Last active
August 29, 2015 14:27
-
-
Save olajep/bbd62ca934aae8134138 to your computer and use it in GitHub Desktop.
pal cflags benchmark 20150812
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
PAL Benchmark | |
============= | |
Comparison between different CFLAGS | |
Date: 2015-08-12 | |
Commit: d88cd210f7774ba4472a494b8bd919657db8d36c | |
Arch: x86_64 | |
CPU: Intel(R) Core(TM) i7-2760QM | |
CFLAGS: "-O2 -ffast-math" vs. | |
"-O3 -ffast-math -march=corei7-avx" | |
Speedup | |
----------------------- | |
0.24 p_tan_f32 | |
0.36 p_exp_f32 | |
0.47 p_min_f32 | |
0.48 p_cosh_f32 | |
0.50 p_sinh_f32 | |
0.50 p_tanh_f32 | |
0.88 p_gauss3x3_f32 | |
0.97 p_rand | |
0.97 p_asinh_f32 | |
0.99 p_cbrt_f32 | |
0.99 p_median3x3_f32 | |
0.99 p_laplace3x3_f32 | |
0.99 p_max_f32 | |
0.99 p_atanh_f32 | |
1.00 p_acosh_f32 | |
1.00 p_invcbrt_f32 | |
1.01 p_median_f32 | |
1.02 p_atan2_f32 | |
1.07 p_sobel3x3_f32 | |
1.10 p_box3x3_f32 | |
1.13 p_prewitt3x3_f32 | |
1.19 p_scharr3x3_f32 | |
1.32 p_sort_f32 | |
1.41 p_mode_f32 | |
1.82 p_popcount_u64 | |
1.93 p_pow_f32 | |
2.42 p_add_f32 | |
2.43 p_mul_f32 | |
2.66 p_asin_f32 | |
2.78 p_acos_f32 | |
2.95 p_sub_f32 | |
3.20 p_mac_f32 | |
3.90 p_abs_f32 | |
4.18 p_dot_f32 | |
4.37 p_absdiff_f32 | |
4.63 p_invsqrt_f32 | |
4.71 p_ln_f32 | |
4.71 p_popcount_u32 | |
4.72 p_log10_f32 | |
5.46 p_itof | |
5.47 p_sqrt_f32 | |
5.57 p_sumsq_f32 | |
6.84 p_ftoi | |
7.15 p_inv_f32 | |
7.25 p_mean_f32 | |
7.48 p_atan_f32 | |
7.65 p_sum_f32 | |
7.73 p_cos_f32 | |
8.07 p_sincos_f32 | |
8.28 p_sin_f32 | |
13.00 p_div_f32 | |
--------------------- | |
2.07 (Geometric mean) | |
Arch: ARMV7 | |
CPU: Cortex-A9 | |
CFLAGS: "-O2 -ffast-math" vs. | |
"-O3 -ffast-math -mcpu=cortex-a9 -mfpu=neon" | |
Speedup | |
------------------------- | |
0.29 p_tan_f32 | |
0.71 p_exp_f32 | |
0.76 p_sinh_f32 | |
0.76 p_cosh_f32 | |
0.80 p_tanh_f32 | |
0.94 p_laplace3x3_f32 | |
0.95 p_median3x3_f32 | |
0.99 p_gauss3x3_f32 | |
0.99 p_scharr3x3_f32 | |
0.99 p_div_f32 | |
1.00 p_cbrt_f32 | |
1.01 p_sobel3x3_f32 | |
1.01 p_prewitt3x3_f32 | |
1.01 p_box3x3_f32 | |
1.01 p_atan2_f32 | |
1.01 p_invcbrt_f32 | |
1.02 p_asinh_f32 | |
1.03 p_acosh_f32 | |
1.05 p_atanh_f32 | |
1.06 p_rand | |
1.08 p_median_f32 | |
1.09 p_max_f32 | |
1.11 p_pow_f32 | |
1.13 p_ln_f32 | |
1.16 p_abs_f32 | |
1.22 p_log10_f32 | |
1.25 p_popcount_u64 | |
1.35 p_sort_f32 | |
1.36 p_mode_f32 | |
1.36 p_acos_f32 | |
1.44 p_asin_f32 | |
1.49 p_min_f32 | |
1.53 p_popcount_u32 | |
1.62 p_sub_f32 | |
1.62 p_add_f32 | |
1.66 p_absdiff_f32 | |
1.75 p_mul_f32 | |
1.81 p_mac_f32 | |
1.99 p_dot_f32 | |
2.16 p_itof | |
2.32 p_ftoi | |
2.66 p_mean_f32 | |
2.66 p_sumsq_f32 | |
2.66 p_sum_f32 | |
3.04 p_inv_f32 | |
3.29 p_sin_f32 | |
3.38 p_sqrt_f32 | |
3.42 p_sincos_f32 | |
3.52 p_cos_f32 | |
3.65 p_invsqrt_f32 | |
3.66 p_atan_f32 | |
--------------------- | |
1.40 (Geometric mean) | |
Arch: Epiphany | |
CPU: Epiphany-III | |
CFLAGS: "-O2 -ffast-math-mfp-mode=round-nearest -ffp-contract=fast" vs. | |
"-O2 -ffast-math-mfp-mode=round-nearest -ffp-contract=fast -mno-soft-cmpsf" | |
Speedup | |
---------------------------- | |
0.94 p_max_f32 | |
1 p_abs_f32 | |
1 p_absdiff_f32 | |
1 p_acosh_f32 | |
1 p_add_f32 | |
1 p_asinh_f32 | |
1 p_atan2_f32 | |
1 p_atan_f32 | |
1 p_atanh_f32 | |
1 p_box3x3_f32 | |
1 p_cbrt_f32 | |
1 p_cos_f32 | |
1 p_div_f32 | |
1 p_dot_f32 | |
1 p_ftoi | |
1 p_gauss3x3_f32 | |
1 p_inv_f32 | |
1 p_invcbrt_f32 | |
1 p_invsqrt_f32 | |
1 p_itof | |
1 p_laplace3x3_f32 | |
1 p_ln_f32 | |
1 p_log10_f32 | |
1 p_mac_f32 | |
1 p_mean_f32 | |
1 p_mul_f32 | |
1 p_popcount_u32 | |
1 p_popcount_u64 | |
1 p_prewitt3x3_f32 | |
1 p_rand | |
1 p_scharr3x3_f32 | |
1 p_sin_f32 | |
1 p_sincos_f32 | |
1 p_sobel3x3_f32 | |
1 p_sqrt_f32 | |
1 p_sub_f32 | |
1 p_sum_f32 | |
1 p_sumsq_f32 | |
1.08 p_tanh_f32 | |
1.09 p_cosh_f32 | |
1.09 p_sinh_f32 | |
1.13 p_exp_f32 | |
1.30 p_asin_f32 | |
1.31 p_acos_f32 | |
1.58 p_tan_f32 | |
1.96 p_sort_f32 | |
2.01 p_median_f32 | |
2.18 p_median3x3_f32 | |
3.89 p_min_f32 | |
--------------------- | |
1.10 (Geometric mean) | |
Arch: Epiphany | |
CPU: Epiphany-III | |
CFLAGS: "-O2 -ffast-math-mfp-mode=round-nearest -ffp-contract=fast" vs. | |
"-O3 -ffast-math-mfp-mode=round-nearest -ffp-contract=fast -mno-soft-cmpsf" | |
Speedup | |
---------------------------- | |
0.29 p_tan_f32 | |
0.63 p_exp_f32 | |
0.68 p_tanh_f32 | |
0.69 p_cosh_f32 | |
0.69 p_sinh_f32 | |
0.94 p_max_f32 | |
0.97 p_scharr3x3_f32 | |
0.97 p_sobel3x3_f32 | |
0.99 p_prewitt3x3_f32 | |
1.00 p_cbrt_f32 | |
1.00 p_invcbrt_f32 | |
1.00 p_atan2_f32 | |
1.00 p_ln_f32 | |
1.00 p_atanh_f32 | |
1.00 p_popcount_u64 | |
1.00 p_rand | |
1.00 p_ftoi | |
1.00 p_div_f32 | |
1.00 p_invsqrt_f32 | |
1.00 p_sqrt_f32 | |
1.00 p_popcount_u32 | |
1.00 p_itof | |
1.00 p_box3x3_f32 | |
1.00 p_laplace3x3_f32 | |
1.00 p_gauss3x3_f32 | |
1.00 p_log10_f32 | |
1.00 p_acosh_f32 | |
1.08 p_asinh_f32 | |
1.23 p_cos_f32 | |
1.24 p_sincos_f32 | |
1.26 p_sin_f32 | |
1.29 p_acos_f32 | |
1.30 p_asin_f32 | |
1.41 p_abs_f32 | |
1.42 p_inv_f32 | |
1.51 p_mac_f32 | |
1.55 p_mean_f32 | |
1.56 p_sumsq_f32 | |
1.56 p_sum_f32 | |
1.66 p_atan_f32 | |
1.77 p_dot_f32 | |
1.85 p_add_f32 | |
1.85 p_mul_f32 | |
1.85 p_sub_f32 | |
1.86 p_absdiff_f32 | |
1.93 p_sort_f32 | |
2.01 p_median_f32 | |
2.18 p_median3x3_f32 | |
2.79 p_min_f32 | |
--------------------- | |
1.16 (Geometric mean) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment