-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  --------------------------------------  
                                                   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       4.144ms      1813.24%       4.144ms       1.381ms           0 B           0 B           0 B           0 B             3                                      []  
                                          ProfilerStep*        47.54%       2.402ms        99.94%       5.049ms       1.683ms       0.000us         0.00%     114.114us      38.038us           0 B           0 B           0 B      -2.63 MB             3                                      []  
torchfx::sequential_biquad_kernel(double const*, dou...         0.00%       0.000us         0.00%       0.000us       0.000us     109.759us        48.03%     109.759us      36.586us           0 B           0 B           0 B           0 B             3                                      []  
                                             aten::add_         2.86%     144.329us         5.11%     258.283us      14.349us      26.242us        11.48%      26.242us       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      26.242us        11.48%      26.242us       1.458us           0 B           0 B           0 B           0 B            18                                      []  
                                              aten::mul         4.90%     247.434us         7.79%     393.395us      21.855us      25.150us        11.00%      25.150us       1.397us           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      25.150us        11.00%      25.150us       1.397us           0 B           0 B           0 B           0 B            18                                      []  
                                            aten::copy_         1.85%      93.570us         3.79%     191.502us      21.278us      24.928us        10.91%      24.928us       2.770us           0 B           0 B           0 B           0 B             9                [[2, 512], [2, 512], []]  
                                               aten::to         0.37%      18.486us         5.48%     276.641us      46.107us       0.000us         0.00%      19.329us       3.221us           0 B           0 B      36.00 KB           0 B             6              [[2, 512], [], [], [], []]  
                                         aten::_to_copy         1.15%      58.000us         5.11%     258.155us      43.026us       0.000us         0.00%      19.329us       3.221us           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      14.148us         6.19%      14.148us       1.179us           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       9.697us         4.24%       9.697us       3.232us           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       9.632us         4.21%       9.632us       3.211us           0 B           0 B           0 B           0 B             3                                      []  
                                            aten::clone         0.63%      31.666us         3.69%     186.291us      31.048us       0.000us         0.00%       7.105us       1.184us           0 B           0 B       3.00 KB           0 B             6                         [[1, 2, 2], []]  
                                            aten::copy_         0.69%      34.710us         2.33%     117.811us      19.635us       7.105us         3.11%       7.105us       1.184us           0 B           0 B           0 B           0 B             6              [[1, 2, 2], [1, 2, 2], []]  
                                            aten::copy_         0.83%      41.719us         1.98%      99.949us      16.658us       7.043us         3.08%       7.043us       1.174us           0 B           0 B           0 B           0 B             6                    [[2, 2], [2, 2], []]  
                                            aten::zeros         0.81%      40.691us         4.29%     216.536us      36.089us       0.000us         0.00%       6.783us       1.131us           0 B           0 B       1.67 MB           0 B             6                    [[], [], [], [], []]  
                                            aten::zero_         0.66%      33.200us         2.60%     131.273us      21.879us       0.000us         0.00%       6.783us       1.131us           0 B           0 B           0 B           0 B             6                            [[2, 36512]]  
                                            aten::fill_         0.86%      43.401us         1.94%      98.073us      16.346us       6.783us         2.97%       6.783us       1.131us           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       6.783us         2.97%       6.783us       1.131us           0 B           0 B           0 B           0 B             6                                      []  
                                              aten::cat         1.05%      53.054us         1.60%      80.580us      26.860us       6.496us         2.84%       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         2.84%       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       5.599us         2.45%       5.599us       1.866us           0 B           0 B           0 B           0 B             3                                      []  
                                             aten::lerp         0.75%      37.942us         1.15%      58.142us      19.381us       5.248us         2.30%       5.248us       1.749us           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       5.248us         2.30%       5.248us       1.749us           0 B           0 B           0 B           0 B             3                                      []  
                                             aten::flip         0.98%      49.568us         2.08%     105.049us      35.016us       5.119us         2.24%       5.119us       1.706us           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       5.119us         2.24%       5.119us       1.706us           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       4.672us         2.04%       4.672us       1.557us           0 B           0 B           0 B           0 B             3                                      []  
                                    aten::empty_strided         2.25%     113.663us         2.25%     113.663us       7.578us       0.000us         0.00%       0.000us       0.000us           0 B           0 B      40.50 KB      40.50 KB            15                [[], [], [], [], [], []]  
                                       cudaLaunchKernel        10.54%     532.498us        10.54%     532.498us       8.068us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            66                                      []  
                                        cudaMemcpyAsync         2.80%     141.331us         2.80%     141.331us      11.778us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            12                                      []  
                                           aten::select         1.41%      71.089us         1.63%      82.122us       5.475us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                        [[1, 6], [], []]  
                                       aten::as_strided         0.22%      11.033us         0.22%      11.033us       0.736us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                    [[1, 6], [], [], []]  
                                           aten::select         0.93%      47.193us         1.15%      58.136us       3.876us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                           [[6], [], []]  
                                       aten::as_strided         0.22%      10.943us         0.22%      10.943us       0.730us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                       [[6], [], [], []]  
                                             aten::item         0.39%      19.479us         0.50%      25.443us       1.696us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                                    [[]]  
                              aten::_local_scalar_dense         0.12%       5.964us         0.12%       5.964us       0.398us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            15                                    [[]]  
                                           aten::select         0.88%      44.419us         1.07%      54.117us       4.510us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            12                     [[1, 2, 2], [], []]  
                                       aten::as_strided         0.19%       9.698us         0.19%       9.698us       0.808us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            12                 [[1, 2, 2], [], [], []]  
                                            aten::empty         1.69%      85.354us         1.69%      85.354us       7.113us       0.000us         0.00%       0.000us       0.000us           0 B           0 B       1.72 MB       1.72 MB            12                [[], [], [], [], [], []]  
-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  --------------------------------------  
Self CPU time total: 5.052ms
Self CUDA time total: 228.545us
