linux gpu硬件加速

#include <iostream>
#include <cuda_runtime.h>

__global__ void matrixMulKernel(float *A, float *B, float *C, int N) {
    int row = blockIdx.y * blockDim.y + threadIdx.y;
    int col = blockIdx.x * blockDim.x + threadIdx.x;

    float sum = 0.0f;
    if (row < N && col < N) {
        for (int k = 0; k < N; ++k) {
            sum += A[row * N + k] * B[k * N + col];
        }
        C[row * N + col] = sum;
    }
}

void matrixMul(float *h_A, float *h_B, float *h_C, int N) {
    float *d_A, *d_B, *d_C;
    cudaMalloc(&d_A, N * N * sizeof(float));
    cudaMalloc(&d_B, N * N * sizeof(float));
    cudaMalloc(&d_C, N * N * sizeof(float));

    cudaMemcpy(d_A, h_A, N * N * sizeof(float), cudaMemcpyHostToDevice);
    cudaMemcpy(d_B, h_B, N * N * sizeof(float), cudaMemcpyHostToDevice);

    dim3 threadsPerBlock(16, 16);
    dim3 numBlocks((N + 15) / 16, (N + 15) / 16);
    matrixMulKernel<<<numBlocks, threadsPerBlock>>>(d_A, d_B, d_C, N);

    cudaMemcpy(h_C, d_C, N * N * sizeof(float), cudaMemcpyDeviceToHost);

    cudaFree(d_A);
    cudaFree(d_B);
    cudaFree(d_C);
}

int main() {
    int N = 2;
    float h_A[N * N] = {1, 2, 3, 4};
    float h_B[N * N] = {5, 6, 7, 8};
    float h_C[N * N];

    matrixMul(h_A, h_B, h_C, N);

    for (int i = 0; i < N; ++i) {
        for (int j = 0; j < N; ++j) {
            std::cout << h_C[i * N + j] << " ";
        }
        std::cout << std::endl;
    }

    return 0;
}