Question 2 a. Balancing performance between processor, memory, buses and peripheral devices, is almost impossible as due to constant evolving nature of certain two major factors. Identify these factors and discuss how their nature hinders the attempt to keep these devices in balance. b. During an optimal use of the computer, where there are several application running the CPU usage would usually be amount only 37%, which means that the CPU is idle most of the time and hence being inefficient. Discuss using at least two or more jobs, how Interrupts would help boost the efficiency of the machine and reduce the idle times.

Question 2 a. Balancing performance between processor, memory, buses and peripheral devices, is almost impossible as due to constant evolving nature of certain two major factors. Identify these factors and discuss how their nature hinders the attempt to keep these devices in balance. b. During an optimal use of the computer, where there are several application running the CPU usage would usually be amount only 37%, which means that the CPU is idle most of the time and hence being inefficient. Discuss using at least two or more jobs, how Interrupts would help boost the efficiency of the machine and reduce the idle times.

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 the following scenario. Please share your understanding of a multi-core processor and how it works then explain which student is correct and why. Your post should be at least two paragraphs. Scenario: One friend claims that a dual-core system runs at twice the speed as a single-core system; another friend disagrees by saying that it runs twice as many programs at the same time; a third friend says it runs twice as much data at the same time.
Assume that every 18 months, the number of cores that are available on a new generation of CPUs doubles. How much extra off-chip memory bandwidth will be required for a CPU that is introduced in three years in order to retain the same level of per-core performance?
A benchmark program to evaluate the performance of a processor spends 80% of its time on floating-point commands and 20% on non-floating point commands. A design team wants to obtain an overall speedup of 40% over the existing run time of this benchmark program by speeding up ONLY the non-floating point commands. What should be the ratio of the non-floating point commands new runtime to that of its old runtime? Select the best answer. This is a trick question! In this scenario, it is impossible to speed up only the non-floating point commands to obtain an overall 40% speedup! 2 0.5 2.5
On a uniprocessor, portion A of program P consumes 24 seconds, while portion B consumes 822 seconds. On a parallel computer, moderately serial portion A speeds up 4 times, while perfectly parallel portion B speeds up by the number of processors. 1- What is the speedup of program P on 1,024 processors? _______ times 2- How many processors are required to achieve at least half the theoretical maximum possible speedup on P?
Assume that every 18 months a new generation of CPUs with twice as many cores is produced. In three years, how much more off-chip memory bandwidth will a CPU need to retain the same per-core performance?
3. The table below shows instruction-type breakdown for different programs. Using this data, you will be exploring the performance trade-offs for different changes made to an MIPS processor. Compute Load Store Branch Total Program1 600 600 200 50 ? Program2 900 500 100 200 ? a. Assuming that computes take 1 cycle, loads and store instructions take 10 cycles, and branches take 3 cycles, find the execution time for both the programs on a 3 GHz Processor. b. Assuming that computes take 1 cycle, loads and store instructions take 2 cycles, and branches take 3 cycles, what is the speedup if the number of compute instruction can be reduced by one-half?
When a CPU interrupt is issued, the processor pauses what it is doing and processes the signal. Why should the operation be halted so that this action may be carried out? Let's take care of the interrupting process first, then complete the executing process afterwards. explain?
Question 3 Suppose you have hardware that you are trying to improve by adding additional processors. The goal is to achieve a speed-up of 89 times faster, while being restricted to having .6% of the original computation remain sequential. How many additional processors should be added? (You don’t have to give a single number as the solution; just show an equation that will evaluate to the answer ....
Question 1 (Processes) a. A multi-programmed system with a single CPU has a very large number of CPU bound processes running on it that all have the same priority. Could you think of a CPU scheduling algorithm that would combine the lowest possible response times with the highest possible throughput and no starvation? Briefly explain your answer. b. Some operating systems force a context switch when a mutex (or spinlock) has been spin- ning for too long. List two reasons why this approach may be useful. c. This question relates to threads. Assume two user threads that increment a shared counter. The code runs on a multi-core system. Is it possible to obtain a concurrent implementation that is free of race conditions without using mutexes or semaphores (yes / no)? Briefly explain your answer. d. Figure 1 illustrates the times at which 10 different processes run on a single core of a single CPU. Every "row" represents a different process. The times increase towards the right, and…
The relative performance of the IBM 360 Model 75 is 50 times that of the 360 Model 30, yet the instruction cycle time is only 5 times as fast. How do you account for this discrepancy? Provide a computational example and justify your answer. ul ul
When an interrupt occurs, the CPU suspends the current process and handles the problem. In technical terms, this is known as interrupt service. What is the cause for the current process's halt? Consider completing the task now and dealing with the interruption afterwards.
We want to build a word organized main memory of 8 GB for a 32-bit CPU architecture composed of word organized memory modules of 30-bit address and 8-bit data buses each. a) Draw the interface of the main memory by clearly indicating the widths of the buses. b) Howmanymemorymoduleswouldbenecessarytobuildthememorysystem? c) Design the main memory internal organization built out of the above memory modules (use multiplexers and/or decoders as needed) by clearly indicating the widths of the used busses d) CanweusethismemorysystemasRAMfortheCPUinProblem1?Explainyouranswer.