Matrix multiplication using CUDA

This is a CUDA program to multiply two matrices P_{a x b} and Q_{b x c} to calculate R_{a x c}. The values for a, b and c are specified by user and their default value is 1024. The program also accepts the number of blocks and threads per blocks from user.

I have used MS Windows as my development environment. If you are using Linux, please check steps to build.

System requirements

MS Windows environment:

1. MS Visual Studio
2. NVCC and Nsight

Linux:

1. NVCC

How to build

MS Windows environment:

1. Import the kernel.cu file in MS Visual Studio
2. Set the value of WINDOWS to 1. It has been #defined on first line of kernel.cu
3. Build the project

Linux:

1. Open kernel.cu and unset the value of WINDOWS to 0. It has been #defined on first line of kernel.cu
2. Make the project

    
        $ cd matrix_mult
        $ make
    

How to run

MS Windows environment:

1. Execute the project in MS Visual Studio using Nsight

Linux:

1. Execute kernel binary file

    
        $ cd matrix_mult
        $ ./kernel
    

Note: It accepts the values of a, b and c using command-line arguments if all three values are provided. Otherwise, the program uses default value.