Assume that you have a program that has a part at the beginning that is sequential in nature (for example, reading a file, that must be executed by only one processor) and takes 20 ms. Also there is a part at the end of the program that is sequential and takes 10 ms. Between these two parts, there is a perfectly parallelizable part and it take 480 ms in sequential. a) What is maximum speed-up according to Amdahl's law? b) What is the speed-up for 4 processors? c) What is the efficiency for 4 processors?

Assume that you have a program that has a part at the beginning that is sequential in nature (for example, reading a file, that must be executed by only one processor) and takes 20 ms. Also there is a part at the end of the program that is sequential and takes 10 ms. Between these two parts, there is a perfectly parallelizable part and it take 480 ms in sequential. a) What is maximum speed-up according to Amdahl's law? b) What is the speed-up for 4 processors? c) What is the efficiency for 4 processors?

Name: Assume that you have a program that has a part at the beginning that
Uploaded: 2024-03-20T06:51:23.000Z
Channel: Bartleby
Description: Assume that you have a program that has a part at the beginning that is sequential in nature(for example, reading a file, that must be executed by only one processor) and takes 20 ms.Also there is a part at the end of the program that is sequential

Database System Concepts

7th Edition

ISBN:9780078022159

Author:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Publisher:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Chapter1: Introduction

Section: Chapter Questions

Problem 1PE

See similar textbooks

Related questions

Q: The equivalent resistance Reg of four resistors R₁, R2, R3 and R4 connected in series is given as…

A: Code: ch=input('Enter the type of connection(1 for series and 2 for parallel): ');if(ch==1 || ch==2)…

Q: Suppose that the execution time of a given program on a single processor is 9.5 ms. If you run this…

A: Answer is given below-

Q: Write a parallel program using MPI (and not OpeMP) to accomplish the same as the following serial…

A: Write a parallel program using MPI (and not OpeMP) to accomplish the same as the following serial…

Q: Assume an add takes 1 cycle, a mult 4 cycles, and a sub 2 cycles. Two different compilers produce…

A: i) CPI for Program A =(4+1+4+2)/4 =11/4 =2.75 CPI for Program B =(1+1+4+2+1+1)/6 =10/6 =1.667

Q: In MATLAB, a grey-scale image is stored a a matrix of numbers, all between 0 (black) and 255…

A: In MATLAB, grayscale images are represented as matrices of numbers, where each pixel's intensity…

Q: Computer A has an overall CPI of 1.3 and can be run at a clock rate of 600MHz. Computer B has a CPI…

A: To find out how many instructions the program needs when compiled for Computer B in order for the…

Q: You are asked to write two programs in Hack assembly language. You should use the stock 16-bit Hack…

A: Hack assembly language.

Q: When translating conditionals or loops, the generated low-level code contains jumps. For the CPU to…

A: i. Symbolic addresses allow code generators to generate code that is easier to read, understand, and…

Q: a) Your colleague has invented a new scheduling algorithm using the multilevel queue approach. This…

A: Given processes are P1, P2, P3 and P4. The Burst of the processes are: P1=21ms, P2=8ms, P3=35ms and…

Q: code

A: Given:- An assembly code is given in above question Need to run the given code and mention the…

Q: Suppose you are asked to design a rotating disk where the number of bits per track is constant. You…

A: Consider the information given:

Q: a complete program in MIPS assembly language

A: Given :- In the above given question, the statement is mention in the above given question Need to…

Q: In a main memory-disk virtual storage system, the page size is 1KByte and the OPTIMAL algorithm is…

A: We need to fill in the contents of the three page frames after each memory reference in a table and…

Q: Amdahl’s Law My speedup factor is 6. My new execution time after speedup is 5 seconds. What was…

A: Execution time, often referred to as runtime or elapsed time, is the duration it takes for a…

Q: Create a program of priority scheduling algorithm on c++ with gantt chart the output should look…

A: C++ code: #include<iostream>#include<algorithm>using namespace std; // process node…

Q: Consider a program that performs the following steps repeatedly: Use the CPU for 4 milliseconds. By…

A: The program in question uses CPU, disk, and network resources to iteratively go through a series of…

Q: please help!! PLEASE INCLUDE THE graphs of the corresponding experiments AND THE analysis +…

A: SubmissionEnsure you include the following in your submission:C Programs: copy_byte_by_byte.c and…

Q: OS ASSEMBLY CODE Using YASM assembly code(x86) .Create a program that accepts two user…

A: Introduction: Create a program that accepts two user inputs. For any input from the two users,…

Q: Write a Marie program named: Program1.max that will Input a variable named: Max. (Note the file…

Topic Video

Question

Assume that you have a program that has a part at the beginning that is sequential in nature
(for example, reading a file, that must be executed by only one processor) and takes 20 ms.
Also there is a part at the end of the program that is sequential and takes 10 ms.
Between these two parts, there is a perfectly parallelizable part and it take 480 ms in
sequential.
a) What is maximum speed-up according to Amdahl's law?
b) What is the speed-up for 4 processors?
c) What is the efficiency for 4 processors?
Sorunun tüm bölümlerine cevap verin

Expert Solution

This question has been solved!

Explore an expertly crafted, step-by-step solution for a thorough understanding of key concepts.

SEE SOLUTION Check out a sample Q&A here

Step 1

VIEW

Step 2

VIEW

Step by step

Solved in 2 steps with 1 images

SEE SOLUTION Check out a sample Q&A here

Knowledge Booster

Learn more about

Need a deep-dive on the concept behind this application? Look no further. Learn more about this topic, computer-science and related others by exploring similar questions and additional content below.

Similar questions

Answer the given question with a proper explanation and step-by-step solution. Write an MIPS program that computes terms of the Fibonacci series, defined as: 1, 1, 2, 3, 5, 8, 13, 21, 34, 55 ... (This is sometimes started with a 0th term: 0, 1, 1, 2, etc.)The first two terms in the series are fixed, and each subsequent term in the series is the sum of the preceding two terms. So, for example, the term 13 is the sum of the terms 5 and 8.Write the program as a counting loop that terminates when the 100th term of the series has been computed. Use a register for the current term and a register for the previous term. Each execution of the loop computes a new current term and then copies the old current term to the previous term register. Count the number of passes to stop after the 100th term. Do not worry about overflow: this will FAR exceed the capacity of a register to hold the value. Stop the program with a syscall with 10 in $v0.
For a 100-cylinder disk, compute the total number of head movements for the request queue provided below, using FCFS scheduling and a 100-cylinder disk (0-99). It is expected that the read write head is present at cylinder number 50 at the start of the program. Request queue for disk cylinders has the following numbers: 75, 25, 30, 68, 40, 89, 10.
given a file(use any text file) write MIPS instruction to count all words in that file. note: A single letter is counted as a word for example assume this sentence written in txet file : "bartleby is a website" the output should be: word count = 4
Fortran Linking Multiple Files Together: I have a main fortran file. This file calls on ProgramA, ProgramB and ProgamC. The function to compute the area is pi x radius^2 x A for programA, pi x radius^2 x B for progam B and the same for programC. I'm not sure what to put down for ProgramA.f90, ProgramB.f90 and ProgramC.f90 it has inputs for radius and A, B or C respectively. I also need a printout once the functions/programs ProgramA, ProgramB and ProgramC are callled. This is my main.f90: program practicedynamo implicit none real:: A,B,C, radius A = 10 B =5 C = 2 radius = 3 !read*,radius call programA(radius,A) call programB(radius,B) call programC(radius,C) end program practicedynamo
Programming Project: For Loops Write an Assembly Language Program that produces the Times Table for a specific integer value between 1 to 12. NOTE: You choose and hard code only one value (i.e. 7) and produce the times table for that value. Also note that since you are using registers and memory locations make sure that at each step you screen shot each result for each part of the Times Table. For example 7 x 12 = 84 but in Hexadecimal the value is 54. Sample code in C #include void main() ( int i, j; printf("Enter an integer: "); scanf("%d", &i); printf("Times %d Table\n", i). for(j = 0; j<= 12; j =j+1) { printf("%d x %d = %d\n", j, 1. j'i); } printf("\n");
Given the following: Logical Memory size of 1000 Physical Memory size of 2000 Page (and frame) size of 100 Block A contains data for a program Select Block A’s size and its starting point in both memories. Then write the page table for Block A based on your selections. See below for the layout of both memories and an example of Block A of size 200. Logical Memory Physical Memory location/ page location/frame 0 to 99/ 0 0 to 99/ 0 100 to 199 /1 Block A 100 to 199/ 1 200 to 299/ 2 Block A 200 to 299/ 2 300 to 399/ 3 300 to 399/ 3 400 to 499/ 4 400 to 499/ 4 500 to 599/ 5 500 to 599/ 5 600 to 699/ 6 600 to 699/ 6 700 to 799/ 7 700 to 799/ 7 800 to 899/ 8 800 to 899/ 8 900 to 999/ 9 900 to 999/ 9 1000 to 1099/ 10 1100 to 1199/ 11 1200 to 1299/ 12 1300 to 1399/ 13 Block A 1400 to 1499/ 14 Block…
TRY to do it under 40 minutes
Consider the following problem:You are given a tower of n disks and three pegs. Disks are initially stacked in decreasing size (from the largest in the bottom to the smallest at the top) on one of the pegs. The objective is to transfer the entire tower to one of the other pegs (the third, let’s say), moving only one disk at a time and never a larger one onto a smaller one. (1) Write a code/pseudocode that uses the divide and conquer technique to solve the problem. (2) Write a recurrence relation for the time complexity of the problem and explain how you came up with the relation. (3) then express the time taken by your algorithm in Big-O notation.
The following four requests could come in to an operating system as it is running on a computer system: The clock in the computer has just “ticked,” and we need to update a seconds counter. The program running on processor 2 is trying to perform an illegal operation code. Someone pulled the plug on the power supply, and the system will run out of power in 50 msec. The disk has just read the character that passed under the read/write head, and it wants to store it in memory before the next one arrives. In what order should the operating system handle these requests?
Although most of your programming courses have focused on writing sequential programs, using lots of parallelism is the way to faster execution. We talked about two different basic execution models that can support massively-parallel execution: MIMD and SIMD. One of the easiest ways to get some speedup by parallel processing is to simultaneously execute multiple copies of the same sequential program with different input data. For example, if you need to convert thousands of images from color to black & white, simultaneously running 32 copies of a sequential program that converts a single image at a time could easily get you nearly 32X speedup over running one copy of the program at a time to process each image. Is that type of parallel execution essentially MIMD, SIMD, or equally suited to both MIMD and SIMD? Why?
2. a) Your colleague has invented a new scheduling algorithm using the multilevel queue approach. This list of processes showing CPU burst times is below. There are three queues used in the application. The processes all start on the first queue and receive upto 10ms of burst time. Once the process has received the 10ms on the first queue, if the process still requires burst time it is passed to the second queue where it receives upto 20ms. Once the process has received the 20ms on the second queue, if the process still requires burst time it is passed to the third queue where it receives CPU time until it is completed. The operating system will only start allocating CPU time to processes on the second queue when queue 1 is empty. The operating system will only start allocating CPU time to processes on the third queue when queue 2 is empty. Process Number P1 P2 P3 P4 Burst time (ms) 21 8 35 50 i) Does this algorithm give higher priority to any queue over the others and any processes…
Case Study Assume a computer system has a main memory of 256 Bytes. The following is a memory byte-access trace history of a program run on this system. For example, as it is shown, the program first accesses memory address 0000 0000, and then it accesses memory address 0000 0001 and so on. Note the memory addresses are represented in binary: 00000000, 00000001, 00000010, 00000011, 00001000, 00010000, 00010001, 00000100, 00000101, 00000110, 00000111, 00001001, 00001010, 00001011, 00001100, 00001000, 00001001, 00001010, 00011100, 00011101. Q3. Assume the system has a 16-Byte direct mapped unified L1 cache with a block size of 2 Bytes. The following table shows how the cache looks like after the first access to the memory is finished. Please show; in the provided table, how it looks like after the 20th access is finished. You could ignore the "Data" Column. (Add or remove Rows/Columns in the provided table for your answer, as you see fit). Cache contents after the 1st access: Cache Index…