Generating SQLite file gpu.sqlite from gpu.nsys-rep
Processing [gpu.sqlite] with [/home/dl/.local/sg/nvhpc/Linux_x86_64/26.1/profilers/13.1/Nsight_Systems/host-linux-x64/reports/cuda_api_sum.py]... 

 ** CUDA API Summary (cuda_api_sum):

 Time (%)  Total Time (ms)  Num Calls  Avg (ms)  Med (ms)  Min (ms)  Max (ms)  StdDev (ms)               Name             
 --------  ---------------  ---------  --------  --------  --------  --------  -----------  ------------------------------
     41.2        8600.7280     296966    0.0290    0.0022    0.0010    8.7394       0.1642  cudaStreamSynchronize_ptsz    
     34.5        7192.0127     348169    0.0207    0.0078    0.0020    3.7245       0.0996  cudaMemcpyAsync_ptsz          
      9.0        1872.9448     292424    0.0064    0.0048    0.0025    3.5974       0.0182  cudaLaunchKernel_ptsz         
      7.7        1596.0419     342064    0.0047    0.0009    0.0004    2.1536       0.0288  cudaEventRecord               
      4.1         852.3416     513381    0.0017    0.0015    0.0003    0.3436       0.0013  cudaEventQuery                
      1.7         354.5542      58492    0.0061    0.0045    0.0017    1.6333       0.0131  cudaMemsetAsync_ptsz          
      0.8         176.8914      24585    0.0072    0.0048    0.0023    1.0682       0.0125  cuLaunchKernel                
      0.4          81.5717      65536    0.0012    0.0009    0.0004    0.7003       0.0051  cudaEventRecord_ptsz          
      0.2          46.1104        114    0.4045    0.3400    0.1610    1.0409       0.2014  cuModuleLoadData              
      0.1          16.1497        231    0.0699    0.0140    0.0004    0.9949       0.1675  cudaEventCreateWithFlags      
      0.1          14.4077         15    0.9605    0.1343    0.0176    4.3020       1.6888  cudaFree                      
      0.1          12.5301         15    0.8353    0.1521    0.0082    4.7466       1.5586  cudaMalloc                    
      0.0           8.5106          9    0.9456    0.9513    0.0134    2.3930       0.8928  cudaMemcpyAsync               
      0.0           6.3954        116    0.0551    0.0096    0.0037    1.7497       0.2294  cuMemcpyHtoD_v2               
      0.0           5.5441        114    0.0486    0.0268    0.0157    0.5746       0.0916  cuModuleUnload                
      0.0           2.8771          6    0.4795    0.3522    0.0652    1.0456       0.4302  cudaMalloc3DArray             
      0.0           2.7801         26    0.1069    0.0001    0.0001    2.6712       0.5234  cuMemFree_v2                  
      0.0           2.5428          6    0.4238    0.2742    0.1984    0.8035       0.2863  cudaMemcpy3D_ptds             
      0.0           2.4190          2    1.2095    1.2095    1.2046    1.2144       0.0070  cudaGetDeviceProperties_v12000
      0.0           1.3386         54    0.0248    0.0187    0.0081    0.1111       0.0197  cuMemGetInfo_v2               
      0.0           0.7151          6    0.1192    0.1147    0.0627    0.1799       0.0608  cudaFreeArray                 
      0.0           0.4690         19    0.0247    0.0228    0.0088    0.0715       0.0140  cudaMemGetInfo                
      0.0           0.4006          2    0.2003    0.2003    0.1734    0.2273       0.0381  cuMemAlloc_v2                 
      0.0           0.1929        152    0.0013    0.0012    0.0010    0.0032       0.0004  cudaEventSynchronize          
      0.0           0.1316          9    0.0146    0.0072    0.0031    0.0395       0.0150  cudaMemset_ptds               
      0.0           0.1217        231    0.0005    0.0004    0.0003    0.0038       0.0004  cudaEventDestroy              
      0.0           0.1150          9    0.0128    0.0046    0.0031    0.0409       0.0133  cudaMemsetAsync               
      0.0           0.1057         12    0.0088    0.0059    0.0028    0.0244       0.0071  cudaStreamCreate              
      0.0           0.0878          6    0.0146    0.0103    0.0023    0.0385       0.0141  cudaCreateTextureObject       
      0.0           0.0704         12    0.0059    0.0046    0.0036    0.0104       0.0023  cudaStreamDestroy             
      0.0           0.0588          6    0.0098    0.0084    0.0063    0.0159       0.0035  cudaDeviceSynchronize         
      0.0           0.0325          6    0.0054    0.0057    0.0012    0.0099       0.0041  cudaDestroyTextureObject      
      0.0           0.0140         54    0.0003    0.0002    0.0001    0.0009       0.0002  cuCtxSetCurrent               
      0.0           0.0125          1    0.0125    0.0125    0.0125    0.0125       0.0000  cuInit                        
      0.0           0.0067          1    0.0067    0.0067    0.0067    0.0067       0.0000  cuModuleGetLoadingMode        

Processing [gpu.sqlite] with [/home/dl/.local/sg/nvhpc/Linux_x86_64/26.1/profilers/13.1/Nsight_Systems/host-linux-x64/reports/cuda_gpu_kern_sum.py]... 

 ** CUDA GPU Kernel Summary (cuda_gpu_kern_sum):

 Time (%)  Total Time (ms)  Instances  Avg (ms)  Med (ms)  Min (ms)  Max (ms)  StdDev (ms)                                                  Name                                                
 --------  ---------------  ---------  --------  --------  --------  --------  -----------  ----------------------------------------------------------------------------------------------------
     40.9        2080.3041       2048    1.0158    1.0140    0.9269    1.1371       0.0256  void cuda_kernel_diff2_CC_coarse<(bool)1, (bool)0, (int)128>(float *, float *, float *, float *, fl…
     14.1         715.0124       6144    0.1164    0.1056    0.0478    0.5826       0.0550  void cuda_kernel_backproject3D<(bool)0, (bool)0>(float *, float *, float *, float *, float *, float…
      9.3         471.8976       6144    0.0768    0.0693    0.0348    0.5053       0.0364  void cuda_kernel_wavg<(bool)1, (bool)1, (bool)0, (int)256>(float *, AccProjectorKernel, unsigned in…
      8.1         412.1067       4096    0.1006    0.0911    0.0737    0.2560       0.0277  void cuda_kernel_diff2_coarse<(bool)1, (bool)0, (int)128, (int)16, (int)4>(float *, float *, float …
      4.1         210.1795      15784    0.0133    0.0126    0.0097    0.1204       0.0032  void cub::CUB_200802_SM_800::DeviceRadixSortOnesweepKernel<cub::CUB_200802_SM_800::detail::radix::p…
      2.9         147.7816       4096    0.0361    0.0311    0.0280    0.1289       0.0127  void cuda_kernel_diff2_coarse<(bool)1, (bool)0, (int)128, (int)1, (int)4>(float *, float *, float *…
      2.2         111.9243       4096    0.0273    0.0272    0.0151    0.3845       0.0162  void cuda_kernel_diff2_fine<(bool)1, (bool)0, (int)256, (int)7>(float *, float *, float *, float *,…
      1.6          80.1484      16384    0.0049    0.0049    0.0032    0.0245       0.0009  void regular_fft<(unsigned int)120, EPT<(unsigned int)10, (unsigned int)12>, (unsigned int)16, (uns…
      1.2          62.9190       4246    0.0148    0.0144    0.0140    0.0346       0.0016  void cub::CUB_200802_SM_800::DeviceRadixSortSingleTileKernel<cub::CUB_200802_SM_800::detail::radix:…
      0.8          40.8860      18432    0.0022    0.0020    0.0012    0.0149       0.0011  void cuda_kernel_init_value<float>(T1 *, T1, unsigned long, int)                                    
      0.8          39.0428      12288    0.0032    0.0027    0.0022    0.0215       0.0011  cuda_kernel_initOrientations(double *, float *, bool *, unsigned long)                              
      0.7          38.0700      16384    0.0023    0.0022    0.0017    0.0129       0.0006  void CudaKernels::cuda_kernel_multi<float>(T1 *, T1, int)                                           
      0.7          35.4250       6144    0.0058    0.0048    0.0039    0.0318       0.0024  void cuda_kernel_make_eulers_3D<(bool)1, (bool)0, (bool)1>(float *, float *, float *, float *, unsi…
      0.7          33.6336       8192    0.0041    0.0038    0.0031    0.0159       0.0008  void regular_fft_r2c<(unsigned int)120, EPT<(unsigned int)10, (unsigned int)12>, (unsigned int)8, (…
      0.6          32.6394      12288    0.0027    0.0025    0.0019    0.0139       0.0006  void cuda_kernel_window_fourier_transform<(bool)0>(float2 *, float2 *, unsigned long, unsigned long…
      0.6          31.7895       8192    0.0039    0.0040    0.0023    0.0410       0.0014  void cub::CUB_200802_SM_800::DeviceScanKernel<cub::CUB_200802_SM_800::detail::scan::policy_hub<floa…
      0.6          30.7328      12288    0.0025    0.0023    0.0019    0.0223       0.0007  void cuda_kernel_centerFFT_2D<float>(T1 *, int, int, int, int, int)                                 
      0.5          27.4497      12288    0.0022    0.0020    0.0016    0.0111       0.0007  void cub::CUB_200802_SM_800::DeviceReduceSingleTileKernel<cub::CUB_200802_SM_800::detail::reduce::p…
      0.5          27.1635       2048    0.0133    0.0125    0.0114    0.0604       0.0031  void cuda_kernel_diff2_CC_fine<(bool)1, (bool)0, (int)256, (int)7>(float *, float *, float *, float…
      0.5          24.8082       3946    0.0063    0.0055    0.0048    0.0583       0.0028  void cub::CUB_200802_SM_800::DeviceRadixSortHistogramKernel<cub::CUB_200802_SM_800::detail::radix::…
      0.5          24.1122       4096    0.0059    0.0055    0.0042    0.0440       0.0016  void cub::CUB_200802_SM_800::DeviceSelectSweepKernel<cub::CUB_200802_SM_800::detail::select::policy…
      0.5          24.0337       6211    0.0039    0.0030    0.0023    0.0158       0.0023  void cub::CUB_200802_SM_800::DeviceReduceKernel<cub::CUB_200802_SM_800::detail::reduce::policy_hub<…
      0.5          23.2037       6144    0.0038    0.0031    0.0025    0.0241       0.0019  void cuda_kernel_collect2jobs<(bool)0>(float *, float *, float *, float *, float *, float, float, i…
      0.4          22.8408       6144    0.0037    0.0028    0.0025    0.0194       0.0023  cuda_kernel_allweights_to_mweights(unsigned long *, float *, float *, unsigned long, unsigned long,…
      0.4          22.3725       4096    0.0055    0.0051    0.0046    0.0252       0.0010  void cuda_kernel_weights_exponent_coarse<float>(T1 *, bool *, T1 *, bool *, T1 *, T1, int, int, int)
      0.4          21.9854       6144    0.0036    0.0033    0.0027    0.0234       0.0014  cuda_kernel_softMaskBackgroundValue(float *, long, long, long, long, long, long, long, float, float…
      0.4          21.7891       6144    0.0035    0.0032    0.0029    0.0166       0.0014  void cuda_kernel_powerClass<(bool)0>(float2 *, float *, int, int, int, int, int, int, float *)      
      0.4          19.7903       8192    0.0024    0.0025    0.0014    0.0271       0.0009  void cuda_kernel_exponentiate<float>(T1 *, T1, unsigned long)                                       
      0.4          19.6237       8192    0.0024    0.0024    0.0014    0.0252       0.0009  void cuda_kernel_find_threshold_idx_in_cumulative<float>(T1 *, T1, unsigned long, unsigned long *, …
      0.4          18.9473       6144    0.0031    0.0029    0.0025    0.0126       0.0006  cuda_kernel_cosineFilter(float *, long, long, long, long, long, long, long, bool, float *, float, f…
      0.4          18.1189       4096    0.0044    0.0043    0.0035    0.0203       0.0008  cuda_kernel_exponentiate_weights_fine(float *, bool *, float *, bool *, float *, float, int, int, u…
      0.3          16.0489       6144    0.0026    0.0023    0.0019    0.0129       0.0010  void CudaKernels::cuda_kernel_translate2D<float>(T1 *, T1 *, int, int, int, int, int)               
      0.3          15.4955       5986    0.0026    0.0022    0.0017    0.0128       0.0013  void cub::CUB_200802_SM_800::DeviceReduceSingleTileKernel<cub::CUB_200802_SM_800::detail::reduce::p…
      0.3          15.1742       6211    0.0024    0.0022    0.0017    0.0113       0.0007  void cub::CUB_200802_SM_800::DeviceReduceSingleTileKernel<cub::CUB_200802_SM_800::detail::reduce::p…
      0.3          14.9026       6077    0.0025    0.0022    0.0017    0.0256       0.0010  void cub::CUB_200802_SM_800::DeviceReduceSingleTileKernel<cub::CUB_200802_SM_800::detail::reduce::p…
      0.3          13.7222       4096    0.0034    0.0028    0.0023    0.0120       0.0011  void CudaKernels::cuda_kernel_add<float>(T1 *, T1, int)                                             
      0.3          13.5403       4163    0.0033    0.0031    0.0022    0.0105       0.0007  void cub::CUB_200802_SM_800::DeviceReduceKernel<cub::CUB_200802_SM_800::detail::reduce::policy_hub<…
      0.3          13.0961       4254    0.0031    0.0028    0.0022    0.0169       0.0007  void cub::CUB_200802_SM_800::DeviceReduceKernel<cub::CUB_200802_SM_800::detail::reduce::policy_hub<…
      0.3          13.0935       8192    0.0016    0.0014    0.0012    0.0056       0.0004  void cub::CUB_200802_SM_800::DeviceScanInitKernel<cub::CUB_200802_SM_800::ScanTileState<float, (boo…
      0.2          10.6316       4096    0.0026    0.0023    0.0021    0.0156       0.0007  void cuda_kernel_array_over_threshold<float>(T1 *, bool *, T1, unsigned long, int)                  
      0.2          10.0861       4163    0.0024    0.0022    0.0017    0.0081       0.0007  void cub::CUB_200802_SM_800::DeviceReduceSingleTileKernel<cub::CUB_200802_SM_800::detail::reduce::p…
      0.2           9.9532       3946    0.0025    0.0024    0.0017    0.0062       0.0005  void cub::CUB_200802_SM_800::DeviceRadixSortExclusiveSumKernel<cub::CUB_200802_SM_800::detail::radi…
      0.2           9.9488       4254    0.0023    0.0021    0.0017    0.0065       0.0006  void cub::CUB_200802_SM_800::DeviceReduceSingleTileKernel<cub::CUB_200802_SM_800::detail::reduce::p…
      0.2           9.8668       4029    0.0024    0.0023    0.0017    0.0104       0.0007  void cub::CUB_200802_SM_800::DeviceReduceSingleTileKernel<cub::CUB_200802_SM_800::detail::reduce::p…
      0.1           6.9464       4096    0.0017    0.0016    0.0012    0.0055       0.0005  void cub::CUB_200802_SM_800::DeviceCompactInitKernel<cub::CUB_200802_SM_800::ScanTileState<int, (bo…
      0.1           6.0221       2048    0.0029    0.0028    0.0025    0.0161       0.0006  void cub::CUB_200802_SM_800::DeviceReduceKernel<cub::CUB_200802_SM_800::detail::reduce::policy_hub<…
      0.1           4.8525       2048    0.0024    0.0020    0.0017    0.0163       0.0011  void cub::CUB_200802_SM_800::DeviceReduceSingleTileKernel<cub::CUB_200802_SM_800::detail::reduce::p…
      0.1           4.5278       2048    0.0022    0.0021    0.0017    0.0056       0.0005  void cub::CUB_200802_SM_800::DeviceReduceSingleTileKernel<cub::CUB_200802_SM_800::detail::reduce::p…
      0.0           0.8803          6    0.1467    0.1465    0.1429    0.1509       0.0040  void regular_fft<(unsigned int)240, EPT<(unsigned int)5, (unsigned int)6, (unsigned int)8>, (unsign…
      0.0           0.7650          3    0.2550    0.2550    0.2544    0.2556       0.0006  void regular_fft_r2c<(unsigned int)240, EPT<(unsigned int)5, (unsigned int)6, (unsigned int)8>, (un…
      0.0           0.5738          3    0.1913    0.1468    0.0737    0.3533       0.1450  void cuda_kernel_calcPowerSpectrum<double2>(T1 *, int, T1 *, int, double *, double *, int, int, dou…
      0.0           0.4764          3    0.1588    0.1606    0.1533    0.1625       0.0048  void cuda_kernel_centerFFTbySign<double2>(T1 *, int, int, int)                                      
      0.0           0.3933          3    0.1311    0.1329    0.1276    0.1329       0.0031  void CudaKernels::cuda_kernel_multi<double>(T1 *, T1, int)                                          
      0.0           0.2572          3    0.0857    0.0858    0.0853    0.0861       0.0004  void cuda_kernel_window_transform<double>(T1 *, T1 *, int, int, int, int, int, int, int, int, int)  
      0.0           0.1004          3    0.0335    0.0355    0.0289    0.0361       0.0040  cuda_kernel_griddingCorrect(double *, int, double, double, unsigned long, unsigned long, unsigned l…
      0.0           0.0071          3    0.0024    0.0023    0.0023    0.0025       0.0001  cuda_kernel_updatePowerSpectrum(double *, double *, int)                                            

Processing [gpu.sqlite] with [/home/dl/.local/sg/nvhpc/Linux_x86_64/26.1/profilers/13.1/Nsight_Systems/host-linux-x64/reports/cuda_gpu_mem_time_sum.py]... 

 ** CUDA GPU MemOps Summary (by Time) (cuda_gpu_mem_time_sum):

 Time (%)  Total Time (ms)  Count   Avg (ms)  Med (ms)  Min (ms)  Max (ms)  StdDev (ms)            Operation           
 --------  ---------------  ------  --------  --------  --------  --------  -----------  ------------------------------
     47.7         446.4207  200823    0.0022    0.0017    0.0010    2.0604       0.0074  [CUDA memcpy Host-to-Device]  
     37.6         352.2796  135183    0.0026    0.0016    0.0011    1.9072       0.0094  [CUDA memcpy Device-to-Host]  
     11.6         108.4065   58510    0.0019    0.0017    0.0010    0.0255       0.0010  [CUDA memset]                 
      2.9          27.2300   12288    0.0022    0.0020    0.0017    0.0188       0.0008  [CUDA memcpy Device-to-Device]
      0.2           1.5583       6    0.2597    0.0940    0.0521    0.6558       0.2901  [CUDA memcpy Host-to-Array]   

