-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  --------------------------------------  
                                                   Name    Self CPU %      Self CPU   CPU total %     CPU total  CPU time avg     Self CUDA   Self CUDA %    CUDA total  CUDA time avg       CPU Mem  Self CPU Mem      CUDA Mem  Self CUDA Mem    # of Calls                            Input Shapes  
-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  --------------------------------------  
                                          ProfilerStep*         0.00%       0.000us         0.00%       0.000us       0.000us       4.427ms      1798.31%       4.427ms       1.476ms           0 B           0 B           0 B           0 B             3                                      []  
                                          ProfilerStep*        50.27%       2.785ms        99.94%       5.537ms       1.846ms       0.000us         0.00%     126.697us      42.232us           0 B         -72 B           0 B      -5.14 MB             3                                      []  
torchfx::sequential_biquad_kernel(double const*, dou...         0.00%       0.000us         0.00%       0.000us       0.000us     109.728us        44.57%     109.728us      36.576us           0 B           0 B           0 B           0 B             3                                      []  
void at::native::vectorized_elementwise_kernel<4, at...         0.00%       0.000us         0.00%       0.000us       0.000us      34.210us        13.90%      34.210us       1.425us           0 B           0 B           0 B           0 B            24                                      []  
void at::native::vectorized_elementwise_kernel<4, at...         0.00%       0.000us         0.00%       0.000us       0.000us      31.140us        12.65%      31.140us       1.483us           0 B           0 B           0 B           0 B            21                                      []  
                                             aten::add_         2.42%     134.067us         4.30%     238.057us      13.225us      26.116us        10.61%      26.116us       1.451us           0 B           0 B           0 B           0 B            18                      [[512], [512], []]  
                                              aten::mul         3.79%     210.085us         6.27%     347.455us      19.303us      25.505us        10.36%      25.505us       1.417us           0 B           0 B      36.00 KB      36.00 KB            18                             [[512], []]  
                                            aten::copy_         1.57%      86.870us         3.03%     167.900us      18.656us      23.906us         9.71%      23.906us       2.656us           0 B           0 B           0 B           0 B             9                [[2, 512], [2, 512], []]  
void at::native::unrolled_elementwise_kernel<at::nat...         0.00%       0.000us         0.00%       0.000us       0.000us      19.425us         7.89%      19.425us       2.158us           0 B           0 B           0 B           0 B             9                                      []  
                                               aten::to         0.24%      13.221us         3.59%     199.165us      33.194us       0.000us         0.00%      18.241us       3.040us           0 B           0 B      36.00 KB           0 B             6              [[2, 512], [], [], [], []]  
                                         aten::_to_copy         0.68%      37.912us         3.36%     185.944us      30.991us       0.000us         0.00%      18.241us       3.040us           0 B           0 B      36.00 KB           0 B             6      [[2, 512], [], [], [], [], [], []]  
                                         aten::_to_copy         1.15%      63.638us         5.97%     330.774us      36.753us       0.000us         0.00%      13.729us       1.525us          72 B           0 B       3.00 KB           0 B             9           [[3], [], [], [], [], [], []]  
                                            aten::copy_         1.36%      75.488us         3.64%     201.589us      22.399us      13.729us         5.58%      13.729us       1.525us           0 B           0 B           0 B           0 B             9                          [[3], [3], []]  
                                               aten::to         0.29%      15.966us         4.53%     250.727us      41.788us       0.000us         0.00%      10.624us       1.771us           0 B           0 B       3.00 KB           0 B             6                   [[3], [], [], [], []]  
void at::native::unrolled_elementwise_kernel<at::nat...         0.00%       0.000us         0.00%       0.000us       0.000us       9.440us         3.83%       9.440us       3.147us           0 B           0 B           0 B           0 B             3                                      []  
                                              aten::mul         1.22%      67.814us         1.87%     103.712us      17.285us       8.705us         3.54%       8.705us       1.451us           0 B           0 B       1.67 MB       1.67 MB             6                        [[2, 36512], []]  
                                            aten::zeros         0.58%      31.919us         3.34%     185.067us      30.844us       0.000us         0.00%       6.690us       1.115us           0 B           0 B       1.67 MB           0 B             6                    [[], [], [], [], []]  
                                            aten::zero_         0.39%      21.602us         2.09%     115.833us      19.305us       0.000us         0.00%       6.690us       1.115us           0 B           0 B           0 B           0 B             6                            [[2, 36512]]  
                                            aten::fill_         0.78%      43.047us         1.70%      94.231us      15.705us       6.690us         2.72%       6.690us       1.115us           0 B           0 B           0 B           0 B             6                        [[2, 36512], []]  
void at::native::vectorized_elementwise_kernel<4, at...         0.00%       0.000us         0.00%       0.000us       0.000us       6.690us         2.72%       6.690us       1.115us           0 B           0 B           0 B           0 B             6                                      []  
                                              aten::cat         1.20%      66.313us         1.76%      97.355us      32.452us       6.430us         2.61%       6.430us       2.143us           0 B           0 B       1.50 KB       1.50 KB             3                                [[], []]  
void at::native::(anonymous namespace)::CatArrayBatc...         0.00%       0.000us         0.00%       0.000us       0.000us       6.430us         2.61%       6.430us       2.143us           0 B           0 B           0 B           0 B             3                                      []  
void at::native::elementwise_kernel<128, 2, at::nati...         0.00%       0.000us         0.00%       0.000us       0.000us       5.665us         2.30%       5.665us       1.888us           0 B           0 B           0 B           0 B             3                                      []  
                                             aten::item         0.49%      26.989us         3.58%     198.591us      13.239us       0.000us         0.00%       5.472us       0.365us           0 B           0 B           0 B           0 B            15                                    [[]]  
                              aten::_local_scalar_dense         1.24%      68.565us         3.10%     171.602us      11.440us       5.472us         2.22%       5.472us       0.365us           0 B           0 B           0 B           0 B            15                                    [[]]  
                         Memcpy DtoH (Device -> Pinned)         0.00%       0.000us         0.00%       0.000us       0.000us       5.472us         2.22%       5.472us       0.912us           0 B           0 B           0 B           0 B             6                                      []  
                                             aten::flip         0.95%      52.505us         1.97%     108.875us      36.292us       5.120us         2.08%       5.120us       1.707us           0 B           0 B       1.50 KB           0 B             3                            [[2, 2], []]  
void at::native::index_elementwise_kernel<128, 4, at...         0.00%       0.000us         0.00%       0.000us       0.000us       5.120us         2.08%       5.120us       1.707us           0 B           0 B           0 B           0 B             3                                      []  
                                              aten::add         0.64%      35.191us         0.93%      51.616us      17.205us       5.024us         2.04%       5.024us       1.675us           0 B           0 B     856.50 KB     856.50 KB             3            [[2, 36512], [2, 36512], []]  
torchfx::delay_line_kernel(float const*, float*, int...         0.00%       0.000us         0.00%       0.000us       0.000us       5.023us         2.04%       5.023us       1.674us           0 B           0 B           0 B           0 B             3                                      []  
torchfx::forcing_kernel(double const*, double const*...         0.00%       0.000us         0.00%       0.000us       0.000us       4.736us         1.92%       4.736us       1.579us           0 B           0 B           0 B           0 B             3                                      []  
                                               aten::to         0.10%       5.551us         1.83%     101.564us      33.855us       0.000us         0.00%       3.105us       1.035us          72 B           0 B           0 B           0 B             3       [[3], [], [], [], [], [], [], []]  
                       Memcpy DtoH (Device -> Pageable)         0.00%       0.000us         0.00%       0.000us       0.000us       3.105us         1.26%       3.105us       1.035us           0 B           0 B           0 B           0 B             3                                      []  
                                    aten::empty_strided         2.58%     143.101us         2.58%     143.101us       6.814us       0.000us         0.00%       0.000us       0.000us          72 B          72 B     897.00 KB     897.00 KB            21                [[], [], [], [], [], []]  
                                       cudaLaunchKernel        11.51%     637.445us        11.51%     637.445us       7.870us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            81                                      []  
                                           aten::select         1.26%      69.940us         1.55%      85.911us       5.727us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                           [[3], [], []]  
                                       aten::as_strided         0.29%      15.971us         0.29%      15.971us       1.065us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                       [[3], [], [], []]  
                                        cudaMemcpyAsync         2.19%     121.466us         2.19%     121.466us      13.496us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             9                                      []  
                                  cudaStreamSynchronize         0.62%      34.336us         0.62%      34.336us       3.815us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             9                                      []  
                                           aten::detach         0.11%       5.882us         0.36%      19.721us       6.574us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             3                                   [[3]]  
-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  --------------------------------------  
Self CPU time total: 5.540ms
Self CUDA time total: 246.184us
