBUl R2, R2, #8 ;decrement Y index BNE R1, R3, loop ;stopping address in R3 Assume a single-issue pipeline. (Both the integer and .D floating point instructions are in the same pipeline.) Unroll the loop as many times as necessary to schedule it without any delays. What is the execution time per element