School of computer science

Georgia Institute of Technology

Introduction This is an individual assignment. In this assignment, you will implement a matrix multiplication using CUDA.

0) Install CUDA SDK in your home directory. How to install CUDA SDK.
1) Untar lab1.tar.gz into ~/NVIDIA_CUDA_SDK/projects
Instruction:
cd ~/NVIDIA_GPU_Computing_SDK/C/src
tar -xvf lab1.tar.gz
cd lab1
make
To run the program ../../bin/linux/release/matrixmul
2) Edit the source files matrixmul.cu and matrixmul_kernel.cu to complete the functionality of the matrix multiplication on the device. You do not need to need to support other sizes. The default size is 10x10.
3) Measure the speedup of 10x10 (default size). You must see slowdown.
4) Submission:
The lab1.tar.gz file should contain the lab1 folder provided, with all the changes and additions you have made to the source code. Include a pdf file with the answer of question 3.

Instruction:
cd ~/NVIDIA_GPU_Computing_SDK/C/src/
make clean
cd ..
tar cvf lab1.tar lab1
gzip lab1.tar
upload lab1.tar.gz file at T-square

5) Grading.
We will grade the functionality of the code with the default matrix size (10x10).
(Source: UIUC EE498AL)