3-Assume a program requires the execution of 60*10^6 FP instructions, 120 × 10^6 INT instructions, 40 x 10^6 LIS instructions, and 30 x 10^6 branch instruc- tions. The CPI for each type of instruction is 4, 2, 3 and 5, respectively. Assume that the processor has a 4 GHz clock rate. a. By how much must we improve the CPI of FP instructions if we want the pro- gram to run three times faster? b. By how much must we improve the CPI of L/S instructions if we want the pro- gram to run three times faster? c. By how much is the execution time of the program improved if the CPI of INT and FP instructions is reduced by 40% and the CPI of L/S and Branch is re- duced by 45%?

3-Assume a program requires the execution of 60*10^6 FP instructions, 120 × 10^6 INT instructions, 40 x 10^6 LIS instructions, and 30 x 10^6 branch instruc- tions. The CPI for each type of instruction is 4, 2, 3 and 5, respectively. Assume that the processor has a 4 GHz clock rate. a. By how much must we improve the CPI of FP instructions if we want the pro- gram to run three times faster? b. By how much must we improve the CPI of L/S instructions if we want the pro- gram to run three times faster? c. By how much is the execution time of the program improved if the CPI of INT and FP instructions is reduced by 40% and the CPI of L/S and Branch is re- duced by 45%?

Computer Networking: A Top-Down Approach (7th Edition)

7th Edition

ISBN:9780133594140

Author:James Kurose, Keith Ross

Publisher:James Kurose, Keith Ross

Chapter1: Computer Networks And The Internet

Section: Chapter Questions

Problem R1RQ: What is the difference between a host and an end system? List several different types of end...

See similar textbooks

Similar questions

:- We will be implementing a new instruction within the MIPS architecture. New instruction will decrement a Variable stored in a memory location and store the decremented value in a register (Rt). This new instruction will be called DECR. Its usage and interpretation is Usage: DECR Offset(4*Rs),Rt Interpretation: Reg[Rt]= Mem[4*Rs+Offset] - 1 Which blocks are used and which control signals are generated for this instruction. How would the Instruction code fields look like ? Do we need to add an extra hardware logic, explain ? (You may draw a simplified datapath flow)
CPI stands for clock cycles per instruction. Speedup from pipelining = (Number of pipeline stages) / (Achieved CPI ). Assume a 5-stage pipeline. Assume that CPI = 1 when there are no pipeline stalls (the ideal case). Now assume that every branch instruction causes a 3 clock cycle stall in the pipeline. Assume that for the program being executed 30% of executed instructions are branch instructions. What speedup from pipelining is achieved by this program?
Suppose we have the instruction Load 500. Given memory and register R1contain the values below:
Assume that we have a simple processor which is able to execute 7 instructions: load doubleword (ld), store double world (sd), add (add), subtract (sub), AND (and), OR (or), and branch if equal (beq). Assume the operation times for the major functional units are in the table (assuming target address for beq instructions is calculated by ALU): Inst. Fetch Reg. Read ALU Operation Data Mem. Reg. Write 200ps 100ps 200ps 200ps 100ps a) If the processor is in single-cycle model, what are total times for load doubleword (ld), store doubleword (sd), R-format (add, sub, and, or), and branch if equal (beq) instructions, respectively? What is the (minimum) clock period? b) If the processor is 5-stage pipelined (with steps Inst. Fetch, Reg. Read, ALU Operation, Data Mem., and Reg. Write), what is the (minimum) clock period? What is the execution time for a load doubleword (ld) instruction? c) Suppose the following instructions run on the processor. Id x1,0(sp) Id x10,8(sp) add x7,x5,x6 What is the…