How to measure a computer performance ? 2. Suppose we have a program runs in 100 seconds on a computer, and the multiplication subroutine takes 40 seconds. If we want the program to run 30% faster, how many seconds do we have to improve the multiplication subroutine ? 3. There are 2 computers. Computer A clock cycle time is 350ps, CPI is 3. Computer B clock cycle time is 400ps, CPI is 2.5. Which computer runs faster on same program ?

How to measure a computer performance ? 2. Suppose we have a program runs in 100 seconds on a computer, and the multiplication subroutine takes 40 seconds. If we want the program to run 30% faster, how many seconds do we have to improve the multiplication subroutine ? 3. There are 2 computers. Computer A clock cycle time is 350ps, CPI is 3. Computer B clock cycle time is 400ps, CPI is 2.5. Which computer runs faster on same program ?

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

Similar questions

Consider a computer running a program that requires 250 seconds, where 70 seconds is spent executing FP instructions, 55 seconds for INT operations, 85 seconds for load/save operations, and 40 seconds for branch instructions. By how much is the time for INT operations reduced if the total time is reduced by 20%?
The next job might be carried out while the CPU waits for an interrupt. Do we need to pause the sentence? Instead of worrying about the finer points, why don't we just go ahead and do the operation?
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.
2. Develop a ladder program for following system: PB 1 is used for main system ON. PB 2 is used Main OFF. Lights will be switched on and off with following sequence. Lights White light Action Switch ON for 30 second when sensor 1 is sensed Red light Green light Orange light Yellow light Switch ON for 1minute when sensor 2 is sensed Switch ON for 2 minute when sensor 3 is sensed Switch ON when no sensors are sensed Switch ON when all sensors are sensed
Suppose you are a software engineer. Your friend owns a grocery shop. He asks you to write an inventory software for him and he will pay you for this. The software works very well and later you discover that your friend has given copies to his several friends who also operate small grocery shop. Do you think your friend should have asked your permission to give away your software? Do you believe the other merchants should pay you for the copies? Why or Why not?
Abstract: the main purpose of this experiment is build real time system using PPI 8255 to control devices connected to. Problem description: assume that there are two devices are connected to port A and two sensors are connected to port B of PPI 8255. They work according to the following table Sensors (S1S2) Devices (DID2) 00 01 01 10 10 11 11 00 Write a program to control these two devices according to the values of sensors.
Machine A runs a program in 100 seconds, Machine B runs the same program in 125 seconds. Find the performance and Execution time of both systems and find which is better.
You are working on a project to build a temperature control system for an industrial machine. The machine should only operate between positive 20-150 Fahrenheit, but we need to show the operator the temp range negative 20 through positive 300. 1. What level of numeric precision can we get using only a single byte of memory? 2. Using the same project as question #1. What binary number would represent positive 20 degrees?
A video system can take videos from one of the two video sources, but can only display one source at a provided time. Each source outputs a stream of digitized videos on its 8-bit output. A switch with a single-bit output determines which of the two 8-bit streams will be passed on a display’s single 8-bit input. Implement a circuit that combines the two video sources, the switch, and the display. Use either ONE of the following: a single mux AND/OR an N-bit mux decoder
A video frame displayed onscreen consists of many pixels, with eachpixel, or cell, representing one unit of video output. A videodisplay’s resolution is typically specified in horizontal and verticalpixels (such as 1920 3 1080), and the number of pixels onscreen issimply the product of these numbers (1920 3 1080 5 2,073,600 pixels).A pixel’s data content is one or more unsigned integers. For ablack-and-white display, each pixel is a single number (usuallybetween 0 and 255) representing the intensity of the color white.Color pixel data is typically represented as one or three unsignedintegers.When three numbers are used, the numbers are usually between 0 and255, and each number represents the inten- sity of a primary color(red, green, or blue). When a single number is used, it represents apredefined color selected from a table (palette) of colors.Motion video is displayed onscreen by copying frames rapidly to thevideo display controller. Because video images or frames require manybytes…
The latest super-duper supercomputer has memory locations that are 64-bits wide. What is the largest unsigned integer that can be stored in one memory location? Suppose that we use sign-magnitude for storing negative numbers and dedicate one bit for a sign bit. What would be the largest POSITIVE integer that can be stored in a memory location.
1. Implement the following Boolean equations in a Structured Text program. If the program was for a state machine what changes would be required to make it work? light = (light + dark • switch) • switch • light dark (dark + light • switch) • switch • dark