Device chosen is "GeForce GTX 1070"
Device has 15 multi processors and compute capability 6.1
Max threads per block supported are 1024

Reading dataset and labels...
Done.

Device memory allocation wall clock time = 0.083752

calculate_kernel_matrix_kernel called with:
dimBlock.x = 32, dimBlock.y = 32
dimGrid.x = 157, dimGrid.y = 157

calculate_denominator called with:
dimBlock.x = 1024, dimBlock.y = 1
dimGrid.x = 5, dimGrid.y = 1

shift_points_kernel called with:
dimBlock.x = 512, dimBlock.y = 2
dimGrid.x = 10, dimGrid.y = 1

Recursion n. 0, error	1433009.094419 
Recursion n. 1, error	846076.669706 
Recursion n. 2, error	457323.896842 
Recursion n. 3, error	232981.679496 
Recursion n. 4, error	129695.421325 
Recursion n. 5, error	73386.379913 
Recursion n. 6, error	42859.404834 
Recursion n. 7, error	34613.230704 
Recursion n. 8, error	31166.226384 
Recursion n. 9, error	25075.599825 
Recursion n. 10, error	14788.867230 
Recursion n. 11, error	6526.169908 
Recursion n. 12, error	2538.871384 
Recursion n. 13, error	953.135636 
Recursion n. 14, error	354.381780 
Recursion n. 15, error	131.434483 
Recursion n. 16, error	48.740960 
Recursion n. 17, error	18.090348 
Recursion n. 18, error	6.723606 
Recursion n. 19, error	2.503479 
Recursion n. 20, error	0.934231 
Recursion n. 21, error	0.349569 
Recursion n. 22, error	0.131220 
Recursion n. 23, error	0.049442 
Recursion n. 24, error	0.018711 
Recursion n. 25, error	0.007116 
Recursion n. 26, error	0.002722 
Recursion n. 27, error	0.001047 
Recursion n. 28, error	0.000406 
Recursion n. 29, error	0.000158 
Recursion n. 30, error	0.000062 

Copying between device and host wall clock time = 1.291885

Total number of recursions = 30
Mean Shift wall clock time = 2.356798