RAPP Compute Tuning Report


Best generic

Best SWAR

Best SIMD
Linux gcc1-power7.osuosl.org 3.17.2-200.fc20.ppc64p7 #1 SMP Wed Feb 18 20:59:33 MST 2015 ppc64 ppc64 ppc64 GNU/Linux
Function
0%Relative Execution Speed100%
Gain
rc_bitblt_wa_copy_bin

1.04
rc_bitblt_vm_copy_bin

2.55
rc_bitblt_vm_not_bin

2.51
rc_bitblt_vm_and_bin

2.93
rc_bitblt_vm_or_bin

2.95
rc_bitblt_vm_xor_bin

2.96
rc_bitblt_vm_nand_bin

2.83
rc_bitblt_vm_nor_bin

2.95
rc_bitblt_vm_xnor_bin

2.82
rc_bitblt_vm_andn_bin

2.93
rc_bitblt_vm_orn_bin

2.81
rc_bitblt_vm_nandn_bin

2.90
rc_bitblt_vm_norn_bin

2.94
rc_bitblt_va_copy_bin

1.66
rc_bitblt_va_not_bin

1.52
rc_bitblt_va_and_bin

1.80
rc_bitblt_va_or_bin

1.81
rc_bitblt_va_xor_bin

1.78
rc_bitblt_va_nand_bin

1.67
rc_bitblt_va_nor_bin

1.76
rc_bitblt_va_xnor_bin

1.64
rc_bitblt_va_andn_bin

1.70
rc_bitblt_va_orn_bin

1.62
rc_bitblt_va_nandn_bin

1.66
rc_bitblt_va_norn_bin

1.77
rc_pixop_set_u8

2.08
rc_pixop_not_u8

9.34
rc_pixop_flip_u8

9.17
rc_pixop_abs_u8

7.00
rc_pixop_addc_u8

15.56
rc_pixop_lerpc_u8

28.42
rc_pixop_lerpnc_u8

14.84
rc_pixop_add_u8

14.22
rc_pixop_avg_u8

9.17
rc_pixop_sub_u8

11.33
rc_pixop_subh_u8

9.75
rc_pixop_suba_u8

10.47
rc_pixop_lerp_u8

8.28
rc_pixop_lerpn_u8

8.22
rc_pixop_lerpi_u8

8.80
rc_pixop_norm_u8

7.39
rc_type_u8_to_bin

3.60
rc_type_bin_to_u8

1.51
rc_thresh_gt_u8

3.83
rc_thresh_lt_u8

3.89
rc_thresh_gtlt_u8

4.28
rc_thresh_ltgt_u8

4.29
rc_thresh_gt_pixel_u8

4.02
rc_thresh_lt_pixel_u8

3.94
rc_thresh_gtlt_pixel_u8

4.35
rc_thresh_ltgt_pixel_u8

4.35
rc_stat_sum_bin

1.77
rc_stat_sum_u8

1.83
rc_stat_sum2_u8

3.72
rc_stat_xsum_u8

7.83
rc_stat_min_bin

1.40
rc_stat_max_bin

1.38
rc_stat_min_u8

31.32
rc_stat_max_u8

30.82
rc_reduce_1x2_u8

6.52
rc_reduce_2x1_u8

10.52
rc_reduce_2x2_u8

5.46
rc_filter_diff_1x2_horz_u8

8.96
rc_filter_diff_1x2_horz_abs_u8

10.66
rc_filter_diff_2x1_vert_u8

12.04
rc_filter_diff_2x1_vert_abs_u8

13.20
rc_filter_diff_2x2_magn_u8

12.57
rc_filter_sobel_3x3_horz_u8

6.35
rc_filter_sobel_3x3_horz_abs_u8

9.42
rc_filter_sobel_3x3_vert_u8

4.41
rc_filter_sobel_3x3_vert_abs_u8

7.45
rc_filter_sobel_3x3_magn_u8

6.80
rc_filter_gauss_3x3_u8

7.26
rc_filter_laplace_3x3_u8

4.75
rc_filter_laplace_3x3_abs_u8

9.25
rc_filter_highpass_3x3_u8

6.96
rc_filter_highpass_3x3_abs_u8

12.77
rc_margin_horz_bin

1.65
rc_cond_set_u8

1.05
rc_cond_addc_u8

2.90
rc_cond_subc_u8

2.48
rc_cond_copy_u8

1.13
rc_cond_add_u8

2.87