matrix_add_vector.cu File Reference

Implementation of the Matrix::add_vector method for GPU-accelerated addition of a vector to each column of a matrix. More...

#include "matrix.h"
#include "vector.h"
#include <cuda_runtime.h>
#include <stdexcept>
#include <string>

Include dependency graph for matrix_add_vector.cu:

Go to the source code of this file.

Functions
__global__ void	addVectorToMatrixKernel (double *m, const double *v, int rows, int cols)
	CUDA kernel for adding a vector to each column of a matrix. More...

Detailed Description

Implementation of the Matrix::add_vector method for GPU-accelerated addition of a vector to each column of a matrix.

Definition in file matrix_add_vector.cu.

Function Documentation

addVectorToMatrixKernel()

__global__ void addVectorToMatrixKernel	(	double *	m,
		const double *	v,
		int	rows,
		int	cols
	)

CUDA kernel for adding a vector to each column of a matrix.

Parameters

m	Pointer to the matrix data.
v	Pointer to the vector data.
rows	Number of rows in the matrix.
cols	Number of columns in the matrix.

Definition at line 19 of file matrix_add_vector.cu.

                                                                                        {
    // Calculate global thread indices
    int col = blockIdx.x * blockDim.x + threadIdx.x;
    int row = blockIdx.y * blockDim.y + threadIdx.y;
 
    // Check if thread is within matrix bounds
    if (row < rows && col < cols) {
        // Calculate index of current matrix element
        int index = row * cols + col;
 
        // Add vector element to matrix element
        m[index] += v[row];
    }
}