Answered step by step
Verified Expert Solution
Link Copied!

Question

1 Approved Answer

UU . CIS The goal of this project is to complete a runtime study of execution times of matrix multiplication on various sized data sets

image text in transcribed
UU . CIS The goal of this project is to complete a runtime study of execution times of matrix multiplication on various sized data sets (NX N) matrices. The study will be completed on the DMC supercomputer. As discussed in class, matrix multiplication typically has a computational complexity of O(N). This implies that the time required for solution is proportional to the cubic of the number of variables (rows or columns), N. The constant(s) of proportionality will depend on the computer utilized. Successful completion of the project will require the following tasks: Copying the multiply program source code "Source Code" folder to your supercomputer account. (e.g. cp-R SHOME/class shared/Source Code.) Use of the matrix multiplier software found in the "Source Code" directory. Creating an executable file for the DMC system using "make". Run the executable using the input files from "Multiply_Data" subdirectory. Evidence of Login [10 points Evidence of compiling and running the executable from your user account on the DMC machine, for each (N X N) matrix in the data directory. [15 points Complete the Table Below 15 points) Create a plot of T vs. N using Excel 15 points Predict the value of T for N-20,000 and N-50,000 based on your results. 15 points Brief write-up (-2 pages) describing your work, 15 points results and conclusions. 15 points N, number of variables Elapsed CPU Time Elapsed Wall Clock Time 500 (n500.dat) 1000 (n 1000 dar) 2000 (n.2000. dar) 5000 (65000 dar) 10000 (n 10000.dat) 20.000 (estimated) 50.000 (estimated) UU . CIS The goal of this project is to complete a runtime study of execution times of matrix multiplication on various sized data sets (NX N) matrices. The study will be completed on the DMC supercomputer. As discussed in class, matrix multiplication typically has a computational complexity of O(N). This implies that the time required for solution is proportional to the cubic of the number of variables (rows or columns), N. The constant(s) of proportionality will depend on the computer utilized. Successful completion of the project will require the following tasks: Copying the multiply program source code "Source Code" folder to your supercomputer account. (e.g. cp-R SHOME/class shared/Source Code.) Use of the matrix multiplier software found in the "Source Code" directory. Creating an executable file for the DMC system using "make". Run the executable using the input files from "Multiply_Data" subdirectory. Evidence of Login [10 points Evidence of compiling and running the executable from your user account on the DMC machine, for each (N X N) matrix in the data directory. [15 points Complete the Table Below 15 points) Create a plot of T vs. N using Excel 15 points Predict the value of T for N-20,000 and N-50,000 based on your results. 15 points Brief write-up (-2 pages) describing your work, 15 points results and conclusions. 15 points N, number of variables Elapsed CPU Time Elapsed Wall Clock Time 500 (n500.dat) 1000 (n 1000 dar) 2000 (n.2000. dar) 5000 (65000 dar) 10000 (n 10000.dat) 20.000 (estimated) 50.000 (estimated)

Step by Step Solution

There are 3 Steps involved in it

Step: 1

blur-text-image

Get Instant Access to Expert-Tailored Solutions

See step-by-step solutions with expert insights and AI powered tools for academic success

Step: 2

blur-text-image

Step: 3

blur-text-image

Ace Your Homework with AI

Get the answers you need in no time with our AI-driven, step-by-step assistance

Get Started

Students also viewed these Databases questions

Question

L . R . = ( a + b + c ) * a ( b c ) * obtener un automata

Answered: 1 week ago