-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  --------------------------------------  
                                                   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       3.766ms      1609.69%       3.766ms       1.255ms           0 B           0 B           0 B           0 B             3                                      []  
                                          ProfilerStep*        48.82%       2.237ms        99.94%       4.580ms       1.527ms       0.000us         0.00%     114.366us      38.122us           0 B           0 B           0 B      -3.47 MB             3                                      []  
torchfx::sequential_biquad_kernel(double const*, dou...         0.00%       0.000us         0.00%       0.000us       0.000us     109.794us        46.92%     109.794us      36.598us           0 B           0 B           0 B           0 B             3                                      []  
                                             aten::add_         2.80%     128.489us         4.89%     224.009us      12.445us      26.239us        11.21%      26.239us       1.458us           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      26.239us        11.21%      26.239us       1.458us           0 B           0 B           0 B           0 B            18                                      []  
                                              aten::mul         4.69%     214.829us         7.66%     350.964us      19.498us      25.406us        10.86%      25.406us       1.411us           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      25.406us        10.86%      25.406us       1.411us           0 B           0 B           0 B           0 B            18                                      []  
                                            aten::copy_         1.89%      86.428us         3.85%     176.222us      19.580us      24.834us        10.61%      24.834us       2.759us           0 B           0 B           0 B           0 B             9                [[2, 512], [2, 512], []]  
                                               aten::to         0.34%      15.801us         5.39%     246.844us      41.141us       0.000us         0.00%      19.200us       3.200us           0 B           0 B      36.00 KB           0 B             6              [[2, 512], [], [], [], []]  
                                         aten::_to_copy         1.13%      51.905us         5.04%     231.043us      38.507us       0.000us         0.00%      19.200us       3.200us           0 B           0 B      36.00 KB           0 B             6      [[2, 512], [], [], [], [], [], []]  
                         Memcpy DtoD (Device -> Device)         0.00%       0.000us         0.00%       0.000us       0.000us      14.207us         6.07%      14.207us       1.184us           0 B           0 B           0 B           0 B            12                                      []  
void at::native::unrolled_elementwise_kernel<at::nat...         0.00%       0.000us         0.00%       0.000us       0.000us       9.664us         4.13%       9.664us       3.221us           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       9.536us         4.08%       9.536us       3.179us           0 B           0 B           0 B           0 B             3                                      []  
                                            aten::clone         0.59%      27.255us         3.34%     152.940us      25.490us       0.000us         0.00%       7.135us       1.189us           0 B           0 B       3.00 KB           0 B             6                         [[1, 2, 2], []]  
                                            aten::copy_         0.63%      29.046us         2.07%      94.822us      15.804us       7.135us         3.05%       7.135us       1.189us           0 B           0 B           0 B           0 B             6              [[1, 2, 2], [1, 2, 2], []]  
                                            aten::copy_         0.77%      35.126us         1.85%      84.925us      14.154us       7.072us         3.02%       7.072us       1.179us           0 B           0 B           0 B           0 B             6                    [[2, 2], [2, 2], []]  
                                            aten::zeros         0.60%      27.505us         3.77%     172.549us      28.758us       0.000us         0.00%       6.720us       1.120us           0 B           0 B       1.67 MB           0 B             6                    [[], [], [], [], []]  
                                            aten::zero_         0.42%      19.252us         2.32%     106.384us      17.731us       0.000us         0.00%       6.720us       1.120us           0 B           0 B           0 B           0 B             6                            [[2, 36512]]  
                                            aten::fill_         0.83%      37.960us         1.90%      87.132us      14.522us       6.720us         2.87%       6.720us       1.120us           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       6.720us         2.87%       6.720us       1.120us           0 B           0 B           0 B           0 B             6                                      []  
                                              aten::cat         0.98%      44.950us         1.48%      67.737us      22.579us       6.496us         2.78%       6.496us       2.165us           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       6.496us         2.78%       6.496us       2.165us           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       5.634us         2.41%       5.634us       1.878us           0 B           0 B           0 B           0 B             3                                      []  
                                             aten::lerp         0.80%      36.457us         1.22%      55.950us      18.650us       5.312us         2.27%       5.312us       1.771us           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       5.312us         2.27%       5.312us       1.771us           0 B           0 B           0 B           0 B             3                                      []  
                                             aten::flip         1.07%      48.855us         2.12%      97.209us      32.403us       5.152us         2.20%       5.152us       1.717us           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       5.152us         2.20%       5.152us       1.717us           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       5.057us         2.16%       5.057us       1.686us           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       4.766us         2.04%       4.766us       1.589us           0 B           0 B           0 B           0 B             3                                      []  
                                    aten::empty_strided         2.62%     119.916us         2.62%     119.916us       6.662us       0.000us         0.00%       0.000us       0.000us           0 B           0 B     897.00 KB     897.00 KB            18                [[], [], [], [], [], []]  
                                       cudaLaunchKernel        10.87%     498.104us        10.87%     498.104us       7.219us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            69                                      []  
                                        cudaMemcpyAsync         2.52%     115.575us         2.52%     115.575us       9.631us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            12                                      []  
                                           aten::select         1.21%      55.250us         1.50%      68.572us       4.571us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                        [[1, 6], [], []]  
                                       aten::as_strided         0.29%      13.322us         0.29%      13.322us       0.888us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                    [[1, 6], [], [], []]  
                                           aten::select         0.87%      40.055us         1.04%      47.570us       3.171us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                           [[6], [], []]  
                                       aten::as_strided         0.16%       7.515us         0.16%       7.515us       0.501us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                       [[6], [], [], []]  
                                             aten::item         0.35%      16.178us         0.46%      21.182us       1.412us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                                    [[]]  
                              aten::_local_scalar_dense         0.11%       5.004us         0.11%       5.004us       0.334us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                                    [[]]  
                                           aten::select         0.81%      37.109us         1.07%      48.829us       4.069us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            12                     [[1, 2, 2], [], []]  
                                       aten::as_strided         0.26%      11.720us         0.26%      11.720us       0.977us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            12                 [[1, 2, 2], [], [], []]  
-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  --------------------------------------  
Self CPU time total: 4.582ms
Self CUDA time total: 233.983us
