TEST(Index, blah) {
    array a   = randu(20000000, 10);
    array idx = seq(20000000);
    array b = a(idx);
    b.eval();
    af::sync();
}

 Time(%)  Total Time (ns)  Instances    Average      Minimum     Maximum                                                    Name
 -------  ---------------  ---------  ------------  ----------  ----------  ----------------------------------------------------------------------------------------------------
    49.7       10,107,916          1  10,107,916.0  10,107,916  10,107,916  void cuda::index<float>(cuda::Param<float>, cuda::CParam<float>, cuda::AssignKernelParam, int, int)
    38.4        7,811,232          1   7,811,232.0   7,811,232   7,811,232  void cuda::kernel::uniformPhilox<float>(float*, unsigned int, unsigned int, unsigned int, unsigned …
     8.1        1,645,554          1   1,645,554.0   1,645,554   1,645,554  KER9745534647381087054
     3.9          791,546          1     791,546.0     791,546     791,546  void cuda::range<float>(cuda::Param<float>, int, int, int)

 Time(%)  Total Time (ns)  Instances    Average     Minimum    Maximum                                                   Name
 -------  ---------------  ---------  -----------  ---------  ---------  ----------------------------------------------------------------------------------------------------
    60.6        7,809,308          1  7,809,308.0  7,809,308  7,809,308  void cuda::kernel::uniformPhilox<float>(float*, unsigned int, unsigned int, unsigned int, unsigned …
    20.3        2,615,049          1  2,615,049.0  2,615,049  2,615,049  void cuda::index<float>(cuda::Param<float>, cuda::CParam<float>, cuda::AssignKernelParam, int, int)
    12.8        1,646,066          1  1,646,066.0  1,646,066  1,646,066  KER9745534647381087054
     6.3          812,761          1    812,761.0    812,761    812,761  void cuda::range<float>(cuda::Param<float>, int, int, int)