内核执行错误后释放内存时，CUDA失败

#include <cassert>

__global__ void segfault(){
    int* null = NULL;
    *null = 0;
}

int main() {
    int* i;
    assert (cudaSuccess ==  cudaHostAlloc(&i, sizeof(int)*100, cudaHostAllocMapped));
    segfault<<<1,100>>>();
    assert (cudaErrorLaunchFailure == cudaThreadSynchronize());
    assert (cudaErrorLaunchFailure == cudaGetLastError());
    assert (cudaSuccess == cudaGetLastError());
    assert (cudaSuccess == cudaFreeHost(i));
    return 0;
}