#include <time.h>
__global__ void slowKernel(float *output, bool write=false)
{
    float input = 5;
#pragma unroll
    for( int i = 0; i < 10000000; i++ ){
        input = input * .9999999;
    }
    if (write) *output -= input;
}

__global__ void fastKernel(float *output, bool write=false)
{
    float input = 5;
#pragma unroll
    for( int i = 0; i < 100000; i++ ){
        input = input * .9999999;
    }
    if (write) *output -= input;
}

void burntime(long val) {
    struct timespec tv[] = {{0, val}};
    nanosleep(tv, 0);
}

void mallocSynchronize(){
    cudaStream_t stream1, stream2;
    cudaStreamCreate( &stream1 );
    cudaStreamCreate( &stream2 );
    const size_t sz = 1 << 21;
    slowKernel <<<1, 1, 0, stream1 >>>((float *)(0));
    burntime(500000000L); // 500ms wait - slowKernel around 1300ms
    int *dev_a = 0;
    for( int i = 0; i < 10; i++ ){
        cudaMalloc( &dev_a, sz );
        fastKernel <<<1, 1, 0, stream2 >>>((float *)(0));
        burntime(1000000L); // 1ms wait - fastKernel around 15ms
    }
}

int main()
{
    mallocSynchronize();
    cudaDeviceSynchronize();
    cudaDeviceReset();
    return 0;
}