Because every computation includes a sequential portion, there is a limit to how much you can speed up a task by adding processors. 3. Suppose a task includes one minute of sequential steps and a parallelizable portion that would take an hour if done sequentially. Fill in this table: Number of Processors 1 C. 2 3 4 10 20 30 60 120 240 480 Total Time Required 61 minutes (1 hr + 1 min) 31 minutes (30 min + 1 min) Solution Type sequential solution parallel solutions 4. Consider the law of diminishing returns: a. If you have one processor and you add one more, how much time do you save? b. If you have 240 processors and you add 240 more, how much time do you save? Talk with Your Partner How many processors do you think are worth having for this problem?

Because every computation includes a sequential portion, there is a limit to how much you can speed up a task by adding processors. 3. Suppose a task includes one minute of sequential steps and a parallelizable portion that would take an hour if done sequentially. Fill in this table: Number of Processors 1 C. 2 3 4 10 20 30 60 120 240 480 Total Time Required 61 minutes (1 hr + 1 min) 31 minutes (30 min + 1 min) Solution Type sequential solution parallel solutions 4. Consider the law of diminishing returns: a. If you have one processor and you add one more, how much time do you save? b. If you have 240 processors and you add 240 more, how much time do you save? Talk with Your Partner How many processors do you think are worth having for this problem?

Name: Because every computation includes a sequential portion, there is a l
Uploaded: 2024-03-20T06:51:23.000Z
Channel: Bartleby
Description: Because every computation includes a sequential portion, there is a limit to how much you can speed up a task by adding processors.3. Suppose a task includes one minute of sequential steps and a parallelizable portion that would take an hour if done

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

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?
Assume that the operation times of one add instruction for the major functional units are 325 ps for memory access, 185 ps for ALU operations and 125 ps for register file read/writes. Please fill the table first and perform the following a )What is the total cycle in single-cycle implementation? b )What is the total cycle in pipelining implementation? c) What is the total cycle in pipelining implementation if there are 5 million add instructions? d) What is the total cycle in pipelining implementation for 5 million add instructions, if the stages are balanced? e)What is the speed up of pipelining implementation over single-cycle implementation?
A program is profiled on a CPU: 20% of all instructions are arithmetic, 40% are load, 20% are store, 20% are conditional branches. On this CPU, loads take 4 cycles, stores 1 cycle, ALU instructions 2 cycle, and branches 3 cycles. Compute the CPI for each instruction and the average CPI for that program on that CPU: Compute the CPI for each instruction (GIVE ANSWERS WITH 2 DECIMAL DIGITS: CPI for loads is CPI for stores is CPI for ALU is CPI for branches is Average CPI is
Problem 4 There are two approaches for scheduling tasks on multiprocessor platform: the partitioned approach and the global approach. The table below shows Ci (WCET) and Ti (period) for six periodic tasks to be scheduled on m = 3 processors. The relative deadline of each periodic task is equal to its period. T T1 10 T2 10 25 T3 12 30 T4 10 T5 8. 20 T6 7 100 The task set is schedulable using rate-monotonic partitioned scheduling algorithm. Show how the task set is partitioned on m = 3 processors so that all the deadlines are met?
A program sees a 4% miss rate on both the Instruction Cache and the Data Cache. Every instruction requires access to the Instruction cache. Only 35% of the instructions require data access from the Data Cache. The miss penalty for either the data or the instruction cache is 100 cycles. Assume the average Clocks per Instruction (CPI) is 2 without any memory stalls (this is a hypothetical machine where if there were no misses on that instruction, it would get executed in 2 clock cycles. We are not worrying about how it is implemented, just, that suppose it was possible). Assume the number of instructions in a program is X. F1: What is the number of 'instruction miss cycles'? (The number of clock cycles lost due to a miss on the Instruction Cache) F2: What is the number of 'data miss cycles'? F3: What is the total run time of the program including the missed cycles dues to data and instruction misses?
Algorithm A, Algorithm B, and Algorithm C perform the same task. On input of size n, Algorithm A executes 10500n instructions, Algorithm B performs 30n2 instructions, and Algorithm C executes the ceiling of (1/1024) * 2n instructions. Assume each instruction requires the same amount of time in each algorithm. Algorithm A is slower than Algorithm B when the size of the input is less than .... Algorithm A is slower than Algorithm C when the size of the input is less than .... Algorithm C is fastest of the three when the size of the input is less than ....
Write a MARIE program simulation the following Python code. The MARIE program must generate the output similar to Python's. The program must have a loop. Python code: num = [1,2,3,4,5,6]for i in num: print (i) This is what I have so far but it only prints from 1 to infinity: ORG 100START, LOAD NUM STORE COUNT OUTPUT LOAD NUM ADD ONE STORE NUM LOAD NUM SUBT COUNT SKIPCOND 400 // Salta si COUNT < NUM JUMP START HALT ONE, DEC 1NUM, DEC 1COUNT, DEC 1 END START
Consider the execution of a program that results in the execution of 8 million instructions on a 400-MHz processor. The program consists of four major types of instructions. The instruction mix and the CPI for each instruction type are given below. What is the program execution time in the second? Instruction Type Arithmetic and logic Load/store with cache hit Branch Floating-point arithmetic operation Execution Time: sec CPI 3 4 3 9 Instruction Mix (%) 60 20 12 8
Assume a 5-stage pipelined CPU (IF – ID – MU- EX – WR) requires following time for different sections: Required time 15 ns Pipeline stages Fetch Unit Decode Unit 10 ns 20 ns Memory Unit Execution Unit 8 ns 15 ns Write back Unit The maximum delay required to transfer contents from one state to another is 2ns. a) Show the time steps of pipelining stages for the first 10 instructions of a program. Assume that Instruction-4 is a conditional loop instruction. If the condition is TRUE, CPU runs instructions: 7 - 9 twice. Please note that a single-port RAM is used with the system, such that CPU read only one data from RAM or save only one data to RAM at a time. Calculate the execution time for the first 10 instructions of a program as well. b) Show the time steps and calculate the execution time for above problem while a multiport RAM is used with the system.
Assume we have a cluster consisting of 4 identical computer nodes. Now, let’s say the program has been parallelized or partitioned for parallel execution on such a cluster. 25% of the program code must be executed sequentially, while the remaining 75% can be run parallel on the available nodes. Using Amdahl’s law, calculate the speed up if the cluster is upgraded to have 16 nodes compared to 4 nodes.
Suppose that we are developing a new version of the AMD Barcelona proces- sor with a 4 GHz clock rate. We have added some additional instructions to the instruction set in such a way that the number of instructions has been reduced by 15% from the values shown for each benchmark in Exercise 1.12. The execution times obtained are shown in the following table. a. Name Execution Time (seconds) Reference Time (seconds) bzip2 700 9650 SPECratio 13.7 1.13.2 [10] In general, these CPI values are larger than those obtained in previous exercises for the same benchmarks. This is due mainly to the clock rate used in both cases, 3 GHz and 4 GHz. Determine whether the increase in the CPI is similar to that of the clock rate. If they are dissimilar, why?
As a sort-of prediction for your midterm assignment, how many CPU cores do you think is ideal? Hint: think about Amdahl's Law, which describes the theoretical maximum speedup for a parallel program.