-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  --------------------------------------  
                                                   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       4.199ms      1932.95%       4.199ms       1.400ms           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     109.919us        50.60%     109.919us      36.640us           0 B           0 B           0 B           0 B             3                                      []  
                                          ProfilerStep*        49.46%       2.583ms        99.93%       5.219ms       1.740ms       0.000us         0.00%     102.501us      34.167us           0 B         -72 B           0 B      -2.63 MB             3                                      []  
                                             aten::add_         3.11%     162.578us         5.46%     285.264us      15.848us      26.112us        12.02%      26.112us       1.451us           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      26.112us        12.02%      26.112us       1.451us           0 B           0 B           0 B           0 B            18                                      []  
                                              aten::mul         5.10%     266.423us         8.27%     431.725us      23.985us      25.444us        11.71%      25.444us       1.414us           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      25.444us        11.71%      25.444us       1.414us           0 B           0 B           0 B           0 B            18                                      []  
                                            aten::copy_         2.21%     115.200us         4.30%     224.445us      24.938us      24.481us        11.27%      24.481us       2.720us           0 B           0 B           0 B           0 B             9                [[2, 512], [2, 512], []]  
                                               aten::to         0.39%      20.414us         6.03%     314.728us      52.455us       0.000us         0.00%      18.881us       3.147us           0 B           0 B      36.00 KB           0 B             6              [[2, 512], [], [], [], []]  
                                         aten::_to_copy         1.27%      66.196us         5.64%     294.314us      49.052us       0.000us         0.00%      18.881us       3.147us           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       9.568us         4.40%       9.568us       3.189us           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       9.313us         4.29%       9.313us       3.104us           0 B           0 B           0 B           0 B             3                                      []  
                                            aten::zeros         1.03%      53.603us         4.81%     251.106us      41.851us       0.000us         0.00%       6.783us       1.130us           0 B           0 B       1.67 MB           0 B             6                    [[], [], [], [], []]  
                                            aten::zero_         0.75%      39.349us         2.83%     148.045us      24.674us       0.000us         0.00%       6.783us       1.130us           0 B           0 B           0 B           0 B             6                            [[2, 36512]]  
                                            aten::fill_         0.94%      49.229us         2.08%     108.696us      18.116us       6.783us         3.12%       6.783us       1.130us           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         3.12%       6.783us       1.130us           0 B           0 B           0 B           0 B             6                                      []  
                                              aten::cat         1.06%      55.461us         1.60%      83.766us      27.922us       6.464us         2.98%       6.464us       2.155us           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       6.464us         2.98%       6.464us       2.155us           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       5.600us         2.58%       5.600us       1.867us           0 B           0 B           0 B           0 B             3                                      []  
                                             aten::lerp         1.10%      57.331us         1.58%      82.585us      27.528us       5.344us         2.46%       5.344us       1.781us           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       5.344us         2.46%       5.344us       1.781us           0 B           0 B           0 B           0 B             3                                      []  
                                             aten::flip         0.98%      51.068us         2.20%     114.944us      38.315us       5.088us         2.34%       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         2.34%       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       4.832us         2.22%       4.832us       1.611us           0 B           0 B           0 B           0 B             3                                      []  
                                               aten::to         0.11%       5.624us         2.51%     131.104us      43.701us       0.000us         0.00%       2.785us       0.928us          72 B           0 B           0 B           0 B             3       [[3], [], [], [], [], [], [], []]  
                                         aten::_to_copy         0.36%      18.833us         2.40%     125.480us      41.827us       0.000us         0.00%       2.785us       0.928us          72 B           0 B           0 B           0 B             3           [[3], [], [], [], [], [], []]  
                                            aten::copy_         0.46%      24.078us         1.80%      93.823us      31.274us       2.785us         1.28%       2.785us       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       2.785us         1.28%       2.785us       0.928us           0 B           0 B           0 B           0 B             3                                      []  
                                    aten::empty_strided         1.88%      98.282us         1.88%      98.282us       8.190us       0.000us         0.00%       0.000us       0.000us          72 B          72 B      37.50 KB      37.50 KB            12                [[], [], [], [], [], []]  
                                       cudaLaunchKernel        11.39%     595.070us        11.39%     595.070us       9.016us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            66                                      []  
                                           aten::detach         0.11%       5.599us         0.28%      14.713us       4.904us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             3                                   [[3]]  
                                                 detach         0.17%       9.114us         0.17%       9.114us       3.038us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             3                                   [[3]]  
                                        cudaMemcpyAsync         1.17%      61.064us         1.17%      61.064us      20.355us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             3                                      []  
                                  cudaStreamSynchronize         0.17%       8.681us         0.17%       8.681us       2.894us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             3                                      []  
                                           aten::select         0.93%      48.443us         1.07%      56.132us       6.237us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             9                           [[3], [], []]  
                                       aten::as_strided         0.15%       7.689us         0.15%       7.689us       0.854us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             9                       [[3], [], [], []]  
                                             aten::item         0.29%      15.284us         0.38%      19.991us       2.221us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             9                                    [[]]  
                              aten::_local_scalar_dense         0.09%       4.707us         0.09%       4.707us       0.523us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B             9                                    [[]]  
                                            aten::empty         1.86%      96.956us         1.86%      96.956us       8.080us       0.000us         0.00%       0.000us       0.000us           0 B           0 B       1.72 MB       1.72 MB            12                [[], [], [], [], [], []]  
                                           aten::select         1.76%      92.131us         2.12%     110.641us       4.610us       0.000us         0.00%       0.000us       0.000us           0 B           0 B           0 B           0 B            24                      [[2, 512], [], []]  
-------------------------------------------------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  ------------  --------------------------------------  
Self CPU time total: 5.222ms
Self CUDA time total: 217.252us
