-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  --------------------------------------  
                                                   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       3.047ms      1372.61%       3.047ms       1.016ms           0 B           0 B           0 B           0 B             3                                      []  
torchfx::sequential_biquad_kernel(double const*, dou...         0.00%       0.000us         0.00%       0.000us       0.000us     109.824us        49.47%     109.824us      36.608us           0 B           0 B           0 B           0 B             3                                      []  
                                          ProfilerStep*        49.81%       1.855ms        99.93%       3.722ms       1.241ms       0.000us         0.00%     102.395us      34.132us           0 B         -72 B           0 B      -3.47 MB             3                                      []  
                                             aten::add_         3.02%     112.449us         5.27%     196.318us      10.907us      26.047us        11.73%      26.047us       1.447us           0 B           0 B           0 B           0 B            18                      [[512], [512], []]  
void at::native::vectorized_elementwise_kernel<4, at...         0.00%       0.000us         0.00%       0.000us       0.000us      26.047us        11.73%      26.047us       1.447us           0 B           0 B           0 B           0 B            18                                      []  
                                              aten::mul         5.03%     187.200us         8.08%     300.926us      16.718us      25.439us        11.46%      25.439us       1.413us           0 B           0 B      36.00 KB      36.00 KB            18                             [[512], []]  
void at::native::vectorized_elementwise_kernel<4, at...         0.00%       0.000us         0.00%       0.000us       0.000us      25.439us        11.46%      25.439us       1.413us           0 B           0 B           0 B           0 B            18                                      []  
                                            aten::copy_         2.28%      84.998us         4.43%     165.161us      18.351us      24.543us        11.05%      24.543us       2.727us           0 B           0 B           0 B           0 B             9                [[2, 512], [2, 512], []]  
                                               aten::to         0.36%      13.428us         6.01%     223.918us      37.320us       0.000us         0.00%      18.911us       3.152us           0 B           0 B      36.00 KB           0 B             6              [[2, 512], [], [], [], []]  
                                         aten::_to_copy         1.15%      43.010us         5.65%     210.490us      35.082us       0.000us         0.00%      18.911us       3.152us           0 B           0 B      36.00 KB           0 B             6      [[2, 512], [], [], [], [], [], []]  
void at::native::unrolled_elementwise_kernel<at::nat...         0.00%       0.000us         0.00%       0.000us       0.000us       9.503us         4.28%       9.503us       3.168us           0 B           0 B           0 B           0 B             3                                      []  
void at::native::unrolled_elementwise_kernel<at::nat...         0.00%       0.000us         0.00%       0.000us       0.000us       9.408us         4.24%       9.408us       3.136us           0 B           0 B           0 B           0 B             3                                      []  
                                            aten::zeros         0.61%      22.734us         3.94%     146.754us      24.459us       0.000us         0.00%       6.623us       1.104us           0 B           0 B       1.67 MB           0 B             6                    [[], [], [], [], []]  
                                            aten::zero_         0.43%      16.171us         2.42%      90.036us      15.006us       0.000us         0.00%       6.623us       1.104us           0 B           0 B           0 B           0 B             6                            [[2, 36512]]  
                                            aten::fill_         0.91%      33.759us         1.98%      73.865us      12.311us       6.623us         2.98%       6.623us       1.104us           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       6.623us         2.98%       6.623us       1.104us           0 B           0 B           0 B           0 B             6                                      []  
                                              aten::cat         1.10%      40.828us         1.66%      61.872us      20.624us       6.591us         2.97%       6.591us       2.197us           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       6.591us         2.97%       6.591us       2.197us           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       5.632us         2.54%       5.632us       1.877us           0 B           0 B           0 B           0 B             3                                      []  
                                             aten::lerp         0.91%      34.008us         1.36%      50.502us      16.834us       5.280us         2.38%       5.280us       1.760us           0 B           0 B     856.50 KB     856.50 KB             3            [[2, 36512], [2, 36512], []]  
void at::native::vectorized_elementwise_kernel<4, at...         0.00%       0.000us         0.00%       0.000us       0.000us       5.280us         2.38%       5.280us       1.760us           0 B           0 B           0 B           0 B             3                                      []  
                                             aten::flip         0.98%      36.360us         2.14%      79.826us      26.609us       5.088us         2.29%       5.088us       1.696us           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       5.088us         2.29%       5.088us       1.696us           0 B           0 B           0 B           0 B             3                                      []  
torchfx::delay_line_kernel(float const*, float*, int...         0.00%       0.000us         0.00%       0.000us       0.000us       5.088us         2.29%       5.088us       1.696us           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       4.704us         2.12%       4.704us       1.568us           0 B           0 B           0 B           0 B             3                                      []  
                                               aten::to         0.11%       4.063us         2.65%      98.736us      32.912us       0.000us         0.00%       2.784us       0.928us          72 B           0 B           0 B           0 B             3       [[3], [], [], [], [], [], [], []]  
                                         aten::_to_copy         0.35%      12.947us         2.54%      94.673us      31.558us       0.000us         0.00%       2.784us       0.928us          72 B           0 B           0 B           0 B             3           [[3], [], [], [], [], [], []]  
                                            aten::copy_         0.47%      17.330us         1.94%      72.355us      24.118us       2.784us         1.25%       2.784us       0.928us           0 B           0 B           0 B           0 B             3                          [[3], [3], []]  
                       Memcpy DtoH (Device -> Pageable)         0.00%       0.000us         0.00%       0.000us       0.000us       2.784us         1.25%       2.784us       0.928us           0 B           0 B           0 B           0 B             3                                      []  
                                    aten::empty_strided         2.44%      90.832us         2.44%      90.832us       6.055us       0.000us         0.00%       0.000us       0.000us          72 B          72 B     894.00 KB     894.00 KB            15                [[], [], [], [], [], []]  
                                       cudaLaunchKernel        11.75%     437.647us        11.75%     437.647us       6.343us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            69                                      []  
                                           aten::detach         0.10%       3.860us         0.30%      11.023us       3.674us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             3                                   [[3]]  
                                                 detach         0.19%       7.163us         0.19%       7.163us       2.388us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             3                                   [[3]]  
                                        cudaMemcpyAsync         1.30%      48.494us         1.30%      48.494us      16.165us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             3                                      []  
                                  cudaStreamSynchronize         0.18%       6.531us         0.18%       6.531us       2.177us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             3                                      []  
                                           aten::select         0.82%      30.446us         0.97%      36.288us       4.032us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             9                           [[3], [], []]  
                                       aten::as_strided         0.16%       5.842us         0.16%       5.842us       0.649us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             9                       [[3], [], [], []]  
                                             aten::item         0.26%       9.778us         0.36%      13.360us       1.484us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             9                                    [[]]  
                              aten::_local_scalar_dense         0.10%       3.582us         0.10%       3.582us       0.398us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             9                                    [[]]  
                                            aten::empty         1.81%      67.533us         1.81%      67.533us       5.628us       0.000us         0.00%       0.000us       0.000us           0 B           0 B       1.72 MB       1.72 MB            12                [[], [], [], [], [], []]  
-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  --------------------------------------  
Self CPU time total: 3.724ms
Self CUDA time total: 222.011us
