diff --git a/mean_shift_cuda/32.txt b/mean_shift_cuda/32.txt new file mode 100644 index 0000000..91d6b48 --- /dev/null +++ b/mean_shift_cuda/32.txt @@ -0,0 +1,50 @@ +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. + +Device memory allocation wall clock time = 0.039595 + +calculate_kernel_matrix_kernel called with: +dimBlock.x = 30, dimBlock.y = 30 +dimGrid.x = 35, dimGrid.y = 35 + +calculate_denominator called with: +dimBlock.x = 1024, dimBlock.y = 1 +dimGrid.x = 1, dimGrid.y = 1 + +shift_points_kernel called with: +dimBlock.x = 28, dimBlock.y = 32 +dimGrid.x = 37, dimGrid.y = 1 + +Recursion n. 0, error 638.769335 +Recursion n. 1, error 86.996834 +Recursion n. 2, error 540.383480 +Recursion n. 3, error 130.879803 +Recursion n. 4, error 126.467953 +Recursion n. 5, error 256.415922 +Recursion n. 6, error 6.383913 +Recursion n. 7, error 1.206431 +Recursion n. 8, error 0.373697 +Recursion n. 9, error 0.190936 +Recursion n. 10, error 0.107748 +Recursion n. 11, error 0.061548 +Recursion n. 12, error 0.035299 +Recursion n. 13, error 0.020304 +Recursion n. 14, error 0.011708 +Recursion n. 15, error 0.006766 +Recursion n. 16, error 0.003918 +Recursion n. 17, error 0.002273 +Recursion n. 18, error 0.001321 +Recursion n. 19, error 0.000769 +Recursion n. 20, error 0.000448 +Recursion n. 21, error 0.000262 +Recursion n. 22, error 0.000153 +Recursion n. 23, error 0.000090 + +Copying between device and host wall clock time = 0.111358 + +Total number of recursions = 23 +Mean Shift wall clock time = 1.279128 diff --git a/mean_shift_serial/32_serial.txt b/mean_shift_serial/32_serial.txt new file mode 100644 index 0000000..dad970b --- /dev/null +++ b/mean_shift_serial/32_serial.txt @@ -0,0 +1,26 @@ +Iteration n. 0, error 212.611066 +Iteration n. 1, error 51.768217 +Iteration n. 2, error 18.321997 +Iteration n. 3, error 7.902559 +Iteration n. 4, error 3.830385 +Iteration n. 5, error 1.990884 +Iteration n. 6, error 1.077207 +Iteration n. 7, error 0.596253 +Iteration n. 8, error 0.334476 +Iteration n. 9, error 0.189225 +Iteration n. 10, error 0.107681 +Iteration n. 11, error 0.061545 +Iteration n. 12, error 0.035299 +Iteration n. 13, error 0.020304 +Iteration n. 14, error 0.011708 +Iteration n. 15, error 0.006766 +Iteration n. 16, error 0.003918 +Iteration n. 17, error 0.002273 +Iteration n. 18, error 0.001321 +Iteration n. 19, error 0.000769 +Iteration n. 20, error 0.000448 +Iteration n. 21, error 0.000262 +Iteration n. 22, error 0.000153 +Iteration n. 23, error 0.000090 +Total iterations = 23 +Mean Shift wall clock time = 14.111556