matrix_relu.cu File Reference

Implementation of the ReLU activation function for matrices. More...

#include "matrix.h"
#include <cuda_runtime.h>

Include dependency graph for matrix_relu.cu:

Go to the source code of this file.

Functions
__global__ void	reluKernel (const double *input, double *output, int size)
	CUDA kernel for applying the ReLU activation function element-wise. More...

Detailed Description

Implementation of the ReLU activation function for matrices.

Definition in file matrix_relu.cu.

Function Documentation

reluKernel()

__global__ void reluKernel	(	const double *	input,
		double *	output,
		int	size
	)

CUDA kernel for applying the ReLU activation function element-wise.

Parameters

input	Pointer to the input matrix data.
output	Pointer to the output matrix data.
size	Total number of elements in the matrix.

Definition at line 15 of file matrix_relu.cu.

                                                                          {
    // Calculate the global thread index
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    
    // Check if the thread is within the matrix bounds
    if (idx < size) {
        // Apply ReLU: max(0, x)
        output[idx] = fmax(0.0, input[idx]);
    }
}