使用Cuda时: TypeError：(‘未理解关键字参数：’，‘激活’)

#include <stdio.h>

__global__ void addKernel(int* a, int* b, int* c, int size) {
    int tid = blockIdx.x * blockDim.x + threadIdx.x;
    if (tid < size) {
        c[tid] = a[tid] + b[tid];
    }
}

int main() {
    int size = 1000;
    int* a, * b, * c;  // Host arrays
    int* d_a, * d_b, * d_c;  // Device arrays

    // Allocate memory on host
    a = (int*)malloc(size * sizeof(int));
    b = (int*)malloc(size * sizeof(int));
    c = (int*)malloc(size * sizeof(int));

    // Initialize input arrays
    for (int i = 0; i < size; i++) {
        a[i] = i;
        b[i] = i;
    }

    // Allocate memory on device
    cudaMalloc((void**)&d_a, size * sizeof(int));
    cudaMalloc((void**)&d_b, size * sizeof(int));
    cudaMalloc((void**)&d_c, size * sizeof(int));

    // Copy input arrays from host to device
    cudaMemcpy(d_a, a, size * sizeof(int), cudaMemcpyHostToDevice);
    cudaMemcpy(d_b, b, size * sizeof(int), cudaMemcpyHostToDevice);

    // Launch kernel on device
    int threadsPerBlock = 256;
    int blocksPerGrid = (size + threadsPerBlock - 1) / threadsPerBlock;
    addKernel<<<blocksPerGrid, threadsPerBlock>>>(d_a, d_b, d_c, size);

    // Copy result from device to host
    cudaMemcpy(c, d_c, size * sizeof(int), cudaMemcpyDeviceToHost);

    // Print result
    for (int i = 0; i < size; i++) {
        printf("%d + %d = %d\n", a[i], b[i], c[i]);
    }

    // Free memory
    free(a);
    free(b);
    free(c);
    cudaFree(d_a);
    cudaFree(d_b);
    cudaFree(d_c);

    return 0;
}