Created
June 5, 2015 21:27
-
-
Save nowls/37c78d89342053bae0ea to your computer and use it in GitHub Desktop.
Lots of fails for arches: neon, neonasm, orc
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
odroid@odroid:~$ volk_profile | |
Using Volk machine: neon_hardfp_orc | |
RUN_VOLK_TESTS: volk_64u_popcntpuppet_64u(131071,1987) | |
generic completed in 766.022ms | |
neon completed in 1729.77ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_16u_byteswappuppet_16u(131071,1987) | |
generic completed in 180.853ms | |
neon completed in 275.772ms | |
neon_table completed in 252.538ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32u_byteswappuppet_32u(131071,1987) | |
generic completed in 360.664ms | |
neon completed in 510.135ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32u_popcntpuppet_32u(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_64u_byteswappuppet_64u(131071,1987) | |
generic completed in 857.572ms | |
neon completed in 1158.84ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32fc_s32fc_rotatorpuppet_32fc(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_8u_conv_k7_r2puppet_8u(131071,198) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_s32f_32f_fm_detect_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_16ic_s32f_deinterleave_real_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_16ic_deinterleave_real_8i(131071,1987) | |
generic completed in 128.986ms | |
neon completed in 126.624ms | |
u_orc completed in 198.349ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_16ic_deinterleave_16i_x2(131071,1987) | |
generic completed in 220.996ms | |
u_orc completed in 348.453ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_16ic_s32f_deinterleave_32f_x2(131071,1987) | |
generic completed in 756.353ms | |
neon completed in 606.583ms | |
u_orc completed in 2.46351e+16ms | |
offset 0 in1: 40.5229 in2: 40.5229 | |
offset 1 in1: 34.6177 in2: 34.6177 | |
offset 2 in1: -99.1437 in2: -99.1437 | |
offset 3 in1: 29.5199 in2: 29.5199 | |
offset 4 in1: -46.2966 in2: -46.2966 | |
offset 5 in1: 73.8593 in2: 73.8593 | |
offset 6 in1: 38.4434 in2: 38.4434 | |
offset 7 in1: 46.893 in2: 46.893 | |
offset 8 in1: 83.945 in2: 83.945 | |
offset 9 in1: -79.3517 in2: -79.3517 | |
volk_16ic_s32f_deinterleave_32f_x2: fail on arch neon | |
offset 0 in1: -42.9052 in2: -42.9052 | |
offset 1 in1: -89.5474 in2: -89.5474 | |
offset 2 in1: 39.8012 in2: 39.8012 | |
offset 3 in1: 79 in2: 79 | |
offset 4 in1: -21.1468 in2: -21.1468 | |
offset 5 in1: 10.4679 in2: 10.4679 | |
offset 6 in1: -99.3976 in2: -99.3976 | |
offset 7 in1: -88.0612 in2: -88.0612 | |
offset 8 in1: 15.8838 in2: 15.8838 | |
offset 9 in1: -93.7462 in2: -93.7462 | |
volk_16ic_s32f_deinterleave_32f_x2: fail on arch neon | |
offset 0 in1: 40.5229 in2: 40.5229 | |
offset 1 in1: 34.6177 in2: 34.6177 | |
offset 2 in1: -99.1437 in2: -99.1437 | |
offset 3 in1: 29.5199 in2: 29.5199 | |
offset 4 in1: -46.2966 in2: -46.2966 | |
offset 5 in1: 73.8593 in2: 73.8593 | |
offset 6 in1: 38.4434 in2: 38.4434 | |
offset 7 in1: 46.893 in2: 46.893 | |
offset 8 in1: 83.945 in2: 83.9449 | |
offset 9 in1: -79.3517 in2: -79.3517 | |
volk_16ic_s32f_deinterleave_32f_x2: fail on arch u_orc | |
offset 0 in1: -42.9052 in2: -42.9052 | |
offset 1 in1: -89.5474 in2: -89.5474 | |
offset 2 in1: 39.8012 in2: 39.8012 | |
offset 3 in1: 79 in2: 79 | |
offset 4 in1: -21.1468 in2: -21.1468 | |
offset 5 in1: 10.4679 in2: 10.4679 | |
offset 6 in1: -99.3976 in2: -99.3975 | |
offset 7 in1: -88.0612 in2: -88.0611 | |
offset 8 in1: 15.8838 in2: 15.8838 | |
offset 9 in1: -93.7462 in2: -93.7462 | |
volk_16ic_s32f_deinterleave_32f_x2: fail on arch u_orc | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_16ic_deinterleave_real_16i(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_16ic_magnitude_16i(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_16ic_s32f_magnitude_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_16i_s32f_convert_32f(131071,1987) | |
generic completed in 258.713ms | |
neon completed in 301.611ms | |
a_generic completed in 242.447ms | |
Best aligned arch: a_generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_16i_convert_8i(131071,1987) | |
generic completed in 102.896ms | |
neon completed in 59.922ms | |
a_generic completed in 96.139ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_16i_32fc_dot_prod_32fc(131071,1987) | |
generic completed in 951.333ms | |
neon completed in 606.117ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32f_accumulator_s32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_x2_add_32f(131071,1987) | |
generic completed in 254.373ms | |
u_neon completed in 300.637ms | |
a_generic completed in 248.974ms | |
u_orc completed in 261.766ms | |
Best aligned arch: a_generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32fc_32f_multiply_32fc(131071,1987) | |
generic completed in 719.351ms | |
neon completed in 861.212ms | |
u_orc completed in 884.274ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32f_log2_32f(131071,1987) | |
generic completed in 13672.8ms | |
neon completed in 1472.62ms | |
u_generic completed in 13710.1ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32f_expfast_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_x2_pow_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_sin_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_cos_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_tan_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_atan_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_asin_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_acos_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32fc_s32f_power_32fc(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_s32f_calc_spectral_noise_floor_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32fc_s32f_atan2_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32fc_x2_conjugate_dot_prod_32fc(131071,1987) | |
generic completed in 1821.25ms | |
neon completed in 1357.61ms | |
a_generic completed in 1750.96ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32fc_deinterleave_32f_x2(131071,1987) | |
neon completed in 1097.16ms | |
generic completed in 1138.95ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32fc_deinterleave_64f_x2(131071,1987) | |
generic completed in 2825.83ms | |
a_generic completed in 2790.44ms | |
Best aligned arch: a_generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32fc_s32f_deinterleave_real_16i(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32fc_deinterleave_imag_32f(131071,1987) | |
neon completed in 261.402ms | |
generic completed in 472.686ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32fc_deinterleave_real_32f(131071,1987) | |
generic completed in 251.884ms | |
neon completed in 253.676ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32fc_deinterleave_real_64f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32fc_x2_dot_prod_32fc(131071,1987) | |
generic completed in 1830.7ms | |
a_generic completed in 1921.16ms | |
neon completed in 1632.39ms | |
neon_opttests completed in 1223.43ms | |
neon_optfma completed in 1302.98ms | |
neon_optfmaunroll completed in 1712.43ms | |
Best aligned arch: neon_opttests | |
Best unaligned arch: neon_opttests | |
RUN_VOLK_TESTS: volk_32fc_32f_dot_prod_32fc(131071,1987) | |
generic completed in 778.034ms | |
neon_unroll completed in 624.694ms | |
a_neon completed in 756.277ms | |
a_neonasm completed in 763.388ms | |
a_neonpipeline completed in 489.792ms | |
Best aligned arch: a_neonpipeline | |
Best unaligned arch: neon_unroll | |
RUN_VOLK_TESTS: volk_32fc_index_max_16u(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32fc_s32f_magnitude_16i(131071,1987) | |
generic completed in 2440.25ms | |
u_orc completed in -nanms | |
offset 0 in1: 273 in2: 0 | |
offset 1 in1: 360 in2: 0 | |
offset 2 in1: 153 in2: 0 | |
offset 3 in1: 294 in2: 0 | |
offset 4 in1: 86 in2: 0 | |
offset 5 in1: 254 in2: 0 | |
offset 6 in1: 218 in2: 0 | |
offset 7 in1: 99 in2: 0 | |
offset 8 in1: 157 in2: 0 | |
offset 9 in1: 49 in2: 0 | |
volk_32fc_s32f_magnitude_16i: fail on arch u_orc | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32fc_magnitude_32f(131071,1987) | |
generic completed in 2244.53ms | |
a_generic completed in 2242.18ms | |
neon completed in 585.049ms | |
neon_fancy_sweet completed in 1590.06ms | |
u_orc completed in 3548.42ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32fc_magnitude_squared_32f(131071,1987) | |
generic completed in 423.67ms | |
neon completed in 425.044ms | |
a_generic completed in 352.318ms | |
Best aligned arch: a_generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32fc_x2_multiply_32fc(131071,1987) | |
generic completed in 3937.92ms | |
a_generic completed in 3981.28ms | |
neon completed in 2547.73ms | |
neon_opttests completed in 2087.32ms | |
neonasm completed in 1985.21ms | |
u_orc completed in 7.2297ms | |
offset 0 in1: 0.650656 + 0.251833j in2: 0.650656 + 0.251833j | |
offset 1 in1: -0.105713 + 0.902544j in2: -0.105713 + 0.902544j | |
offset 2 in1: -0.119164 + 0.127007j in2: -0.119164 + 0.127007j | |
offset 3 in1: 0.0764787 + 0.942304j in2: 0.0764787 + 0.942304j | |
offset 4 in1: -0.231038 + 0.314776j in2: -0.231038 + 0.314776j | |
offset 5 in1: 0.211129 + -0.375836j in2: 0.211129 + -0.375836j | |
offset 6 in1: 0.517588 + -0.0842386j in2: 0.517588 + -0.0842386j | |
offset 7 in1: -0.31959 + -0.100726j in2: -0.31959 + -0.100726j | |
offset 8 in1: -0.0563166 + 0.520983j in2: -0.0563166 + 0.520983j | |
offset 9 in1: 0.189895 + -0.054877j in2: 0.189895 + -0.054877j | |
volk_32fc_x2_multiply_32fc: fail on arch a_generic | |
offset 0 in1: -0.750938 + -0.973669j in2: -0.750938 + -0.973669j | |
offset 1 in1: 0.727278 + 0.903957j in2: 0.727278 + 0.903957j | |
offset 2 in1: -0.928061 + 0.322169j in2: -0.928061 + 0.322169j | |
offset 3 in1: -0.496702 + -0.801419j in2: -0.496702 + -0.801419j | |
offset 4 in1: 0.0621829 + -0.350147j in2: 0.0621829 + -0.350147j | |
offset 5 in1: -0.0503087 + -0.446615j in2: -0.0503087 + -0.446615j | |
offset 6 in1: -0.136221 + -0.989573j in2: -0.136221 + -0.989573j | |
offset 7 in1: 0.260201 + -0.130055j in2: 0.260201 + -0.130055j | |
offset 8 in1: 0.152315 + 0.539569j in2: 0.152315 + 0.539569j | |
offset 9 in1: 0.124593 + -0.699341j in2: 0.124593 + -0.699341j | |
volk_32fc_x2_multiply_32fc: fail on arch a_generic | |
offset 0 in1: -0.48534 + 0.293935j in2: -0.48534 + 0.293935j | |
offset 1 in1: 0.548989 + 0.558633j in2: 0.548989 + 0.558633j | |
offset 2 in1: 0.15699 + -0.0823541j in2: 0.15699 + -0.0823541j | |
offset 3 in1: -0.892216 + -0.457547j in2: -0.892216 + -0.457547j | |
offset 4 in1: -0.985094 + -0.484888j in2: -0.985094 + -0.484888j | |
offset 5 in1: 0.778393 + 0.560413j in2: 0.778393 + 0.560413j | |
offset 6 in1: 0.0128819 + 0.524815j in2: 0.0128819 + 0.524815j | |
offset 7 in1: -0.827922 + -0.800927j in2: -0.827922 + -0.800927j | |
offset 8 in1: 0.867002 + 0.34912j in2: 0.867002 + 0.34912j | |
offset 9 in1: 0.122943 + 0.249632j in2: 0.122943 + 0.249632j | |
volk_32fc_x2_multiply_32fc: fail on arch a_generic | |
offset 0 in1: 0.650656 + 0.251833j in2: 0.650656 + 0.251833j | |
offset 1 in1: -0.105713 + 0.902544j in2: -0.105713 + 0.902544j | |
offset 2 in1: -0.119164 + 0.127007j in2: -0.119164 + 0.127007j | |
offset 3 in1: 0.0764787 + 0.942304j in2: 0.0764787 + 0.942304j | |
offset 4 in1: -0.231038 + 0.314776j in2: -0.231038 + 0.314776j | |
offset 5 in1: 0.211129 + -0.375836j in2: 0.211129 + -0.375836j | |
offset 6 in1: 0.517588 + -0.0842386j in2: 0.517588 + -0.0842386j | |
offset 7 in1: -0.31959 + -0.100726j in2: -0.31959 + -0.100726j | |
offset 8 in1: -0.0563166 + 0.520983j in2: -0.0563166 + 0.520983j | |
offset 9 in1: 0.189895 + -0.054877j in2: 0.189895 + -0.054877j | |
volk_32fc_x2_multiply_32fc: fail on arch neon | |
offset 0 in1: -0.750938 + -0.973669j in2: -0.750938 + -0.973669j | |
offset 1 in1: 0.727278 + 0.903957j in2: 0.727278 + 0.903957j | |
offset 2 in1: -0.928061 + 0.322169j in2: -0.928061 + 0.322169j | |
offset 3 in1: -0.496702 + -0.801419j in2: -0.496702 + -0.801419j | |
offset 4 in1: 0.0621829 + -0.350147j in2: 0.0621829 + -0.350147j | |
offset 5 in1: -0.0503087 + -0.446615j in2: -0.0503087 + -0.446615j | |
offset 6 in1: -0.136221 + -0.989573j in2: -0.136221 + -0.989573j | |
offset 7 in1: 0.260201 + -0.130055j in2: 0.260201 + -0.130055j | |
offset 8 in1: 0.152315 + 0.539569j in2: 0.152315 + 0.539569j | |
offset 9 in1: 0.124593 + -0.699341j in2: 0.124593 + -0.699341j | |
volk_32fc_x2_multiply_32fc: fail on arch neon | |
offset 0 in1: -0.48534 + 0.293935j in2: -0.48534 + 0.293935j | |
offset 1 in1: 0.548989 + 0.558633j in2: 0.548989 + 0.558633j | |
offset 2 in1: 0.15699 + -0.0823541j in2: 0.15699 + -0.0823541j | |
offset 3 in1: -0.892216 + -0.457547j in2: -0.892216 + -0.457547j | |
offset 4 in1: -0.985094 + -0.484888j in2: -0.985094 + -0.484888j | |
offset 5 in1: 0.778393 + 0.560413j in2: 0.778393 + 0.560413j | |
offset 6 in1: 0.0128819 + 0.524815j in2: 0.0128819 + 0.524815j | |
offset 7 in1: -0.827922 + -0.800927j in2: -0.827922 + -0.800927j | |
offset 8 in1: 0.867002 + 0.34912j in2: 0.867002 + 0.34912j | |
offset 9 in1: 0.122943 + 0.249632j in2: 0.122943 + 0.249632j | |
volk_32fc_x2_multiply_32fc: fail on arch neon | |
offset 0 in1: 0.650656 + 0.251833j in2: 0.650656 + 0.251833j | |
offset 1 in1: -0.105713 + 0.902544j in2: -0.105713 + 0.902544j | |
offset 2 in1: -0.119164 + 0.127007j in2: -0.119164 + 0.127007j | |
offset 3 in1: 0.0764787 + 0.942304j in2: 0.0764787 + 0.942304j | |
offset 4 in1: -0.231038 + 0.314776j in2: -0.231038 + 0.314776j | |
offset 5 in1: 0.211129 + -0.375836j in2: 0.211129 + -0.375836j | |
offset 6 in1: 0.517588 + -0.0842386j in2: 0.517588 + -0.0842386j | |
offset 7 in1: -0.31959 + -0.100726j in2: -0.31959 + -0.100726j | |
offset 8 in1: -0.0563166 + 0.520983j in2: -0.0563166 + 0.520983j | |
offset 9 in1: 0.189895 + -0.054877j in2: 0.189895 + -0.054877j | |
volk_32fc_x2_multiply_32fc: fail on arch neon_opttests | |
offset 0 in1: -0.750938 + -0.973669j in2: -0.750938 + -0.973669j | |
offset 1 in1: 0.727278 + 0.903957j in2: 0.727278 + 0.903957j | |
offset 2 in1: -0.928061 + 0.322169j in2: -0.928061 + 0.322169j | |
offset 3 in1: -0.496702 + -0.801419j in2: -0.496702 + -0.801419j | |
offset 4 in1: 0.0621829 + -0.350147j in2: 0.0621829 + -0.350147j | |
offset 5 in1: -0.0503087 + -0.446615j in2: -0.0503087 + -0.446615j | |
offset 6 in1: -0.136221 + -0.989573j in2: -0.136221 + -0.989573j | |
offset 7 in1: 0.260201 + -0.130055j in2: 0.260201 + -0.130055j | |
offset 8 in1: 0.152315 + 0.539569j in2: 0.152315 + 0.539569j | |
offset 9 in1: 0.124593 + -0.699341j in2: 0.124593 + -0.699341j | |
volk_32fc_x2_multiply_32fc: fail on arch neon_opttests | |
offset 0 in1: -0.48534 + 0.293935j in2: -0.48534 + 0.293935j | |
offset 1 in1: 0.548989 + 0.558633j in2: 0.548989 + 0.558633j | |
offset 2 in1: 0.15699 + -0.0823541j in2: 0.15699 + -0.0823541j | |
offset 3 in1: -0.892216 + -0.457547j in2: -0.892216 + -0.457547j | |
offset 4 in1: -0.985094 + -0.484888j in2: -0.985094 + -0.484888j | |
offset 5 in1: 0.778393 + 0.560413j in2: 0.778393 + 0.560413j | |
offset 6 in1: 0.0128819 + 0.524815j in2: 0.0128819 + 0.524815j | |
offset 7 in1: -0.827922 + -0.800927j in2: -0.827922 + -0.800927j | |
offset 8 in1: 0.867002 + 0.34912j in2: 0.867002 + 0.34912j | |
offset 9 in1: 0.122943 + 0.249632j in2: 0.122943 + 0.249632j | |
volk_32fc_x2_multiply_32fc: fail on arch neon_opttests | |
offset 0 in1: 0.650656 + 0.251833j in2: 0.650656 + 0.251833j | |
offset 1 in1: -0.105713 + 0.902544j in2: -0.105713 + 0.902544j | |
offset 2 in1: -0.119164 + 0.127007j in2: -0.119164 + 0.127007j | |
offset 3 in1: 0.0764787 + 0.942304j in2: 0.0764787 + 0.942304j | |
offset 4 in1: -0.231038 + 0.314776j in2: -0.231038 + 0.314776j | |
offset 5 in1: 0.211129 + -0.375836j in2: 0.211129 + -0.375836j | |
offset 6 in1: 0.517588 + -0.0842386j in2: 0.517588 + -0.0842386j | |
offset 7 in1: -0.31959 + -0.100726j in2: -0.31959 + -0.100726j | |
offset 8 in1: -0.0563166 + 0.520983j in2: -0.0563166 + 0.520983j | |
offset 9 in1: 0.189895 + -0.054877j in2: 0.189895 + -0.054877j | |
volk_32fc_x2_multiply_32fc: fail on arch neonasm | |
offset 0 in1: -0.750938 + -0.973669j in2: -0.750938 + -0.973669j | |
offset 1 in1: 0.727278 + 0.903957j in2: 0.727278 + 0.903957j | |
offset 2 in1: -0.928061 + 0.322169j in2: -0.928061 + 0.322169j | |
offset 3 in1: -0.496702 + -0.801419j in2: -0.496702 + -0.801419j | |
offset 4 in1: 0.0621829 + -0.350147j in2: 0.0621829 + -0.350147j | |
offset 5 in1: -0.0503087 + -0.446615j in2: -0.0503087 + -0.446615j | |
offset 6 in1: -0.136221 + -0.989573j in2: -0.136221 + -0.989573j | |
offset 7 in1: 0.260201 + -0.130055j in2: 0.260201 + -0.130055j | |
offset 8 in1: 0.152315 + 0.539569j in2: 0.152315 + 0.539569j | |
offset 9 in1: 0.124593 + -0.699341j in2: 0.124593 + -0.699341j | |
volk_32fc_x2_multiply_32fc: fail on arch neonasm | |
offset 0 in1: -0.48534 + 0.293935j in2: -0.48534 + 0.293935j | |
offset 1 in1: 0.548989 + 0.558633j in2: 0.548989 + 0.558633j | |
offset 2 in1: 0.15699 + -0.0823541j in2: 0.15699 + -0.0823541j | |
offset 3 in1: -0.892216 + -0.457547j in2: -0.892216 + -0.457547j | |
offset 4 in1: -0.985094 + -0.484888j in2: -0.985094 + -0.484888j | |
offset 5 in1: 0.778393 + 0.560413j in2: 0.778393 + 0.560413j | |
offset 6 in1: 0.0128819 + 0.524815j in2: 0.0128819 + 0.524815j | |
offset 7 in1: -0.827922 + -0.800927j in2: -0.827922 + -0.800927j | |
offset 8 in1: 0.867002 + 0.34912j in2: 0.867002 + 0.34912j | |
offset 9 in1: 0.122943 + 0.249632j in2: 0.122943 + 0.249632j | |
volk_32fc_x2_multiply_32fc: fail on arch neonasm | |
offset 0 in1: 0.650656 + 0.251833j in2: 0.650656 + 0.251833j | |
offset 1 in1: -0.105713 + 0.902544j in2: -0.105713 + 0.902544j | |
offset 2 in1: -0.119164 + 0.127007j in2: -0.119164 + 0.127007j | |
offset 3 in1: 0.0764787 + 0.942304j in2: 0.0764787 + 0.942304j | |
offset 4 in1: -0.231038 + 0.314776j in2: -0.231038 + 0.314776j | |
offset 5 in1: 0.211129 + -0.375836j in2: 0.211129 + -0.375836j | |
offset 6 in1: 0.517588 + -0.0842386j in2: 0.517588 + -0.0842386j | |
offset 7 in1: -0.31959 + -0.100726j in2: -0.31959 + -0.100726j | |
offset 8 in1: -0.0563166 + 0.520983j in2: -0.0563166 + 0.520983j | |
offset 9 in1: 0.189895 + -0.054877j in2: 0.189895 + -0.054877j | |
volk_32fc_x2_multiply_32fc: fail on arch u_orc | |
offset 0 in1: -0.750938 + -0.973669j in2: -0.750938 + -0.973669j | |
offset 1 in1: 0.727278 + 0.903957j in2: 0.727278 + 0.903957j | |
offset 2 in1: -0.928061 + 0.322169j in2: -0.928061 + 0.322169j | |
offset 3 in1: -0.496702 + -0.801419j in2: -0.496702 + -0.801419j | |
offset 4 in1: 0.0621829 + -0.350147j in2: 0.0621829 + -0.350147j | |
offset 5 in1: -0.0503087 + -0.446615j in2: -0.0503087 + -0.446615j | |
offset 6 in1: -0.136221 + -0.989573j in2: -0.136221 + -0.989573j | |
offset 7 in1: 0.260201 + -0.130055j in2: 0.260201 + -0.130055j | |
offset 8 in1: 0.152315 + 0.539569j in2: 0.152315 + 0.539569j | |
offset 9 in1: 0.124593 + -0.699341j in2: 0.124593 + -0.699341j | |
volk_32fc_x2_multiply_32fc: fail on arch u_orc | |
offset 0 in1: -0.48534 + 0.293935j in2: -0.48534 + 0.293935j | |
offset 1 in1: 0.548989 + 0.558633j in2: 0.548989 + 0.558633j | |
offset 2 in1: 0.15699 + -0.0823541j in2: 0.15699 + -0.0823541j | |
offset 3 in1: -0.892216 + -0.457547j in2: -0.892216 + -0.457547j | |
offset 4 in1: -0.985094 + -0.484888j in2: -0.985094 + -0.484888j | |
offset 5 in1: 0.778393 + 0.560413j in2: 0.778393 + 0.560413j | |
offset 6 in1: 0.0128819 + 0.524815j in2: 0.0128819 + 0.524815j | |
offset 7 in1: -0.827922 + -0.800927j in2: -0.827922 + -0.800927j | |
offset 8 in1: 0.867002 + 0.34912j in2: 0.867002 + 0.34912j | |
offset 9 in1: 0.122943 + 0.249632j in2: 0.122943 + 0.249632j | |
volk_32fc_x2_multiply_32fc: fail on arch u_orc | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32fc_x2_multiply_conjugate_32fc(131071,1987) | |
generic completed in 4017.61ms | |
neon completed in 2562.61ms | |
a_generic completed in 3848.08ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32fc_conjugate_32fc(131071,1987) | |
generic completed in 430.768ms | |
a_neon completed in 451.637ms | |
a_generic completed in 471.491ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32f_s32f_convert_16i(131071,1987) | |
generic completed in 3154.79ms | |
a_generic completed in 3154.57ms | |
Best aligned arch: a_generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32f_s32f_convert_32i(131071,1987) | |
generic completed in 1242.92ms | |
a_generic completed in 1225.51ms | |
Best aligned arch: a_generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32f_convert_64f(131071,1987) | |
generic completed in 550.689ms | |
a_generic completed in 527.613ms | |
Best aligned arch: a_generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32f_s32f_convert_8i(131071,1987) | |
generic completed in 3673.72ms | |
a_generic completed in 3676.89ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32fc_s32f_power_spectrum_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32fc_x2_square_dist_32f(131071,1987) | |
neon completed in 637.44ms | |
generic completed in 646.889ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32fc_x2_s32f_square_dist_scalar_mult_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_x2_divide_32f(131071,1987) | |
generic completed in 2356.33ms | |
u_orc completed in 702.991ms | |
Best aligned arch: u_orc | |
Best unaligned arch: u_orc | |
RUN_VOLK_TESTS: volk_32f_x2_dot_prod_32f(131071,1987) | |
generic completed in 205.057ms | |
a_generic completed in 207.069ms | |
neonopts completed in 269.656ms | |
neon completed in 248.404ms | |
neonasm completed in 161.257ms | |
neonasm_opts completed in 333.138ms | |
Best aligned arch: neonasm | |
Best unaligned arch: neonasm | |
RUN_VOLK_TESTS: volk_32f_x2_s32f_interleave_16ic(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_x2_interleave_32fc(131071,1987) | |
neon completed in 560.539ms | |
generic completed in 455.057ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32f_x2_max_32f(131071,1987) | |
neon completed in 352.389ms | |
generic completed in 271.81ms | |
u_orc completed in 250.938ms | |
Best aligned arch: u_orc | |
Best unaligned arch: u_orc | |
RUN_VOLK_TESTS: volk_32f_x2_min_32f(131071,1987) | |
neon completed in 247.01ms | |
generic completed in 260.976ms | |
u_orc completed in 251.263ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32f_x2_multiply_32f(131071,1987) | |
generic completed in 357.257ms | |
neon completed in 248.413ms | |
a_generic completed in 248.09ms | |
u_orc completed in 251.436ms | |
Best aligned arch: a_generic | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32f_s32f_normalize(131071,1987) | |
generic completed in 172.807ms | |
u_orc completed in 171.261ms | |
Best aligned arch: u_orc | |
Best unaligned arch: u_orc | |
RUN_VOLK_TESTS: volk_32f_s32f_power_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_sqrt_32f(131071,1987) | |
neon completed in 225.484ms | |
generic completed in 7176.23ms | |
u_orc completed in 1390.58ms | |
offset 1 in1: 0.44071 in2: 0.439453 | |
offset 2 in1: 0.95402 in2: 0.949219 | |
offset 3 in1: 0.893398 in2: 0.892578 | |
offset 4 in1: 0.673432 in2: 0.671875 | |
offset 5 in1: 0.12039 in2: 0.120117 | |
offset 6 in1: 0.953849 in2: 0.949219 | |
offset 10 in1: 0.468671 in2: 0.467773 | |
offset 15 in1: 0.244115 in2: 0.243652 | |
offset 16 in1: 0.807306 in2: 0.806641 | |
offset 17 in1: 0.677051 in2: 0.675781 | |
volk_32f_sqrt_32f: fail on arch neon | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32f_s32f_stddev_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_stddev_and_mean_32f_x2(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_32f_x2_subtract_32f(131071,1987) | |
generic completed in 272.208ms | |
neon completed in 247.17ms | |
u_orc completed in 295.989ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32f_x3_sum_of_poly_32f(131071,1987) | |
generic completed in 2324.72ms | |
a_neon completed in 1790.53ms | |
neonvert completed in 872.13ms | |
offset 0 in1: -25831.4 in2: -25753.4 | |
volk_32f_x3_sum_of_poly_32f: fail on arch a_neon | |
offset 0 in1: -25831.4 in2: -25795.2 | |
volk_32f_x3_sum_of_poly_32f: fail on arch neonvert | |
Best aligned arch: neonvert | |
Best unaligned arch: neonvert | |
RUN_VOLK_TESTS: volk_32i_x2_and_32i(131071,1987) | |
neon completed in 243.006ms | |
generic completed in 245.144ms | |
u_orc completed in 265.12ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32i_s32f_convert_32f(131071,1987) | |
generic completed in 210.385ms | |
a_generic completed in 228.831ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32i_x2_or_32i(131071,1987) | |
neon completed in 256.584ms | |
generic completed in 315.366ms | |
u_orc completed in 248.808ms | |
Best aligned arch: u_orc | |
Best unaligned arch: u_orc | |
RUN_VOLK_TESTS: volk_32f_x2_dot_prod_16i(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_64f_convert_32f(131071,1987) | |
generic completed in 549.244ms | |
a_generic completed in 505.344ms | |
Best aligned arch: a_generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_64f_x2_max_64f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_64f_x2_min_64f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_8ic_deinterleave_16i_x2(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_8ic_s32f_deinterleave_32f_x2(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_8ic_deinterleave_real_16i(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_8ic_s32f_deinterleave_real_32f(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_8ic_deinterleave_real_8i(131071,1987) | |
generic completed in 63.716ms | |
neon completed in 69.744ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_8ic_x2_multiply_conjugate_16ic(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_8ic_x2_s32f_multiply_conjugate_32fc(131071,1987) | |
no architectures to test | |
RUN_VOLK_TESTS: volk_8i_convert_16i(131071,1987) | |
generic completed in 100.98ms | |
a_generic completed in 104.965ms | |
neon completed in 104.435ms | |
u_orc completed in 105.818ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_8i_s32f_convert_32f(131071,1987) | |
generic completed in 262.982ms | |
a_generic completed in 280.022ms | |
u_orc completed in 657.695ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32fc_s32fc_multiply_32fc(131071,1987) | |
generic completed in 2525.31ms | |
neon completed in 748.716ms | |
a_generic completed in 2522.68ms | |
offset 0 in1: 243.314 + -325.266j in2: 20.686 + 215.755j | |
offset 1 in1: 204.205 + -243.1j in2: -143.122 + -33.1291j | |
offset 2 in1: -183.673 + -47.1018j in2: 156.971 + -239.169j | |
offset 3 in1: -104.442 + -153.784j in2: -0 + -0j | |
offset 5 in1: -189.456 + -129.959j in2: -9.76803e-07 + -9.76803e-07j | |
offset 7 in1: -69.2244 + -144.518j in2: -0 + -0j | |
offset 9 in1: 303.751 + 125.22j in2: 1.31184e-06 + 1.31184e-06j | |
offset 11 in1: -212.632 + -230.374j in2: -0 + -0j | |
offset 13 in1: -213.532 + 290.173j in2: 2.34377e-07 + 2.34377e-07j | |
offset 15 in1: 14.0298 + -126.853j in2: 0 + 0j | |
volk_32fc_s32fc_multiply_32fc: fail on arch neon | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32f_s32f_multiply_32f(131071,1987) | |
generic completed in 189.442ms | |
u_neon completed in 211.161ms | |
a_generic completed in 190.583ms | |
u_orc completed in 192.196ms | |
Best aligned arch: generic | |
Best unaligned arch: generic | |
RUN_VOLK_TESTS: volk_32f_binary_slicer_32i(131071,1987) | |
generic completed in 794.104ms | |
generic_branchless completed in 774.649ms | |
Best aligned arch: generic_branchless | |
Best unaligned arch: generic_branchless | |
RUN_VOLK_TESTS: volk_32f_binary_slicer_8i(131071,1987) | |
generic completed in 749.028ms | |
generic_branchless completed in 734.127ms | |
neon completed in 254.498ms | |
Best aligned arch: neon | |
Best unaligned arch: neon | |
RUN_VOLK_TESTS: volk_32f_tanh_32f(131071,1987) | |
generic completed in 22850.7ms | |
series completed in 3251.31ms | |
Best aligned arch: series | |
Best unaligned arch: series | |
Creating "/home/odroid/.volk"... | |
Writing "/home/odroid/.volk/volk_config"... |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment