Exercise 3 for the course "Parallel and distributed systems" of THMMY in AUTH university.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 

34 lines
1.1 KiB

Device chosen is "GeForce GTX 480"
Device has 15 multi processors and compute capability 2.0
Max threads per block supported are 1024
Reading dataset and labels...
Done.
0.043654 calculate_kernel_matrix_kernel called with:
dimBlock.x = 30, dimBlock.y = 30
dimGrid.x = 20, dimGrid.y = 20
0.003856 calculate_denominator called with:
dimBlock.x = 1024, dimBlock.y = 1
dimGrid.x = 1, dimGrid.y = 1
shift_points_kernel called with:
dimBlock.x = 448, dimBlock.y = 2
dimGrid.x = 2, dimGrid.y = 1
0.000053 Iteration n. 0, error 7.503378
0.001773 0.000049 Iteration n. 1, error 2.319695
0.001640 0.000047 Iteration n. 2, error 0.968228
0.001495 0.000046 Iteration n. 3, error 0.493493
0.001435 0.000050 Iteration n. 4, error 0.407053
0.001421 0.000050 Iteration n. 5, error 0.240149
0.001425 0.000052 Iteration n. 6, error 0.222551
0.001418 0.000050 Iteration n. 7, error 0.158582
0.001413 0.000051 Iteration n. 8, error 0.070010
0.001419 0.000053 Iteration n. 9, error 0.006547
0.001416 0.000050 Iteration n. 10, error 0.000603
0.001413 0.000053 Iteration n. 11, error 0.000056
Total number of iterations = 11
Mean Shift wall clock time = 0.283774