_gpu_mtx_kernel.c File Reference

Go to the source code of this file.

Functions
__kernel void	gpu_mtx_add (__global const int *A, __global const int *B, __global int *C)
__kernel void	matrixMul (__global float *C, __global float *A, __global float *B, int wA, int wB)

Function Documentation

gpu_mtx_add()

__kernel void gpu_mtx_add	(	__global const int *	A,
		__global const int *	B,
		__global int *	C
	)

This file implements OpenCL matrix operation related kernel functions add vectors using GPU

Definition at line 9 of file _gpu_mtx_kernel.c.

                                                                           {
    int i = get_global_id(0);
    int j = get_global_id(1);
    int index = i * get_global_size(1) + j;
    C[index] = A[index] + B[index];
}

References python.linalg::A, python.linalg::B, and python.linalg::C.

matrixMul()

__kernel void matrixMul	(	__global float *	C,
		__global float *	A,
		__global float *	B,
		int	wA,
		int	wB
	)

Definition at line 16 of file _gpu_mtx_kernel.c.

                                {
 
    int tx = get_global_id(0);
    int ty = get_global_id(1);
 
    // value stores the element that is
    // computed by the thread
    float value = 0;
    for (int k = 0; k < wA; ++k) {
        float elementA = A[ty * wA + k];
        float elementB = B[k * wB + tx];
        value += elementA * elementB;
    }
 
    // Write the matrix to device memory each
    // thread writes one element
    C[ty * wA + tx] = value;
}

References python.linalg::A, python.linalg::B, and python.linalg::C.