Given an instruction sequence with instructions in classes A, B, and C as the table below (same as the last two questions): Instruction Class A BC |CPI Instruction Count|10|40|10 2 1 3 Suppose we are considering improving the execution with the following restrictions: We can only select one class of instructions to improve; and • We will be able to reduce the execution time for the selected instruction class by 50%; No changes to other instructions. Which instruction class should we select to achieve the most improvement? class A class B class C Either one: the improvement will always be the same.

Given an instruction sequence with instructions in classes A, B, and C as the table below (same as the last two questions): Instruction Class A BC |CPI Instruction Count|10|40|10 2 1 3 Suppose we are considering improving the execution with the following restrictions: We can only select one class of instructions to improve; and • We will be able to reduce the execution time for the selected instruction class by 50%; No changes to other instructions. Which instruction class should we select to achieve the most improvement? class A class B class C Either one: the improvement will always be the same.

C++ for Engineers and Scientists

4th Edition

ISBN:9781133187844

Author:Bronson, Gary J.

Publisher:Bronson, Gary J.

Chapter2: Problem Solving Using C++using

Section2.3: Data Types

Problem 9E: (Practice) Although the total number of bytes varies from computer to computer, memory sizes of...

See similar textbooks

Similar questions

Q1: Consider two computers, P1 and P2, of the same instruction set (ISA). We have a program of 7.5x10° instructions and we want to run this program on P1 and P2. The P1 computer is a 5 GHz machine with CPI of 0.8. The P2 computer is a 6 GHz machine with CPI of 1.2. Which computer is faster?
Computer A has an overall CPI of 1.3 and can be run at a clock rate of 600MHz. Computer B has a CPI of 2.5 and can be run at a clock rate of 750 MHz. We have a particular program we wish to run. When compiled for computer A, this program has exactly 100,000 instructions. How many instructions would the program need to have when compiled for Computer B, in order for the two computers to have exactly the same execution time for this program? Please explain how to solve
In this problem we want to modify the single cycle datapath shown below (also in in slide #1 of "chapter3_single_cycle_datapaths.pptx") so that it supports execution of a new instruction called jump register (jr). PC Add Read address Instruction [31:0) Instruction [25:21) Instruction [20:16] Instruction Instruction [15:11] memory (DMUXT RegDst Instruction [15:0] RegWrite Read register 1 Read register 2 Read data 1 Write Read register data 2 Write data Registers 16 Sign- extend Instruction [5:0] 32 Shift left 2/ ALUSrc (OMUXI) ALU Addresult Zero ALU ALU result ALU control ALUOP #copy contents of "rs" register to PC (PC = $rs) PCSrc ( E3X MemWrite Read data Address Data Write memory data MemRead MemtoReg (-MUXO) jr $rs You are allowed to add new control signal(s), wire(s), muxe(s) to support this instruction. First briefly explain the required modifications. Then indicate the value of each control signal (RegDst, RegWrite, ALUSrc, ALUOP, MemRead, Mem Write, MemToReg). You must use "X"…
a) By how much is the total execution time changed if the time for class D is reduced by 20% and the time for class C is increased by 10% (assuming no other changes)? b) If we want to reduce the total execution time by 20% by optimizing class A only, what is the arget execution time of class A instructions in order to achieve the reduction (assuming all other nstructions are not changed)? c) Can the total time be reduced by 25% if we only optimize class B? Use calculation to justify vour answer.
The CPU clock is 1 GHz. One OP requires 5 clock cycles (for example arithmetic instruction and conditional). Each memory access (read or write) requires 100 clock cycles and the problem size is 1 million or n = 1,000,000. There is no memory access cost of loop index variable: don't count any arithmetic instructions for initializing or incrementing the loop index value. Assume the loop index variable is free of charge. There is an arithmetic operation involved in updating the accumulator variable. Algorithm Sum = 0 For i in range (0, n); Sum += i; Print (“sum =, sum) How many memory accesses and clocks are required by this algorithm?
The CPU clock is 1 GHz. One OP requires 5 clock cycles (for example arithmetic instruction and conditional). Each memory access (read or write) requires 100 clock cycles and the problem size is 1 million or n = 1,000,000.There is no memory access cost of loop index variable: don't count any arithmetic instructions for initializing or incrementing the loop index value. Assume the loop index variable is free of charge. There is an arithmetic operation involved in updating the accumulator variable. AlgorithmSum = 0A = list (range(0,N)) //vectorFor i in range (0, n);Sum += A[i];Print (“sum =, sum) In this algorithm how many memory accesses and clocks are required?
Given an instruction sequence with instructions in classes A, B, and C as the table below: Instruction Class A B C |CPI Instruction Count|10|40|10| 2 1 3 Total number of instructions in this sequence = Number of clock cycles from instruction class A = Number of clock cycles from instruction class B = Number of clock cycles from instruction class C = Total number of clock cycles = Average CPI for this instruction sequence = (Answer with a float the decimal point, e.g. 4.5)
3. Job Scheduling: Consider the problem of scheduling n jobs of known durations t1, t2, ..., tn, for execution by a single processor. The jobs can be executed in any order, one job at a time. You want to find a schedule that minimizes the total time spent by all the jobs in the system. (The time spent by one job in the system is the sum of the time spent by this job in waiting plus the time spent on its execution.) Design a greedy algorithm for this problem. Does the greedy algorithm always yield an optimal solution?
Computer A has an overall CPI of 1.3 and can be run at a clock rate of 600MHz.Computer B has a CPI of 2.5 and can be run at a clock rate of 750 Mhz. Wehave a particular program we wish to run. When compiled for computer A, thisprogram has exactly 100,000 instructions. How many instructions would theprogram need to have when compiled for Computer B, in order for the twocomputers to have exactly the same execution time for this program?
4. The Single Instruction Computer (SIC) has only one instruction that can do all operations our RISC-V does (you did a homework problem). The instruction has the following format sbn a, b, c # Mem[a]=Mem[a]- Mem[b]; if (Mem[a]- Mem[b]<0) go to PC+c For example, here is the program to copy a number from location a to location b: sbn temp, temp, 1 sbn temp, a, 1 sbn b,b, 1 sbn b, temp 1 Start: Design a single cycle datapath and control for this instruction set architecture.
Suppose the implementation of an instruction set architecture uses three classes of instructions, which are called A, B, and C. The total dynamic instruction count is 1 x 10^7 and the processor's clock rate is 2.5 GHz. Details for the three classes are given in the table below: Class CPI % of instructions A 1 20% В 50% C 3 30% Complete the following table. Express all answers in scientific notation and round to two decimal places, when needed. Class Instruction Count Number of Clock Cycles x 10^ x 10^ A х 10^ х 10^ x 10^ x 10^
A CPU has a frequency of 2GHz and can execute code with three types of instructions: Type 1 instructions require 1 cycle to finish. Type 2 instructions require 4 cycles to finish. Type 3 instructions require 10 cycles to finish. For each combination of instruction types below, estimate the total number of instructions executed in 1 second. Select the closest choice (round to the nearest). Note, the percentages indicate the number of instructions of each type in the executed code.