Last active
December 11, 2016 03:57
-
-
Save simcop2387/32c8fb863403ee714227afe0ee3dd637 to your computer and use it in GitHub Desktop.
running some fft code, will edit with updates since running takes a bit
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
| cpu info: (HT enabled) | |
| model name : Intel(R) Core(TM) i7-3840QM CPU @ 2.80GHz | |
| -> % ./compile.sh | |
| gcc -O1 -o fft-test-fft-portable.c-O1 fft-test.c fft-portable.c -lm -march=native | |
| gcc -O1 -o fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O1 fft-test.c fft-x8664-avx-aux.c fft-x8664-avx.s -lm -march=native | |
| gcc -O1 -o fft-test-fft-fast-reverse.c-O1 fft-test.c fft-fast-reverse.c -lm -march=native | |
| gcc -O2 -o fft-test-fft-portable.c-O2 fft-test.c fft-portable.c -lm -march=native | |
| gcc -O2 -o fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O2 fft-test.c fft-x8664-avx-aux.c fft-x8664-avx.s -lm -march=native | |
| gcc -O2 -o fft-test-fft-fast-reverse.c-O2 fft-test.c fft-fast-reverse.c -lm -march=native | |
| gcc -O3 -o fft-test-fft-portable.c-O3 fft-test.c fft-portable.c -lm -march=native | |
| gcc -O3 -o fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O3 fft-test.c fft-x8664-avx-aux.c fft-x8664-avx.s -lm -march=native | |
| gcc -O3 -o fft-test-fft-fast-reverse.c-O3 fft-test.c fft-fast-reverse.c -lm -march=native | |
| gcc -O1 -o fft-test-fft-portable.c-O1 fft-test.c fft-portable.c -lm -ffast-math -march=native | |
| gcc -O1 -o fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O1 fft-test.c fft-x8664-avx-aux.c fft-x8664-avx.s -lm -ffast-math -march=native | |
| gcc -O1 -o fft-test-fft-fast-reverse.c-O1 fft-test.c fft-fast-reverse.c -lm -ffast-math -march=native | |
| gcc -O2 -o fft-test-fft-portable.c-O2 fft-test.c fft-portable.c -lm -ffast-math -march=native | |
| gcc -O2 -o fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O2 fft-test.c fft-x8664-avx-aux.c fft-x8664-avx.s -lm -ffast-math -march=native | |
| gcc -O2 -o fft-test-fft-fast-reverse.c-O2 fft-test.c fft-fast-reverse.c -lm -ffast-math -march=native | |
| gcc -O3 -o fft-test-fft-portable.c-O3 fft-test.c fft-portable.c -lm -ffast-math -march=native | |
| gcc -O3 -o fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O3 fft-test.c fft-x8664-avx-aux.c fft-x8664-avx.s -lm -ffast-math -march=native | |
| gcc -O3 -o fft-test-fft-fast-reverse.c-O3 fft-test.c fft-fast-reverse.c -lm -ffast-math -march=native | |
| ryan@pegasus [05:25:39] [~/tmp/ffttest] [master *] ∞ | |
| -> % ls | |
| compile.sh fft-test-fft-fast-reverse.c-O1 fft-test-fft-portable.c-O1 fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O1 fft-x8664-avx-aux.c | |
| fft-fast-reverse.c fft-test-fft-fast-reverse.c-O1-ffast-math fft-test-fft-portable.c-O1-ffast-math fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O1-ffast-math fft-x8664-avx.s | |
| fft.h fft-test-fft-fast-reverse.c-O2 fft-test-fft-portable.c-O2 fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O2 | |
| fft-model-of-x8664-avx.c fft-test-fft-fast-reverse.c-O2-ffast-math fft-test-fft-portable.c-O2-ffast-math fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O2-ffast-math | |
| fft-portable.c fft-test-fft-fast-reverse.c-O3 fft-test-fft-portable.c-O3 fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O3 | |
| fft-test.c fft-test-fft-fast-reverse.c-O3-ffast-math fft-test-fft-portable.c-O3-ffast-math fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O3-ffast-math | |
| ryan@pegasus [05:25:41] [~/tmp/ffttest] [master *] ∞ | |
| -> % for i in fft-test-*; do echo $i; ./"$i"; done | |
| fft-test-fft-fast-reverse.c-O1 | |
| Self-test passed | |
| Size Time per FFT (ns) | |
| 4 min=33 mean=33 sd=0.51% | |
| 8 min=63 mean=64 sd=0.40% | |
| 16 min=124 mean=127 sd=4.07% | |
| 32 min=255 mean=260 sd=1.55% | |
| 64 min=547 mean=548 sd=0.40% | |
| 128 min=1175 mean=1184 sd=0.40% | |
| 256 min=2688 mean=2760 sd=4.41% | |
| 512 min=6439 mean=6560 sd=1.23% | |
| 1024 min=14559 mean=14824 sd=1.52% | |
| 2048 min=33516 mean=33967 sd=0.89% | |
| 4096 min=84175 mean=85336 sd=1.45% | |
| 8192 min=203415 mean=204443 sd=0.45% | |
| 16384 min=450769 mean=452903 sd=0.30% | |
| 32768 min=1085327 mean=1090649 sd=0.37% | |
| 65536 min=2521460 mean=2544502 sd=1.42% | |
| 131072 min=5449538 mean=5481806 sd=0.31% | |
| 262144 min=12632371 mean=12734313 sd=0.60% | |
| 524288 min=48876464 mean=49182393 sd=0.45% | |
| 1048576 min=137156168 mean=143718204 sd=4.84% | |
| 2097152 min=329195512 mean=341430551 sd=3.09% | |
| 4194304 min=770286820 mean=779868243 sd=1.20% | |
| 8388608 min=1714753804 mean=1744676667 sd=1.19% | |
| 16777216 min=3698690960 mean=3726221257 sd=0.46% | |
| 33554432 min=8686518102 mean=8948786357 sd=2.78% | |
| 67108864 min=19508434801 mean=20031424657 sd=1.41% | |
| fft-test-fft-fast-reverse.c-O1-ffast-math | |
| Self-test passed | |
| Size Time per FFT (ns) | |
| 4 min=32 mean=32 sd=3.10% | |
| 8 min=63 mean=64 sd=0.96% | |
| 16 min=125 mean=126 sd=0.83% | |
| 32 min=255 mean=257 sd=0.55% | |
| 64 min=549 mean=558 sd=0.73% | |
| 128 min=1185 mean=1237 sd=4.49% | |
| 256 min=2659 mean=2746 sd=2.06% | |
| 512 min=6536 mean=6755 sd=3.10% | |
| 1024 min=14685 mean=14820 sd=0.68% | |
| 2048 min=33361 mean=33579 sd=0.36% | |
| 4096 min=83192 mean=84005 sd=0.52% | |
| 8192 min=203026 mean=205558 sd=0.87% | |
| 16384 min=461842 mean=464257 sd=0.51% | |
| 32768 min=1061349 mean=1067589 sd=0.37% | |
| 65536 min=2527941 mean=2539377 sd=0.44% | |
| 131072 min=5486153 mean=5579665 sd=1.97% | |
| 262144 min=12520282 mean=12721374 sd=1.08% | |
| 524288 min=47926482 mean=48992224 sd=1.34% | |
| 1048576 min=125446996 mean=130424607 sd=1.87% | |
| 2097152 min=326062006 mean=331144270 sd=0.94% | |
| 4194304 min=770928941 mean=783470377 sd=1.20% | |
| 8388608 min=1720961150 mean=1738438403 sd=0.81% | |
| 16777216 min=3619071155 mean=3716338192 sd=1.37% | |
| 33554432 min=9351507217 mean=9739494844 sd=1.63% | |
| 67108864 min=20027338992 mean=20999033842 sd=2.71% | |
| fft-test-fft-fast-reverse.c-O2 | |
| Self-test passed | |
| Size Time per FFT (ns) | |
| 4 min=33 mean=33 sd=0.78% | |
| 8 min=64 mean=65 sd=1.04% | |
| 16 min=127 mean=131 sd=3.45% | |
| 32 min=263 mean=265 sd=0.73% | |
| 64 min=554 mean=559 sd=0.63% | |
| 128 min=1205 mean=1215 sd=0.76% | |
| 256 min=2743 mean=2776 sd=1.24% | |
| 512 min=6355 mean=6984 sd=17.21% | |
| 1024 min=14149 mean=14343 sd=1.60% | |
| 2048 min=32398 mean=32643 sd=0.37% | |
| 4096 min=80891 mean=83002 sd=1.38% | |
| 8192 min=200328 mean=204820 sd=0.91% | |
| 16384 min=471322 mean=478540 sd=1.61% | |
| 32768 min=1076839 mean=1102180 sd=1.35% | |
| 65536 min=2495814 mean=2554673 sd=1.83% | |
| 131072 min=5375042 mean=5433872 sd=0.71% | |
| 262144 min=11979172 mean=12162848 sd=1.06% | |
| 524288 min=46814770 mean=47623088 sd=1.71% | |
| 1048576 min=127624421 mean=131521130 sd=1.73% | |
| 2097152 min=330593540 mean=332444874 sd=0.39% | |
| 4194304 min=779137558 mean=783693574 sd=0.63% | |
| 8388608 min=1672096117 mean=1689973187 sd=1.53% | |
| 16777216 min=3783191272 mean=3817596426 sd=0.84% | |
| 33554432 min=9002983278 mean=9038537507 sd=0.63% | |
| 67108864 min=19766120945 mean=20011697860 sd=1.41% | |
| fft-test-fft-fast-reverse.c-O2-ffast-math | |
| Self-test passed | |
| Size Time per FFT (ns) | |
| 4 min=32 mean=33 sd=0.33% | |
| 8 min=64 mean=65 sd=1.11% | |
| 16 min=126 mean=128 sd=3.28% | |
| 32 min=263 mean=264 sd=0.47% | |
| 64 min=555 mean=560 sd=1.29% | |
| 128 min=1199 mean=1202 sd=0.24% | |
| 256 min=2703 mean=2715 sd=0.29% | |
| 512 min=6284 mean=6377 sd=2.09% | |
| 1024 min=13935 mean=14033 sd=0.41% | |
| 2048 min=32048 mean=32221 sd=0.32% | |
| 4096 min=80721 mean=81661 sd=1.45% | |
| 8192 min=196526 mean=197526 sd=0.48% | |
| 16384 min=443216 mean=448448 sd=0.56% | |
| 32768 min=1063794 mean=1071064 sd=0.31% | |
| 65536 min=2456222 mean=2477332 sd=0.50% | |
| 131072 min=5275760 mean=5315918 sd=0.65% | |
| 262144 min=12107042 mean=12237415 sd=0.65% | |
| 524288 min=47373218 mean=48458316 sd=2.29% | |
| 1048576 min=135656856 mean=138771699 sd=1.85% | |
| 2097152 min=316536908 mean=324781964 sd=1.61% | |
| 4194304 min=783505615 mean=790194482 sd=0.61% | |
| 8388608 min=1709911655 mean=1734177075 sd=1.43% | |
| 16777216 min=3849116216 mean=3903447563 sd=0.88% | |
| 33554432 min=9551807506 mean=9688232278 sd=0.89% | |
| 67108864 min=21115700012 mean=21447073175 sd=0.94% | |
| fft-test-fft-fast-reverse.c-O3 | |
| Self-test passed | |
| Size Time per FFT (ns) | |
| 4 min=32 mean=33 sd=1.61% | |
| 8 min=64 mean=67 sd=4.38% | |
| 16 min=128 mean=129 sd=0.43% | |
| 32 min=261 mean=264 sd=0.80% | |
| 64 min=553 mean=560 sd=0.62% | |
| 128 min=1209 mean=1219 sd=0.77% | |
| 256 min=2723 mean=2758 sd=1.26% | |
| 512 min=6301 mean=6914 sd=10.62% | |
| 1024 min=14147 mean=14273 sd=0.69% | |
| 2048 min=31950 mean=32078 sd=0.34% | |
| 4096 min=80297 mean=80966 sd=0.36% | |
| 8192 min=192731 mean=194548 sd=0.77% | |
| 16384 min=435562 mean=438140 sd=0.23% | |
| 32768 min=1054986 mean=1058726 sd=0.29% | |
| 65536 min=2465264 mean=2493980 sd=0.42% | |
| 131072 min=5349606 mean=5419895 sd=2.72% | |
| 262144 min=11888259 mean=12181527 sd=1.88% | |
| 524288 min=46664307 mean=47205191 sd=0.54% | |
| 1048576 min=129513085 mean=131481428 sd=1.11% | |
| 2097152 min=330716476 mean=333448843 sd=0.87% | |
| 4194304 min=776329846 mean=793749046 sd=2.03% | |
| 8388608 min=1788287558 mean=1801021542 sd=0.65% | |
| 16777216 min=3712038163 mean=3773374890 sd=1.94% | |
| 33554432 min=9499434283 mean=9855332309 sd=2.04% | |
| 67108864 min=20449026789 mean=21139111412 sd=2.16% | |
| fft-test-fft-fast-reverse.c-O3-ffast-math | |
| Self-test passed | |
| Size Time per FFT (ns) | |
| 4 min=34 mean=35 sd=5.33% | |
| 8 min=64 mean=64 sd=0.31% | |
| 16 min=125 mean=126 sd=0.33% | |
| 32 min=262 mean=263 sd=0.20% | |
| 64 min=551 mean=554 sd=0.27% | |
| 128 min=1200 mean=1254 sd=7.89% | |
| 256 min=2728 mean=2755 sd=0.66% | |
| 512 min=6314 mean=6361 sd=0.51% | |
| 1024 min=14069 mean=14194 sd=0.75% | |
| 2048 min=31992 mean=32107 sd=0.21% | |
| 4096 min=79786 mean=80281 sd=0.29% | |
| 8192 min=193619 mean=197042 sd=0.92% | |
| 16384 min=445652 mean=449063 sd=0.48% | |
| 32768 min=1042601 mean=1095536 sd=5.55% | |
| 65536 min=2456270 mean=2497578 sd=1.04% | |
| 131072 min=5377907 mean=5455902 sd=1.34% | |
| 262144 min=11911059 mean=12210526 sd=2.30% | |
| 524288 min=47385903 mean=48479036 sd=1.81% | |
| 1048576 min=130848773 mean=132817797 sd=1.17% | |
| 2097152 min=320440721 mean=322104962 sd=0.68% | |
| 4194304 min=767777558 mean=771998215 sd=0.69% | |
| 8388608 min=1703993385 mean=1724462865 sd=1.63% | |
| 16777216 min=3575134162 mean=3612203704 sd=1.04% | |
| 33554432 min=9293039293 mean=9458641813 sd=1.63% | |
| 67108864 min=20093664062 mean=20779339844 sd=2.24% | |
| fft-test-fft-portable.c-O1 | |
| Self-test passed | |
| Size Time per FFT (ns) | |
| 4 min=33 mean=33 sd=0.88% | |
| 8 min=63 mean=64 sd=1.46% | |
| 16 min=126 mean=134 sd=7.85% | |
| 32 min=259 mean=260 sd=0.32% | |
| 64 min=555 mean=560 sd=0.37% | |
| 128 min=1203 mean=1218 sd=2.28% | |
| 256 min=2721 mean=2728 sd=0.15% | |
| 512 min=6459 mean=6879 sd=7.33% | |
| 1024 min=15223 mean=18242 sd=8.82% | |
| 2048 min=33390 mean=35529 sd=5.77% | |
| 4096 min=85012 mean=87692 sd=2.60% | |
| 8192 min=208326 mean=213258 sd=2.11% | |
| 16384 min=456313 mean=462664 sd=1.82% | |
| 32768 min=1106090 mean=1110366 sd=0.32% | |
| 65536 min=2537227 mean=2556189 sd=0.28% | |
| 131072 min=5531075 mean=5598869 sd=0.52% | |
| 262144 min=12739647 mean=12954491 sd=0.79% | |
| 524288 min=49626074 mean=49771418 sd=0.21% | |
| 1048576 min=126092066 mean=129133033 sd=0.98% | |
| 2097152 min=329515588 mean=332574020 sd=0.61% | |
| 4194304 min=803590319 mean=809120005 sd=0.61% | |
| 8388608 min=1732371490 mean=1745769877 sd=0.35% | |
| 16777216 min=3706188958 mean=3754443075 sd=0.98% | |
| 33554432 min=9226044323 mean=9606186306 sd=2.93% | |
| 67108864 min=19981840657 mean=20894473367 sd=2.76% | |
| fft-test-fft-portable.c-O1-ffast-math | |
| Self-test passed | |
| Size Time per FFT (ns) | |
| 4 min=33 mean=33 sd=0.61% | |
| 8 min=64 mean=67 sd=6.93% | |
| 16 min=126 mean=127 sd=0.30% | |
| 32 min=260 mean=261 sd=0.27% | |
| 64 min=562 mean=564 sd=0.23% | |
| 128 min=1226 mean=1234 sd=0.61% | |
| 256 min=2724 mean=2745 sd=0.65% | |
| 512 min=6483 mean=6519 sd=0.39% | |
| 1024 min=14485 mean=14626 sd=0.78% | |
| 2048 min=33637 mean=34157 sd=2.20% | |
| 4096 min=86887 mean=87922 sd=0.97% | |
| 8192 min=205585 mean=207690 sd=1.03% | |
| 16384 min=450643 mean=453683 sd=0.51% | |
| 32768 min=1087247 mean=1095044 sd=0.73% | |
| 65536 min=2528114 mean=2562585 sd=0.91% | |
| 131072 min=5607945 mean=5694001 sd=1.29% | |
| 262144 min=12733404 mean=13558646 sd=6.44% | |
| 524288 min=49519156 mean=50270619 sd=2.05% | |
| 1048576 min=140985020 mean=143076889 sd=0.65% | |
| 2097152 min=329845496 mean=332574982 sd=0.56% | |
| 4194304 min=786666091 mean=793451604 sd=1.11% | |
| 8388608 min=1704163841 mean=1751911575 sd=1.83% | |
| 16777216 min=3730602579 mean=3756672846 sd=0.43% | |
| 33554432 min=9812799097 mean=9983337800 sd=0.77% | |
| 67108864 min=21480264180 mean=21642786494 sd=0.54% | |
| fft-test-fft-portable.c-O2 | |
| Self-test passed | |
| Size Time per FFT (ns) | |
| 4 min=32 mean=32 sd=0.68% | |
| 8 min=63 mean=64 sd=0.35% | |
| 16 min=125 mean=126 sd=0.56% | |
| 32 min=260 mean=263 sd=1.73% | |
| 64 min=546 mean=550 sd=0.48% | |
| 128 min=1183 mean=1189 sd=0.49% | |
| 256 min=2685 mean=2703 sd=0.51% | |
| 512 min=6211 mean=6235 sd=0.31% | |
| 1024 min=13796 mean=13886 sd=0.69% | |
| 2048 min=38069 mean=38280 sd=0.47% | |
| 4096 min=79696 mean=80204 sd=0.55% | |
| 8192 min=193119 mean=195284 sd=1.99% | |
| 16384 min=440551 mean=455068 sd=6.24% | |
| 32768 min=1064527 mean=1070281 sd=0.41% | |
| 65536 min=2470544 mean=2483433 sd=0.38% | |
| 131072 min=5316888 mean=5344487 sd=0.35% | |
| 262144 min=11925276 mean=12060757 sd=0.59% | |
| 524288 min=46074476 mean=46396722 sd=0.63% | |
| 1048576 min=124396636 mean=128481673 sd=2.04% | |
| 2097152 min=312700279 mean=324409812 sd=1.94% | |
| 4194304 min=764645453 mean=784309770 sd=1.44% | |
| 8388608 min=1648134838 mean=1655667357 sd=0.45% | |
| 16777216 min=3627722457 mean=3683716120 sd=1.14% | |
| 33554432 min=9309375153 mean=9574886508 sd=3.04% | |
| 67108864 min=19781142428 mean=19991910873 sd=0.63% | |
| fft-test-fft-portable.c-O2-ffast-math | |
| Self-test passed | |
| Size Time per FFT (ns) | |
| 4 min=33 mean=34 sd=2.35% | |
| 8 min=65 mean=65 sd=2.34% | |
| 16 min=128 mean=128 sd=0.15% | |
| 32 min=265 mean=266 sd=0.12% | |
| 64 min=558 mean=560 sd=0.28% | |
| 128 min=1207 mean=1220 sd=0.82% | |
| 256 min=2719 mean=2744 sd=0.47% | |
| 512 min=6363 mean=6408 sd=0.97% | |
| 1024 min=14204 mean=14363 sd=1.60% | |
| 2048 min=32382 mean=32479 sd=0.21% | |
| 4096 min=81050 mean=81287 sd=0.18% | |
| 8192 min=196286 mean=196660 sd=0.11% | |
| 16384 min=447396 mean=447822 sd=0.10% | |
| 32768 min=1070570 mean=1077543 sd=0.52% | |
| 65536 min=2482243 mean=2487836 sd=0.17% | |
| 131072 min=5404039 mean=5422047 sd=0.18% | |
| 262144 min=12962883 mean=13193971 sd=1.31% | |
| 524288 min=47942510 mean=48236116 sd=0.41% | |
| 1048576 min=122287532 mean=122990488 sd=0.48% | |
| 2097152 min=319009829 mean=320311138 sd=0.26% | |
| 4194304 min=774144789 mean=787387485 sd=1.96% | |
| 8388608 min=1619068874 mean=1626296720 sd=0.27% | |
| 16777216 min=3654319919 mean=3669755180 sd=0.43% | |
| 33554432 min=9274670681 mean=9396478072 sd=1.24% | |
| 67108864 min=19826230212 mean=20560723772 sd=2.47% | |
| fft-test-fft-portable.c-O3 | |
| Self-test passed | |
| Size Time per FFT (ns) | |
| 4 min=33 mean=34 sd=1.52% | |
| 8 min=65 mean=65 sd=0.51% | |
| 16 min=128 mean=131 sd=3.33% | |
| 32 min=265 mean=266 sd=0.24% | |
| 64 min=559 mean=567 sd=2.58% | |
| 128 min=1218 mean=1229 sd=1.47% | |
| 256 min=2753 mean=2761 sd=0.21% | |
| 512 min=6375 mean=6387 sd=0.16% | |
| 1024 min=14181 mean=14245 sd=0.26% | |
| 2048 min=32440 mean=32513 sd=0.15% | |
| 4096 min=80605 mean=81881 sd=1.20% | |
| 8192 min=195834 mean=199943 sd=4.14% | |
| 16384 min=443070 mean=447856 sd=1.38% | |
| 32768 min=1081364 mean=1093407 sd=0.67% | |
| 65536 min=2441118 mean=2468687 sd=0.87% | |
| 131072 min=5309112 mean=5335444 sd=0.35% | |
| 262144 min=12069155 mean=12563809 sd=2.25% | |
| 524288 min=46432918 mean=47466513 sd=1.19% | |
| 1048576 min=126822411 mean=129339033 sd=1.66% | |
| 2097152 min=319883807 mean=325519758 sd=1.77% | |
| 4194304 min=773366467 mean=787231627 sd=1.70% | |
| 8388608 min=1710091508 mean=1752380782 sd=1.75% | |
| 16777216 min=3723426064 mean=3770146226 sd=1.56% | |
| 33554432 min=8740544068 mean=8831110774 sd=1.02% | |
| 67108864 min=19886327183 mean=20314730926 sd=1.50% | |
| fft-test-fft-portable.c-O3-ffast-math | |
| Self-test passed | |
| Size Time per FFT (ns) | |
| 4 min=33 mean=33 sd=1.13% | |
| 8 min=65 mean=65 sd=0.08% | |
| 16 min=128 mean=129 sd=0.36% | |
| 32 min=267 mean=267 sd=0.22% | |
| 64 min=559 mean=568 sd=2.86% | |
| 128 min=1216 mean=1220 sd=0.19% | |
| 256 min=2743 mean=2779 sd=2.28% | |
| 512 min=6323 mean=6366 sd=0.40% | |
| 1024 min=14153 mean=14282 sd=1.01% | |
| 2048 min=32189 mean=32315 sd=0.24% | |
| 4096 min=81896 mean=82190 sd=0.47% | |
| 8192 min=196323 mean=197921 sd=0.73% | |
| 16384 min=451136 mean=461474 sd=4.23% | |
| 32768 min=1063786 mean=1071010 sd=0.68% | |
| 65536 min=2485735 mean=2504352 sd=0.42% | |
| 131072 min=5430607 mean=5478230 sd=0.82% | |
| 262144 min=12213142 mean=12492096 sd=1.51% | |
| 524288 min=48459677 mean=49558897 sd=1.85% | |
| 1048576 min=125758242 mean=129102183 sd=2.69% | |
| 2097152 min=327173785 mean=340811631 sd=2.73% | |
| 4194304 min=781606514 mean=795803339 sd=2.35% | |
| 8388608 min=1697543193 mean=1723655378 sd=1.10% | |
| 16777216 min=3613735354 mean=3707026661 sd=2.12% | |
| 33554432 min=9487643321 mean=9755146803 sd=1.90% | |
| 67108864 min=20500538843 mean=21433058687 sd=1.55% | |
| [ED: These all segfaulted, not sure why. I'll investigate later but i suspect there's something weird with the asm and GCC-6] | |
| fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O1 | |
| fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O1-ffast-math | |
| fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O2 | |
| fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O2-ffast-math | |
| fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O3 | |
| fft-test-fft-x8664-avx-aux.c fft-x8664-avx.s-O3-ffast-math | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment