To: benchfft@theory.lcs.mit.edu Subject: SUBMIT ------------------- @@SUBMIT@@ @ submitter = David Palmer @ submitter email = dmpalmer (at) clark (period) net @ submitter organization = NONE @ computer manufacturer = Apple @ computer model = Power Mac G3 266 Tower @ CPU manufacturer = Motorola @ CPU model = PowerPC 750 @ CPU speed = 266 MHz @ RAM = 32 MB @ L2 cache size = 512 kB @ operating system = MacOS 8 @ C compiler = Metrowerks CodeWarrior Pro 2 @ C compiler flags = all @ Fortran compiler = NONE @ Fortran compiler flags = NONE @ remarks = All extensions off (shift-key startup) @ FFTW version = FFTW V1.2 @ floating-point precision = double @ floating-point size = 8 bytes ------------------------------------------------------ @@@@ bench.1d.p2.log Benchmarking for sizes: 2 (0.000228882 MB) 4 (0.000534058 MB) 8 (0.000839233 MB) 16 (0.00164795 MB) 32 (0.00297546 MB) 64 (0.00616455 MB) 128 (0.0119019 MB) 256 (0.0238037 MB) 512 (0.0476074 MB) 1024 (0.0939941 MB) 2048 (0.189575 MB) 4096 (0.37915 MB) 8192 (0.765991 MB) 16384 (1.51184 MB) 32768 (3.02368 MB) 65536 (6.09973 MB) 131072 (12.1995 MB) Maximum array size = 144144 Benchmarking FFTs: 0. Arndt DIF 1. Arndt DIT 2. Arndt Split-Radix 3. Arndt 4-step 4. Beauregard 5. Bergland 6. CWP (min N) 7. CWP (best N) 8. Edelblute 9. FFTPACK (f2c) 10. FFTW 11. FFTW_ESTIMATE 12. Frigo-old 13. Green 14. GSL 15. GSL DIT 16. GSL DIF 17. Krukar 18. Mayer (Buneman) 19. Mayer (simple) 20. Mayer (lookup) 21. NAPACK (f2c) 22. Nielsen 23. NR (C) 24. Ooura (C) 25. QFT 26. Ransom 27. Singleton (f2c) 28. Temperton (f2c) 29. Valkenburg Computing normalized averages (30 transforms). Benchmarking for array size = 2 (power of 2): 0. Arndt DIF: elapsed time t=1.70386 s, 4194304 iters, t-(init.)=1.46725 s t(norm)=0.17491, mflops=28.5862 (err=1.7e-17) 1. Arndt DIT: elapsed time t=1.83005 s, 4194304 iters, t-(init.)=1.59351 s t(norm)=0.189961, mflops=26.3211 (err=1.7e-17) 2. Arndt Split-Radix: elapsed time t=1.31154 s, 2097152 iters, t-(init.)=1.19349 s t(norm)=0.284551, mflops=17.5715 (err=1.7e-17) 3. Arndt 4-step: elapsed time t=1.01995 s, 131072 iters, t-(init.)=1.0125 s t(norm)=3.86239, mflops=1.29453 (err=1.7e-17) 4. Beauregard: elapsed time t=1.27102 s, 524288 iters, t-(init.)=1.2414 s t(norm)=1.18389, mflops=4.22336 (err=1.7e-17) 5. Bergland: elapsed time t=1.73058 s, 1048576 iters, t-(init.)=1.67146 s t(norm)=0.797014, mflops=6.27342 (err=1.7e-17) 6. CWP (min N): elapsed time t=1.09439 s, 524288 iters, t-(init.)=1.06479 s t(norm)=1.01547, mflops=4.92384 7. CWP (best N) (N=3): elapsed time t=1.1694 s, 524288 iters, t-(init.)=1.13191 s t(norm)=1.07948, mflops=4.63188 8. Skipping fft (Edelblute can't handle N <= 2). 9. FFTPACK (f2c): elapsed time t=1.46731 s, 1048576 iters, t-(init.)=1.40819 s t(norm)=0.671479, mflops=7.44625 (err=1.7e-17) FFTW_MEASURE plan: (cost = 3.649750e-07) FFTW_NOTW 2 10. FFTW: elapsed time t=1.62477 s, 4194304 iters, t-(init.)=1.38813 s t(norm)=0.165478, mflops=30.2156 (err=1.7e-17) FFTW_ESTIMATE plan: (cost = 1.820000e+02) FFTW_NOTW 2 11. FFTW_ESTIMATE: elapsed time t=1.60915 s, 4194304 iters, t-(init.)=1.37252 s t(norm)=0.163617, mflops=30.5592 (err=1.7e-17) 12. Frigo-old: elapsed time t=1.13578 s, 4194304 iters, t-(init.)=0.899089 s t(norm)=0.10718, mflops=46.6506 (err=1.7e-17) 13. Skipping fft (Green can't handle this size.). 14. GSL: elapsed time t=1.84372 s, 2097152 iters, t-(init.)=1.72543 s t(norm)=0.411375, mflops=12.1544 (err=1.7e-17) 15. GSL DIT: elapsed time t=1.46369 s, 1048576 iters, t-(init.)=1.40452 s t(norm)=0.669729, mflops=7.4657 (err=1.7e-17) 16. GSL DIF: elapsed time t=1.54278 s, 1048576 iters, t-(init.)=1.48362 s t(norm)=0.707446, mflops=7.06768 (err=1.7e-17) 17. Krukar: elapsed time t=1.73535 s, 4194304 iters, t-(init.)=1.49853 s t(norm)=0.178639, mflops=27.9894 (err=1.7e-17) 18. Skipping fft (Mayer can't handle N <= 2). 19. Skipping fft (Mayer can't handle N <= 2). 20. Skipping fft (Mayer can't handle N <= 2). 21. NAPACK (f2c): elapsed time t=1.75703 s, 524288 iters, t-(init.)=1.72744 s t(norm)=1.64741, mflops=3.03506 (err=1.7e-17) 22. Nielsen: elapsed time t=1.20837 s, 262144 iters, t-(init.)=1.19356 s t(norm)=2.27654, mflops=2.19631 (err=1.7e-17) 23. NR (C): elapsed time t=1.37247 s, 1048576 iters, t-(init.)=1.31327 s t(norm)=0.626217, mflops=7.98445 (err=1.7e-17) 24. Ooura (C): elapsed time t=1.98771 s, 4194304 iters, t-(init.)=1.75116 s t(norm)=0.208755, mflops=23.9516 (err=1.7e-17) 25. Skipping fft (QFT requires N >= 16). 26. Skipping fft (Ransom doesn't work for N=2). 27. Singleton (f2c): elapsed time t=1.8576 s, 1048576 iters, t-(init.)=1.7984 s t(norm)=0.857544, mflops=5.8306 (err=1.7e-17) 28. Temperton (f2c): elapsed time t=1.65513 s, 524288 iters, t-(init.)=1.62559 s t(norm)=1.55029, mflops=3.22521 (err=1.7e-17) 29. Valkenburg: elapsed time t=1.41331 s, 1048576 iters, t-(init.)=1.35419 s t(norm)=0.645727, mflops=7.74321 (err=1.7e-17) Top mflops for N=2 = 46.6506 Normalized results and averages for N=2: fft 0: mflops = 28.5862 (norm. = 0.612772), norm. avg. (of 1) = 0.612772 fft 1: mflops = 26.3211 (norm. = 0.564219), norm. avg. (of 1) = 0.564219 fft 2: mflops = 17.5715 (norm. = 0.376663), norm. avg. (of 1) = 0.376663 fft 3: mflops = 1.29453 (norm. = 0.0277496), norm. avg. (of 1) = 0.0277496 fft 4: mflops = 4.22336 (norm. = 0.0905318), norm. avg. (of 1) = 0.0905318 fft 5: mflops = 6.27342 (norm. = 0.134477), norm. avg. (of 1) = 0.134477 fft 6: mflops = 4.92384 (norm. = 0.105547), norm. avg. (of 1) = 0.105547 fft 7: mflops = 4.63188 (norm. = 0.0992887), norm. avg. (of 1) = 0.0992887 fft 8: mflops = -1 (norm. = -0.021436), norm. avg. (of 0) = -1 fft 9: mflops = 7.44625 (norm. = 0.159618), norm. avg. (of 1) = 0.159618 fft 10: mflops = 30.2156 (norm. = 0.6477), norm. avg. (of 1) = 0.6477 fft 11: mflops = 30.5592 (norm. = 0.655066), norm. avg. (of 1) = 0.655066 fft 12: mflops = 46.6506 (norm. = 1), norm. avg. (of 1) = 1 fft 13: mflops = -1 (norm. = -0.021436), norm. avg. (of 0) = -1 fft 14: mflops = 12.1544 (norm. = 0.26054), norm. avg. (of 1) = 0.26054 fft 15: mflops = 7.4657 (norm. = 0.160034), norm. avg. (of 1) = 0.160034 fft 16: mflops = 7.06768 (norm. = 0.151502), norm. avg. (of 1) = 0.151502 fft 17: mflops = 27.9894 (norm. = 0.59998), norm. avg. (of 1) = 0.59998 fft 18: mflops = -1 (norm. = -0.021436), norm. avg. (of 0) = -1 fft 19: mflops = -1 (norm. = -0.021436), norm. avg. (of 0) = -1 fft 20: mflops = -1 (norm. = -0.021436), norm. avg. (of 0) = -1 fft 21: mflops = 3.03506 (norm. = 0.0650595), norm. avg. (of 1) = 0.0650595 fft 22: mflops = 2.19631 (norm. = 0.0470801), norm. avg. (of 1) = 0.0470801 fft 23: mflops = 7.98445 (norm. = 0.171154), norm. avg. (of 1) = 0.171154 fft 24: mflops = 23.9516 (norm. = 0.513425), norm. avg. (of 1) = 0.513425 fft 25: mflops = -1 (norm. = -0.021436), norm. avg. (of 0) = -1 fft 26: mflops = -1 (norm. = -0.021436), norm. avg. (of 0) = -1 fft 27: mflops = 5.8306 (norm. = 0.124985), norm. avg. (of 1) = 0.124985 fft 28: mflops = 3.22521 (norm. = 0.0691354), norm. avg. (of 1) = 0.0691354 fft 29: mflops = 7.74321 (norm. = 0.165983), norm. avg. (of 1) = 0.165983 Benchmarking for array size = 4 (power of 2): 0. Arndt DIF: elapsed time t=1.44343 s, 2097152 iters, t-(init.)=1.26205 s t(norm)=0.0752238, mflops=66.4683 (err=1.3e-16) 1. Arndt DIT: elapsed time t=1.51443 s, 2097152 iters, t-(init.)=1.33261 s t(norm)=0.0794295, mflops=62.9489 (err=1.3e-16) 2. Arndt Split-Radix: elapsed time t=1.64858 s, 1048576 iters, t-(init.)=1.5579 s t(norm)=0.185716, mflops=26.9228 (err=1.3e-16) 3. Arndt 4-step: elapsed time t=1.93389 s, 262144 iters, t-(init.)=1.91121 s t(norm)=0.911335, mflops=5.48645 (err=1.3e-16) 4. Beauregard: elapsed time t=1.1317 s, 262144 iters, t-(init.)=1.10902 s t(norm)=0.528821, mflops=9.455 (err=5.3e-17) 5. Bergland: elapsed time t=1.97968 s, 1048576 iters, t-(init.)=1.88903 s t(norm)=0.22519, mflops=22.2035 (err=5.3e-17) 6. CWP (min N): elapsed time t=1.17531 s, 524288 iters, t-(init.)=1.12993 s t(norm)=0.269395, mflops=18.5601 7. CWP (best N) (N=15): elapsed time t=1.27203 s, 262144 iters, t-(init.)=1.20584 s t(norm)=0.57499, mflops=8.6958 8. Edelblute: elapsed time t=1.76081 s, 1048576 iters, t-(init.)=1.67013 s t(norm)=0.199095, mflops=25.1136 (err=1.3e-16) 9. FFTPACK (f2c): elapsed time t=1.14766 s, 524288 iters, t-(init.)=1.1023 s t(norm)=0.262809, mflops=19.0252 (err=5.3e-17) FFTW_MEASURE plan: (cost = 4.850693e-07) FFTW_NOTW 4 10. FFTW: elapsed time t=1.08061 s, 2097152 iters, t-(init.)=0.899253 s t(norm)=0.0535997, mflops=93.2842 (err=5.3e-17) FFTW_ESTIMATE plan: (cost = 3.176000e+02) FFTW_NOTW 4 11. FFTW_ESTIMATE: elapsed time t=1.07271 s, 2097152 iters, t-(init.)=0.891319 s t(norm)=0.0531268, mflops=94.1145 (err=5.3e-17) 12. Frigo-old: elapsed time t=1.59329 s, 4194304 iters, t-(init.)=1.23034 s t(norm)=0.036667, mflops=136.362 (err=5.3e-17) 13. Skipping fft (Green can't handle this size.). 14. GSL: elapsed time t=1.42361 s, 1048576 iters, t-(init.)=1.33288 s t(norm)=0.158891, mflops=31.4681 (err=5.3e-17) 15. GSL DIT: elapsed time t=1.48245 s, 524288 iters, t-(init.)=1.43706 s t(norm)=0.342622, mflops=14.5933 (err=6.4e-17) 16. GSL DIF: elapsed time t=1.53233 s, 524288 iters, t-(init.)=1.48698 s t(norm)=0.354523, mflops=14.1035 (err=6.4e-17) 17. Krukar: elapsed time t=1.32534 s, 2097152 iters, t-(init.)=1.14394 s t(norm)=0.0681842, mflops=73.3308 (err=5.3e-17) 18. Mayer (Buneman): elapsed time t=1.32386 s, 1048576 iters, t-(init.)=1.2331 s t(norm)=0.146997, mflops=34.0143 (err=1.3e-16) 19. Mayer (simple): elapsed time t=1.24501 s, 1048576 iters, t-(init.)=1.15433 s t(norm)=0.137606, mflops=36.3355 20. Mayer (lookup): elapsed time t=1.39234 s, 1048576 iters, t-(init.)=1.30153 s t(norm)=0.155155, mflops=32.2259 (err=1.3e-16) 21. NAPACK (f2c): elapsed time t=1.56524 s, 262144 iters, t-(init.)=1.54254 s t(norm)=0.735541, mflops=6.79772 (err=5.3e-17) 22. Nielsen: elapsed time t=1.31341 s, 262144 iters, t-(init.)=1.29073 s t(norm)=0.61547, mflops=8.12387 (err=1.3e-16) 23. NR (C): elapsed time t=1.44954 s, 524288 iters, t-(init.)=1.40419 s t(norm)=0.334784, mflops=14.935 (err=6.4e-17) 24. Ooura (C): elapsed time t=1.76197 s, 2097152 iters, t-(init.)=1.5805 s t(norm)=0.0942052, mflops=53.0756 (err=5.3e-17) 25. Skipping fft (QFT requires N >= 16). 26. Ransom: elapsed time t=1.11021 s, 131072 iters, t-(init.)=1.09884 s t(norm)=1.04794, mflops=4.77127 (err=2.4e-16) 27. Singleton (f2c): elapsed time t=1.09048 s, 524288 iters, t-(init.)=1.04504 s t(norm)=0.249158, mflops=20.0676 (err=5.3e-17) 28. Temperton (f2c): elapsed time t=1.05261 s, 262144 iters, t-(init.)=1.02993 s t(norm)=0.491109, mflops=10.181 (err=5.3e-17) 29. Valkenburg: elapsed time t=1.30731 s, 262144 iters, t-(init.)=1.28463 s t(norm)=0.61256, mflops=8.16247 (err=5.3e-17) Top mflops for N=4 = 136.362 Normalized results and averages for N=4: fft 0: mflops = 66.4683 (norm. = 0.487439), norm. avg. (of 2) = 0.550105 fft 1: mflops = 62.9489 (norm. = 0.46163), norm. avg. (of 2) = 0.512924 fft 2: mflops = 26.9228 (norm. = 0.197436), norm. avg. (of 2) = 0.287049 fft 3: mflops = 5.48645 (norm. = 0.0402344), norm. avg. (of 2) = 0.033992 fft 4: mflops = 9.455 (norm. = 0.0693374), norm. avg. (of 2) = 0.0799346 fft 5: mflops = 22.2035 (norm. = 0.162827), norm. avg. (of 2) = 0.148652 fft 6: mflops = 18.5601 (norm. = 0.136109), norm. avg. (of 2) = 0.120828 fft 7: mflops = 8.6958 (norm. = 0.0637698), norm. avg. (of 2) = 0.0815293 fft 8: mflops = 25.1136 (norm. = 0.184168), norm. avg. (of 1) = 0.184168 fft 9: mflops = 19.0252 (norm. = 0.13952), norm. avg. (of 2) = 0.149569 fft 10: mflops = 93.2842 (norm. = 0.684091), norm. avg. (of 2) = 0.665895 fft 11: mflops = 94.1145 (norm. = 0.69018), norm. avg. (of 2) = 0.672623 fft 12: mflops = 136.362 (norm. = 1), norm. avg. (of 2) = 1 fft 13: mflops = -1 (norm. = -0.0073334), norm. avg. (of 0) = -1 fft 14: mflops = 31.4681 (norm. = 0.230768), norm. avg. (of 2) = 0.245654 fft 15: mflops = 14.5933 (norm. = 0.107019), norm. avg. (of 2) = 0.133527 fft 16: mflops = 14.1035 (norm. = 0.103426), norm. avg. (of 2) = 0.127464 fft 17: mflops = 73.3308 (norm. = 0.537764), norm. avg. (of 2) = 0.568872 fft 18: mflops = 34.0143 (norm. = 0.249441), norm. avg. (of 1) = 0.249441 fft 19: mflops = 36.3355 (norm. = 0.266463), norm. avg. (of 1) = 0.266463 fft 20: mflops = 32.2259 (norm. = 0.236326), norm. avg. (of 1) = 0.236326 fft 21: mflops = 6.79772 (norm. = 0.0498504), norm. avg. (of 2) = 0.0574549 fft 22: mflops = 8.12387 (norm. = 0.0595756), norm. avg. (of 2) = 0.0533279 fft 23: mflops = 14.935 (norm. = 0.109524), norm. avg. (of 2) = 0.140339 fft 24: mflops = 53.0756 (norm. = 0.389225), norm. avg. (of 2) = 0.451325 fft 25: mflops = -1 (norm. = -0.0073334), norm. avg. (of 0) = -1 fft 26: mflops = 4.77127 (norm. = 0.0349897), norm. avg. (of 1) = 0.0349897 fft 27: mflops = 20.0676 (norm. = 0.147164), norm. avg. (of 2) = 0.136074 fft 28: mflops = 10.181 (norm. = 0.0746616), norm. avg. (of 2) = 0.0718985 fft 29: mflops = 8.16247 (norm. = 0.0598587), norm. avg. (of 2) = 0.112921 Benchmarking for array size = 8 (power of 2): 0. Arndt DIF: elapsed time t=1.40227 s, 1048576 iters, t-(init.)=1.24844 s t(norm)=0.0496084, mflops=100.789 (err=1.1e-16) 1. Arndt DIT: elapsed time t=1.44104 s, 1048576 iters, t-(init.)=1.28726 s t(norm)=0.0511512, mflops=97.7494 (err=1.1e-16) 2. Arndt Split-Radix: elapsed time t=1.97411 s, 524288 iters, t-(init.)=1.89719 s t(norm)=0.150775, mflops=33.162 (err=7.7e-17) 3. Arndt 4-step: elapsed time t=1.04651 s, 65536 iters, t-(init.)=1.03685 s t(norm)=0.659211, mflops=7.58482 (err=9.0e-17) 4. Beauregard: elapsed time t=1.23171 s, 131072 iters, t-(init.)=1.21247 s t(norm)=0.385434, mflops=12.9724 (err=1.5e-16) 5. Bergland: elapsed time t=1.89912 s, 524288 iters, t-(init.)=1.8222 s t(norm)=0.144815, mflops=34.5267 (err=1.6e-16) 6. CWP (min N): elapsed time t=1.52837 s, 524288 iters, t-(init.)=1.45153 s t(norm)=0.115358, mflops=43.3435 7. CWP (best N) (N=15): elapsed time t=1.27495 s, 262144 iters, t-(init.)=1.20889 s t(norm)=0.192147, mflops=26.0217 8. Edelblute: elapsed time t=1.22749 s, 262144 iters, t-(init.)=1.18904 s t(norm)=0.188993, mflops=26.4559 (err=8.3e-17) 9. FFTPACK (f2c): elapsed time t=1.17217 s, 262144 iters, t-(init.)=1.13372 s t(norm)=0.1802, mflops=27.747 (err=1.5e-16) FFTW_MEASURE plan: (cost = 9.256287e-07) FFTW_NOTW 8 10. FFTW: elapsed time t=1.00575 s, 1048576 iters, t-(init.)=0.852002 s t(norm)=0.0338555, mflops=147.686 (err=1.4e-16) FFTW_ESTIMATE plan: (cost = 4.688000e+02) FFTW_NOTW 8 11. FFTW_ESTIMATE: elapsed time t=1.00177 s, 1048576 iters, t-(init.)=0.848024 s t(norm)=0.0336974, mflops=148.379 (err=1.4e-16) 12. Frigo-old: elapsed time t=1.59316 s, 2097152 iters, t-(init.)=1.28539 s t(norm)=0.0255384, mflops=195.783 (err=1.4e-16) 13. Green: elapsed time t=1.87293 s, 1048576 iters, t-(init.)=1.7191 s t(norm)=0.0683109, mflops=73.1947 (err=1.4e-16) 14. GSL: elapsed time t=1.44804 s, 524288 iters, t-(init.)=1.37109 s t(norm)=0.108964, mflops=45.8866 (err=1.4e-16) 15. GSL DIT: elapsed time t=1.28673 s, 262144 iters, t-(init.)=1.24828 s t(norm)=0.198408, mflops=25.2005 (err=1.5e-16) 16. GSL DIF: elapsed time t=1.3292 s, 262144 iters, t-(init.)=1.2907 s t(norm)=0.205152, mflops=24.3722 (err=1.6e-16) 17. Krukar: elapsed time t=1.47913 s, 1048576 iters, t-(init.)=1.32534 s t(norm)=0.0526645, mflops=94.9407 (err=1.5e-16) 18. Mayer (Buneman): elapsed time t=1.21965 s, 524288 iters, t-(init.)=1.14273 s t(norm)=0.090816, mflops=55.0564 (err=1.1e-16) 19. Mayer (simple): elapsed time t=1.17129 s, 524288 iters, t-(init.)=1.09437 s t(norm)=0.0869726, mflops=57.4894 20. Mayer (lookup): elapsed time t=1.26302 s, 524288 iters, t-(init.)=1.18602 s t(norm)=0.0942566, mflops=53.0467 (err=1.1e-16) 21. NAPACK (f2c): elapsed time t=1.49669 s, 131072 iters, t-(init.)=1.4772 s t(norm)=0.46959, mflops=10.6476 (err=1.7e-16) 22. Nielsen: elapsed time t=1.73097 s, 262144 iters, t-(init.)=1.69252 s t(norm)=0.269019, mflops=18.586 (err=7.5e-16) 23. NR (C): elapsed time t=1.28388 s, 262144 iters, t-(init.)=1.24539 s t(norm)=0.197949, mflops=25.259 (err=1.6e-16) 24. Ooura (C): elapsed time t=1.55989 s, 1048576 iters, t-(init.)=1.40603 s t(norm)=0.0558708, mflops=89.4922 (err=1.5e-16) 25. Skipping fft (QFT requires N >= 16). 26. Ransom: elapsed time t=1.36607 s, 65536 iters, t-(init.)=1.3565 s t(norm)=0.862441, mflops=5.7975 (err=3.1e-16) 27. Singleton (f2c): elapsed time t=1.43578 s, 262144 iters, t-(init.)=1.39733 s t(norm)=0.2221, mflops=22.5124 (err=1.4e-16) 28. Temperton (f2c): elapsed time t=1.09591 s, 131072 iters, t-(init.)=1.07666 s t(norm)=0.342262, mflops=14.6087 (err=1.4e-16) 29. Valkenburg: elapsed time t=1.84919 s, 131072 iters, t-(init.)=1.82997 s t(norm)=0.581732, mflops=8.59502 (err=1.4e-16) Top mflops for N=8 = 195.783 Normalized results and averages for N=8: fft 0: mflops = 100.789 (norm. = 0.514801), norm. avg. (of 3) = 0.538337 fft 1: mflops = 97.7494 (norm. = 0.499274), norm. avg. (of 3) = 0.508374 fft 2: mflops = 33.162 (norm. = 0.169381), norm. avg. (of 3) = 0.247827 fft 3: mflops = 7.58482 (norm. = 0.0387409), norm. avg. (of 3) = 0.035575 fft 4: mflops = 12.9724 (norm. = 0.066259), norm. avg. (of 3) = 0.075376 fft 5: mflops = 34.5267 (norm. = 0.176352), norm. avg. (of 3) = 0.157885 fft 6: mflops = 43.3435 (norm. = 0.221385), norm. avg. (of 3) = 0.154347 fft 7: mflops = 26.0217 (norm. = 0.132911), norm. avg. (of 3) = 0.0986565 fft 8: mflops = 26.4559 (norm. = 0.135129), norm. avg. (of 2) = 0.159649 fft 9: mflops = 27.747 (norm. = 0.141723), norm. avg. (of 3) = 0.146953 fft 10: mflops = 147.686 (norm. = 0.754336), norm. avg. (of 3) = 0.695376 fft 11: mflops = 148.379 (norm. = 0.757875), norm. avg. (of 3) = 0.70104 fft 12: mflops = 195.783 (norm. = 1), norm. avg. (of 3) = 1 fft 13: mflops = 73.1947 (norm. = 0.373856), norm. avg. (of 1) = 0.373856 fft 14: mflops = 45.8866 (norm. = 0.234375), norm. avg. (of 3) = 0.241894 fft 15: mflops = 25.2005 (norm. = 0.128717), norm. avg. (of 3) = 0.131923 fft 16: mflops = 24.3722 (norm. = 0.124486), norm. avg. (of 3) = 0.126471 fft 17: mflops = 94.9407 (norm. = 0.484927), norm. avg. (of 3) = 0.54089 fft 18: mflops = 55.0564 (norm. = 0.281211), norm. avg. (of 2) = 0.265326 fft 19: mflops = 57.4894 (norm. = 0.293638), norm. avg. (of 2) = 0.280051 fft 20: mflops = 53.0467 (norm. = 0.270946), norm. avg. (of 2) = 0.253636 fft 21: mflops = 10.6476 (norm. = 0.0543846), norm. avg. (of 3) = 0.0564315 fft 22: mflops = 18.586 (norm. = 0.0949317), norm. avg. (of 3) = 0.0671958 fft 23: mflops = 25.259 (norm. = 0.129015), norm. avg. (of 3) = 0.136565 fft 24: mflops = 89.4922 (norm. = 0.457098), norm. avg. (of 3) = 0.453249 fft 25: mflops = -1 (norm. = -0.00510769), norm. avg. (of 0) = -1 fft 26: mflops = 5.7975 (norm. = 0.0296118), norm. avg. (of 2) = 0.0323007 fft 27: mflops = 22.5124 (norm. = 0.114986), norm. avg. (of 3) = 0.129045 fft 28: mflops = 14.6087 (norm. = 0.0746166), norm. avg. (of 3) = 0.0728045 fft 29: mflops = 8.59502 (norm. = 0.0439007), norm. avg. (of 3) = 0.0899141 Benchmarking for array size = 16 (power of 2): 0. Arndt DIF: elapsed time t=1.496 s, 262144 iters, t-(init.)=1.42591 s t(norm)=0.084991, mflops=58.8298 (err=1.9e-16) 1. Arndt DIT: elapsed time t=1.50753 s, 262144 iters, t-(init.)=1.43726 s t(norm)=0.0856675, mflops=58.3652 (err=1.9e-16) 2. Arndt Split-Radix: elapsed time t=1.09563 s, 131072 iters, t-(init.)=1.0604 s t(norm)=0.12641, mflops=39.5539 (err=1.5e-16) 3. Arndt 4-step: elapsed time t=1.49787 s, 65536 iters, t-(init.)=1.48034 s t(norm)=0.35294, mflops=14.1667 (err=2.0e-16) 4. Beauregard: elapsed time t=1.46647 s, 65536 iters, t-(init.)=1.44894 s t(norm)=0.345454, mflops=14.4737 (err=2.3e-16) 5. Bergland: elapsed time t=1.63545 s, 262144 iters, t-(init.)=1.56543 s t(norm)=0.0933071, mflops=53.5865 (err=2.6e-16) 6. CWP (min N): elapsed time t=1.17283 s, 262144 iters, t-(init.)=1.10271 s t(norm)=0.0657264, mflops=76.0729 7. CWP (best N) (N=28): elapsed time t=1.83995 s, 262144 iters, t-(init.)=1.72264 s t(norm)=0.102677, mflops=48.6963 8. Edelblute: elapsed time t=1.47041 s, 131072 iters, t-(init.)=1.4354 s t(norm)=0.171113, mflops=29.2205 (err=1.6e-16) 9. FFTPACK (f2c): elapsed time t=1.12149 s, 131072 iters, t-(init.)=1.08648 s t(norm)=0.129519, mflops=38.6045 (err=2.1e-16) FFTW_MEASURE plan: (cost = 1.850006e-06) FFTW_NOTW 16 10. FFTW: elapsed time t=1.00566 s, 524288 iters, t-(init.)=0.865645 s t(norm)=0.0257982, mflops=193.812 (err=2.2e-16) FFTW_ESTIMATE plan: (cost = 4.256000e+02) FFTW_NOTW 16 11. FFTW_ESTIMATE: elapsed time t=1.00381 s, 524288 iters, t-(init.)=0.863839 s t(norm)=0.0257444, mflops=194.217 (err=2.2e-16) 12. Frigo-old: elapsed time t=1.83803 s, 1048576 iters, t-(init.)=1.55808 s t(norm)=0.0232172, mflops=215.357 (err=2.2e-16) 13. Green: elapsed time t=1.77687 s, 524288 iters, t-(init.)=1.63681 s t(norm)=0.0487809, mflops=102.499 (err=2.6e-16) 14. GSL: elapsed time t=1.32441 s, 262144 iters, t-(init.)=1.25443 s t(norm)=0.0747696, mflops=66.8721 (err=2.1e-16) 15. GSL DIT: elapsed time t=1.1739 s, 131072 iters, t-(init.)=1.13889 s t(norm)=0.135766, mflops=36.828 (err=3.1e-16) 16. GSL DIF: elapsed time t=1.19453 s, 131072 iters, t-(init.)=1.15952 s t(norm)=0.138226, mflops=36.1727 (err=2.5e-16) 17. Krukar: elapsed time t=1.70393 s, 524288 iters, t-(init.)=1.56386 s t(norm)=0.0466067, mflops=107.281 (err=1.7e-16) 18. Mayer (Buneman): elapsed time t=1.64915 s, 262144 iters, t-(init.)=1.57909 s t(norm)=0.0941213, mflops=53.123 (err=2.3e-16) 19. Mayer (simple): elapsed time t=1.38627 s, 262144 iters, t-(init.)=1.31621 s t(norm)=0.0784522, mflops=63.7331 20. Mayer (lookup): elapsed time t=1.41002 s, 262144 iters, t-(init.)=1.34004 s t(norm)=0.0798725, mflops=62.5997 (err=2.1e-16) 21. NAPACK (f2c): elapsed time t=1.3968 s, 65536 iters, t-(init.)=1.37929 s t(norm)=0.328849, mflops=15.2046 (err=2.7e-16) 22. Nielsen: elapsed time t=1.12572 s, 65536 iters, t-(init.)=1.10819 s t(norm)=0.264212, mflops=18.9242 (err=1.8e-16) 23. NR (C): elapsed time t=1.15815 s, 131072 iters, t-(init.)=1.12316 s t(norm)=0.133891, mflops=37.3437 (err=2.9e-16) 24. Ooura (C): elapsed time t=1.55823 s, 524288 iters, t-(init.)=1.41822 s t(norm)=0.0422663, mflops=118.298 (err=2.5e-16) 25. QFT: elapsed time t=1.27689 s, 262144 iters, t-(init.)=1.20692 s t(norm)=0.0719378, mflops=69.5045 (err=1.4e-16) 26. Ransom: elapsed time t=1.19467 s, 65536 iters, t-(init.)=1.17717 s t(norm)=0.280659, mflops=17.8152 (err=5.0e-16) 27. Singleton (f2c): elapsed time t=1.50223 s, 262144 iters, t-(init.)=1.43225 s t(norm)=0.0853685, mflops=58.5696 (err=2.0e-16) 28. Temperton (f2c): elapsed time t=1.01586 s, 65536 iters, t-(init.)=0.998354 s t(norm)=0.238026, mflops=21.0061 (err=2.1e-16) 29. Valkenburg: elapsed time t=1.18394 s, 32768 iters, t-(init.)=1.17519 s t(norm)=0.560373, mflops=8.92262 (err=2.5e-16) Top mflops for N=16 = 215.357 Normalized results and averages for N=16: fft 0: mflops = 58.8298 (norm. = 0.273173), norm. avg. (of 4) = 0.472046 fft 1: mflops = 58.3652 (norm. = 0.271016), norm. avg. (of 4) = 0.449034 fft 2: mflops = 39.5539 (norm. = 0.183666), norm. avg. (of 4) = 0.231787 fft 3: mflops = 14.1667 (norm. = 0.0657824), norm. avg. (of 4) = 0.0431268 fft 4: mflops = 14.4737 (norm. = 0.067208), norm. avg. (of 4) = 0.073334 fft 5: mflops = 53.5865 (norm. = 0.248826), norm. avg. (of 4) = 0.18062 fft 6: mflops = 76.0729 (norm. = 0.353241), norm. avg. (of 4) = 0.20407 fft 7: mflops = 48.6963 (norm. = 0.226119), norm. avg. (of 4) = 0.130522 fft 8: mflops = 29.2205 (norm. = 0.135684), norm. avg. (of 3) = 0.15166 fft 9: mflops = 38.6045 (norm. = 0.179258), norm. avg. (of 4) = 0.155029 fft 10: mflops = 193.812 (norm. = 0.899955), norm. avg. (of 4) = 0.74652 fft 11: mflops = 194.217 (norm. = 0.901836), norm. avg. (of 4) = 0.751239 fft 12: mflops = 215.357 (norm. = 1), norm. avg. (of 4) = 1 fft 13: mflops = 102.499 (norm. = 0.47595), norm. avg. (of 2) = 0.424903 fft 14: mflops = 66.8721 (norm. = 0.310517), norm. avg. (of 4) = 0.25905 fft 15: mflops = 36.828 (norm. = 0.171009), norm. avg. (of 4) = 0.141695 fft 16: mflops = 36.1727 (norm. = 0.167966), norm. avg. (of 4) = 0.136845 fft 17: mflops = 107.281 (norm. = 0.498153), norm. avg. (of 4) = 0.530206 fft 18: mflops = 53.123 (norm. = 0.246674), norm. avg. (of 3) = 0.259108 fft 19: mflops = 63.7331 (norm. = 0.295941), norm. avg. (of 3) = 0.285347 fft 20: mflops = 62.5997 (norm. = 0.290679), norm. avg. (of 3) = 0.265983 fft 21: mflops = 15.2046 (norm. = 0.0706016), norm. avg. (of 4) = 0.059974 fft 22: mflops = 18.9242 (norm. = 0.0878734), norm. avg. (of 4) = 0.0723652 fft 23: mflops = 37.3437 (norm. = 0.173404), norm. avg. (of 4) = 0.145774 fft 24: mflops = 118.298 (norm. = 0.549309), norm. avg. (of 4) = 0.477264 fft 25: mflops = 69.5045 (norm. = 0.322741), norm. avg. (of 1) = 0.322741 fft 26: mflops = 17.8152 (norm. = 0.082724), norm. avg. (of 3) = 0.0491085 fft 27: mflops = 58.5696 (norm. = 0.271965), norm. avg. (of 4) = 0.164775 fft 28: mflops = 21.0061 (norm. = 0.0975407), norm. avg. (of 4) = 0.0789886 fft 29: mflops = 8.92262 (norm. = 0.0414317), norm. avg. (of 4) = 0.0777935 Benchmarking for array size = 32 (power of 2): 0. Arndt DIF: elapsed time t=1.57203 s, 131072 iters, t-(init.)=1.50548 s t(norm)=0.0717867, mflops=69.6508 (err=2.4e-16) 1. Arndt DIT: elapsed time t=1.59003 s, 131072 iters, t-(init.)=1.5234 s t(norm)=0.0726412, mflops=68.8314 (err=2.7e-16) 2. Arndt Split-Radix: elapsed time t=1.18778 s, 65536 iters, t-(init.)=1.15448 s t(norm)=0.1101, mflops=45.4134 (err=3.0e-16) 3. Arndt 4-step: elapsed time t=1.53778 s, 32768 iters, t-(init.)=1.52113 s t(norm)=0.290133, mflops=17.2335 (err=2.4e-16) 4. Beauregard: elapsed time t=1.75841 s, 32768 iters, t-(init.)=1.74177 s t(norm)=0.332217, mflops=15.0504 (err=2.5e-16) 5. Bergland: elapsed time t=1.42125 s, 131072 iters, t-(init.)=1.35462 s t(norm)=0.0645935, mflops=77.4072 (err=2.6e-16) 6. CWP (min N) (N=33): elapsed time t=1.44503 s, 131072 iters, t-(init.)=1.37651 s t(norm)=0.0656373, mflops=76.1762 7. CWP (best N) (N=35): elapsed time t=1.24826 s, 131072 iters, t-(init.)=1.17572 s t(norm)=0.0560628, mflops=89.1857 8. Edelblute: elapsed time t=1.64395 s, 65536 iters, t-(init.)=1.61065 s t(norm)=0.153604, mflops=32.5512 (err=2.9e-16) 9. FFTPACK (f2c): elapsed time t=1.59599 s, 65536 iters, t-(init.)=1.56271 s t(norm)=0.149032, mflops=33.5498 (err=2.3e-16) FFTW_MEASURE plan: (cost = 4.146301e-06) FFTW_NOTW 32 10. FFTW: elapsed time t=1.12217 s, 262144 iters, t-(init.)=0.988895 s t(norm)=0.0235771, mflops=212.07 (err=2.4e-16) FFTW_ESTIMATE plan: (cost = 3.200000e+01) FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.12116 s, 262144 iters, t-(init.)=0.988003 s t(norm)=0.0235558, mflops=212.262 (err=2.4e-16) 12. Frigo-old: elapsed time t=1.09846 s, 262144 iters, t-(init.)=0.965378 s t(norm)=0.0230164, mflops=217.236 (err=2.1e-16) 13. Green: elapsed time t=1.63593 s, 262144 iters, t-(init.)=1.50284 s t(norm)=0.0358306, mflops=139.545 (err=2.4e-16) 14. GSL: elapsed time t=1.74561 s, 131072 iters, t-(init.)=1.67906 s t(norm)=0.0800637, mflops=62.4503 (err=2.3e-16) 15. GSL DIT: elapsed time t=1.12609 s, 65536 iters, t-(init.)=1.09268 s t(norm)=0.104206, mflops=47.9818 (err=3.1e-16) 16. GSL DIF: elapsed time t=1.12426 s, 65536 iters, t-(init.)=1.09091 s t(norm)=0.104038, mflops=48.0595 (err=3.2e-16) 17. Krukar: elapsed time t=1.03305 s, 131072 iters, t-(init.)=0.966494 s t(norm)=0.046086, mflops=108.493 (err=2.7e-16) 18. Mayer (Buneman): elapsed time t=1.81622 s, 131072 iters, t-(init.)=1.74967 s t(norm)=0.0834309, mflops=59.9298 (err=2.8e-16) 19. Mayer (simple): elapsed time t=1.46182 s, 131072 iters, t-(init.)=1.39527 s t(norm)=0.0665316, mflops=75.1523 20. Mayer (lookup): elapsed time t=1.4464 s, 131072 iters, t-(init.)=1.37989 s t(norm)=0.0657981, mflops=75.99 (err=2.6e-16) 21. NAPACK (f2c): elapsed time t=1.48135 s, 32768 iters, t-(init.)=1.4647 s t(norm)=0.27937, mflops=17.8974 (err=6.4e-16) 22. Nielsen: elapsed time t=1.94995 s, 65536 iters, t-(init.)=1.91668 s t(norm)=0.182788, mflops=27.354 (err=1.1e-15) 23. NR (C): elapsed time t=1.08904 s, 65536 iters, t-(init.)=1.05577 s t(norm)=0.100686, mflops=49.6591 (err=2.9e-16) 24. Ooura (C): elapsed time t=1.7826 s, 262144 iters, t-(init.)=1.64946 s t(norm)=0.0393263, mflops=127.141 (err=2.5e-16) 25. QFT: elapsed time t=1.76767 s, 131072 iters, t-(init.)=1.70112 s t(norm)=0.0811159, mflops=61.6402 (err=2.8e-16) 26. Ransom: elapsed time t=1.42711 s, 32768 iters, t-(init.)=1.41046 s t(norm)=0.269024, mflops=18.5857 (err=7.4e-16) 27. Singleton (f2c): elapsed time t=1.45853 s, 131072 iters, t-(init.)=1.39197 s t(norm)=0.0663745, mflops=75.3301 (err=2.3e-16) 28. Temperton (f2c): elapsed time t=1.31325 s, 32768 iters, t-(init.)=1.2966 s t(norm)=0.247307, mflops=20.2178 (err=2.6e-16) 29. Valkenburg: elapsed time t=1.43366 s, 16384 iters, t-(init.)=1.42524 s t(norm)=0.543687, mflops=9.19647 (err=2.8e-16) Top mflops for N=32 = 217.236 Normalized results and averages for N=32: fft 0: mflops = 69.6508 (norm. = 0.320622), norm. avg. (of 5) = 0.441761 fft 1: mflops = 68.8314 (norm. = 0.31685), norm. avg. (of 5) = 0.422598 fft 2: mflops = 45.4134 (norm. = 0.209051), norm. avg. (of 5) = 0.227239 fft 3: mflops = 17.2335 (norm. = 0.0793306), norm. avg. (of 5) = 0.0503676 fft 4: mflops = 15.0504 (norm. = 0.0692813), norm. avg. (of 5) = 0.0725235 fft 5: mflops = 77.4072 (norm. = 0.356327), norm. avg. (of 5) = 0.215762 fft 6: mflops = 76.1762 (norm. = 0.35066), norm. avg. (of 5) = 0.233388 fft 7: mflops = 89.1857 (norm. = 0.410547), norm. avg. (of 5) = 0.186527 fft 8: mflops = 32.5512 (norm. = 0.149843), norm. avg. (of 4) = 0.151206 fft 9: mflops = 33.5498 (norm. = 0.154439), norm. avg. (of 5) = 0.154911 fft 10: mflops = 212.07 (norm. = 0.976219), norm. avg. (of 5) = 0.79246 fft 11: mflops = 212.262 (norm. = 0.9771), norm. avg. (of 5) = 0.796412 fft 12: mflops = 217.236 (norm. = 1), norm. avg. (of 5) = 1 fft 13: mflops = 139.545 (norm. = 0.642367), norm. avg. (of 3) = 0.497391 fft 14: mflops = 62.4503 (norm. = 0.287476), norm. avg. (of 5) = 0.264735 fft 15: mflops = 47.9818 (norm. = 0.220874), norm. avg. (of 5) = 0.157531 fft 16: mflops = 48.0595 (norm. = 0.221231), norm. avg. (of 5) = 0.153722 fft 17: mflops = 108.493 (norm. = 0.499423), norm. avg. (of 5) = 0.524049 fft 18: mflops = 59.9298 (norm. = 0.275874), norm. avg. (of 4) = 0.2633 fft 19: mflops = 75.1523 (norm. = 0.345947), norm. avg. (of 4) = 0.300497 fft 20: mflops = 75.99 (norm. = 0.349803), norm. avg. (of 4) = 0.286938 fft 21: mflops = 17.8974 (norm. = 0.0823867), norm. avg. (of 5) = 0.0644566 fft 22: mflops = 27.354 (norm. = 0.125918), norm. avg. (of 5) = 0.0830758 fft 23: mflops = 49.6591 (norm. = 0.228595), norm. avg. (of 5) = 0.162338 fft 24: mflops = 127.141 (norm. = 0.585268), norm. avg. (of 5) = 0.498865 fft 25: mflops = 61.6402 (norm. = 0.283747), norm. avg. (of 2) = 0.303244 fft 26: mflops = 18.5857 (norm. = 0.0855551), norm. avg. (of 4) = 0.0582201 fft 27: mflops = 75.3301 (norm. = 0.346766), norm. avg. (of 5) = 0.201173 fft 28: mflops = 20.2178 (norm. = 0.0930683), norm. avg. (of 5) = 0.0818045 fft 29: mflops = 9.19647 (norm. = 0.042334), norm. avg. (of 5) = 0.0707016 Benchmarking for array size = 64 (power of 2): 0. Arndt DIF: elapsed time t=1.86008 s, 65536 iters, t-(init.)=1.79517 s t(norm)=0.0713337, mflops=70.0931 (err=5.0e-16) 1. Arndt DIT: elapsed time t=1.88729 s, 65536 iters, t-(init.)=1.82251 s t(norm)=0.0724201, mflops=69.0416 (err=4.9e-16) 2. Arndt Split-Radix: elapsed time t=1.267 s, 32768 iters, t-(init.)=1.2346 s t(norm)=0.0981168, mflops=50.9597 (err=4.5e-16) 3. Arndt 4-step: elapsed time t=1.28976 s, 16384 iters, t-(init.)=1.27354 s t(norm)=0.202424, mflops=24.7007 (err=4.9e-16) 4. Beauregard: elapsed time t=1.04397 s, 8192 iters, t-(init.)=1.03587 s t(norm)=0.329293, mflops=15.184 (err=4.5e-16) 5. Bergland: elapsed time t=1.45964 s, 65536 iters, t-(init.)=1.39484 s t(norm)=0.0554258, mflops=90.2107 (err=5.5e-16) 6. CWP (min N) (N=65): elapsed time t=1.61207 s, 65536 iters, t-(init.)=1.54626 s t(norm)=0.0614427, mflops=81.3766 7. CWP (best N) (N=84): elapsed time t=1.32915 s, 65536 iters, t-(init.)=1.24457 s t(norm)=0.0494548, mflops=101.102 8. Edelblute: elapsed time t=1.77004 s, 32768 iters, t-(init.)=1.7376 s t(norm)=0.138092, mflops=36.2078 (err=4.6e-16) 9. FFTPACK (f2c): elapsed time t=1.65947 s, 32768 iters, t-(init.)=1.62703 s t(norm)=0.129305, mflops=38.6684 (err=4.4e-16) FFTW_MEASURE plan: (cost = 9.087646e-06) FFTW_NOTW 64 10. FFTW: elapsed time t=1.22649 s, 131072 iters, t-(init.)=1.09683 s t(norm)=0.0217921, mflops=229.441 (err=4.4e-16) FFTW_ESTIMATE plan: (cost = 7.680000e+02) FFTW_TWIDDLE 2 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.51807 s, 131072 iters, t-(init.)=1.38831 s t(norm)=0.0275833, mflops=181.269 (err=4.7e-16) 12. Frigo-old: elapsed time t=1.79203 s, 131072 iters, t-(init.)=1.66234 s t(norm)=0.0330277, mflops=151.388 (err=4.5e-16) 13. Green: elapsed time t=1.50609 s, 131072 iters, t-(init.)=1.37627 s t(norm)=0.027344, mflops=182.855 (err=4.6e-16) 14. GSL: elapsed time t=1.75579 s, 65536 iters, t-(init.)=1.69096 s t(norm)=0.0671927, mflops=74.4128 (err=4.4e-16) 15. GSL DIT: elapsed time t=1.14992 s, 32768 iters, t-(init.)=1.11751 s t(norm)=0.0888119, mflops=56.2988 (err=4.6e-16) 16. GSL DIF: elapsed time t=1.12713 s, 32768 iters, t-(init.)=1.09457 s t(norm)=0.0869883, mflops=57.479 (err=4.9e-16) 17. Krukar: elapsed time t=1.2234 s, 65536 iters, t-(init.)=1.15855 s t(norm)=0.0460368, mflops=108.609 (err=5.2e-16) 18. Mayer (Buneman): elapsed time t=1.05572 s, 32768 iters, t-(init.)=1.02328 s t(norm)=0.0813229, mflops=61.4833 (err=4.8e-16) 19. Mayer (simple): elapsed time t=1.63839 s, 65536 iters, t-(init.)=1.57332 s t(norm)=0.0625182, mflops=79.9767 20. Mayer (lookup): elapsed time t=1.60172 s, 65536 iters, t-(init.)=1.53681 s t(norm)=0.0610672, mflops=81.877 (err=4.5e-16) 21. NAPACK (f2c): elapsed time t=1.52114 s, 16384 iters, t-(init.)=1.50492 s t(norm)=0.239201, mflops=20.9029 (err=1.1e-15) 22. Nielsen: elapsed time t=1.83498 s, 32768 iters, t-(init.)=1.80257 s t(norm)=0.143255, mflops=34.9027 (err=1.9e-15) 23. NR (C): elapsed time t=1.08754 s, 32768 iters, t-(init.)=1.05513 s t(norm)=0.0838544, mflops=59.6272 (err=4.4e-16) 24. Ooura (C): elapsed time t=1.88879 s, 131072 iters, t-(init.)=1.75914 s t(norm)=0.0349509, mflops=143.058 (err=5.4e-16) 25. QFT: elapsed time t=1.12129 s, 32768 iters, t-(init.)=1.08887 s t(norm)=0.0865359, mflops=57.7795 (err=4.9e-16) 26. Ransom: elapsed time t=1.83315 s, 32768 iters, t-(init.)=1.80071 s t(norm)=0.143107, mflops=34.9388 (err=9.1e-16) 27. Singleton (f2c): elapsed time t=1.28135 s, 65536 iters, t-(init.)=1.21643 s t(norm)=0.0483365, mflops=103.442 (err=6.5e-16) 28. Temperton (f2c): elapsed time t=1.23137 s, 16384 iters, t-(init.)=1.21515 s t(norm)=0.193143, mflops=25.8875 (err=4.7e-16) 29. Valkenburg: elapsed time t=1.68256 s, 8192 iters, t-(init.)=1.67446 s t(norm)=0.532296, mflops=9.39328 (err=6.0e-16) Top mflops for N=64 = 229.441 Normalized results and averages for N=64: fft 0: mflops = 70.0931 (norm. = 0.305495), norm. avg. (of 6) = 0.41905 fft 1: mflops = 69.0416 (norm. = 0.300912), norm. avg. (of 6) = 0.402317 fft 2: mflops = 50.9597 (norm. = 0.222104), norm. avg. (of 6) = 0.226383 fft 3: mflops = 24.7007 (norm. = 0.107656), norm. avg. (of 6) = 0.0599156 fft 4: mflops = 15.184 (norm. = 0.0661784), norm. avg. (of 6) = 0.071466 fft 5: mflops = 90.2107 (norm. = 0.393176), norm. avg. (of 6) = 0.245331 fft 6: mflops = 81.3766 (norm. = 0.354673), norm. avg. (of 6) = 0.253603 fft 7: mflops = 101.102 (norm. = 0.440646), norm. avg. (of 6) = 0.22888 fft 8: mflops = 36.2078 (norm. = 0.157809), norm. avg. (of 5) = 0.152526 fft 9: mflops = 38.6684 (norm. = 0.168533), norm. avg. (of 6) = 0.157182 fft 10: mflops = 229.441 (norm. = 1), norm. avg. (of 6) = 0.82705 fft 11: mflops = 181.269 (norm. = 0.790046), norm. avg. (of 6) = 0.795351 fft 12: mflops = 151.388 (norm. = 0.659813), norm. avg. (of 6) = 0.943302 fft 13: mflops = 182.855 (norm. = 0.79696), norm. avg. (of 4) = 0.572283 fft 14: mflops = 74.4128 (norm. = 0.324322), norm. avg. (of 6) = 0.274666 fft 15: mflops = 56.2988 (norm. = 0.245374), norm. avg. (of 6) = 0.172171 fft 16: mflops = 57.479 (norm. = 0.250518), norm. avg. (of 6) = 0.169855 fft 17: mflops = 108.609 (norm. = 0.473362), norm. avg. (of 6) = 0.515602 fft 18: mflops = 61.4833 (norm. = 0.26797), norm. avg. (of 5) = 0.264234 fft 19: mflops = 79.9767 (norm. = 0.348572), norm. avg. (of 5) = 0.310112 fft 20: mflops = 81.877 (norm. = 0.356854), norm. avg. (of 5) = 0.300922 fft 21: mflops = 20.9029 (norm. = 0.0911038), norm. avg. (of 6) = 0.0688978 fft 22: mflops = 34.9027 (norm. = 0.152121), norm. avg. (of 6) = 0.0945833 fft 23: mflops = 59.6272 (norm. = 0.25988), norm. avg. (of 6) = 0.178595 fft 24: mflops = 143.058 (norm. = 0.623506), norm. avg. (of 6) = 0.519638 fft 25: mflops = 57.7795 (norm. = 0.251827), norm. avg. (of 3) = 0.286105 fft 26: mflops = 34.9388 (norm. = 0.152278), norm. avg. (of 5) = 0.0770317 fft 27: mflops = 103.442 (norm. = 0.450842), norm. avg. (of 6) = 0.242784 fft 28: mflops = 25.8875 (norm. = 0.112829), norm. avg. (of 6) = 0.0869752 fft 29: mflops = 9.39328 (norm. = 0.0409398), norm. avg. (of 6) = 0.0657413 Benchmarking for array size = 128 (power of 2): 0. Arndt DIF: elapsed time t=1.96478 s, 32768 iters, t-(init.)=1.90085 s t(norm)=0.0647426, mflops=77.2289 (err=4.0e-16) 1. Arndt DIT: elapsed time t=1.99264 s, 32768 iters, t-(init.)=1.92872 s t(norm)=0.0656917, mflops=76.1131 (err=4.1e-16) 2. Arndt Split-Radix: elapsed time t=1.33795 s, 16384 iters, t-(init.)=1.30597 s t(norm)=0.0889623, mflops=56.2036 (err=4.4e-16) 3. Arndt 4-step: elapsed time t=1.48111 s, 8192 iters, t-(init.)=1.46511 s t(norm)=0.199605, mflops=25.0495 (err=4.0e-16) 4. Beauregard: elapsed time t=1.2213 s, 4096 iters, t-(init.)=1.21328 s t(norm)=0.330593, mflops=15.1243 (err=4.1e-16) 5. Bergland: elapsed time t=1.59651 s, 32768 iters, t-(init.)=1.53258 s t(norm)=0.0521993, mflops=95.7867 (err=4.3e-16) 6. CWP (min N) (N=130): elapsed time t=1.62692 s, 32768 iters, t-(init.)=1.56196 s t(norm)=0.0532, mflops=93.985 7. CWP (best N) (N=140): elapsed time t=1.1573 s, 32768 iters, t-(init.)=1.08744 s t(norm)=0.0370381, mflops=134.996 8. Edelblute: elapsed time t=1.86988 s, 16384 iters, t-(init.)=1.83794 s t(norm)=0.1252, mflops=39.9361 (err=4.1e-16) 9. FFTPACK (f2c): elapsed time t=1.86333 s, 16384 iters, t-(init.)=1.83135 s t(norm)=0.124751, mflops=40.0799 (err=4.1e-16) FFTW_MEASURE plan: (cost = 2.399268e-05) FFTW_TWIDDLE 2 FFTW_NOTW 64 10. FFTW: elapsed time t=1.60482 s, 65536 iters, t-(init.)=1.4768 s t(norm)=0.0251498, mflops=198.809 (err=4.5e-16) FFTW_ESTIMATE plan: (cost = 1.075200e+03) FFTW_TWIDDLE 4 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.61846 s, 65536 iters, t-(init.)=1.49053 s t(norm)=0.0253835, mflops=196.978 (err=4.2e-16) 12. Frigo-old: elapsed time t=1.8658 s, 65536 iters, t-(init.)=1.73794 s t(norm)=0.029597, mflops=168.936 (err=4.4e-16) 13. Green: elapsed time t=1.81118 s, 65536 iters, t-(init.)=1.68322 s t(norm)=0.028665, mflops=174.429 (err=4.4e-16) 14. GSL: elapsed time t=1.9644 s, 32768 iters, t-(init.)=1.90043 s t(norm)=0.0647282, mflops=77.2461 (err=4.2e-16) 15. GSL DIT: elapsed time t=1.2141 s, 16384 iters, t-(init.)=1.18223 s t(norm)=0.0805333, mflops=62.0861 (err=4.3e-16) 16. GSL DIF: elapsed time t=1.17207 s, 16384 iters, t-(init.)=1.14009 s t(norm)=0.0776622, mflops=64.3814 (err=4.6e-16) 17. Krukar: elapsed time t=1.92553 s, 32768 iters, t-(init.)=1.86158 s t(norm)=0.0634051, mflops=78.858 (err=4.6e-16) 18. Mayer (Buneman): elapsed time t=1.1425 s, 16384 iters, t-(init.)=1.11051 s t(norm)=0.0756478, mflops=66.0958 (err=4.0e-16) 19. Mayer (simple): elapsed time t=1.74967 s, 32768 iters, t-(init.)=1.68572 s t(norm)=0.0574154, mflops=87.0846 20. Mayer (lookup): elapsed time t=1.69912 s, 32768 iters, t-(init.)=1.63515 s t(norm)=0.0556928, mflops=89.7782 (err=4.3e-16) 21. NAPACK (f2c): elapsed time t=1.70434 s, 8192 iters, t-(init.)=1.68834 s t(norm)=0.230018, mflops=21.7374 (err=1.2e-15) 22. Nielsen: elapsed time t=1.12531 s, 8192 iters, t-(init.)=1.10928 s t(norm)=0.151127, mflops=33.0848 (err=1.3e-15) 23. NR (C): elapsed time t=1.12185 s, 16384 iters, t-(init.)=1.08987 s t(norm)=0.0742416, mflops=67.3477 (err=4.4e-16) 24. Ooura (C): elapsed time t=1.10109 s, 32768 iters, t-(init.)=1.03715 s t(norm)=0.0353251, mflops=141.543 (err=4.1e-16) 25. QFT: elapsed time t=1.35201 s, 16384 iters, t-(init.)=1.32002 s t(norm)=0.0899192, mflops=55.6055 (err=4.6e-16) 26. Ransom: elapsed time t=1.11242 s, 8192 iters, t-(init.)=1.09642 s t(norm)=0.149375, mflops=33.4728 (err=1.1e-15) 27. Singleton (f2c): elapsed time t=1.55123 s, 32768 iters, t-(init.)=1.48719 s t(norm)=0.0506535, mflops=98.7099 (err=5.3e-16) 28. Temperton (f2c): elapsed time t=1.48107 s, 8192 iters, t-(init.)=1.46506 s t(norm)=0.199599, mflops=25.0502 (err=4.4e-16) 29. Valkenburg: elapsed time t=1.94267 s, 4096 iters, t-(init.)=1.93462 s t(norm)=0.527142, mflops=9.48511 (err=4.8e-16) Top mflops for N=128 = 198.809 Normalized results and averages for N=128: fft 0: mflops = 77.2289 (norm. = 0.388459), norm. avg. (of 7) = 0.41468 fft 1: mflops = 76.1131 (norm. = 0.382846), norm. avg. (of 7) = 0.399535 fft 2: mflops = 56.2036 (norm. = 0.282702), norm. avg. (of 7) = 0.234429 fft 3: mflops = 25.0495 (norm. = 0.125998), norm. avg. (of 7) = 0.0693559 fft 4: mflops = 15.1243 (norm. = 0.0760748), norm. avg. (of 7) = 0.0721244 fft 5: mflops = 95.7867 (norm. = 0.481804), norm. avg. (of 7) = 0.279113 fft 6: mflops = 93.985 (norm. = 0.472741), norm. avg. (of 7) = 0.284908 fft 7: mflops = 134.996 (norm. = 0.679025), norm. avg. (of 7) = 0.293187 fft 8: mflops = 39.9361 (norm. = 0.200877), norm. avg. (of 6) = 0.160585 fft 9: mflops = 40.0799 (norm. = 0.2016), norm. avg. (of 7) = 0.163527 fft 10: mflops = 198.809 (norm. = 1), norm. avg. (of 7) = 0.851757 fft 11: mflops = 196.978 (norm. = 0.990794), norm. avg. (of 7) = 0.823271 fft 12: mflops = 168.936 (norm. = 0.849742), norm. avg. (of 7) = 0.929936 fft 13: mflops = 174.429 (norm. = 0.877369), norm. avg. (of 5) = 0.6333 fft 14: mflops = 77.2461 (norm. = 0.388545), norm. avg. (of 7) = 0.290935 fft 15: mflops = 62.0861 (norm. = 0.312291), norm. avg. (of 7) = 0.192188 fft 16: mflops = 64.3814 (norm. = 0.323836), norm. avg. (of 7) = 0.191852 fft 17: mflops = 78.858 (norm. = 0.396653), norm. avg. (of 7) = 0.498609 fft 18: mflops = 66.0958 (norm. = 0.33246), norm. avg. (of 6) = 0.275605 fft 19: mflops = 87.0846 (norm. = 0.438033), norm. avg. (of 6) = 0.331432 fft 20: mflops = 89.7782 (norm. = 0.451581), norm. avg. (of 6) = 0.326031 fft 21: mflops = 21.7374 (norm. = 0.109339), norm. avg. (of 7) = 0.074675 fft 22: mflops = 33.0848 (norm. = 0.166415), norm. avg. (of 7) = 0.104845 fft 23: mflops = 67.3477 (norm. = 0.338757), norm. avg. (of 7) = 0.201476 fft 24: mflops = 141.543 (norm. = 0.711954), norm. avg. (of 7) = 0.547112 fft 25: mflops = 55.6055 (norm. = 0.279693), norm. avg. (of 4) = 0.284502 fft 26: mflops = 33.4728 (norm. = 0.168367), norm. avg. (of 6) = 0.0922542 fft 27: mflops = 98.7099 (norm. = 0.496508), norm. avg. (of 7) = 0.279031 fft 28: mflops = 25.0502 (norm. = 0.126002), norm. avg. (of 7) = 0.0925504 fft 29: mflops = 9.48511 (norm. = 0.0477098), norm. avg. (of 7) = 0.0631654 Benchmarking for array size = 256 (power of 2): 0. Arndt DIF: elapsed time t=1.06793 s, 8192 iters, t-(init.)=1.03616 s t(norm)=0.0617598, mflops=80.9588 (err=6.7e-16) 1. Arndt DIT: elapsed time t=1.0866 s, 8192 iters, t-(init.)=1.05483 s t(norm)=0.0628728, mflops=79.5256 (err=7.1e-16) 2. Arndt Split-Radix: elapsed time t=1.40953 s, 8192 iters, t-(init.)=1.37762 s t(norm)=0.0821128, mflops=60.8919 (err=7.4e-16) 3. Arndt 4-step: elapsed time t=1.50995 s, 4096 iters, t-(init.)=1.49406 s t(norm)=0.178106, mflops=28.0732 (err=7.2e-16) 4. Beauregard: elapsed time t=1.39825 s, 2048 iters, t-(init.)=1.39026 s t(norm)=0.331463, mflops=15.0846 (err=7.8e-16) 5. Bergland: elapsed time t=1.58184 s, 16384 iters, t-(init.)=1.51829 s t(norm)=0.0452486, mflops=110.501 (err=8.3e-16) 6. CWP (min N) (N=260): elapsed time t=1.59892 s, 16384 iters, t-(init.)=1.53439 s t(norm)=0.0457283, mflops=109.342 7. CWP (best N) (N=280): elapsed time t=1.28492 s, 16384 iters, t-(init.)=1.21533 s t(norm)=0.0362195, mflops=138.047 8. Edelblute: elapsed time t=1.95947 s, 8192 iters, t-(init.)=1.9277 s t(norm)=0.1149, mflops=43.5161 (err=7.0e-16) 9. FFTPACK (f2c): elapsed time t=1.98385 s, 8192 iters, t-(init.)=1.95191 s t(norm)=0.116343, mflops=42.9764 (err=7.8e-16) FFTW_MEASURE plan: (cost = 5.150195e-05) FFTW_TWIDDLE 4 FFTW_NOTW 64 10. FFTW: elapsed time t=1.71836 s, 32768 iters, t-(init.)=1.59135 s t(norm)=0.023713, mflops=210.854 (err=8.0e-16) FFTW_ESTIMATE plan: (cost = 9.216000e+02) FFTW_TWIDDLE 8 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.76075 s, 32768 iters, t-(init.)=1.63356 s t(norm)=0.0243419, mflops=205.407 (err=8.1e-16) 12. Frigo-old: elapsed time t=1.00813 s, 16384 iters, t-(init.)=0.944611 s t(norm)=0.0281516, mflops=177.61 (err=8.0e-16) 13. Green: elapsed time t=1.89028 s, 32768 iters, t-(init.)=1.76304 s t(norm)=0.0262713, mflops=190.322 (err=7.6e-16) 14. GSL: elapsed time t=1.01525 s, 8192 iters, t-(init.)=0.983451 s t(norm)=0.0586182, mflops=85.2977 (err=7.8e-16) 15. GSL DIT: elapsed time t=1.3035 s, 8192 iters, t-(init.)=1.27163 s t(norm)=0.0757948, mflops=65.9676 (err=7.7e-16) 16. GSL DIF: elapsed time t=1.24381 s, 8192 iters, t-(init.)=1.21196 s t(norm)=0.0722387, mflops=69.2149 (err=8.3e-16) 17. Krukar: elapsed time t=1.09964 s, 8192 iters, t-(init.)=1.06783 s t(norm)=0.0636474, mflops=78.5577 (err=7.7e-16) 18. Mayer (Buneman): elapsed time t=1.25305 s, 8192 iters, t-(init.)=1.22128 s t(norm)=0.0727937, mflops=68.6872 (err=7.0e-16) 19. Mayer (simple): elapsed time t=1.92413 s, 16384 iters, t-(init.)=1.86062 s t(norm)=0.0554507, mflops=90.1702 20. Mayer (lookup): elapsed time t=1.86437 s, 16384 iters, t-(init.)=1.80075 s t(norm)=0.0536664, mflops=93.1681 (err=7.1e-16) 21. NAPACK (f2c): elapsed time t=1.80506 s, 4096 iters, t-(init.)=1.78916 s t(norm)=0.213285, mflops=23.4428 (err=3.6e-15) 22. Nielsen: elapsed time t=1.14489 s, 4096 iters, t-(init.)=1.12896 s t(norm)=0.134583, mflops=37.1519 (err=3.4e-15) 23. NR (C): elapsed time t=1.18623 s, 8192 iters, t-(init.)=1.15446 s t(norm)=0.0688115, mflops=72.6623 (err=8.6e-16) 24. Ooura (C): elapsed time t=1.16915 s, 16384 iters, t-(init.)=1.1056 s t(norm)=0.0329495, mflops=151.747 (err=7.9e-16) 25. QFT: elapsed time t=1.58102 s, 8192 iters, t-(init.)=1.54917 s t(norm)=0.0923378, mflops=54.149 (err=9.5e-16) 26. Ransom: elapsed time t=1.77683 s, 8192 iters, t-(init.)=1.74506 s t(norm)=0.104014, mflops=48.0707 (err=1.7e-15) 27. Singleton (f2c): elapsed time t=1.37836 s, 16384 iters, t-(init.)=1.31481 s t(norm)=0.0391845, mflops=127.601 (err=1.3e-15) 28. Temperton (f2c): elapsed time t=1.55193 s, 4096 iters, t-(init.)=1.536 s t(norm)=0.183105, mflops=27.3067 (err=7.5e-16) 29. Valkenburg: elapsed time t=1.09723 s, 1024 iters, t-(init.)=1.09322 s t(norm)=0.521287, mflops=9.59164 (err=7.4e-16) Top mflops for N=256 = 210.854 Normalized results and averages for N=256: fft 0: mflops = 80.9588 (norm. = 0.383956), norm. avg. (of 8) = 0.41084 fft 1: mflops = 79.5256 (norm. = 0.377159), norm. avg. (of 8) = 0.396738 fft 2: mflops = 60.8919 (norm. = 0.288786), norm. avg. (of 8) = 0.241224 fft 3: mflops = 28.0732 (norm. = 0.13314), norm. avg. (of 8) = 0.077329 fft 4: mflops = 15.0846 (norm. = 0.0715405), norm. avg. (of 8) = 0.0720514 fft 5: mflops = 110.501 (norm. = 0.524062), norm. avg. (of 8) = 0.309731 fft 6: mflops = 109.342 (norm. = 0.518564), norm. avg. (of 8) = 0.314115 fft 7: mflops = 138.047 (norm. = 0.654703), norm. avg. (of 8) = 0.338376 fft 8: mflops = 43.5161 (norm. = 0.20638), norm. avg. (of 7) = 0.167127 fft 9: mflops = 42.9764 (norm. = 0.20382), norm. avg. (of 8) = 0.168564 fft 10: mflops = 210.854 (norm. = 1), norm. avg. (of 8) = 0.870288 fft 11: mflops = 205.407 (norm. = 0.974164), norm. avg. (of 8) = 0.842133 fft 12: mflops = 177.61 (norm. = 0.842334), norm. avg. (of 8) = 0.918986 fft 13: mflops = 190.322 (norm. = 0.902621), norm. avg. (of 6) = 0.678187 fft 14: mflops = 85.2977 (norm. = 0.404533), norm. avg. (of 8) = 0.305135 fft 15: mflops = 65.9676 (norm. = 0.312858), norm. avg. (of 8) = 0.207272 fft 16: mflops = 69.2149 (norm. = 0.328259), norm. avg. (of 8) = 0.208903 fft 17: mflops = 78.5577 (norm. = 0.372569), norm. avg. (of 8) = 0.482854 fft 18: mflops = 68.6872 (norm. = 0.325757), norm. avg. (of 7) = 0.282769 fft 19: mflops = 90.1702 (norm. = 0.427642), norm. avg. (of 7) = 0.345177 fft 20: mflops = 93.1681 (norm. = 0.44186), norm. avg. (of 7) = 0.342578 fft 21: mflops = 23.4428 (norm. = 0.11118), norm. avg. (of 8) = 0.0792381 fft 22: mflops = 37.1519 (norm. = 0.176197), norm. avg. (of 8) = 0.113764 fft 23: mflops = 72.6623 (norm. = 0.344609), norm. avg. (of 8) = 0.219367 fft 24: mflops = 151.747 (norm. = 0.719677), norm. avg. (of 8) = 0.568683 fft 25: mflops = 54.149 (norm. = 0.256808), norm. avg. (of 5) = 0.278963 fft 26: mflops = 48.0707 (norm. = 0.22798), norm. avg. (of 7) = 0.111644 fft 27: mflops = 127.601 (norm. = 0.605163), norm. avg. (of 8) = 0.319797 fft 28: mflops = 27.3067 (norm. = 0.129505), norm. avg. (of 8) = 0.0971697 fft 29: mflops = 9.59164 (norm. = 0.0454894), norm. avg. (of 8) = 0.0609559 Benchmarking for array size = 512 (power of 2): 0. Arndt DIF: elapsed time t=1.13795 s, 4096 iters, t-(init.)=1.10629 s t(norm)=0.0586132, mflops=85.3049 (err=6.7e-16) 1. Arndt DIT: elapsed time t=1.15711 s, 4096 iters, t-(init.)=1.12545 s t(norm)=0.0596284, mflops=83.8527 (err=6.2e-16) 2. Arndt Split-Radix: elapsed time t=1.50453 s, 4096 iters, t-(init.)=1.47283 s t(norm)=0.0780334, mflops=64.0751 (err=6.5e-16) 3. Arndt 4-step: elapsed time t=1.5923 s, 2048 iters, t-(init.)=1.57646 s t(norm)=0.167048, mflops=29.9316 (err=6.3e-16) 4. Beauregard: elapsed time t=1.57787 s, 1024 iters, t-(init.)=1.56996 s t(norm)=0.332717, mflops=15.0278 (err=6.8e-16) 5. Bergland: elapsed time t=1.64929 s, 8192 iters, t-(init.)=1.58595 s t(norm)=0.0420134, mflops=119.01 (err=7.2e-16) 6. CWP (min N) (N=520): elapsed time t=1.75939 s, 8192 iters, t-(init.)=1.69508 s t(norm)=0.0449042, mflops=111.348 7. CWP (best N) (N=560): elapsed time t=1.4331 s, 8192 iters, t-(init.)=1.36387 s t(norm)=0.0361303, mflops=138.388 8. Edelblute: elapsed time t=1.03032 s, 2048 iters, t-(init.)=1.01448 s t(norm)=0.107498, mflops=46.5124 (err=6.2e-16) 9. FFTPACK (f2c): elapsed time t=1.28666 s, 2048 iters, t-(init.)=1.27078 s t(norm)=0.134657, mflops=37.1315 (err=6.4e-16) FFTW_MEASURE plan: (cost = 1.121523e-04) FFTW_TWIDDLE 8 FFTW_NOTW 64 10. FFTW: elapsed time t=1.87074 s, 16384 iters, t-(init.)=1.74404 s t(norm)=0.0231007, mflops=216.444 (err=6.4e-16) FFTW_ESTIMATE plan: (cost = 1.843200e+03) FFTW_TWIDDLE 16 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.002 s, 8192 iters, t-(init.)=0.938653 s t(norm)=0.0248658, mflops=201.079 (err=6.5e-16) 12. Frigo-old: elapsed time t=1.12044 s, 8192 iters, t-(init.)=1.05712 s t(norm)=0.028004, mflops=178.546 (err=6.3e-16) 13. Green: elapsed time t=1.96562 s, 16384 iters, t-(init.)=1.83889 s t(norm)=0.0243569, mflops=205.28 (err=6.2e-16) 14. GSL: elapsed time t=1.26394 s, 4096 iters, t-(init.)=1.23227 s t(norm)=0.065288, mflops=76.5837 (err=6.4e-16) 15. GSL DIT: elapsed time t=1.41976 s, 4096 iters, t-(init.)=1.38807 s t(norm)=0.0735425, mflops=67.9879 (err=9.0e-16) 16. GSL DIF: elapsed time t=1.3348 s, 4096 iters, t-(init.)=1.30311 s t(norm)=0.0690413, mflops=72.4205 (err=7.8e-16) 17. Krukar: elapsed time t=1.16749 s, 4096 iters, t-(init.)=1.13581 s t(norm)=0.0601774, mflops=83.0876 (err=6.9e-16) 18. Mayer (Buneman): elapsed time t=1.32448 s, 4096 iters, t-(init.)=1.29278 s t(norm)=0.0684942, mflops=72.9989 (err=6.5e-16) 19. Mayer (simple): elapsed time t=1.02131 s, 4096 iters, t-(init.)=0.989484 s t(norm)=0.0524247, mflops=95.3748 20. Mayer (lookup): elapsed time t=1.97782 s, 8192 iters, t-(init.)=1.91435 s t(norm)=0.0507129, mflops=98.5942 (err=6.5e-16) 21. NAPACK (f2c): elapsed time t=1.01251 s, 1024 iters, t-(init.)=1.00454 s t(norm)=0.21289, mflops=23.4863 (err=6.7e-15) 22. Nielsen: elapsed time t=1.1737 s, 2048 iters, t-(init.)=1.15786 s t(norm)=0.122691, mflops=40.7527 (err=3.2e-15) 23. NR (C): elapsed time t=1.26692 s, 4096 iters, t-(init.)=1.23512 s t(norm)=0.065439, mflops=76.407 (err=7.1e-16) 24. Ooura (C): elapsed time t=1.3358 s, 8192 iters, t-(init.)=1.2724 s t(norm)=0.0337071, mflops=148.337 (err=6.9e-16) 25. QFT: elapsed time t=1.84156 s, 4096 iters, t-(init.)=1.80989 s t(norm)=0.0958914, mflops=52.1423 (err=9.5e-16) 26. Ransom: elapsed time t=1.0589 s, 2048 iters, t-(init.)=1.04306 s t(norm)=0.110526, mflops=45.2381 (err=1.5e-15) 27. Singleton (f2c): elapsed time t=1.52256 s, 8192 iters, t-(init.)=1.45922 s t(norm)=0.0386563, mflops=129.345 (err=8.4e-16) 28. Temperton (f2c): elapsed time t=1.91825 s, 2048 iters, t-(init.)=1.9024 s t(norm)=0.201586, mflops=24.8033 (err=6.4e-16) 29. Valkenburg: elapsed time t=1.22322 s, 512 iters, t-(init.)=1.21927 s t(norm)=0.516795, mflops=9.67502 (err=7.4e-16) Top mflops for N=512 = 216.444 Normalized results and averages for N=512: fft 0: mflops = 85.3049 (norm. = 0.39412), norm. avg. (of 9) = 0.408982 fft 1: mflops = 83.8527 (norm. = 0.387411), norm. avg. (of 9) = 0.395702 fft 2: mflops = 64.0751 (norm. = 0.296035), norm. avg. (of 9) = 0.247314 fft 3: mflops = 29.9316 (norm. = 0.138288), norm. avg. (of 9) = 0.0841022 fft 4: mflops = 15.0278 (norm. = 0.0694303), norm. avg. (of 9) = 0.0717602 fft 5: mflops = 119.01 (norm. = 0.549841), norm. avg. (of 9) = 0.33641 fft 6: mflops = 111.348 (norm. = 0.514444), norm. avg. (of 9) = 0.336374 fft 7: mflops = 138.388 (norm. = 0.63937), norm. avg. (of 9) = 0.37182 fft 8: mflops = 46.5124 (norm. = 0.214893), norm. avg. (of 8) = 0.173098 fft 9: mflops = 37.1315 (norm. = 0.171552), norm. avg. (of 9) = 0.168896 fft 10: mflops = 216.444 (norm. = 1), norm. avg. (of 9) = 0.8847 fft 11: mflops = 201.079 (norm. = 0.929013), norm. avg. (of 9) = 0.851786 fft 12: mflops = 178.546 (norm. = 0.824905), norm. avg. (of 9) = 0.908533 fft 13: mflops = 205.28 (norm. = 0.948423), norm. avg. (of 7) = 0.716792 fft 14: mflops = 76.5837 (norm. = 0.353827), norm. avg. (of 9) = 0.310545 fft 15: mflops = 67.9879 (norm. = 0.314113), norm. avg. (of 9) = 0.219143 fft 16: mflops = 72.4205 (norm. = 0.334592), norm. avg. (of 9) = 0.222869 fft 17: mflops = 83.0876 (norm. = 0.383876), norm. avg. (of 9) = 0.471856 fft 18: mflops = 72.9989 (norm. = 0.337265), norm. avg. (of 8) = 0.289581 fft 19: mflops = 95.3748 (norm. = 0.440644), norm. avg. (of 8) = 0.35711 fft 20: mflops = 98.5942 (norm. = 0.455519), norm. avg. (of 8) = 0.356696 fft 21: mflops = 23.4863 (norm. = 0.10851), norm. avg. (of 9) = 0.0824905 fft 22: mflops = 40.7527 (norm. = 0.188283), norm. avg. (of 9) = 0.122044 fft 23: mflops = 76.407 (norm. = 0.353011), norm. avg. (of 9) = 0.234216 fft 24: mflops = 148.337 (norm. = 0.685335), norm. avg. (of 9) = 0.581644 fft 25: mflops = 52.1423 (norm. = 0.240904), norm. avg. (of 6) = 0.27262 fft 26: mflops = 45.2381 (norm. = 0.209006), norm. avg. (of 8) = 0.123814 fft 27: mflops = 129.345 (norm. = 0.597592), norm. avg. (of 9) = 0.350663 fft 28: mflops = 24.8033 (norm. = 0.114595), norm. avg. (of 9) = 0.0991058 fft 29: mflops = 9.67502 (norm. = 0.0446999), norm. avg. (of 9) = 0.0591497 Benchmarking for array size = 1024 (power of 2): 0. Arndt DIF: elapsed time t=1.20826 s, 2048 iters, t-(init.)=1.17662 s t(norm)=0.0561055, mflops=89.1178 (err=1.0e-15) 1. Arndt DIT: elapsed time t=1.2328 s, 2048 iters, t-(init.)=1.20119 s t(norm)=0.0572771, mflops=87.295 (err=1.0e-15) 2. Arndt Split-Radix: elapsed time t=1.57417 s, 2048 iters, t-(init.)=1.54252 s t(norm)=0.073553, mflops=67.9782 (err=1.0e-15) 3. Arndt 4-step: elapsed time t=1.55681 s, 1024 iters, t-(init.)=1.54099 s t(norm)=0.146961, mflops=34.0227 (err=1.0e-15) 4. Beauregard: elapsed time t=1.76385 s, 512 iters, t-(init.)=1.75595 s t(norm)=0.33492, mflops=14.9289 (err=1.1e-15) 5. Bergland: elapsed time t=1.84699 s, 4096 iters, t-(init.)=1.78367 s t(norm)=0.042526, mflops=117.575 (err=1.1e-15) 6. CWP (min N) (N=1040): elapsed time t=1.90414 s, 4096 iters, t-(init.)=1.83995 s t(norm)=0.0438678, mflops=113.979 7. CWP (best N) (N=1040): elapsed time t=1.90403 s, 4096 iters, t-(init.)=1.83981 s t(norm)=0.0438644, mflops=113.988 8. Edelblute: elapsed time t=1.06739 s, 1024 iters, t-(init.)=1.05154 s t(norm)=0.100283, mflops=49.8589 (err=1.0e-15) 9. FFTPACK (f2c): elapsed time t=1.44304 s, 1024 iters, t-(init.)=1.4272 s t(norm)=0.136109, mflops=36.7353 (err=1.1e-15) FFTW_MEASURE plan: (cost = 3.330625e-04) FFTW_TWIDDLE 4 FFTW_TWIDDLE 4 FFTW_NOTW 64 10. FFTW: elapsed time t=1.40193 s, 4096 iters, t-(init.)=1.33857 s t(norm)=0.031914, mflops=156.671 (err=1.1e-15) FFTW_ESTIMATE plan: (cost = 1.126400e+04) FFTW_TWIDDLE 8 FFTW_TWIDDLE 4 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.44177 s, 4096 iters, t-(init.)=1.37837 s t(norm)=0.0328628, mflops=152.148 (err=1.1e-15) 12. Frigo-old: elapsed time t=1.67379 s, 4096 iters, t-(init.)=1.61054 s t(norm)=0.0383983, mflops=130.214 (err=1.1e-15) 13. Green: elapsed time t=1.15524 s, 4096 iters, t-(init.)=1.09205 s t(norm)=0.0260366, mflops=192.037 (err=1.1e-15) 14. GSL: elapsed time t=1.48023 s, 2048 iters, t-(init.)=1.44859 s t(norm)=0.0690743, mflops=72.3858 (err=1.1e-15) 15. GSL DIT: elapsed time t=1.5407 s, 2048 iters, t-(init.)=1.50909 s t(norm)=0.071959, mflops=69.484 (err=1.3e-15) 16. GSL DIF: elapsed time t=1.43127 s, 2048 iters, t-(init.)=1.39965 s t(norm)=0.0667407, mflops=74.9168 (err=1.4e-15) 17. Krukar: elapsed time t=1.79114 s, 2048 iters, t-(init.)=1.7595 s t(norm)=0.0838997, mflops=59.595 (err=1.1e-15) 18. Mayer (Buneman): elapsed time t=1.41824 s, 2048 iters, t-(init.)=1.38663 s t(norm)=0.0661199, mflops=75.6202 (err=1.0e-15) 19. Mayer (simple): elapsed time t=1.10682 s, 2048 iters, t-(init.)=1.07521 s t(norm)=0.0512698, mflops=97.5233 20. Mayer (lookup): elapsed time t=1.07376 s, 2048 iters, t-(init.)=1.04214 s t(norm)=0.0496931, mflops=100.618 (err=1.0e-15) 21. NAPACK (f2c): elapsed time t=1.10341 s, 512 iters, t-(init.)=1.09548 s t(norm)=0.208946, mflops=23.9296 (err=1.6e-14) 22. Nielsen: elapsed time t=1.41323 s, 1024 iters, t-(init.)=1.39738 s t(norm)=0.133264, mflops=37.5194 (err=7.2e-15) 23. NR (C): elapsed time t=1.36086 s, 2048 iters, t-(init.)=1.32922 s t(norm)=0.0633823, mflops=78.8863 (err=1.2e-15) 24. Ooura (C): elapsed time t=1.40401 s, 4096 iters, t-(init.)=1.34077 s t(norm)=0.0319666, mflops=156.413 (err=1.1e-15) 25. QFT: elapsed time t=1.13711 s, 1024 iters, t-(init.)=1.12123 s t(norm)=0.106929, mflops=46.7601 (err=1.4e-15) 26. Ransom: elapsed time t=1.83377 s, 2048 iters, t-(init.)=1.80216 s t(norm)=0.0859335, mflops=58.1845 (err=2.1e-15) 27. Singleton (f2c): elapsed time t=1.56308 s, 4096 iters, t-(init.)=1.49979 s t(norm)=0.0357579, mflops=139.829 (err=1.6e-15) 28. Temperton (f2c): elapsed time t=1.88911 s, 1024 iters, t-(init.)=1.87328 s t(norm)=0.17865, mflops=27.9877 (err=1.1e-15) 29. Valkenburg: elapsed time t=1.38388 s, 256 iters, t-(init.)=1.37988 s t(norm)=0.526381, mflops=9.49882 (err=1.1e-15) Top mflops for N=1024 = 192.037 Normalized results and averages for N=1024: fft 0: mflops = 89.1178 (norm. = 0.464065), norm. avg. (of 10) = 0.41449 fft 1: mflops = 87.295 (norm. = 0.454573), norm. avg. (of 10) = 0.401589 fft 2: mflops = 67.9782 (norm. = 0.353984), norm. avg. (of 10) = 0.257981 fft 3: mflops = 34.0227 (norm. = 0.177167), norm. avg. (of 10) = 0.0934087 fft 4: mflops = 14.9289 (norm. = 0.0777397), norm. avg. (of 10) = 0.0723581 fft 5: mflops = 117.575 (norm. = 0.612251), norm. avg. (of 10) = 0.363994 fft 6: mflops = 113.979 (norm. = 0.593524), norm. avg. (of 10) = 0.362089 fft 7: mflops = 113.988 (norm. = 0.59357), norm. avg. (of 10) = 0.393995 fft 8: mflops = 49.8589 (norm. = 0.259632), norm. avg. (of 9) = 0.182713 fft 9: mflops = 36.7353 (norm. = 0.191293), norm. avg. (of 10) = 0.171136 fft 10: mflops = 156.671 (norm. = 0.815837), norm. avg. (of 10) = 0.877814 fft 11: mflops = 152.148 (norm. = 0.792283), norm. avg. (of 10) = 0.845836 fft 12: mflops = 130.214 (norm. = 0.678068), norm. avg. (of 10) = 0.885486 fft 13: mflops = 192.037 (norm. = 1), norm. avg. (of 8) = 0.752193 fft 14: mflops = 72.3858 (norm. = 0.376936), norm. avg. (of 10) = 0.317184 fft 15: mflops = 69.484 (norm. = 0.361826), norm. avg. (of 10) = 0.233411 fft 16: mflops = 74.9168 (norm. = 0.390116), norm. avg. (of 10) = 0.239593 fft 17: mflops = 59.595 (norm. = 0.31033), norm. avg. (of 10) = 0.455704 fft 18: mflops = 75.6202 (norm. = 0.393779), norm. avg. (of 9) = 0.301159 fft 19: mflops = 97.5233 (norm. = 0.507835), norm. avg. (of 9) = 0.373857 fft 20: mflops = 100.618 (norm. = 0.523949), norm. avg. (of 9) = 0.37528 fft 21: mflops = 23.9296 (norm. = 0.124609), norm. avg. (of 10) = 0.0867024 fft 22: mflops = 37.5194 (norm. = 0.195376), norm. avg. (of 10) = 0.129377 fft 23: mflops = 78.8863 (norm. = 0.410787), norm. avg. (of 10) = 0.251874 fft 24: mflops = 156.413 (norm. = 0.814495), norm. avg. (of 10) = 0.604929 fft 25: mflops = 46.7601 (norm. = 0.243495), norm. avg. (of 7) = 0.268459 fft 26: mflops = 58.1845 (norm. = 0.302986), norm. avg. (of 9) = 0.143722 fft 27: mflops = 139.829 (norm. = 0.728137), norm. avg. (of 10) = 0.388411 fft 28: mflops = 27.9877 (norm. = 0.145741), norm. avg. (of 10) = 0.103769 fft 29: mflops = 9.49882 (norm. = 0.0494634), norm. avg. (of 10) = 0.058181 Benchmarking for array size = 2048 (power of 2): 0. Arndt DIF: elapsed time t=1.31382 s, 1024 iters, t-(init.)=1.28129 s t(norm)=0.0555425, mflops=90.0212 (err=1.4e-15) 1. Arndt DIT: elapsed time t=1.35541 s, 1024 iters, t-(init.)=1.32264 s t(norm)=0.0573348, mflops=87.2071 (err=1.4e-15) 2. Arndt Split-Radix: elapsed time t=1.74005 s, 1024 iters, t-(init.)=1.7076 s t(norm)=0.0740224, mflops=67.5471 (err=1.4e-15) 3. Arndt 4-step: elapsed time t=1.76239 s, 512 iters, t-(init.)=1.74604 s t(norm)=0.151378, mflops=33.03 (err=1.4e-15) 4. Beauregard: elapsed time t=1.96291 s, 256 iters, t-(init.)=1.95475 s t(norm)=0.338945, mflops=14.7517 (err=1.5e-15) 5. Bergland: elapsed time t=1.95827 s, 2048 iters, t-(init.)=1.89316 s t(norm)=0.0410332, mflops=121.853 (err=1.5e-15) 6. CWP (min N) (N=2145): elapsed time t=1.26101 s, 1024 iters, t-(init.)=1.20411 s t(norm)=0.0521966, mflops=95.7916 7. CWP (best N) (N=2184): elapsed time t=1.13171 s, 1024 iters, t-(init.)=1.06427 s t(norm)=0.0461347, mflops=108.378 8. Edelblute: elapsed time t=1.15403 s, 512 iters, t-(init.)=1.13761 s t(norm)=0.098628, mflops=50.6956 (err=1.4e-15) 9. FFTPACK (f2c): elapsed time t=1.67588 s, 512 iters, t-(init.)=1.65951 s t(norm)=0.143876, mflops=34.7521 (err=1.5e-15) FFTW_MEASURE plan: (cost = 8.409062e-04) FFTW_TWIDDLE 32 FFTW_NOTW 64 10. FFTW: elapsed time t=1.717 s, 2048 iters, t-(init.)=1.65197 s t(norm)=0.0358056, mflops=139.643 (err=1.5e-15) FFTW_ESTIMATE plan: (cost = 1.269760e+04) FFTW_TWIDDLE 8 FFTW_TWIDDLE 8 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.75748 s, 2048 iters, t-(init.)=1.69248 s t(norm)=0.0366834, mflops=136.301 (err=1.5e-15) 12. Frigo-old: elapsed time t=1.1672 s, 1024 iters, t-(init.)=1.1347 s t(norm)=0.0491879, mflops=101.651 (err=1.5e-15) 13. Green: elapsed time t=1.47031 s, 2048 iters, t-(init.)=1.4053 s t(norm)=0.0304591, mflops=164.155 (err=1.5e-15) 14. GSL: elapsed time t=1.00318 s, 512 iters, t-(init.)=0.986902 s t(norm)=0.0855621, mflops=58.4371 (err=1.5e-15) 15. GSL DIT: elapsed time t=1.72016 s, 1024 iters, t-(init.)=1.68763 s t(norm)=0.0731567, mflops=68.3464 (err=2.1e-15) 16. GSL DIF: elapsed time t=1.5969 s, 1024 iters, t-(init.)=1.56434 s t(norm)=0.0678122, mflops=73.733 (err=2.2e-15) 17. Krukar: elapsed time t=1.04777 s, 512 iters, t-(init.)=1.03148 s t(norm)=0.0894269, mflops=55.9116 (err=1.5e-15) 18. Mayer (Buneman): elapsed time t=1.50608 s, 1024 iters, t-(init.)=1.47358 s t(norm)=0.063878, mflops=78.2742 (err=1.4e-15) 19. Mayer (simple): elapsed time t=1.18751 s, 1024 iters, t-(init.)=1.15504 s t(norm)=0.0500695, mflops=99.8613 20. Mayer (lookup): elapsed time t=1.21869 s, 1024 iters, t-(init.)=1.18624 s t(norm)=0.051422, mflops=97.2346 (err=1.4e-15) 21. NAPACK (f2c): elapsed time t=1.55059 s, 256 iters, t-(init.)=1.54233 s t(norm)=0.267433, mflops=18.6962 (err=1.5e-14) 22. Nielsen: elapsed time t=1.62797 s, 512 iters, t-(init.)=1.61167 s t(norm)=0.139728, mflops=35.7837 (err=1.2e-14) 23. NR (C): elapsed time t=1.51182 s, 1024 iters, t-(init.)=1.47927 s t(norm)=0.0641248, mflops=77.9729 (err=1.6e-15) 24. Ooura (C): elapsed time t=1.81928 s, 2048 iters, t-(init.)=1.75428 s t(norm)=0.038023, mflops=131.499 (err=1.4e-15) 25. QFT: elapsed time t=1.35237 s, 512 iters, t-(init.)=1.33607 s t(norm)=0.115834, mflops=43.1652 (err=1.9e-15) 26. Ransom: elapsed time t=1.14887 s, 512 iters, t-(init.)=1.13252 s t(norm)=0.0981868, mflops=50.9234 (err=2.6e-15) 27. Singleton (f2c): elapsed time t=1.92402 s, 2048 iters, t-(init.)=1.85907 s t(norm)=0.0402943, mflops=124.087 (err=2.0e-15) 28. Temperton (f2c): elapsed time t=1.12088 s, 256 iters, t-(init.)=1.11258 s t(norm)=0.192916, mflops=25.918 (err=1.5e-15) 29. Valkenburg: elapsed time t=1.61632 s, 128 iters, t-(init.)=1.61225 s t(norm)=0.559113, mflops=8.94274 (err=1.5e-15) Top mflops for N=2048 = 164.155 Normalized results and averages for N=2048: fft 0: mflops = 90.0212 (norm. = 0.548393), norm. avg. (of 11) = 0.426663 fft 1: mflops = 87.2071 (norm. = 0.531249), norm. avg. (of 11) = 0.413376 fft 2: mflops = 67.5471 (norm. = 0.411484), norm. avg. (of 11) = 0.271936 fft 3: mflops = 33.03 (norm. = 0.201213), norm. avg. (of 11) = 0.103209 fft 4: mflops = 14.7517 (norm. = 0.0898645), norm. avg. (of 11) = 0.0739496 fft 5: mflops = 121.853 (norm. = 0.742303), norm. avg. (of 11) = 0.398386 fft 6: mflops = 95.7916 (norm. = 0.583545), norm. avg. (of 11) = 0.382221 fft 7: mflops = 108.378 (norm. = 0.660221), norm. avg. (of 11) = 0.418197 fft 8: mflops = 50.6956 (norm. = 0.308828), norm. avg. (of 10) = 0.195324 fft 9: mflops = 34.7521 (norm. = 0.211704), norm. avg. (of 11) = 0.174824 fft 10: mflops = 139.643 (norm. = 0.850679), norm. avg. (of 11) = 0.875347 fft 11: mflops = 136.301 (norm. = 0.830323), norm. avg. (of 11) = 0.844425 fft 12: mflops = 101.651 (norm. = 0.61924), norm. avg. (of 11) = 0.861282 fft 13: mflops = 164.155 (norm. = 1), norm. avg. (of 9) = 0.779727 fft 14: mflops = 58.4371 (norm. = 0.355988), norm. avg. (of 11) = 0.320712 fft 15: mflops = 68.3464 (norm. = 0.416354), norm. avg. (of 11) = 0.250043 fft 16: mflops = 73.733 (norm. = 0.449168), norm. avg. (of 11) = 0.258646 fft 17: mflops = 55.9116 (norm. = 0.340603), norm. avg. (of 11) = 0.44524 fft 18: mflops = 78.2742 (norm. = 0.476832), norm. avg. (of 10) = 0.318726 fft 19: mflops = 99.8613 (norm. = 0.608336), norm. avg. (of 10) = 0.397305 fft 20: mflops = 97.2346 (norm. = 0.592335), norm. avg. (of 10) = 0.396985 fft 21: mflops = 18.6962 (norm. = 0.113894), norm. avg. (of 11) = 0.0891744 fft 22: mflops = 35.7837 (norm. = 0.217988), norm. avg. (of 11) = 0.137433 fft 23: mflops = 77.9729 (norm. = 0.474997), norm. avg. (of 11) = 0.272157 fft 24: mflops = 131.499 (norm. = 0.80107), norm. avg. (of 11) = 0.62276 fft 25: mflops = 43.1652 (norm. = 0.262954), norm. avg. (of 8) = 0.267771 fft 26: mflops = 50.9234 (norm. = 0.310216), norm. avg. (of 10) = 0.160371 fft 27: mflops = 124.087 (norm. = 0.755915), norm. avg. (of 11) = 0.42182 fft 28: mflops = 25.918 (norm. = 0.157888), norm. avg. (of 11) = 0.108689 fft 29: mflops = 8.94274 (norm. = 0.0544775), norm. avg. (of 11) = 0.0578444 Benchmarking for array size = 4096 (power of 2): 0. Arndt DIF: elapsed time t=1.40336 s, 256 iters, t-(init.)=1.35992 s t(norm)=0.108076, mflops=46.2636 (err=2.5e-15) 1. Arndt DIT: elapsed time t=1.39611 s, 256 iters, t-(init.)=1.35284 s t(norm)=0.107514, mflops=46.5056 (err=2.5e-15) 2. Arndt Split-Radix: elapsed time t=1.7845 s, 256 iters, t-(init.)=1.74101 s t(norm)=0.138363, mflops=36.1368 (err=2.5e-15) 3. Arndt 4-step: elapsed time t=1.04211 s, 128 iters, t-(init.)=1.02034 s t(norm)=0.162178, mflops=30.8303 (err=2.5e-15) 4. Beauregard: elapsed time t=1.16456 s, 64 iters, t-(init.)=1.15364 s t(norm)=0.366733, mflops=13.6339 (err=2.6e-15) 5. Bergland: elapsed time t=1.53716 s, 512 iters, t-(init.)=1.45019 s t(norm)=0.0576254, mflops=86.7673 (err=2.5e-15) 6. CWP (min N) (N=4290): elapsed time t=1.59384 s, 512 iters, t-(init.)=1.50265 s t(norm)=0.0597097, mflops=83.7384 7. CWP (best N) (N=4368): elapsed time t=1.41308 s, 512 iters, t-(init.)=1.32023 s t(norm)=0.0524612, mflops=95.3086 8. Edelblute: elapsed time t=1.03495 s, 128 iters, t-(init.)=1.01324 s t(norm)=0.16105, mflops=31.0462 (err=2.5e-15) 9. FFTPACK (f2c): elapsed time t=1.77101 s, 256 iters, t-(init.)=1.72745 s t(norm)=0.137286, mflops=36.4204 (err=2.6e-15) FFTW_MEASURE plan: (cost = 1.849656e-03) FFTW_TWIDDLE 8 FFTW_TWIDDLE 8 FFTW_NOTW 64 10. FFTW: elapsed time t=1.90798 s, 1024 iters, t-(init.)=1.73401 s t(norm)=0.0344516, mflops=145.131 (err=2.6e-15) FFTW_ESTIMATE plan: (cost = 2.539520e+04) FFTW_TWIDDLE 16 FFTW_TWIDDLE 8 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.08259 s, 512 iters, t-(init.)=0.995522 s t(norm)=0.0395585, mflops=126.395 (err=2.6e-15) 12. Frigo-old: elapsed time t=1.29303 s, 512 iters, t-(init.)=1.20607 s t(norm)=0.0479248, mflops=104.33 (err=2.6e-15) 13. Green: elapsed time t=1.17324 s, 512 iters, t-(init.)=1.08627 s t(norm)=0.0431645, mflops=115.836 (err=2.6e-15) 14. GSL: elapsed time t=1.03948 s, 256 iters, t-(init.)=0.995868 s t(norm)=0.0791445, mflops=63.1756 (err=2.6e-15) 15. GSL DIT: elapsed time t=1.4733 s, 256 iters, t-(init.)=1.42966 s t(norm)=0.113619, mflops=44.0067 (err=3.0e-15) 16. GSL DIF: elapsed time t=1.4902 s, 256 iters, t-(init.)=1.44675 s t(norm)=0.114978, mflops=43.4867 (err=3.1e-15) 17. Krukar: elapsed time t=1.24558 s, 256 iters, t-(init.)=1.20191 s t(norm)=0.0955193, mflops=52.3454 (err=2.6e-15) 18. Mayer (Buneman): elapsed time t=1.74601 s, 512 iters, t-(init.)=1.6591 s t(norm)=0.0659269, mflops=75.8416 (err=2.5e-15) 19. Mayer (simple): elapsed time t=1.40922 s, 512 iters, t-(init.)=1.32212 s t(norm)=0.0525364, mflops=95.1722 20. Mayer (lookup): elapsed time t=1.54343 s, 512 iters, t-(init.)=1.45652 s t(norm)=0.0578768, mflops=86.3904 (err=2.5e-15) 21. NAPACK (f2c): elapsed time t=1.64799 s, 128 iters, t-(init.)=1.62617 s t(norm)=0.258472, mflops=19.3444 (err=4.7e-14) 22. Nielsen: elapsed time t=1.04179 s, 128 iters, t-(init.)=1.02001 s t(norm)=0.162126, mflops=30.8403 (err=2.2e-14) 23. NR (C): elapsed time t=1.37137 s, 256 iters, t-(init.)=1.32777 s t(norm)=0.105522, mflops=47.3837 (err=2.6e-15) 24. Ooura (C): elapsed time t=1.33857 s, 512 iters, t-(init.)=1.25161 s t(norm)=0.0497346, mflops=100.534 (err=2.5e-15) 25. QFT: elapsed time t=1.62009 s, 256 iters, t-(init.)=1.57651 s t(norm)=0.12529, mflops=39.9075 (err=3.1e-15) 26. Ransom: elapsed time t=1.1853 s, 256 iters, t-(init.)=1.1417 s t(norm)=0.0907343, mflops=55.1059 (err=3.1e-15) 27. Singleton (f2c): elapsed time t=1.72173 s, 512 iters, t-(init.)=1.63473 s t(norm)=0.0649582, mflops=76.9726 (err=3.8e-15) 28. Temperton (f2c): elapsed time t=1.23904 s, 128 iters, t-(init.)=1.21728 s t(norm)=0.193481, mflops=25.8423 (err=2.6e-15) 29. Valkenburg: elapsed time t=1.82491 s, 64 iters, t-(init.)=1.81399 s t(norm)=0.576652, mflops=8.67075 (err=2.5e-15) Top mflops for N=4096 = 145.131 Normalized results and averages for N=4096: fft 0: mflops = 46.2636 (norm. = 0.318771), norm. avg. (of 12) = 0.417672 fft 1: mflops = 46.5056 (norm. = 0.320438), norm. avg. (of 12) = 0.405631 fft 2: mflops = 36.1368 (norm. = 0.248994), norm. avg. (of 12) = 0.270024 fft 3: mflops = 30.8303 (norm. = 0.212431), norm. avg. (of 12) = 0.112311 fft 4: mflops = 13.6339 (norm. = 0.0939419), norm. avg. (of 12) = 0.0756156 fft 5: mflops = 86.7673 (norm. = 0.597854), norm. avg. (of 12) = 0.415008 fft 6: mflops = 83.7384 (norm. = 0.576985), norm. avg. (of 12) = 0.398452 fft 7: mflops = 95.3086 (norm. = 0.656707), norm. avg. (of 12) = 0.438073 fft 8: mflops = 31.0462 (norm. = 0.213918), norm. avg. (of 11) = 0.197015 fft 9: mflops = 36.4204 (norm. = 0.250948), norm. avg. (of 12) = 0.181167 fft 10: mflops = 145.131 (norm. = 1), norm. avg. (of 12) = 0.885735 fft 11: mflops = 126.395 (norm. = 0.870903), norm. avg. (of 12) = 0.846632 fft 12: mflops = 104.33 (norm. = 0.718867), norm. avg. (of 12) = 0.849414 fft 13: mflops = 115.836 (norm. = 0.798147), norm. avg. (of 10) = 0.781569 fft 14: mflops = 63.1756 (norm. = 0.4353), norm. avg. (of 12) = 0.330261 fft 15: mflops = 44.0067 (norm. = 0.30322), norm. avg. (of 12) = 0.254474 fft 16: mflops = 43.4867 (norm. = 0.299638), norm. avg. (of 12) = 0.262062 fft 17: mflops = 52.3454 (norm. = 0.360677), norm. avg. (of 12) = 0.438193 fft 18: mflops = 75.8416 (norm. = 0.522573), norm. avg. (of 11) = 0.337258 fft 19: mflops = 95.1722 (norm. = 0.655767), norm. avg. (of 11) = 0.420802 fft 20: mflops = 86.3904 (norm. = 0.595258), norm. avg. (of 11) = 0.41501 fft 21: mflops = 19.3444 (norm. = 0.133289), norm. avg. (of 12) = 0.0928506 fft 22: mflops = 30.8403 (norm. = 0.212499), norm. avg. (of 12) = 0.143688 fft 23: mflops = 47.3837 (norm. = 0.326489), norm. avg. (of 12) = 0.276685 fft 24: mflops = 100.534 (norm. = 0.69271), norm. avg. (of 12) = 0.628589 fft 25: mflops = 39.9075 (norm. = 0.274975), norm. avg. (of 9) = 0.268572 fft 26: mflops = 55.1059 (norm. = 0.379698), norm. avg. (of 11) = 0.18031 fft 27: mflops = 76.9726 (norm. = 0.530366), norm. avg. (of 12) = 0.430865 fft 28: mflops = 25.8423 (norm. = 0.178062), norm. avg. (of 12) = 0.11447 fft 29: mflops = 8.67075 (norm. = 0.0597442), norm. avg. (of 12) = 0.0580027 Benchmarking for array size = 8192 (power of 2): 0. Arndt DIF: elapsed time t=1.46338 s, 128 iters, t-(init.)=1.41983 s t(norm)=0.104158, mflops=48.0038 (err=3.0e-15) 1. Arndt DIT: elapsed time t=1.45215 s, 128 iters, t-(init.)=1.40871 s t(norm)=0.103342, mflops=48.383 (err=3.0e-15) 2. Arndt Split-Radix: elapsed time t=1.97393 s, 128 iters, t-(init.)=1.93039 s t(norm)=0.141612, mflops=35.3077 (err=3.0e-15) 3. Arndt 4-step: elapsed time t=1.21405 s, 64 iters, t-(init.)=1.19233 s t(norm)=0.174937, mflops=28.5817 (err=2.9e-15) 4. Beauregard: elapsed time t=1.26547 s, 32 iters, t-(init.)=1.2544 s t(norm)=0.368089, mflops=13.5837 (err=2.9e-15) 5. Bergland: elapsed time t=1.77645 s, 256 iters, t-(init.)=1.68941 s t(norm)=0.0619672, mflops=80.6878 (err=2.9e-15) 6. CWP (min N) (N=8580): elapsed time t=1.666 s, 256 iters, t-(init.)=1.57478 s t(norm)=0.0577627, mflops=86.5611 7. CWP (best N) (N=9240): elapsed time t=1.58132 s, 256 iters, t-(init.)=1.48326 s t(norm)=0.0544057, mflops=91.9022 8. Edelblute: elapsed time t=1.13012 s, 64 iters, t-(init.)=1.10841 s t(norm)=0.162625, mflops=30.7455 (err=3.0e-15) 9. FFTPACK (f2c): elapsed time t=1.075 s, 64 iters, t-(init.)=1.0531 s t(norm)=0.15451, mflops=32.3604 (err=2.9e-15) FFTW_MEASURE plan: (cost = 4.301375e-03) FFTW_TWIDDLE 8 FFTW_TWIDDLE 16 FFTW_NOTW 64 10. FFTW: elapsed time t=1.15617 s, 256 iters, t-(init.)=1.06907 s t(norm)=0.0392132, mflops=127.508 (err=2.9e-15) FFTW_ESTIMATE plan: (cost = 5.079040e+04) FFTW_TWIDDLE 16 FFTW_TWIDDLE 16 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.20062 s, 256 iters, t-(init.)=1.1135 s t(norm)=0.040843, mflops=122.42 (err=2.9e-15) 12. Frigo-old: elapsed time t=1.51844 s, 256 iters, t-(init.)=1.43125 s t(norm)=0.0524981, mflops=95.2416 (err=2.9e-15) 13. Green: elapsed time t=1.37561 s, 256 iters, t-(init.)=1.28864 s t(norm)=0.0472671, mflops=105.782 (err=2.9e-15) 14. GSL: elapsed time t=1.28241 s, 128 iters, t-(init.)=1.23884 s t(norm)=0.0908805, mflops=55.0173 (err=2.9e-15) 15. GSL DIT: elapsed time t=1.6044 s, 128 iters, t-(init.)=1.5609 s t(norm)=0.114507, mflops=43.6654 (err=3.6e-15) 16. GSL DIF: elapsed time t=1.61468 s, 128 iters, t-(init.)=1.57119 s t(norm)=0.115262, mflops=43.3796 (err=3.6e-15) 17. Skipping fft (Krukar can't handle N > 4096). 18. Mayer (Buneman): elapsed time t=1.46672 s, 128 iters, t-(init.)=1.42321 s t(norm)=0.104406, mflops=47.8898 (err=2.9e-15) 19. Mayer (simple): elapsed time t=1.30553 s, 128 iters, t-(init.)=1.26208 s t(norm)=0.0925854, mflops=54.0042 20. Mayer (lookup): elapsed time t=1.34915 s, 128 iters, t-(init.)=1.30555 s t(norm)=0.0957746, mflops=52.2059 (err=3.0e-15) 21. NAPACK (f2c): elapsed time t=1.82094 s, 64 iters, t-(init.)=1.79916 s t(norm)=0.26397, mflops=18.9415 (err=4.3e-14) 22. Nielsen: elapsed time t=1.21242 s, 64 iters, t-(init.)=1.19054 s t(norm)=0.174675, mflops=28.6245 (err=1.1e-14) 23. NR (C): elapsed time t=1.49402 s, 128 iters, t-(init.)=1.45033 s t(norm)=0.106396, mflops=46.9943 (err=3.0e-15) 24. Ooura (C): elapsed time t=1.51301 s, 256 iters, t-(init.)=1.42589 s t(norm)=0.0523014, mflops=95.5998 (err=2.9e-15) 25. QFT: elapsed time t=1.02596 s, 64 iters, t-(init.)=1.00395 s t(norm)=0.147298, mflops=33.9447 (err=4.0e-15) 26. Ransom: elapsed time t=1.42459 s, 128 iters, t-(init.)=1.38113 s t(norm)=0.101319, mflops=49.3491 (err=4.1e-15) 27. Singleton (f2c): elapsed time t=1.96172 s, 256 iters, t-(init.)=1.87466 s t(norm)=0.0687623, mflops=72.7143 (err=4.4e-15) 28. Temperton (f2c): elapsed time t=1.45827 s, 64 iters, t-(init.)=1.43644 s t(norm)=0.210754, mflops=23.7243 (err=2.9e-15) 29. Valkenburg: elapsed time t=1.0125 s, 16 iters, t-(init.)=1.00699 s t(norm)=0.590978, mflops=8.46056 (err=2.9e-15) Top mflops for N=8192 = 127.508 Normalized results and averages for N=8192: fft 0: mflops = 48.0038 (norm. = 0.376476), norm. avg. (of 13) = 0.414503 fft 1: mflops = 48.383 (norm. = 0.37945), norm. avg. (of 13) = 0.403617 fft 2: mflops = 35.3077 (norm. = 0.276905), norm. avg. (of 13) = 0.270553 fft 3: mflops = 28.5817 (norm. = 0.224156), norm. avg. (of 13) = 0.120914 fft 4: mflops = 13.5837 (norm. = 0.106532), norm. avg. (of 13) = 0.0779938 fft 5: mflops = 80.6878 (norm. = 0.632806), norm. avg. (of 13) = 0.431762 fft 6: mflops = 86.5611 (norm. = 0.678868), norm. avg. (of 13) = 0.420022 fft 7: mflops = 91.9022 (norm. = 0.720756), norm. avg. (of 13) = 0.459818 fft 8: mflops = 30.7455 (norm. = 0.241126), norm. avg. (of 12) = 0.200691 fft 9: mflops = 32.3604 (norm. = 0.253791), norm. avg. (of 13) = 0.186754 fft 10: mflops = 127.508 (norm. = 1), norm. avg. (of 13) = 0.894524 fft 11: mflops = 122.42 (norm. = 0.960097), norm. avg. (of 13) = 0.85536 fft 12: mflops = 95.2416 (norm. = 0.746946), norm. avg. (of 13) = 0.841532 fft 13: mflops = 105.782 (norm. = 0.82961), norm. avg. (of 11) = 0.785937 fft 14: mflops = 55.0173 (norm. = 0.431481), norm. avg. (of 13) = 0.338047 fft 15: mflops = 43.6654 (norm. = 0.342452), norm. avg. (of 13) = 0.261242 fft 16: mflops = 43.3796 (norm. = 0.340211), norm. avg. (of 13) = 0.268073 fft 17: mflops = -1 (norm. = -0.00784264), norm. avg. (of 12) = 0.438193 fft 18: mflops = 47.8898 (norm. = 0.375583), norm. avg. (of 12) = 0.340451 fft 19: mflops = 54.0042 (norm. = 0.423536), norm. avg. (of 12) = 0.42103 fft 20: mflops = 52.2059 (norm. = 0.409432), norm. avg. (of 12) = 0.414545 fft 21: mflops = 18.9415 (norm. = 0.148552), norm. avg. (of 13) = 0.0971353 fft 22: mflops = 28.6245 (norm. = 0.224492), norm. avg. (of 13) = 0.149904 fft 23: mflops = 46.9943 (norm. = 0.36856), norm. avg. (of 13) = 0.283752 fft 24: mflops = 95.5998 (norm. = 0.749755), norm. avg. (of 13) = 0.63791 fft 25: mflops = 33.9447 (norm. = 0.266216), norm. avg. (of 10) = 0.268336 fft 26: mflops = 49.3491 (norm. = 0.387027), norm. avg. (of 12) = 0.197536 fft 27: mflops = 72.7143 (norm. = 0.570272), norm. avg. (of 13) = 0.441589 fft 28: mflops = 23.7243 (norm. = 0.186062), norm. avg. (of 13) = 0.119977 fft 29: mflops = 8.46056 (norm. = 0.0663531), norm. avg. (of 13) = 0.058645 Benchmarking for array size = 16384 (power of 2): 0. Arndt DIF: elapsed time t=1.64883 s, 64 iters, t-(init.)=1.60526 s t(norm)=0.10935, mflops=45.7249 (err=5.6e-15) 1. Arndt DIT: elapsed time t=1.63921 s, 64 iters, t-(init.)=1.59561 s t(norm)=0.108692, mflops=46.0014 (err=5.6e-15) 2. Arndt Split-Radix: elapsed time t=1.05509 s, 32 iters, t-(init.)=1.03331 s t(norm)=0.140777, mflops=35.5172 (err=5.6e-15) 3. Arndt 4-step: elapsed time t=1.09645 s, 32 iters, t-(init.)=1.07461 s t(norm)=0.146404, mflops=34.1521 (err=5.6e-15) 4. Beauregard: elapsed time t=1.36435 s, 16 iters, t-(init.)=1.35348 s t(norm)=0.368794, mflops=13.5577 (err=5.7e-15) 5. Bergland: elapsed time t=1.81178 s, 128 iters, t-(init.)=1.72485 s t(norm)=0.0587482, mflops=85.109 (err=5.7e-15) 6. CWP (min N) (N=17160): elapsed time t=1.77809 s, 128 iters, t-(init.)=1.68682 s t(norm)=0.0574528, mflops=87.028 7. CWP (best N) (N=17160): elapsed time t=1.77852 s, 128 iters, t-(init.)=1.6873 s t(norm)=0.0574692, mflops=87.0032 8. Edelblute: elapsed time t=1.19817 s, 32 iters, t-(init.)=1.1764 s t(norm)=0.160272, mflops=31.1969 (err=5.6e-15) 9. FFTPACK (f2c): elapsed time t=1.24401 s, 32 iters, t-(init.)=1.22194 s t(norm)=0.166476, mflops=30.0344 (err=5.7e-15) FFTW_MEASURE plan: (cost = 1.318900e-02) FFTW_TWIDDLE 8 FFTW_TWIDDLE 8 FFTW_TWIDDLE 4 FFTW_NOTW 64 10. FFTW: elapsed time t=1.68138 s, 128 iters, t-(init.)=1.5931 s t(norm)=0.0542607, mflops=92.1477 (err=5.7e-15) FFTW_ESTIMATE plan: (cost = 1.441792e+05) FFTW_TWIDDLE 8 FFTW_TWIDDLE 8 FFTW_TWIDDLE 8 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.68556 s, 128 iters, t-(init.)=1.59726 s t(norm)=0.0544022, mflops=91.9081 (err=5.7e-15) 12. Frigo-old: elapsed time t=1.18697 s, 64 iters, t-(init.)=1.14235 s t(norm)=0.0778166, mflops=64.2536 (err=5.7e-15) 13. Green: elapsed time t=1.53697 s, 128 iters, t-(init.)=1.45002 s t(norm)=0.0493875, mflops=101.24 (err=5.7e-15) 14. GSL: elapsed time t=1.57333 s, 64 iters, t-(init.)=1.5295 s t(norm)=0.104189, mflops=47.9896 (err=5.7e-15) 15. GSL DIT: elapsed time t=1.72003 s, 64 iters, t-(init.)=1.67674 s t(norm)=0.114219, mflops=43.7756 (err=6.3e-15) 16. GSL DIF: elapsed time t=1.72978 s, 64 iters, t-(init.)=1.68622 s t(norm)=0.114865, mflops=43.5295 (err=6.4e-15) 17. Skipping fft (Krukar can't handle N > 4096). 18. Mayer (Buneman): elapsed time t=1.61935 s, 64 iters, t-(init.)=1.5758 s t(norm)=0.107343, mflops=46.5799 (err=5.6e-15) 19. Mayer (simple): elapsed time t=1.45768 s, 64 iters, t-(init.)=1.41412 s t(norm)=0.0963291, mflops=51.9054 20. Mayer (lookup): elapsed time t=1.51377 s, 64 iters, t-(init.)=1.47024 s t(norm)=0.100152, mflops=49.9241 (err=5.6e-15) 21. NAPACK (f2c): elapsed time t=1.96603 s, 32 iters, t-(init.)=1.94396 s t(norm)=0.264844, mflops=18.879 (err=2.3e-13) 22. Nielsen: elapsed time t=1.25642 s, 32 iters, t-(init.)=1.23425 s t(norm)=0.168153, mflops=29.7349 (err=1.3e-13) 23. NR (C): elapsed time t=1.6035 s, 64 iters, t-(init.)=1.56004 s t(norm)=0.10627, mflops=47.0502 (err=5.6e-15) 24. Ooura (C): elapsed time t=1.55572 s, 128 iters, t-(init.)=1.46873 s t(norm)=0.0500246, mflops=99.9509 (err=5.7e-15) 25. QFT: elapsed time t=1.48054 s, 32 iters, t-(init.)=1.45688 s t(norm)=0.198484, mflops=25.191 (err=7.0e-15) 26. Ransom: elapsed time t=1.25879 s, 64 iters, t-(init.)=1.21522 s t(norm)=0.0827806, mflops=60.4006 (err=6.0e-15) 27. Singleton (f2c): elapsed time t=1.00603 s, 64 iters, t-(init.)=0.962511 s t(norm)=0.0655659, mflops=76.2592 (err=8.5e-15) 28. Temperton (f2c): elapsed time t=1.45809 s, 32 iters, t-(init.)=1.43634 s t(norm)=0.195686, mflops=25.5511 (err=5.7e-15) 29. Valkenburg: elapsed time t=1.13458 s, 8 iters, t-(init.)=1.1284 s t(norm)=0.614927, mflops=8.13105 (err=5.7e-15) Top mflops for N=16384 = 101.24 Normalized results and averages for N=16384: fft 0: mflops = 45.7249 (norm. = 0.451648), norm. avg. (of 14) = 0.417156 fft 1: mflops = 46.0014 (norm. = 0.454379), norm. avg. (of 14) = 0.407243 fft 2: mflops = 35.5172 (norm. = 0.350822), norm. avg. (of 14) = 0.276287 fft 3: mflops = 34.1521 (norm. = 0.337338), norm. avg. (of 14) = 0.136373 fft 4: mflops = 13.5577 (norm. = 0.133916), norm. avg. (of 14) = 0.0819883 fft 5: mflops = 85.109 (norm. = 0.840665), norm. avg. (of 14) = 0.460969 fft 6: mflops = 87.028 (norm. = 0.859619), norm. avg. (of 14) = 0.451422 fft 7: mflops = 87.0032 (norm. = 0.859374), norm. avg. (of 14) = 0.488358 fft 8: mflops = 31.1969 (norm. = 0.308148), norm. avg. (of 13) = 0.208957 fft 9: mflops = 30.0344 (norm. = 0.296665), norm. avg. (of 14) = 0.194604 fft 10: mflops = 92.1477 (norm. = 0.91019), norm. avg. (of 14) = 0.895643 fft 11: mflops = 91.9081 (norm. = 0.907822), norm. avg. (of 14) = 0.859107 fft 12: mflops = 64.2536 (norm. = 0.634665), norm. avg. (of 14) = 0.826756 fft 13: mflops = 101.24 (norm. = 1), norm. avg. (of 12) = 0.803775 fft 14: mflops = 47.9896 (norm. = 0.474017), norm. avg. (of 14) = 0.347759 fft 15: mflops = 43.7756 (norm. = 0.432394), norm. avg. (of 14) = 0.273467 fft 16: mflops = 43.5295 (norm. = 0.429963), norm. avg. (of 14) = 0.279637 fft 17: mflops = -1 (norm. = -0.0098775), norm. avg. (of 12) = 0.438193 fft 18: mflops = 46.5799 (norm. = 0.460093), norm. avg. (of 13) = 0.349655 fft 19: mflops = 51.9054 (norm. = 0.512696), norm. avg. (of 13) = 0.428081 fft 20: mflops = 49.9241 (norm. = 0.493126), norm. avg. (of 13) = 0.42059 fft 21: mflops = 18.879 (norm. = 0.186478), norm. avg. (of 14) = 0.103517 fft 22: mflops = 29.7349 (norm. = 0.293706), norm. avg. (of 14) = 0.160175 fft 23: mflops = 47.0502 (norm. = 0.464738), norm. avg. (of 14) = 0.29668 fft 24: mflops = 99.9509 (norm. = 0.987265), norm. avg. (of 14) = 0.662864 fft 25: mflops = 25.191 (norm. = 0.248824), norm. avg. (of 11) = 0.266562 fft 26: mflops = 60.4006 (norm. = 0.596607), norm. avg. (of 13) = 0.228234 fft 27: mflops = 76.2592 (norm. = 0.753251), norm. avg. (of 14) = 0.463851 fft 28: mflops = 25.5511 (norm. = 0.252382), norm. avg. (of 14) = 0.129435 fft 29: mflops = 8.13105 (norm. = 0.0803144), norm. avg. (of 14) = 0.0601928 Benchmarking for array size = 32768 (power of 2): 0. Arndt DIF: elapsed time t=1.75022 s, 32 iters, t-(init.)=1.7047 s t(norm)=0.108382, mflops=46.1331 (err=5.2e-15) 1. Arndt DIT: elapsed time t=1.75011 s, 32 iters, t-(init.)=1.70448 s t(norm)=0.108368, mflops=46.1392 (err=5.2e-15) 2. Arndt Split-Radix: elapsed time t=1.1737 s, 16 iters, t-(init.)=1.15064 s t(norm)=0.146312, mflops=34.1736 (err=5.2e-15) 3. Arndt 4-step: elapsed time t=1.32012 s, 16 iters, t-(init.)=1.29707 s t(norm)=0.164931, mflops=30.3158 (err=5.2e-15) 4. Beauregard: elapsed time t=1.50362 s, 8 iters, t-(init.)=1.49175 s t(norm)=0.379371, mflops=13.1797 (err=5.2e-15) 5. Bergland: elapsed time t=1.93432 s, 64 iters, t-(init.)=1.84385 s t(norm)=0.0586146, mflops=85.303 (err=5.2e-15) 6. CWP (min N) (N=34320): elapsed time t=1.01376 s, 32 iters, t-(init.)=0.950111 s t(norm)=0.0604064, mflops=82.7726 7. CWP (best N) (N=34320): elapsed time t=1.01446 s, 32 iters, t-(init.)=0.951054 s t(norm)=0.0604664, mflops=82.6906 8. Edelblute: elapsed time t=1.31813 s, 16 iters, t-(init.)=1.29502 s t(norm)=0.16467, mflops=30.3638 (err=5.2e-15) 9. FFTPACK (f2c): elapsed time t=1.89122 s, 16 iters, t-(init.)=1.86683 s t(norm)=0.23738, mflops=21.0633 (err=5.2e-15) FFTW_MEASURE plan: (cost = 3.396350e-02) FFTW_TWIDDLE 64 FFTW_TWIDDLE 8 FFTW_NOTW 64 10. FFTW: elapsed time t=1.08816 s, 32 iters, t-(init.)=1.04014 s t(norm)=0.0661301, mflops=75.6086 (err=5.2e-15) FFTW_ESTIMATE plan: (cost = 2.883584e+05) FFTW_TWIDDLE 16 FFTW_TWIDDLE 8 FFTW_TWIDDLE 8 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.16938 s, 32 iters, t-(init.)=1.12136 s t(norm)=0.071294, mflops=70.1322 (err=5.2e-15) 12. Frigo-old: elapsed time t=1.79547 s, 32 iters, t-(init.)=1.74789 s t(norm)=0.111128, mflops=44.9932 (err=5.2e-15) 13. Green: elapsed time t=1.81126 s, 64 iters, t-(init.)=1.72052 s t(norm)=0.0546939, mflops=91.4179 (err=5.2e-15) 14. GSL: elapsed time t=1.39769 s, 16 iters, t-(init.)=1.3732 s t(norm)=0.174611, mflops=28.635 (err=5.2e-15) 15. GSL DIT: elapsed time t=1.90503 s, 32 iters, t-(init.)=1.85946 s t(norm)=0.118221, mflops=42.2937 (err=5.9e-15) 16. GSL DIF: elapsed time t=1.91819 s, 32 iters, t-(init.)=1.87268 s t(norm)=0.119062, mflops=41.9951 (err=6.0e-15) 17. Skipping fft (Krukar can't handle N > 4096). 18. Mayer (Buneman): elapsed time t=1.73538 s, 32 iters, t-(init.)=1.68948 s t(norm)=0.107414, mflops=46.5488 (err=5.2e-15) 19. Mayer (simple): elapsed time t=1.57334 s, 32 iters, t-(init.)=1.52788 s t(norm)=0.0971403, mflops=51.4719 20. Mayer (lookup): elapsed time t=1.74242 s, 32 iters, t-(init.)=1.69659 s t(norm)=0.107866, mflops=46.3537 (err=5.2e-15) 21. NAPACK (f2c): elapsed time t=1.96991 s, 8 iters, t-(init.)=1.95618 s t(norm)=0.497482, mflops=10.0506 (err=5.6e-13) 22. Nielsen: elapsed time t=1.55449 s, 16 iters, t-(init.)=1.52855 s t(norm)=0.194366, mflops=25.7247 (err=2.3e-13) 23. NR (C): elapsed time t=1.77556 s, 32 iters, t-(init.)=1.73017 s t(norm)=0.110001, mflops=45.454 (err=5.3e-15) 24. Ooura (C): elapsed time t=1.94393 s, 64 iters, t-(init.)=1.85318 s t(norm)=0.0589111, mflops=84.8736 (err=5.2e-15) 25. QFT: elapsed time t=1.9031 s, 16 iters, t-(init.)=1.87738 s t(norm)=0.238722, mflops=20.9449 (err=7.5e-15) 26. Ransom: elapsed time t=1.56417 s, 32 iters, t-(init.)=1.5182 s t(norm)=0.0965246, mflops=51.8003 (err=6.4e-15) 27. Singleton (f2c): elapsed time t=1.24292 s, 32 iters, t-(init.)=1.19759 s t(norm)=0.076141, mflops=65.6677 (err=7.2e-15) 28. Temperton (f2c): elapsed time t=1.79682 s, 16 iters, t-(init.)=1.77281 s t(norm)=0.225424, mflops=22.1804 (err=5.2e-15) 29. Valkenburg: elapsed time t=1.39415 s, 4 iters, t-(init.)=1.38611 s t(norm)=0.705011, mflops=7.09208 (err=5.2e-15) Top mflops for N=32768 = 91.4179 Normalized results and averages for N=32768: fft 0: mflops = 46.1331 (norm. = 0.50464), norm. avg. (of 15) = 0.422989 fft 1: mflops = 46.1392 (norm. = 0.504706), norm. avg. (of 15) = 0.413741 fft 2: mflops = 34.1736 (norm. = 0.373817), norm. avg. (of 15) = 0.282789 fft 3: mflops = 30.3158 (norm. = 0.331617), norm. avg. (of 15) = 0.149389 fft 4: mflops = 13.1797 (norm. = 0.14417), norm. avg. (of 15) = 0.0861337 fft 5: mflops = 85.303 (norm. = 0.93311), norm. avg. (of 15) = 0.492445 fft 6: mflops = 82.7726 (norm. = 0.905431), norm. avg. (of 15) = 0.481689 fft 7: mflops = 82.6906 (norm. = 0.904533), norm. avg. (of 15) = 0.516103 fft 8: mflops = 30.3638 (norm. = 0.332143), norm. avg. (of 14) = 0.217756 fft 9: mflops = 21.0633 (norm. = 0.230406), norm. avg. (of 15) = 0.196991 fft 10: mflops = 75.6086 (norm. = 0.827065), norm. avg. (of 15) = 0.891071 fft 11: mflops = 70.1322 (norm. = 0.76716), norm. avg. (of 15) = 0.852977 fft 12: mflops = 44.9932 (norm. = 0.49217), norm. avg. (of 15) = 0.80445 fft 13: mflops = 91.4179 (norm. = 1), norm. avg. (of 13) = 0.818869 fft 14: mflops = 28.635 (norm. = 0.313232), norm. avg. (of 15) = 0.345457 fft 15: mflops = 42.2937 (norm. = 0.462641), norm. avg. (of 15) = 0.286078 fft 16: mflops = 41.9951 (norm. = 0.459375), norm. avg. (of 15) = 0.291619 fft 17: mflops = -1 (norm. = -0.0109388), norm. avg. (of 12) = 0.438193 fft 18: mflops = 46.5488 (norm. = 0.509187), norm. avg. (of 14) = 0.36105 fft 19: mflops = 51.4719 (norm. = 0.56304), norm. avg. (of 14) = 0.437721 fft 20: mflops = 46.3537 (norm. = 0.507052), norm. avg. (of 14) = 0.426766 fft 21: mflops = 10.0506 (norm. = 0.109941), norm. avg. (of 15) = 0.103945 fft 22: mflops = 25.7247 (norm. = 0.281397), norm. avg. (of 15) = 0.168257 fft 23: mflops = 45.454 (norm. = 0.497211), norm. avg. (of 15) = 0.310049 fft 24: mflops = 84.8736 (norm. = 0.928413), norm. avg. (of 15) = 0.680567 fft 25: mflops = 20.9449 (norm. = 0.229111), norm. avg. (of 12) = 0.263441 fft 26: mflops = 51.8003 (norm. = 0.566631), norm. avg. (of 14) = 0.252405 fft 27: mflops = 65.6677 (norm. = 0.718324), norm. avg. (of 15) = 0.480815 fft 28: mflops = 22.1804 (norm. = 0.242626), norm. avg. (of 15) = 0.136981 fft 29: mflops = 7.09208 (norm. = 0.0775787), norm. avg. (of 15) = 0.0613519 Benchmarking for array size = 65536 (power of 2): 0. Arndt DIF: elapsed time t=1.2795 s, 4 iters, t-(init.)=1.24194 s t(norm)=0.296101, mflops=16.8862 (err=1.6e-14) 1. Arndt DIT: elapsed time t=1.27614 s, 4 iters, t-(init.)=1.2393 s t(norm)=0.295472, mflops=16.9221 (err=1.6e-14) 2. Arndt Split-Radix: elapsed time t=1.62465 s, 4 iters, t-(init.)=1.58721 s t(norm)=0.378419, mflops=13.2129 (err=1.6e-14) 3. Arndt 4-step: elapsed time t=1.74086 s, 8 iters, t-(init.)=1.66574 s t(norm)=0.198571, mflops=25.1799 (err=1.6e-14) 4. Beauregard: elapsed time t=1.00191 s, 2 iters, t-(init.)=0.983151 s t(norm)=0.468803, mflops=10.6655 (err=1.6e-14) 5. Bergland: elapsed time t=1.22724 s, 8 iters, t-(init.)=1.15243 s t(norm)=0.13738, mflops=36.3954 (err=1.6e-14) 6. CWP (min N) (N=72072): elapsed time t=1.63476 s, 16 iters, t-(init.)=1.47038 s t(norm)=0.0876416, mflops=57.0505 7. CWP (best N) (N=72072): elapsed time t=1.63538 s, 16 iters, t-(init.)=1.47098 s t(norm)=0.0876772, mflops=57.0274 8. Edelblute: elapsed time t=1.69638 s, 4 iters, t-(init.)=1.6585 s t(norm)=0.395418, mflops=12.6448 (err=1.6e-14) 9. FFTPACK (f2c): elapsed time t=1.08492 s, 4 iters, t-(init.)=1.04836 s t(norm)=0.249949, mflops=20.004 (err=1.6e-14) FFTW_MEASURE plan: (cost = 9.210600e-02) FFTW_TWIDDLE 8 FFTW_TWIDDLE 8 FFTW_TWIDDLE 16 FFTW_NOTW 64 10. FFTW: elapsed time t=1.41981 s, 16 iters, t-(init.)=1.27029 s t(norm)=0.0757155, mflops=66.0367 (err=1.6e-14) FFTW_ESTIMATE plan: (cost = 5.767168e+05) FFTW_TWIDDLE 16 FFTW_TWIDDLE 16 FFTW_TWIDDLE 8 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.6981 s, 16 iters, t-(init.)=1.5487 s t(norm)=0.0923099, mflops=54.1654 (err=1.6e-14) 12. Frigo-old: elapsed time t=1.22679 s, 8 iters, t-(init.)=1.1526 s t(norm)=0.137401, mflops=36.3899 (err=1.6e-14) 13. Green: elapsed time t=1.06038 s, 8 iters, t-(init.)=0.986745 s t(norm)=0.117629, mflops=42.5065 (err=1.6e-14) 14. GSL: elapsed time t=1.66717 s, 8 iters, t-(init.)=1.593 s t(norm)=0.189901, mflops=26.3295 (err=1.6e-14) 15. GSL DIT: elapsed time t=1.30379 s, 4 iters, t-(init.)=1.26758 s t(norm)=0.302216, mflops=16.5445 (err=1.7e-14) 16. GSL DIF: elapsed time t=1.30922 s, 4 iters, t-(init.)=1.27172 s t(norm)=0.303201, mflops=16.4907 (err=1.8e-14) 17. Skipping fft (Krukar can't handle N > 4096). 18. Mayer (Buneman): elapsed time t=1.07511 s, 8 iters, t-(init.)=1.00018 s t(norm)=0.119231, mflops=41.9353 (err=1.6e-14) 19. Mayer (simple): elapsed time t=1.97125 s, 16 iters, t-(init.)=1.82175 s t(norm)=0.108585, mflops=46.0471 20. Mayer (lookup): elapsed time t=1.19093 s, 8 iters, t-(init.)=1.11653 s t(norm)=0.133101, mflops=37.5654 (err=1.6e-14) 21. NAPACK (f2c): elapsed time t=1.0206 s, 2 iters, t-(init.)=1.00242 s t(norm)=0.477993, mflops=10.4604 (err=8.7e-13) 22. Nielsen: elapsed time t=1.48716 s, 4 iters, t-(init.)=1.44867 s t(norm)=0.345389, mflops=14.4764 (err=2.6e-13) 23. NR (C): elapsed time t=1.27591 s, 4 iters, t-(init.)=1.23966 s t(norm)=0.295558, mflops=16.9171 (err=1.6e-14) 24. Ooura (C): elapsed time t=1.07241 s, 8 iters, t-(init.)=0.997806 s t(norm)=0.118948, mflops=42.0353 (err=1.6e-14) 25. QFT: elapsed time t=1.16208 s, 4 iters, t-(init.)=1.1241 s t(norm)=0.268007, mflops=18.6563 (err=1.9e-14) 26. Ransom: elapsed time t=1.2054 s, 8 iters, t-(init.)=1.12772 s t(norm)=0.134435, mflops=37.1928 (err=1.7e-14) 27. Singleton (f2c): elapsed time t=1.51275 s, 8 iters, t-(init.)=1.43764 s t(norm)=0.17138, mflops=29.1749 (err=2.4e-14) 28. Temperton (f2c): elapsed time t=1.26481 s, 4 iters, t-(init.)=1.22733 s t(norm)=0.292619, mflops=17.0871 (err=1.6e-14) 29. Valkenburg: elapsed time t=1.74123 s, 2 iters, t-(init.)=1.7225 s t(norm)=0.821352, mflops=6.08752 (err=1.6e-14) Top mflops for N=65536 = 66.0367 Normalized results and averages for N=65536: fft 0: mflops = 16.8862 (norm. = 0.255709), norm. avg. (of 16) = 0.412534 fft 1: mflops = 16.9221 (norm. = 0.256253), norm. avg. (of 16) = 0.403898 fft 2: mflops = 13.2129 (norm. = 0.200084), norm. avg. (of 16) = 0.27762 fft 3: mflops = 25.1799 (norm. = 0.381301), norm. avg. (of 16) = 0.163884 fft 4: mflops = 10.6655 (norm. = 0.161508), norm. avg. (of 16) = 0.0908446 fft 5: mflops = 36.3954 (norm. = 0.551139), norm. avg. (of 16) = 0.496114 fft 6: mflops = 57.0505 (norm. = 0.863922), norm. avg. (of 16) = 0.505579 fft 7: mflops = 57.0274 (norm. = 0.863571), norm. avg. (of 16) = 0.53782 fft 8: mflops = 12.6448 (norm. = 0.191482), norm. avg. (of 15) = 0.216004 fft 9: mflops = 20.004 (norm. = 0.302923), norm. avg. (of 16) = 0.203612 fft 10: mflops = 66.0367 (norm. = 1), norm. avg. (of 16) = 0.897879 fft 11: mflops = 54.1654 (norm. = 0.820232), norm. avg. (of 16) = 0.850931 fft 12: mflops = 36.3899 (norm. = 0.551056), norm. avg. (of 16) = 0.788613 fft 13: mflops = 42.5065 (norm. = 0.643679), norm. avg. (of 14) = 0.806356 fft 14: mflops = 26.3295 (norm. = 0.39871), norm. avg. (of 16) = 0.348786 fft 15: mflops = 16.5445 (norm. = 0.250535), norm. avg. (of 16) = 0.283857 fft 16: mflops = 16.4907 (norm. = 0.24972), norm. avg. (of 16) = 0.289 fft 17: mflops = -1 (norm. = -0.0151431), norm. avg. (of 12) = 0.438193 fft 18: mflops = 41.9353 (norm. = 0.635031), norm. avg. (of 15) = 0.379315 fft 19: mflops = 46.0471 (norm. = 0.697295), norm. avg. (of 15) = 0.455026 fft 20: mflops = 37.5654 (norm. = 0.568856), norm. avg. (of 15) = 0.436238 fft 21: mflops = 10.4604 (norm. = 0.158403), norm. avg. (of 16) = 0.107349 fft 22: mflops = 14.4764 (norm. = 0.219218), norm. avg. (of 16) = 0.171442 fft 23: mflops = 16.9171 (norm. = 0.256178), norm. avg. (of 16) = 0.306682 fft 24: mflops = 42.0353 (norm. = 0.636544), norm. avg. (of 16) = 0.677816 fft 25: mflops = 18.6563 (norm. = 0.282514), norm. avg. (of 13) = 0.264909 fft 26: mflops = 37.1928 (norm. = 0.563214), norm. avg. (of 15) = 0.273126 fft 27: mflops = 29.1749 (norm. = 0.441798), norm. avg. (of 16) = 0.478377 fft 28: mflops = 17.0871 (norm. = 0.258752), norm. avg. (of 16) = 0.144591 fft 29: mflops = 6.08752 (norm. = 0.0921839), norm. avg. (of 16) = 0.0632789 Benchmarking for array size = 131072 (power of 2): 0. Arndt DIF: elapsed time t=1.33271 s, 2 iters, t-(init.)=1.29506 s t(norm)=0.290604, mflops=17.2056 (err=3.9e-14) 1. Arndt DIT: elapsed time t=1.33819 s, 2 iters, t-(init.)=1.30123 s t(norm)=0.291987, mflops=17.124 (err=3.9e-14) 2. Arndt Split-Radix: elapsed time t=1.7919 s, 2 iters, t-(init.)=1.75384 s t(norm)=0.39355, mflops=12.7049 (err=3.9e-14) 3. Arndt 4-step: elapsed time t=1.16673 s, 2 iters, t-(init.)=1.12974 s t(norm)=0.253506, mflops=19.7234 (err=3.9e-14) 4. Beauregard: elapsed time t=1.06919 s, 1 iters, t-(init.)=1.05069 s t(norm)=0.471535, mflops=10.6037 (err=3.8e-14) 5. Bergland: elapsed time t=1.27447 s, 4 iters, t-(init.)=1.19973 s t(norm)=0.134606, mflops=37.1454 (err=3.9e-14) 6. CWP (min N) (N=144144): elapsed time t=1.78681 s, 8 iters, t-(init.)=1.62193 s t(norm)=0.0909878, mflops=54.9524 7. CWP (best N) (N=144144): elapsed time t=1.787 s, 8 iters, t-(init.)=1.62251 s t(norm)=0.0910205, mflops=54.9327 8. Edelblute: elapsed time t=1.86443 s, 2 iters, t-(init.)=1.82696 s t(norm)=0.409959, mflops=12.1963 (err=3.9e-14) 9. FFTPACK (f2c): elapsed time t=1.30803 s, 2 iters, t-(init.)=1.27072 s t(norm)=0.285141, mflops=17.5352 (err=3.8e-14) FFTW_MEASURE plan: (cost = 2.103660e-01) FFTW_TWIDDLE 4 FFTW_TWIDDLE 64 FFTW_TWIDDLE 8 FFTW_NOTW 64 10. FFTW: elapsed time t=1.61981 s, 8 iters, t-(init.)=1.47017 s t(norm)=0.0824741, mflops=60.6251 (err=3.8e-14) FFTW_ESTIMATE plan: (cost = 1.153434e+06) FFTW_TWIDDLE 16 FFTW_TWIDDLE 16 FFTW_TWIDDLE 16 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.87967 s, 8 iters, t-(init.)=1.73005 s t(norm)=0.0970532, mflops=51.5181 (err=3.8e-14) 12. Frigo-old: elapsed time t=1.38882 s, 4 iters, t-(init.)=1.31465 s t(norm)=0.1475, mflops=33.8983 (err=3.8e-14) 13. Green: elapsed time t=1.20544 s, 4 iters, t-(init.)=1.13076 s t(norm)=0.126868, mflops=39.4111 (err=3.8e-14) 14. GSL: elapsed time t=1.97524 s, 4 iters, t-(init.)=1.9 s t(norm)=0.213175, mflops=23.4549 (err=3.8e-14) 15. GSL DIT: elapsed time t=1.41588 s, 2 iters, t-(init.)=1.3783 s t(norm)=0.309281, mflops=16.1665 (err=4.0e-14) 16. GSL DIF: elapsed time t=1.41316 s, 2 iters, t-(init.)=1.37602 s t(norm)=0.308771, mflops=16.1932 (err=4.2e-14) 17. Skipping fft (Krukar can't handle N > 4096). 18. Mayer (Buneman): elapsed time t=1.29367 s, 2 iters, t-(init.)=1.25622 s t(norm)=0.281887, mflops=17.7376 (err=3.9e-14) 19. Mayer (simple): elapsed time t=1.25278 s, 2 iters, t-(init.)=1.21524 s t(norm)=0.272693, mflops=18.3356 20. Mayer (lookup): elapsed time t=1.30518 s, 2 iters, t-(init.)=1.2674 s t(norm)=0.284397, mflops=17.5811 (err=3.9e-14) 21. NAPACK (f2c): elapsed time t=1.11093 s, 1 iters, t-(init.)=1.09253 s t(norm)=0.490315, mflops=10.1975 (err=2.0e-12) 22. Nielsen: elapsed time t=1.57598 s, 2 iters, t-(init.)=1.53873 s t(norm)=0.345282, mflops=14.4809 (err=9.2e-13) 23. NR (C): elapsed time t=1.3892 s, 2 iters, t-(init.)=1.3516 s t(norm)=0.303291, mflops=16.4858 (err=3.9e-14) 24. Ooura (C): elapsed time t=1.18004 s, 4 iters, t-(init.)=1.10495 s t(norm)=0.123973, mflops=40.3315 (err=3.9e-14) 25. QFT: elapsed time t=1.51072 s, 2 iters, t-(init.)=1.47313 s t(norm)=0.330561, mflops=15.1258 (err=4.1e-14) 26. Ransom: elapsed time t=1.48985 s, 4 iters, t-(init.)=1.41339 s t(norm)=0.158578, mflops=31.5302 (err=3.9e-14) 27. Singleton (f2c): elapsed time t=1.69692 s, 4 iters, t-(init.)=1.62226 s t(norm)=0.182012, mflops=27.4707 (err=5.7e-14) 28. Temperton (f2c): elapsed time t=1.44749 s, 2 iters, t-(init.)=1.40992 s t(norm)=0.316377, mflops=15.8039 (err=3.8e-14) 29. Valkenburg: elapsed time t=1.91568 s, 1 iters, t-(init.)=1.89703 s t(norm)=0.851366, mflops=5.87292 (err=3.9e-14) Top mflops for N=131072 = 60.6251 Normalized results and averages for N=131072: fft 0: mflops = 17.2056 (norm. = 0.283803), norm. avg. (of 17) = 0.404961 fft 1: mflops = 17.124 (norm. = 0.282458), norm. avg. (of 17) = 0.396754 fft 2: mflops = 12.7049 (norm. = 0.209564), norm. avg. (of 17) = 0.273616 fft 3: mflops = 19.7234 (norm. = 0.325334), norm. avg. (of 17) = 0.173381 fft 4: mflops = 10.6037 (norm. = 0.174906), norm. avg. (of 17) = 0.0957894 fft 5: mflops = 37.1454 (norm. = 0.612707), norm. avg. (of 17) = 0.502972 fft 6: mflops = 54.9524 (norm. = 0.906431), norm. avg. (of 17) = 0.529158 fft 7: mflops = 54.9327 (norm. = 0.906105), norm. avg. (of 17) = 0.559483 fft 8: mflops = 12.1963 (norm. = 0.201177), norm. avg. (of 16) = 0.215077 fft 9: mflops = 17.5352 (norm. = 0.28924), norm. avg. (of 17) = 0.208649 fft 10: mflops = 60.6251 (norm. = 1), norm. avg. (of 17) = 0.903887 fft 11: mflops = 51.5181 (norm. = 0.849782), norm. avg. (of 17) = 0.850863 fft 12: mflops = 33.8983 (norm. = 0.559146), norm. avg. (of 17) = 0.775115 fft 13: mflops = 39.4111 (norm. = 0.650079), norm. avg. (of 15) = 0.795937 fft 14: mflops = 23.4549 (norm. = 0.386885), norm. avg. (of 17) = 0.351027 fft 15: mflops = 16.1665 (norm. = 0.266664), norm. avg. (of 17) = 0.282845 fft 16: mflops = 16.1932 (norm. = 0.267105), norm. avg. (of 17) = 0.287712 fft 17: mflops = -1 (norm. = -0.0164948), norm. avg. (of 12) = 0.438193 fft 18: mflops = 17.7376 (norm. = 0.292579), norm. avg. (of 16) = 0.373894 fft 19: mflops = 18.3356 (norm. = 0.302443), norm. avg. (of 16) = 0.445489 fft 20: mflops = 17.5811 (norm. = 0.289997), norm. avg. (of 16) = 0.427098 fft 21: mflops = 10.1975 (norm. = 0.168207), norm. avg. (of 17) = 0.110929 fft 22: mflops = 14.4809 (norm. = 0.23886), norm. avg. (of 17) = 0.175408 fft 23: mflops = 16.4858 (norm. = 0.27193), norm. avg. (of 17) = 0.304637 fft 24: mflops = 40.3315 (norm. = 0.665261), norm. avg. (of 17) = 0.677077 fft 25: mflops = 15.1258 (norm. = 0.249498), norm. avg. (of 14) = 0.263808 fft 26: mflops = 31.5302 (norm. = 0.520085), norm. avg. (of 16) = 0.288561 fft 27: mflops = 27.4707 (norm. = 0.453124), norm. avg. (of 17) = 0.476891 fft 28: mflops = 15.8039 (norm. = 0.260683), norm. avg. (of 17) = 0.15142 fft 29: mflops = 5.87292 (norm. = 0.0968727), norm. avg. (of 17) = 0.065255 ------------------------------------------------------ @@@@ bench.1d.np2.log Benchmarking for sizes: 6 (0.000686646 MB) 9 (0.000915527 MB) 12 (0.00114441 MB) 15 (0.00137329 MB) 18 (0.00180054 MB) 24 (0.0022583 MB) 36 (0.0032959 MB) 80 (0.00738525 MB) 108 (0.00994873 MB) 210 (0.0192261 MB) 504 (0.0461426 MB) 1000 (0.0916748 MB) 1960 (0.179749 MB) 4725 (0.437393 MB) 10368 (0.960205 MB) 27000 (2.48291 MB) 75600 (6.98975 MB) 165375 (15.3664 MB) Maximum array size = 180180 Benchmarking FFTs: 0. CWP (min N) 1. CWP (best N) 2. FFTPACK (f2c) 3. FFTW 4. FFTW_ESTIMATE 5. Frigo-old 6. GSL 7. NAPACK (f2c) 8. Nielsen 9. Singleton (f2c) 10. Temperton (f2c) 11. Valkenburg Computing normalized averages (12 transforms). Benchmarking for array size = 6: 0. CWP (min N): elapsed time t=1.60342 s, 524288 iters, t-(init.)=1.54229 s t(norm)=0.189666, mflops=26.3621 1. CWP (best N) (N=15): elapsed time t=1.27441 s, 262144 iters, t-(init.)=1.20834 s t(norm)=0.297198, mflops=16.8238 2. FFTPACK (f2c): elapsed time t=1.00183 s, 262144 iters, t-(init.)=0.97126 s t(norm)=0.238886, mflops=20.9305 (err=1.7e-16) FFTW_MEASURE plan: (cost = 8.055420e-07) FFTW_NOTW 6 3. FFTW: elapsed time t=1.76701 s, 2097152 iters, t-(init.)=1.52251 s t(norm)=0.0468085, mflops=106.818 (err=1.3e-16) FFTW_ESTIMATE plan: (cost = 4.116000e+02) FFTW_NOTW 6 4. FFTW_ESTIMATE: elapsed time t=1.7589 s, 2097152 iters, t-(init.)=1.51422 s t(norm)=0.0465537, mflops=107.403 (err=1.3e-16) 5. Frigo-old: elapsed time t=1.00771 s, 262144 iters, t-(init.)=0.977115 s t(norm)=0.240326, mflops=20.8051 (err=3.2e-16) 6. GSL: elapsed time t=1.34453 s, 524288 iters, t-(init.)=1.28342 s t(norm)=0.157832, mflops=31.6794 (err=1.3e-16) 7. NAPACK (f2c): elapsed time t=1.1113 s, 131072 iters, t-(init.)=1.09598 s t(norm)=0.539124, mflops=9.2743 (err=2.3e-16) 8. Nielsen: elapsed time t=1.42987 s, 131072 iters, t-(init.)=1.41457 s t(norm)=0.695839, mflops=7.18557 (err=2.7e-16) 9. Singleton (f2c): elapsed time t=1.23408 s, 262144 iters, t-(init.)=1.20339 s t(norm)=0.29598, mflops=16.893 (err=1.3e-16) 10. Temperton (f2c): elapsed time t=1.01594 s, 131072 iters, t-(init.)=1.00065 s t(norm)=0.492227, mflops=10.1579 (err=1.2e-16) 11. Valkenburg: elapsed time t=1.20042 s, 131072 iters, t-(init.)=1.1851 s t(norm)=0.58296, mflops=8.57692 (err=2.1e-16) Top mflops for N=6 = 107.403 Normalized results and averages for N=6: fft 0: mflops = 26.3621 (norm. = 0.245451), norm. avg. (of 1) = 0.245451 fft 1: mflops = 16.8238 (norm. = 0.156642), norm. avg. (of 1) = 0.156642 fft 2: mflops = 20.9305 (norm. = 0.194879), norm. avg. (of 1) = 0.194879 fft 3: mflops = 106.818 (norm. = 0.994556), norm. avg. (of 1) = 0.994556 fft 4: mflops = 107.403 (norm. = 1), norm. avg. (of 1) = 1 fft 5: mflops = 20.8051 (norm. = 0.193711), norm. avg. (of 1) = 0.193711 fft 6: mflops = 31.6794 (norm. = 0.294958), norm. avg. (of 1) = 0.294958 fft 7: mflops = 9.2743 (norm. = 0.0863507), norm. avg. (of 1) = 0.0863507 fft 8: mflops = 7.18557 (norm. = 0.066903), norm. avg. (of 1) = 0.066903 fft 9: mflops = 16.893 (norm. = 0.157287), norm. avg. (of 1) = 0.157287 fft 10: mflops = 10.1579 (norm. = 0.0945778), norm. avg. (of 1) = 0.0945778 fft 11: mflops = 8.57692 (norm. = 0.0798575), norm. avg. (of 1) = 0.0798575 Benchmarking for array size = 9: 0. CWP (min N): elapsed time t=1.81051 s, 524288 iters, t-(init.)=1.72571 s t(norm)=0.115373, mflops=43.3376 1. CWP (best N) (N=15): elapsed time t=1.27216 s, 262144 iters, t-(init.)=1.2061 s t(norm)=0.161269, mflops=31.0041 2. FFTPACK (f2c): elapsed time t=1.52348 s, 262144 iters, t-(init.)=1.48106 s t(norm)=0.198035, mflops=25.2481 (err=2.8e-16) FFTW_MEASURE plan: (cost = 1.466660e-06) FFTW_NOTW 9 3. FFTW: elapsed time t=1.58951 s, 1048576 iters, t-(init.)=1.41996 s t(norm)=0.0474664, mflops=105.338 (err=1.4e-16) FFTW_ESTIMATE plan: (cost = 4.851000e+02) FFTW_NOTW 9 4. FFTW_ESTIMATE: elapsed time t=1.58551 s, 1048576 iters, t-(init.)=1.41607 s t(norm)=0.0473362, mflops=105.627 (err=1.4e-16) 5. Frigo-old: elapsed time t=1.06493 s, 131072 iters, t-(init.)=1.04367 s t(norm)=0.279102, mflops=17.9146 (err=3.1e-16) 6. GSL: elapsed time t=1.23956 s, 262144 iters, t-(init.)=1.19719 s t(norm)=0.160078, mflops=31.2348 (err=1.4e-16) 7. NAPACK (f2c): elapsed time t=1.61486 s, 131072 iters, t-(init.)=1.59365 s t(norm)=0.426177, mflops=11.7322 (err=5.8e-16) 8. Nielsen: elapsed time t=1.68926 s, 131072 iters, t-(init.)=1.66805 s t(norm)=0.446076, mflops=11.2089 (err=4.5e-16) 9. Singleton (f2c): elapsed time t=1.28357 s, 262144 iters, t-(init.)=1.24115 s t(norm)=0.165956, mflops=30.1285 (err=1.7e-16) 10. Temperton (f2c): elapsed time t=1.27449 s, 131072 iters, t-(init.)=1.25327 s t(norm)=0.335154, mflops=14.9185 (err=1.7e-16) 11. Valkenburg: elapsed time t=1.0873 s, 65536 iters, t-(init.)=1.07666 s t(norm)=0.575849, mflops=8.68284 (err=2.6e-16) Top mflops for N=9 = 105.627 Normalized results and averages for N=9: fft 0: mflops = 43.3376 (norm. = 0.410287), norm. avg. (of 2) = 0.327869 fft 1: mflops = 31.0041 (norm. = 0.293523), norm. avg. (of 2) = 0.225083 fft 2: mflops = 25.2481 (norm. = 0.23903), norm. avg. (of 2) = 0.216954 fft 3: mflops = 105.338 (norm. = 0.997258), norm. avg. (of 2) = 0.995907 fft 4: mflops = 105.627 (norm. = 1), norm. avg. (of 2) = 1 fft 5: mflops = 17.9146 (norm. = 0.169602), norm. avg. (of 2) = 0.181657 fft 6: mflops = 31.2348 (norm. = 0.295707), norm. avg. (of 2) = 0.295333 fft 7: mflops = 11.7322 (norm. = 0.111072), norm. avg. (of 2) = 0.0987111 fft 8: mflops = 11.2089 (norm. = 0.106117), norm. avg. (of 2) = 0.08651 fft 9: mflops = 30.1285 (norm. = 0.285234), norm. avg. (of 2) = 0.22126 fft 10: mflops = 14.9185 (norm. = 0.141237), norm. avg. (of 2) = 0.117908 fft 11: mflops = 8.68284 (norm. = 0.0822025), norm. avg. (of 2) = 0.08103 Benchmarking for array size = 12: 0. CWP (min N): elapsed time t=1.03826 s, 262144 iters, t-(init.)=0.983992 s t(norm)=0.0872541, mflops=57.3039 1. CWP (best N) (N=15): elapsed time t=1.27437 s, 262144 iters, t-(init.)=1.20834 s t(norm)=0.107148, mflops=46.6645 2. FFTPACK (f2c): elapsed time t=1.82963 s, 262144 iters, t-(init.)=1.77541 s t(norm)=0.157432, mflops=31.7597 (err=1.9e-16) FFTW_MEASURE plan: (cost = 1.459244e-06) FFTW_NOTW 12 3. FFTW: elapsed time t=1.57757 s, 1048576 iters, t-(init.)=1.36045 s t(norm)=0.0301589, mflops=165.788 (err=1.3e-16) FFTW_ESTIMATE plan: (cost = 4.920000e+02) FFTW_NOTW 12 4. FFTW_ESTIMATE: elapsed time t=1.57374 s, 1048576 iters, t-(init.)=1.35689 s t(norm)=0.03008, mflops=166.223 (err=1.3e-16) 5. Frigo-old: elapsed time t=1.85085 s, 262144 iters, t-(init.)=1.79664 s t(norm)=0.159314, mflops=31.3845 (err=2.3e-16) 6. GSL: elapsed time t=1.22399 s, 262144 iters, t-(init.)=1.16977 s t(norm)=0.103728, mflops=48.203 (err=1.5e-16) 7. NAPACK (f2c): elapsed time t=1.13055 s, 65536 iters, t-(init.)=1.11697 s t(norm)=0.396182, mflops=12.6205 (err=4.2e-16) 8. Nielsen: elapsed time t=1.93784 s, 131072 iters, t-(init.)=1.91074 s t(norm)=0.338865, mflops=14.7552 (err=4.8e-16) 9. Singleton (f2c): elapsed time t=1.81257 s, 262144 iters, t-(init.)=1.75831 s t(norm)=0.155915, mflops=32.0687 (err=1.9e-16) 10. Temperton (f2c): elapsed time t=1.47726 s, 131072 iters, t-(init.)=1.45012 s t(norm)=0.257174, mflops=19.4421 (err=1.2e-16) 11. Valkenburg: elapsed time t=1.59806 s, 65536 iters, t-(init.)=1.58449 s t(norm)=0.562008, mflops=8.89667 (err=1.9e-16) Top mflops for N=12 = 166.223 Normalized results and averages for N=12: fft 0: mflops = 57.3039 (norm. = 0.34474), norm. avg. (of 3) = 0.333493 fft 1: mflops = 46.6645 (norm. = 0.280733), norm. avg. (of 3) = 0.243633 fft 2: mflops = 31.7597 (norm. = 0.191066), norm. avg. (of 3) = 0.208325 fft 3: mflops = 165.788 (norm. = 0.997382), norm. avg. (of 3) = 0.996399 fft 4: mflops = 166.223 (norm. = 1), norm. avg. (of 3) = 1 fft 5: mflops = 31.3845 (norm. = 0.188809), norm. avg. (of 3) = 0.184041 fft 6: mflops = 48.203 (norm. = 0.289989), norm. avg. (of 3) = 0.293552 fft 7: mflops = 12.6205 (norm. = 0.0759247), norm. avg. (of 3) = 0.0911157 fft 8: mflops = 14.7552 (norm. = 0.088767), norm. avg. (of 3) = 0.0872623 fft 9: mflops = 32.0687 (norm. = 0.192925), norm. avg. (of 3) = 0.211815 fft 10: mflops = 19.4421 (norm. = 0.116963), norm. avg. (of 3) = 0.117593 fft 11: mflops = 8.89667 (norm. = 0.0535223), norm. avg. (of 3) = 0.0718608 Benchmarking for array size = 15: 0. CWP (min N): elapsed time t=1.27687 s, 262144 iters, t-(init.)=1.21075 s t(norm)=0.078812, mflops=63.4421 1. CWP (best N): elapsed time t=1.27539 s, 262144 iters, t-(init.)=1.20933 s t(norm)=0.0787196, mflops=63.5165 2. FFTPACK (f2c): elapsed time t=1.2411 s, 131072 iters, t-(init.)=1.20808 s t(norm)=0.157276, mflops=31.7913 (err=3.6e-16) FFTW_MEASURE plan: (cost = 2.463440e-06) FFTW_NOTW 15 3. FFTW: elapsed time t=1.32736 s, 524288 iters, t-(init.)=1.19529 s t(norm)=0.0389027, mflops=128.526 (err=1.7e-16) FFTW_ESTIMATE plan: (cost = 4.485000e+02) FFTW_NOTW 15 4. FFTW_ESTIMATE: elapsed time t=1.32517 s, 524288 iters, t-(init.)=1.19299 s t(norm)=0.0388279, mflops=128.773 (err=1.7e-16) 5. Frigo-old: elapsed time t=1.86519 s, 131072 iters, t-(init.)=1.83213 s t(norm)=0.23852, mflops=20.9626 (err=2.7e-16) 6. GSL: elapsed time t=1.22519 s, 131072 iters, t-(init.)=1.19216 s t(norm)=0.155204, mflops=32.2157 (err=1.9e-16) 7. NAPACK (f2c): elapsed time t=1.11065 s, 32768 iters, t-(init.)=1.10242 s t(norm)=0.574085, mflops=8.70951 (err=9.4e-16) 8. Nielsen: elapsed time t=1.13667 s, 65536 iters, t-(init.)=1.12011 s t(norm)=0.291649, mflops=17.1439 (err=4.5e-15) 9. Singleton (f2c): elapsed time t=1.10469 s, 131072 iters, t-(init.)=1.07167 s t(norm)=0.139517, mflops=35.8379 (err=2.0e-16) 10. Temperton (f2c): elapsed time t=1.96608 s, 131072 iters, t-(init.)=1.93297 s t(norm)=0.251647, mflops=19.8691 (err=2.5e-16) 11. Valkenburg: elapsed time t=1.22967 s, 32768 iters, t-(init.)=1.22136 s t(norm)=0.636021, mflops=7.86138 (err=2.5e-16) Top mflops for N=15 = 128.773 Normalized results and averages for N=15: fft 0: mflops = 63.4421 (norm. = 0.492665), norm. avg. (of 4) = 0.373286 fft 1: mflops = 63.5165 (norm. = 0.493243), norm. avg. (of 4) = 0.306036 fft 2: mflops = 31.7913 (norm. = 0.246878), norm. avg. (of 4) = 0.217963 fft 3: mflops = 128.526 (norm. = 0.998078), norm. avg. (of 4) = 0.996819 fft 4: mflops = 128.773 (norm. = 1), norm. avg. (of 4) = 1 fft 5: mflops = 20.9626 (norm. = 0.162787), norm. avg. (of 4) = 0.178727 fft 6: mflops = 32.2157 (norm. = 0.250174), norm. avg. (of 4) = 0.282707 fft 7: mflops = 8.70951 (norm. = 0.0676345), norm. avg. (of 4) = 0.0852454 fft 8: mflops = 17.1439 (norm. = 0.133133), norm. avg. (of 4) = 0.0987299 fft 9: mflops = 35.8379 (norm. = 0.278303), norm. avg. (of 4) = 0.228437 fft 10: mflops = 19.8691 (norm. = 0.154295), norm. avg. (of 4) = 0.126768 fft 11: mflops = 7.86138 (norm. = 0.0610482), norm. avg. (of 4) = 0.0691576 Benchmarking for array size = 18: 0. CWP (min N): elapsed time t=1.60435 s, 262144 iters, t-(init.)=1.52644 s t(norm)=0.0775781, mflops=64.4511 1. CWP (best N) (N=28): elapsed time t=1.84033 s, 262144 iters, t-(init.)=1.72294 s t(norm)=0.0875647, mflops=57.1006 2. FFTPACK (f2c): elapsed time t=1.00407 s, 65536 iters, t-(init.)=0.984472 s t(norm)=0.200135, mflops=24.9832 (err=2.6e-16) FFTW_MEASURE plan: (cost = 3.777161e-06) FFTW_TWIDDLE 3 FFTW_NOTW 6 3. FFTW: elapsed time t=1.01658 s, 262144 iters, t-(init.)=0.938678 s t(norm)=0.0477063, mflops=104.808 (err=1.9e-16) FFTW_ESTIMATE plan: (cost = 1.168200e+03) FFTW_TWIDDLE 2 FFTW_NOTW 9 4. FFTW_ESTIMATE: elapsed time t=1.06194 s, 262144 iters, t-(init.)=0.983958 s t(norm)=0.0500076, mflops=99.9848 (err=2.3e-16) 5. Frigo-old: elapsed time t=1.20647 s, 65536 iters, t-(init.)=1.18688 s t(norm)=0.241282, mflops=20.7226 (err=3.8e-16) 6. GSL: elapsed time t=1.95332 s, 262144 iters, t-(init.)=1.87535 s t(norm)=0.095311, mflops=52.4599 (err=2.4e-16) 7. NAPACK (f2c): elapsed time t=1.71553 s, 65536 iters, t-(init.)=1.69606 s t(norm)=0.344795, mflops=14.5014 (err=6.0e-16) 8. Nielsen: elapsed time t=1.83643 s, 65536 iters, t-(init.)=1.81697 s t(norm)=0.369374, mflops=13.5364 (err=7.7e-16) 9. Singleton (f2c): elapsed time t=1.16648 s, 131072 iters, t-(init.)=1.12754 s t(norm)=0.114609, mflops=43.6264 (err=1.7e-16) 10. Temperton (f2c): elapsed time t=1.41899 s, 65536 iters, t-(init.)=1.39944 s t(norm)=0.284494, mflops=17.5751 (err=2.8e-16) 11. Valkenburg: elapsed time t=1.37779 s, 32768 iters, t-(init.)=1.36809 s t(norm)=0.556243, mflops=8.98888 (err=2.8e-16) Top mflops for N=18 = 104.808 Normalized results and averages for N=18: fft 0: mflops = 64.4511 (norm. = 0.614945), norm. avg. (of 5) = 0.421618 fft 1: mflops = 57.1006 (norm. = 0.544812), norm. avg. (of 5) = 0.353791 fft 2: mflops = 24.9832 (norm. = 0.238371), norm. avg. (of 5) = 0.222045 fft 3: mflops = 104.808 (norm. = 1), norm. avg. (of 5) = 0.997455 fft 4: mflops = 99.9848 (norm. = 0.953982), norm. avg. (of 5) = 0.990796 fft 5: mflops = 20.7226 (norm. = 0.19772), norm. avg. (of 5) = 0.182526 fft 6: mflops = 52.4599 (norm. = 0.500533), norm. avg. (of 5) = 0.326272 fft 7: mflops = 14.5014 (norm. = 0.138361), norm. avg. (of 5) = 0.0958685 fft 8: mflops = 13.5364 (norm. = 0.129154), norm. avg. (of 5) = 0.104815 fft 9: mflops = 43.6264 (norm. = 0.416251), norm. avg. (of 5) = 0.266 fft 10: mflops = 17.5751 (norm. = 0.167688), norm. avg. (of 5) = 0.134952 fft 11: mflops = 8.98888 (norm. = 0.0857652), norm. avg. (of 5) = 0.0724792 Benchmarking for array size = 24: 0. CWP (min N): elapsed time t=1.72916 s, 262144 iters, t-(init.)=1.62761 s t(norm)=0.056424, mflops=88.6147 1. CWP (best N) (N=28): elapsed time t=1.83483 s, 262144 iters, t-(init.)=1.71744 s t(norm)=0.059538, mflops=83.98 2. FFTPACK (f2c): elapsed time t=1.25668 s, 65536 iters, t-(init.)=1.2313 s t(norm)=0.170741, mflops=29.2842 (err=2.4e-16) FFTW_MEASURE plan: (cost = 4.189697e-06) FFTW_TWIDDLE 2 FFTW_NOTW 12 3. FFTW: elapsed time t=1.12492 s, 262144 iters, t-(init.)=1.02341 s t(norm)=0.0354782, mflops=140.932 (err=2.0e-16) FFTW_ESTIMATE plan: (cost = 1.248000e+03) FFTW_TWIDDLE 2 FFTW_NOTW 12 4. FFTW_ESTIMATE: elapsed time t=1.12424 s, 262144 iters, t-(init.)=1.02269 s t(norm)=0.0354533, mflops=141.031 (err=2.0e-16) 5. Frigo-old: elapsed time t=1.84879 s, 131072 iters, t-(init.)=1.79801 s t(norm)=0.124662, mflops=40.1085 (err=2.7e-16) 6. GSL: elapsed time t=1.08277 s, 131072 iters, t-(init.)=1.03201 s t(norm)=0.0715528, mflops=69.8785 (err=2.2e-16) 7. NAPACK (f2c): elapsed time t=1.10896 s, 32768 iters, t-(init.)=1.09629 s t(norm)=0.304037, mflops=16.4453 (err=8.2e-16) 8. Nielsen: elapsed time t=1.62289 s, 65536 iters, t-(init.)=1.59752 s t(norm)=0.221523, mflops=22.5711 (err=1.4e-15) 9. Singleton (f2c): elapsed time t=1.74145 s, 131072 iters, t-(init.)=1.69067 s t(norm)=0.11722, mflops=42.6549 (err=2.2e-16) 10. Temperton (f2c): elapsed time t=1.63794 s, 65536 iters, t-(init.)=1.61257 s t(norm)=0.22361, mflops=22.3604 (err=2.7e-16) 11. Valkenburg: elapsed time t=1.98044 s, 32768 iters, t-(init.)=1.96771 s t(norm)=0.545714, mflops=9.16231 (err=2.9e-16) Top mflops for N=24 = 141.031 Normalized results and averages for N=24: fft 0: mflops = 88.6147 (norm. = 0.628337), norm. avg. (of 6) = 0.456071 fft 1: mflops = 83.98 (norm. = 0.595474), norm. avg. (of 6) = 0.394071 fft 2: mflops = 29.2842 (norm. = 0.207644), norm. avg. (of 6) = 0.219645 fft 3: mflops = 140.932 (norm. = 0.999298), norm. avg. (of 6) = 0.997762 fft 4: mflops = 141.031 (norm. = 1), norm. avg. (of 6) = 0.99233 fft 5: mflops = 40.1085 (norm. = 0.284395), norm. avg. (of 6) = 0.199504 fft 6: mflops = 69.8785 (norm. = 0.495485), norm. avg. (of 6) = 0.354474 fft 7: mflops = 16.4453 (norm. = 0.116608), norm. avg. (of 6) = 0.0993252 fft 8: mflops = 22.5711 (norm. = 0.160044), norm. avg. (of 6) = 0.11402 fft 9: mflops = 42.6549 (norm. = 0.302452), norm. avg. (of 6) = 0.272075 fft 10: mflops = 22.3604 (norm. = 0.15855), norm. avg. (of 6) = 0.138885 fft 11: mflops = 9.16231 (norm. = 0.0649668), norm. avg. (of 6) = 0.0712271 Benchmarking for array size = 36: 0. CWP (min N): elapsed time t=1.28944 s, 131072 iters, t-(init.)=1.21499 s t(norm)=0.0498054, mflops=100.391 1. CWP (best N): elapsed time t=1.28922 s, 131072 iters, t-(init.)=1.2148 s t(norm)=0.0497975, mflops=100.407 2. FFTPACK (f2c): elapsed time t=1.00308 s, 32768 iters, t-(init.)=0.984367 s t(norm)=0.161406, mflops=30.9777 (err=3.7e-16) FFTW_MEASURE plan: (cost = 6.902222e-06) FFTW_TWIDDLE 3 FFTW_NOTW 12 3. FFTW: elapsed time t=1.8449 s, 262144 iters, t-(init.)=1.69605 s t(norm)=0.0347627, mflops=143.832 (err=3.5e-16) FFTW_ESTIMATE plan: (cost = 1.803600e+03) FFTW_TWIDDLE 3 FFTW_NOTW 12 4. FFTW_ESTIMATE: elapsed time t=1.84375 s, 262144 iters, t-(init.)=1.69469 s t(norm)=0.0347347, mflops=143.948 (err=3.5e-16) 5. Frigo-old: elapsed time t=1.19252 s, 32768 iters, t-(init.)=1.17381 s t(norm)=0.192469, mflops=25.9783 (err=4.8e-16) 6. GSL: elapsed time t=1.69103 s, 131072 iters, t-(init.)=1.61663 s t(norm)=0.0662697, mflops=75.4493 (err=2.8e-16) 7. NAPACK (f2c): elapsed time t=1.73453 s, 32768 iters, t-(init.)=1.71587 s t(norm)=0.281351, mflops=17.7714 (err=1.0e-15) 8. Nielsen: elapsed time t=1.48605 s, 32768 iters, t-(init.)=1.46741 s t(norm)=0.240611, mflops=20.7804 (err=9.7e-16) 9. Singleton (f2c): elapsed time t=1.94596 s, 131072 iters, t-(init.)=1.87145 s t(norm)=0.0767152, mflops=65.1761 (err=2.7e-16) 10. Temperton (f2c): elapsed time t=1.20762 s, 32768 iters, t-(init.)=1.18901 s t(norm)=0.194961, mflops=25.6462 (err=3.9e-16) 11. Valkenburg: elapsed time t=1.6622 s, 16384 iters, t-(init.)=1.65285 s t(norm)=0.542034, mflops=9.22452 (err=4.0e-16) Top mflops for N=36 = 143.948 Normalized results and averages for N=36: fft 0: mflops = 100.391 (norm. = 0.697408), norm. avg. (of 7) = 0.490548 fft 1: mflops = 100.407 (norm. = 0.697519), norm. avg. (of 7) = 0.437421 fft 2: mflops = 30.9777 (norm. = 0.2152), norm. avg. (of 7) = 0.21901 fft 3: mflops = 143.832 (norm. = 0.999196), norm. avg. (of 7) = 0.997967 fft 4: mflops = 143.948 (norm. = 1), norm. avg. (of 7) = 0.993426 fft 5: mflops = 25.9783 (norm. = 0.180469), norm. avg. (of 7) = 0.196785 fft 6: mflops = 75.4493 (norm. = 0.524142), norm. avg. (of 7) = 0.378713 fft 7: mflops = 17.7714 (norm. = 0.123457), norm. avg. (of 7) = 0.102773 fft 8: mflops = 20.7804 (norm. = 0.14436), norm. avg. (of 7) = 0.118354 fft 9: mflops = 65.1761 (norm. = 0.452775), norm. avg. (of 7) = 0.297889 fft 10: mflops = 25.6462 (norm. = 0.178163), norm. avg. (of 7) = 0.144496 fft 11: mflops = 9.22452 (norm. = 0.0640822), norm. avg. (of 7) = 0.0702064 Benchmarking for array size = 80: 0. CWP (min N): elapsed time t=1.3908 s, 65536 iters, t-(init.)=1.31009 s t(norm)=0.039526, mflops=126.499 1. CWP (best N) (N=84): elapsed time t=1.32915 s, 65536 iters, t-(init.)=1.24463 s t(norm)=0.0375508, mflops=133.153 2. FFTPACK (f2c): elapsed time t=1.11983 s, 16384 iters, t-(init.)=1.09969 s t(norm)=0.132712, mflops=37.6756 (err=7.7e-16) FFTW_MEASURE plan: (cost = 1.654639e-05) FFTW_TWIDDLE 5 FFTW_NOTW 16 3. FFTW: elapsed time t=1.10234 s, 65536 iters, t-(init.)=1.02174 s t(norm)=0.0308263, mflops=162.199 (err=7.3e-16) FFTW_ESTIMATE plan: (cost = 2.600000e+03) FFTW_TWIDDLE 5 FFTW_NOTW 16 4. FFTW_ESTIMATE: elapsed time t=1.10225 s, 65536 iters, t-(init.)=1.02151 s t(norm)=0.0308195, mflops=162.235 (err=7.3e-16) 5. Frigo-old: elapsed time t=1.72276 s, 32768 iters, t-(init.)=1.68247 s t(norm)=0.101521, mflops=49.2507 (err=7.1e-16) 6. GSL: elapsed time t=1.61541 s, 32768 iters, t-(init.)=1.57513 s t(norm)=0.0950445, mflops=52.6069 (err=6.9e-16) 7. NAPACK (f2c): elapsed time t=1.66147 s, 8192 iters, t-(init.)=1.65141 s t(norm)=0.398589, mflops=12.5443 (err=1.1e-15) 8. Nielsen: elapsed time t=1.15244 s, 16384 iters, t-(init.)=1.13222 s t(norm)=0.136638, mflops=36.5929 (err=5.4e-15) 9. Singleton (f2c): elapsed time t=1.82033 s, 65536 iters, t-(init.)=1.73972 s t(norm)=0.0524881, mflops=95.2597 (err=1.3e-15) 10. Temperton (f2c): elapsed time t=1.44019 s, 16384 iters, t-(init.)=1.41997 s t(norm)=0.171364, mflops=29.1777 (err=7.0e-16) 11. Valkenburg: elapsed time t=1.18412 s, 4096 iters, t-(init.)=1.17905 s t(norm)=0.569158, mflops=8.7849 (err=8.4e-16) Top mflops for N=80 = 162.235 Normalized results and averages for N=80: fft 0: mflops = 126.499 (norm. = 0.779727), norm. avg. (of 8) = 0.526695 fft 1: mflops = 133.153 (norm. = 0.820741), norm. avg. (of 8) = 0.485336 fft 2: mflops = 37.6756 (norm. = 0.232228), norm. avg. (of 8) = 0.220662 fft 3: mflops = 162.199 (norm. = 0.99978), norm. avg. (of 8) = 0.998194 fft 4: mflops = 162.235 (norm. = 1), norm. avg. (of 8) = 0.994248 fft 5: mflops = 49.2507 (norm. = 0.303576), norm. avg. (of 8) = 0.210134 fft 6: mflops = 52.6069 (norm. = 0.324264), norm. avg. (of 8) = 0.371906 fft 7: mflops = 12.5443 (norm. = 0.0773215), norm. avg. (of 8) = 0.0995912 fft 8: mflops = 36.5929 (norm. = 0.225555), norm. avg. (of 8) = 0.131754 fft 9: mflops = 95.2597 (norm. = 0.587171), norm. avg. (of 8) = 0.33405 fft 10: mflops = 29.1777 (norm. = 0.179848), norm. avg. (of 8) = 0.148915 fft 11: mflops = 8.7849 (norm. = 0.0541492), norm. avg. (of 8) = 0.0681993 Benchmarking for array size = 108: 0. CWP (min N) (N=110): elapsed time t=1.20611 s, 32768 iters, t-(init.)=1.15085 s t(norm)=0.0481422, mflops=103.859 1. CWP (best N) (N=112): elapsed time t=1.91907 s, 65536 iters, t-(init.)=1.80685 s t(norm)=0.0377921, mflops=132.303 2. FFTPACK (f2c): elapsed time t=1.74937 s, 16384 iters, t-(init.)=1.72233 s t(norm)=0.144097, mflops=34.6989 (err=4.7e-16) FFTW_MEASURE plan: (cost = 2.555762e-05) FFTW_TWIDDLE 9 FFTW_NOTW 12 3. FFTW: elapsed time t=1.70254 s, 65536 iters, t-(init.)=1.59437 s t(norm)=0.0333479, mflops=149.935 (err=3.7e-16) FFTW_ESTIMATE plan: (cost = 4.633200e+03) FFTW_TWIDDLE 9 FFTW_NOTW 12 4. FFTW_ESTIMATE: elapsed time t=1.7022 s, 65536 iters, t-(init.)=1.59398 s t(norm)=0.0333397, mflops=149.972 (err=3.7e-16) 5. Frigo-old: elapsed time t=1.26596 s, 8192 iters, t-(init.)=1.25246 s t(norm)=0.209572, mflops=23.8581 (err=5.5e-16) 6. GSL: elapsed time t=1.68026 s, 32768 iters, t-(init.)=1.62617 s t(norm)=0.0680259, mflops=73.5014 (err=4.7e-16) 7. NAPACK (f2c): elapsed time t=1.52748 s, 8192 iters, t-(init.)=1.51393 s t(norm)=0.253322, mflops=19.7377 (err=2.7e-15) 8. Nielsen: elapsed time t=1.25037 s, 8192 iters, t-(init.)=1.23682 s t(norm)=0.206955, mflops=24.1599 (err=1.1e-15) 9. Singleton (f2c): elapsed time t=1.74529 s, 32768 iters, t-(init.)=1.69111 s t(norm)=0.0707425, mflops=70.6789 (err=5.1e-16) 10. Temperton (f2c): elapsed time t=1.10797 s, 8192 iters, t-(init.)=1.09441 s t(norm)=0.183126, mflops=27.3037 (err=3.8e-16) 11. Valkenburg: elapsed time t=1.60434 s, 4096 iters, t-(init.)=1.59755 s t(norm)=0.534628, mflops=9.35229 (err=5.2e-16) Top mflops for N=108 = 149.972 Normalized results and averages for N=108: fft 0: mflops = 103.859 (norm. = 0.692524), norm. avg. (of 9) = 0.545121 fft 1: mflops = 132.303 (norm. = 0.882186), norm. avg. (of 9) = 0.52943 fft 2: mflops = 34.6989 (norm. = 0.23137), norm. avg. (of 9) = 0.221852 fft 3: mflops = 149.935 (norm. = 0.999754), norm. avg. (of 9) = 0.998367 fft 4: mflops = 149.972 (norm. = 1), norm. avg. (of 9) = 0.994887 fft 5: mflops = 23.8581 (norm. = 0.159084), norm. avg. (of 9) = 0.204462 fft 6: mflops = 73.5014 (norm. = 0.490103), norm. avg. (of 9) = 0.385039 fft 7: mflops = 19.7377 (norm. = 0.13161), norm. avg. (of 9) = 0.103149 fft 8: mflops = 24.1599 (norm. = 0.161096), norm. avg. (of 9) = 0.135014 fft 9: mflops = 70.6789 (norm. = 0.471282), norm. avg. (of 9) = 0.349298 fft 10: mflops = 27.3037 (norm. = 0.182059), norm. avg. (of 9) = 0.152598 fft 11: mflops = 9.35229 (norm. = 0.0623604), norm. avg. (of 9) = 0.0675505 Benchmarking for array size = 210: 0. CWP (min N): elapsed time t=1.01058 s, 16384 iters, t-(init.)=0.958384 s t(norm)=0.0361083, mflops=138.472 1. CWP (best N): elapsed time t=1.01052 s, 16384 iters, t-(init.)=0.958169 s t(norm)=0.0361002, mflops=138.503 2. FFTPACK (f2c): elapsed time t=1.30143 s, 4096 iters, t-(init.)=1.28835 s t(norm)=0.194161, mflops=25.7518 (err=5.7e-16) FFTW_MEASURE plan: (cost = 6.713965e-05) FFTW_TWIDDLE 2 FFTW_TWIDDLE 7 FFTW_NOTW 15 3. FFTW: elapsed time t=1.11684 s, 16384 iters, t-(init.)=1.06467 s t(norm)=0.0401129, mflops=124.648 (err=4.5e-16) FFTW_ESTIMATE plan: (cost = 9.324000e+03) FFTW_TWIDDLE 7 FFTW_TWIDDLE 2 FFTW_NOTW 15 4. FFTW_ESTIMATE: elapsed time t=1.14048 s, 16384 iters, t-(init.)=1.08828 s t(norm)=0.0410025, mflops=121.944 (err=4.6e-16) 5. Frigo-old: elapsed time t=1.39897 s, 4096 iters, t-(init.)=1.38589 s t(norm)=0.208861, mflops=23.9394 (err=5.8e-16) 6. GSL: elapsed time t=1.3213 s, 8192 iters, t-(init.)=1.29517 s t(norm)=0.0975945, mflops=51.2324 (err=5.3e-16) 7. NAPACK (f2c): elapsed time t=1.62817 s, 2048 iters, t-(init.)=1.62167 s t(norm)=0.488788, mflops=10.2294 (err=1.4e-14) 8. Nielsen: elapsed time t=1.11288 s, 4096 iters, t-(init.)=1.09985 s t(norm)=0.165753, mflops=30.1654 (err=7.6e-15) 9. Singleton (f2c): elapsed time t=1.16368 s, 8192 iters, t-(init.)=1.13752 s t(norm)=0.0857147, mflops=58.3331 (err=6.7e-16) 10. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). 11. Valkenburg: elapsed time t=1.12609 s, 1024 iters, t-(init.)=1.1228 s t(norm)=0.676847, mflops=7.38719 (err=6.5e-16) Top mflops for N=210 = 138.503 Normalized results and averages for N=210: fft 0: mflops = 138.472 (norm. = 0.999776), norm. avg. (of 10) = 0.590586 fft 1: mflops = 138.503 (norm. = 1), norm. avg. (of 10) = 0.576487 fft 2: mflops = 25.7518 (norm. = 0.185929), norm. avg. (of 10) = 0.21826 fft 3: mflops = 124.648 (norm. = 0.899964), norm. avg. (of 10) = 0.988527 fft 4: mflops = 121.944 (norm. = 0.880439), norm. avg. (of 10) = 0.983442 fft 5: mflops = 23.9394 (norm. = 0.172843), norm. avg. (of 10) = 0.2013 fft 6: mflops = 51.2324 (norm. = 0.3699), norm. avg. (of 10) = 0.383525 fft 7: mflops = 10.2294 (norm. = 0.0738566), norm. avg. (of 10) = 0.10022 fft 8: mflops = 30.1654 (norm. = 0.217795), norm. avg. (of 10) = 0.143292 fft 9: mflops = 58.3331 (norm. = 0.421167), norm. avg. (of 10) = 0.356484 fft 10: mflops = -1 (norm. = -0.00722004), norm. avg. (of 9) = 0.152598 fft 11: mflops = 7.38719 (norm. = 0.0533358), norm. avg. (of 10) = 0.066129 Benchmarking for array size = 504: 0. CWP (min N): elapsed time t=1.34712 s, 8192 iters, t-(init.)=1.28469 s t(norm)=0.0346603, mflops=144.257 1. CWP (best N): elapsed time t=1.34719 s, 8192 iters, t-(init.)=1.28483 s t(norm)=0.0346642, mflops=144.241 2. FFTPACK (f2c): elapsed time t=1.81148 s, 2048 iters, t-(init.)=1.79587 s t(norm)=0.193808, mflops=25.7988 (err=9.8e-16) FFTW_MEASURE plan: (cost = 1.554473e-04) FFTW_TWIDDLE 7 FFTW_TWIDDLE 6 FFTW_NOTW 12 3. FFTW: elapsed time t=1.28894 s, 8192 iters, t-(init.)=1.22657 s t(norm)=0.0330924, mflops=151.092 (err=9.2e-16) FFTW_ESTIMATE plan: (cost = 2.147040e+04) FFTW_TWIDDLE 6 FFTW_TWIDDLE 6 FFTW_NOTW 14 4. FFTW_ESTIMATE: elapsed time t=1.42919 s, 8192 iters, t-(init.)=1.36682 s t(norm)=0.0368762, mflops=135.589 (err=8.8e-16) 5. Frigo-old: elapsed time t=1.64162 s, 2048 iters, t-(init.)=1.62598 s t(norm)=0.175473, mflops=28.4945 (err=1.0e-15) 6. GSL: elapsed time t=1.33234 s, 4096 iters, t-(init.)=1.30116 s t(norm)=0.0702095, mflops=71.2154 (err=8.9e-16) 7. NAPACK (f2c): elapsed time t=1.7489 s, 1024 iters, t-(init.)=1.74114 s t(norm)=0.375801, mflops=13.3049 (err=4.2e-14) 8. Nielsen: elapsed time t=1.58382 s, 2048 iters, t-(init.)=1.56814 s t(norm)=0.169231, mflops=29.5455 (err=5.8e-15) 9. Singleton (f2c): elapsed time t=1.36304 s, 4096 iters, t-(init.)=1.33184 s t(norm)=0.0718648, mflops=69.5751 (err=1.3e-15) 10. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). 11. Valkenburg: elapsed time t=1.41479 s, 512 iters, t-(init.)=1.4109 s t(norm)=0.609047, mflops=8.20954 (err=1.0e-15) Top mflops for N=504 = 151.092 Normalized results and averages for N=504: fft 0: mflops = 144.257 (norm. = 0.954764), norm. avg. (of 11) = 0.623693 fft 1: mflops = 144.241 (norm. = 0.954655), norm. avg. (of 11) = 0.610866 fft 2: mflops = 25.7988 (norm. = 0.170749), norm. avg. (of 11) = 0.21394 fft 3: mflops = 151.092 (norm. = 1), norm. avg. (of 11) = 0.98957 fft 4: mflops = 135.589 (norm. = 0.897391), norm. avg. (of 11) = 0.975619 fft 5: mflops = 28.4945 (norm. = 0.18859), norm. avg. (of 11) = 0.200144 fft 6: mflops = 71.2154 (norm. = 0.471338), norm. avg. (of 11) = 0.391508 fft 7: mflops = 13.3049 (norm. = 0.0880581), norm. avg. (of 11) = 0.099114 fft 8: mflops = 29.5455 (norm. = 0.195546), norm. avg. (of 11) = 0.148043 fft 9: mflops = 69.5751 (norm. = 0.460481), norm. avg. (of 11) = 0.365939 fft 10: mflops = -1 (norm. = -0.00661847), norm. avg. (of 9) = 0.152598 fft 11: mflops = 8.20954 (norm. = 0.0543346), norm. avg. (of 11) = 0.0650568 Benchmarking for array size = 1000: 0. CWP (min N) (N=1001): elapsed time t=1.0469 s, 2048 iters, t-(init.)=1.01595 s t(norm)=0.0497774, mflops=100.447 1. CWP (best N) (N=1008): elapsed time t=1.47733 s, 4096 iters, t-(init.)=1.41506 s t(norm)=0.034666, mflops=144.234 2. FFTPACK (f2c): elapsed time t=1.61381 s, 1024 iters, t-(init.)=1.59831 s t(norm)=0.156621, mflops=31.9242 (err=3.1e-15) FFTW_MEASURE plan: (cost = 4.327891e-04) FFTW_TWIDDLE 10 FFTW_TWIDDLE 10 FFTW_NOTW 10 3. FFTW: elapsed time t=1.7858 s, 4096 iters, t-(init.)=1.72403 s t(norm)=0.0422352, mflops=118.385 (err=3.1e-15) FFTW_ESTIMATE plan: (cost = 5.220000e+04) FFTW_TWIDDLE 10 FFTW_TWIDDLE 10 FFTW_NOTW 10 4. FFTW_ESTIMATE: elapsed time t=1.78422 s, 4096 iters, t-(init.)=1.72246 s t(norm)=0.0421965, mflops=118.493 (err=3.1e-15) 5. Frigo-old: elapsed time t=1.75135 s, 1024 iters, t-(init.)=1.73588 s t(norm)=0.170101, mflops=29.3943 (err=3.1e-15) 6. GSL: elapsed time t=1.27897 s, 1024 iters, t-(init.)=1.26349 s t(norm)=0.123811, mflops=40.384 (err=3.1e-15) 7. NAPACK (f2c): elapsed time t=1.10653 s, 256 iters, t-(init.)=1.10263 s t(norm)=0.432193, mflops=11.5689 (err=1.8e-14) 8. Nielsen: elapsed time t=1.21999 s, 1024 iters, t-(init.)=1.20451 s t(norm)=0.118031, mflops=42.3616 (err=1.5e-14) 9. Singleton (f2c): elapsed time t=1.13891 s, 2048 iters, t-(init.)=1.10783 s t(norm)=0.054279, mflops=92.1167 (err=4.7e-15) 10. Temperton (f2c): elapsed time t=1.87494 s, 1024 iters, t-(init.)=1.85947 s t(norm)=0.182213, mflops=27.4404 (err=3.0e-15) 11. Valkenburg: elapsed time t=1.62986 s, 256 iters, t-(init.)=1.62595 s t(norm)=0.637318, mflops=7.84538 (err=3.0e-15) Top mflops for N=1000 = 144.234 Normalized results and averages for N=1000: fft 0: mflops = 100.447 (norm. = 0.696419), norm. avg. (of 12) = 0.629754 fft 1: mflops = 144.234 (norm. = 1), norm. avg. (of 12) = 0.643294 fft 2: mflops = 31.9242 (norm. = 0.221337), norm. avg. (of 12) = 0.214557 fft 3: mflops = 118.385 (norm. = 0.820783), norm. avg. (of 12) = 0.975504 fft 4: mflops = 118.493 (norm. = 0.821536), norm. avg. (of 12) = 0.962779 fft 5: mflops = 29.3943 (norm. = 0.203796), norm. avg. (of 12) = 0.200449 fft 6: mflops = 40.384 (norm. = 0.27999), norm. avg. (of 12) = 0.382215 fft 7: mflops = 11.5689 (norm. = 0.0802095), norm. avg. (of 12) = 0.0975386 fft 8: mflops = 42.3616 (norm. = 0.293701), norm. avg. (of 12) = 0.160181 fft 9: mflops = 92.1167 (norm. = 0.638663), norm. avg. (of 12) = 0.388666 fft 10: mflops = 27.4404 (norm. = 0.19025), norm. avg. (of 10) = 0.156363 fft 11: mflops = 7.84538 (norm. = 0.0543935), norm. avg. (of 12) = 0.0641682 Benchmarking for array size = 1960: 0. CWP (min N) (N=1980): elapsed time t=1.7775 s, 2048 iters, t-(init.)=1.71542 s t(norm)=0.0390752, mflops=127.959 1. CWP (best N) (N=1980): elapsed time t=1.77779 s, 2048 iters, t-(init.)=1.71568 s t(norm)=0.0390811, mflops=127.939 2. FFTPACK (f2c): elapsed time t=1.37113 s, 256 iters, t-(init.)=1.3634 s t(norm)=0.248452, mflops=20.1246 (err=1.5e-15) FFTW_MEASURE plan: (cost = 1.043281e-03) FFTW_TWIDDLE 7 FFTW_TWIDDLE 5 FFTW_TWIDDLE 7 FFTW_NOTW 8 3. FFTW: elapsed time t=1.07148 s, 1024 iters, t-(init.)=1.04075 s t(norm)=0.0474139, mflops=105.454 (err=1.5e-15) FFTW_ESTIMATE plan: (cost = 9.662800e+04) FFTW_TWIDDLE 10 FFTW_TWIDDLE 7 FFTW_TWIDDLE 2 FFTW_NOTW 14 4. FFTW_ESTIMATE: elapsed time t=1.13238 s, 1024 iters, t-(init.)=1.10157 s t(norm)=0.0501847, mflops=99.6319 (err=1.5e-15) 5. Frigo-old: elapsed time t=1.03274 s, 256 iters, t-(init.)=1.02507 s t(norm)=0.186799, mflops=26.7667 (err=1.5e-15) 6. GSL: elapsed time t=1.33653 s, 512 iters, t-(init.)=1.32112 s t(norm)=0.120374, mflops=41.5372 (err=1.6e-15) 7. NAPACK (f2c): elapsed time t=1.436 s, 128 iters, t-(init.)=1.43213 s t(norm)=0.521956, mflops=9.57935 (err=1.3e-13) 8. Nielsen: elapsed time t=1.80397 s, 512 iters, t-(init.)=1.78845 s t(norm)=0.162955, mflops=30.6834 (err=1.7e-14) 9. Singleton (f2c): elapsed time t=1.5936 s, 1024 iters, t-(init.)=1.56277 s t(norm)=0.0711961, mflops=70.2286 (err=2.3e-15) 10. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). 11. Valkenburg: elapsed time t=1.0096 s, 64 iters, t-(init.)=1.00764 s t(norm)=0.734489, mflops=6.80745 (err=1.4e-15) Top mflops for N=1960 = 127.959 Normalized results and averages for N=1960: fft 0: mflops = 127.959 (norm. = 1), norm. avg. (of 13) = 0.658234 fft 1: mflops = 127.939 (norm. = 0.999848), norm. avg. (of 13) = 0.670721 fft 2: mflops = 20.1246 (norm. = 0.157275), norm. avg. (of 13) = 0.21015 fft 3: mflops = 105.454 (norm. = 0.82413), norm. avg. (of 13) = 0.96386 fft 4: mflops = 99.6319 (norm. = 0.778627), norm. avg. (of 13) = 0.948613 fft 5: mflops = 26.7667 (norm. = 0.209183), norm. avg. (of 13) = 0.201121 fft 6: mflops = 41.5372 (norm. = 0.324615), norm. avg. (of 13) = 0.377784 fft 7: mflops = 9.57935 (norm. = 0.0748629), norm. avg. (of 13) = 0.0957943 fft 8: mflops = 30.6834 (norm. = 0.239792), norm. avg. (of 13) = 0.166305 fft 9: mflops = 70.2286 (norm. = 0.548839), norm. avg. (of 13) = 0.400987 fft 10: mflops = -1 (norm. = -0.00781503), norm. avg. (of 10) = 0.156363 fft 11: mflops = 6.80745 (norm. = 0.0532005), norm. avg. (of 13) = 0.0633245 Benchmarking for array size = 4725: 0. CWP (min N) (N=5005): elapsed time t=1.78541 s, 512 iters, t-(init.)=1.67905 s t(norm)=0.0568612, mflops=87.9334 1. CWP (best N) (N=5040): elapsed time t=1.42386 s, 512 iters, t-(init.)=1.31686 s t(norm)=0.0445955, mflops=112.119 2. FFTPACK (f2c): elapsed time t=1.56547 s, 128 iters, t-(init.)=1.54037 s t(norm)=0.208659, mflops=23.9625 (err=2.4e-15) FFTW_MEASURE plan: (cost = 2.956562e-03) FFTW_TWIDDLE 9 FFTW_TWIDDLE 5 FFTW_TWIDDLE 7 FFTW_NOTW 15 3. FFTW: elapsed time t=1.87967 s, 512 iters, t-(init.)=1.77907 s t(norm)=0.0602484, mflops=82.9898 (err=2.4e-15) FFTW_ESTIMATE plan: (cost = 1.946700e+05) FFTW_TWIDDLE 5 FFTW_TWIDDLE 7 FFTW_TWIDDLE 9 FFTW_NOTW 15 4. FFTW_ESTIMATE: elapsed time t=1.57455 s, 512 iters, t-(init.)=1.47402 s t(norm)=0.0499177, mflops=100.165 (err=2.3e-15) 5. Frigo-old: elapsed time t=1.00155 s, 64 iters, t-(init.)=0.988923 s t(norm)=0.267919, mflops=18.6623 (err=2.3e-15) 6. GSL: elapsed time t=1.80161 s, 256 iters, t-(init.)=1.75142 s t(norm)=0.118624, mflops=42.1501 (err=2.4e-15) 7. NAPACK (f2c): elapsed time t=1.78829 s, 64 iters, t-(init.)=1.77572 s t(norm)=0.481078, mflops=10.3933 (err=3.5e-13) 8. Nielsen: elapsed time t=1.45845 s, 128 iters, t-(init.)=1.4333 s t(norm)=0.194155, mflops=25.7527 (err=4.4e-14) 9. Singleton (f2c): elapsed time t=1.37035 s, 256 iters, t-(init.)=1.32015 s t(norm)=0.0894136, mflops=55.9199 (err=3.3e-15) 10. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). 11. Valkenburg: elapsed time t=1.28578 s, 32 iters, t-(init.)=1.27951 s t(norm)=0.693288, mflops=7.21201 (err=2.3e-15) Top mflops for N=4725 = 112.119 Normalized results and averages for N=4725: fft 0: mflops = 87.9334 (norm. = 0.784286), norm. avg. (of 14) = 0.667238 fft 1: mflops = 112.119 (norm. = 1), norm. avg. (of 14) = 0.694241 fft 2: mflops = 23.9625 (norm. = 0.213724), norm. avg. (of 14) = 0.210406 fft 3: mflops = 82.9898 (norm. = 0.740193), norm. avg. (of 14) = 0.947884 fft 4: mflops = 100.165 (norm. = 0.893381), norm. avg. (of 14) = 0.944668 fft 5: mflops = 18.6623 (norm. = 0.166451), norm. avg. (of 14) = 0.198644 fft 6: mflops = 42.1501 (norm. = 0.375941), norm. avg. (of 14) = 0.377653 fft 7: mflops = 10.3933 (norm. = 0.0926991), norm. avg. (of 14) = 0.0955732 fft 8: mflops = 25.7527 (norm. = 0.22969), norm. avg. (of 14) = 0.170832 fft 9: mflops = 55.9199 (norm. = 0.498755), norm. avg. (of 14) = 0.40797 fft 10: mflops = -1 (norm. = -0.00891909), norm. avg. (of 10) = 0.156363 fft 11: mflops = 7.21201 (norm. = 0.0643246), norm. avg. (of 14) = 0.063396 Benchmarking for array size = 10368: 0. CWP (min N) (N=10920): elapsed time t=1.01605 s, 128 iters, t-(init.)=0.957771 s t(norm)=0.0541011, mflops=92.4196 1. CWP (best N) (N=11088): elapsed time t=1.87678 s, 256 iters, t-(init.)=1.75897 s t(norm)=0.0496789, mflops=100.646 2. FFTPACK (f2c): elapsed time t=1.52571 s, 64 iters, t-(init.)=1.498 s t(norm)=0.169234, mflops=29.5449 (err=4.7e-15) FFTW_MEASURE plan: (cost = 6.422000e-03) FFTW_TWIDDLE 3 FFTW_TWIDDLE 9 FFTW_TWIDDLE 6 FFTW_NOTW 64 3. FFTW: elapsed time t=1.91737 s, 256 iters, t-(init.)=1.80672 s t(norm)=0.0510275, mflops=97.9864 (err=4.7e-15) FFTW_ESTIMATE plan: (cost = 1.254528e+05) FFTW_TWIDDLE 9 FFTW_TWIDDLE 6 FFTW_TWIDDLE 6 FFTW_NOTW 32 4. FFTW_ESTIMATE: elapsed time t=1.87837 s, 256 iters, t-(init.)=1.76778 s t(norm)=0.0499279, mflops=100.144 (err=4.7e-15) 5. Frigo-old: elapsed time t=1.67615 s, 64 iters, t-(init.)=1.6482 s t(norm)=0.186201, mflops=26.8526 (err=4.8e-15) 6. GSL: elapsed time t=1.5348 s, 128 iters, t-(init.)=1.47958 s t(norm)=0.0835761, mflops=59.8257 (err=4.7e-15) 7. NAPACK (f2c): elapsed time t=1.24566 s, 32 iters, t-(init.)=1.23177 s t(norm)=0.278313, mflops=17.9654 (err=7.8e-14) 8. Nielsen: elapsed time t=1.76573 s, 64 iters, t-(init.)=1.73795 s t(norm)=0.196341, mflops=25.4658 (err=1.1e-14) 9. Singleton (f2c): elapsed time t=1.52472 s, 128 iters, t-(init.)=1.46969 s t(norm)=0.0830178, mflops=60.2281 (err=6.7e-15) 10. Temperton (f2c): elapsed time t=1.76928 s, 64 iters, t-(init.)=1.74177 s t(norm)=0.196773, mflops=25.41 (err=4.7e-15) 11. Valkenburg: elapsed time t=1.37513 s, 16 iters, t-(init.)=1.36801 s t(norm)=0.618191, mflops=8.08811 (err=4.7e-15) Top mflops for N=10368 = 100.646 Normalized results and averages for N=10368: fft 0: mflops = 92.4196 (norm. = 0.918261), norm. avg. (of 15) = 0.683973 fft 1: mflops = 100.646 (norm. = 1), norm. avg. (of 15) = 0.714625 fft 2: mflops = 29.5449 (norm. = 0.293552), norm. avg. (of 15) = 0.215949 fft 3: mflops = 97.9864 (norm. = 0.973571), norm. avg. (of 15) = 0.949596 fft 4: mflops = 100.144 (norm. = 0.995013), norm. avg. (of 15) = 0.948025 fft 5: mflops = 26.8526 (norm. = 0.266802), norm. avg. (of 15) = 0.203188 fft 6: mflops = 59.8257 (norm. = 0.594415), norm. avg. (of 15) = 0.392103 fft 7: mflops = 17.9654 (norm. = 0.1785), norm. avg. (of 15) = 0.101102 fft 8: mflops = 25.4658 (norm. = 0.253023), norm. avg. (of 15) = 0.176312 fft 9: mflops = 60.2281 (norm. = 0.598413), norm. avg. (of 15) = 0.420666 fft 10: mflops = 25.41 (norm. = 0.252468), norm. avg. (of 11) = 0.1651 fft 11: mflops = 8.08811 (norm. = 0.0803617), norm. avg. (of 15) = 0.064527 Benchmarking for array size = 27000: 0. CWP (min N) (N=27720): elapsed time t=1.34398 s, 64 iters, t-(init.)=1.26798 s t(norm)=0.0498471, mflops=100.307 1. CWP (best N) (N=27720): elapsed time t=1.34493 s, 64 iters, t-(init.)=1.26916 s t(norm)=0.0498938, mflops=100.213 2. FFTPACK (f2c): elapsed time t=1.48452 s, 16 iters, t-(init.)=1.4645 s t(norm)=0.230292, mflops=21.7116 (err=7.3e-15) FFTW_MEASURE plan: (cost = 3.113750e-02) FFTW_TWIDDLE 8 FFTW_TWIDDLE 9 FFTW_TWIDDLE 5 FFTW_TWIDDLE 5 FFTW_NOTW 15 3. FFTW: elapsed time t=1.99093 s, 64 iters, t-(init.)=1.91537 s t(norm)=0.0752976, mflops=66.4032 (err=7.3e-15) FFTW_ESTIMATE plan: (cost = 1.231200e+06) FFTW_TWIDDLE 10 FFTW_TWIDDLE 10 FFTW_TWIDDLE 2 FFTW_TWIDDLE 9 FFTW_NOTW 15 4. FFTW_ESTIMATE: elapsed time t=1.96813 s, 64 iters, t-(init.)=1.89217 s t(norm)=0.0743855, mflops=67.2174 (err=7.3e-15) 5. Frigo-old: elapsed time t=1.86821 s, 16 iters, t-(init.)=1.84751 s t(norm)=0.29052, mflops=17.2105 (err=7.3e-15) 6. GSL: elapsed time t=1.05831 s, 16 iters, t-(init.)=1.03961 s t(norm)=0.163478, mflops=30.5852 (err=7.3e-15) 7. NAPACK (f2c): elapsed time t=1.71583 s, 8 iters, t-(init.)=1.70547 s t(norm)=0.536368, mflops=9.32195 (err=1.0e-12) 8. Nielsen: elapsed time t=1.25209 s, 16 iters, t-(init.)=1.23112 s t(norm)=0.193593, mflops=25.8273 (err=2.0e-13) 9. Singleton (f2c): elapsed time t=1.16893 s, 32 iters, t-(init.)=1.13177 s t(norm)=0.0889847, mflops=56.1894 (err=1.1e-14) 10. Temperton (f2c): elapsed time t=1.31336 s, 16 iters, t-(init.)=1.29462 s t(norm)=0.203577, mflops=24.5607 (err=7.3e-15) 11. Valkenburg: elapsed time t=1.20896 s, 4 iters, t-(init.)=1.20225 s t(norm)=0.756213, mflops=6.61189 (err=7.3e-15) Top mflops for N=27000 = 100.307 Normalized results and averages for N=27000: fft 0: mflops = 100.307 (norm. = 1), norm. avg. (of 16) = 0.703724 fft 1: mflops = 100.213 (norm. = 0.999065), norm. avg. (of 16) = 0.732403 fft 2: mflops = 21.7116 (norm. = 0.216452), norm. avg. (of 16) = 0.21598 fft 3: mflops = 66.4032 (norm. = 0.662001), norm. avg. (of 16) = 0.931622 fft 4: mflops = 67.2174 (norm. = 0.670118), norm. avg. (of 16) = 0.930655 fft 5: mflops = 17.2105 (norm. = 0.171579), norm. avg. (of 16) = 0.201212 fft 6: mflops = 30.5852 (norm. = 0.304917), norm. avg. (of 16) = 0.386654 fft 7: mflops = 9.32195 (norm. = 0.0929345), norm. avg. (of 16) = 0.100591 fft 8: mflops = 25.8273 (norm. = 0.257484), norm. avg. (of 16) = 0.181385 fft 9: mflops = 56.1894 (norm. = 0.560176), norm. avg. (of 16) = 0.429386 fft 10: mflops = 24.5607 (norm. = 0.244856), norm. avg. (of 12) = 0.171746 fft 11: mflops = 6.61189 (norm. = 0.0659168), norm. avg. (of 16) = 0.0646139 Benchmarking for array size = 75600: 0. CWP (min N) (N=80080): elapsed time t=1.84877 s, 16 iters, t-(init.)=1.66538 s t(norm)=0.084956, mflops=58.854 1. CWP (best N) (N=80080): elapsed time t=1.84867 s, 16 iters, t-(init.)=1.66525 s t(norm)=0.0849494, mflops=58.8585 2. FFTPACK (f2c): elapsed time t=1.63304 s, 4 iters, t-(init.)=1.58896 s t(norm)=0.32423, mflops=15.4211 (err=9.4e-15) FFTW_MEASURE plan: (cost = 1.046720e-01) FFTW_TWIDDLE 16 FFTW_TWIDDLE 9 FFTW_TWIDDLE 5 FFTW_TWIDDLE 7 FFTW_NOTW 15 3. FFTW: elapsed time t=1.6336 s, 16 iters, t-(init.)=1.46069 s t(norm)=0.0745138, mflops=67.1017 (err=9.4e-15) FFTW_ESTIMATE plan: (cost = 2.971080e+06) FFTW_TWIDDLE 10 FFTW_TWIDDLE 9 FFTW_TWIDDLE 7 FFTW_TWIDDLE 8 FFTW_NOTW 15 4. FFTW_ESTIMATE: elapsed time t=1.73515 s, 16 iters, t-(init.)=1.56231 s t(norm)=0.0796981, mflops=62.7368 (err=9.4e-15) 5. Frigo-old: elapsed time t=1.63387 s, 4 iters, t-(init.)=1.5914 s t(norm)=0.324728, mflops=15.3975 (err=9.4e-15) 6. GSL: elapsed time t=1.9542 s, 8 iters, t-(init.)=1.86811 s t(norm)=0.190596, mflops=26.2336 (err=9.4e-15) 7. NAPACK (f2c): elapsed time t=1.50722 s, 2 iters, t-(init.)=1.4865 s t(norm)=0.606647, mflops=8.24202 (err=5.1e-12) 8. Nielsen: elapsed time t=1.42931 s, 4 iters, t-(init.)=1.3858 s t(norm)=0.282775, mflops=17.6819 (err=4.7e-13) 9. Singleton (f2c): elapsed time t=1.01272 s, 4 iters, t-(init.)=0.971356 s t(norm)=0.198207, mflops=25.2262 (err=1.3e-14) 10. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). 11. Valkenburg: elapsed time t=1.05821 s, 1 iters, t-(init.)=1.04791 s t(norm)=0.855313, mflops=5.84581 (err=9.5e-15) Top mflops for N=75600 = 67.1017 Normalized results and averages for N=75600: fft 0: mflops = 58.854 (norm. = 0.877087), norm. avg. (of 17) = 0.713922 fft 1: mflops = 58.8585 (norm. = 0.877155), norm. avg. (of 17) = 0.740917 fft 2: mflops = 15.4211 (norm. = 0.229817), norm. avg. (of 17) = 0.216794 fft 3: mflops = 67.1017 (norm. = 1), norm. avg. (of 17) = 0.935644 fft 4: mflops = 62.7368 (norm. = 0.934951), norm. avg. (of 17) = 0.930908 fft 5: mflops = 15.3975 (norm. = 0.229465), norm. avg. (of 17) = 0.202874 fft 6: mflops = 26.2336 (norm. = 0.390952), norm. avg. (of 17) = 0.386907 fft 7: mflops = 8.24202 (norm. = 0.122829), norm. avg. (of 17) = 0.101899 fft 8: mflops = 17.6819 (norm. = 0.26351), norm. avg. (of 17) = 0.186216 fft 9: mflops = 25.2262 (norm. = 0.37594), norm. avg. (of 17) = 0.426242 fft 10: mflops = -1 (norm. = -0.0149028), norm. avg. (of 12) = 0.171746 fft 11: mflops = 5.84581 (norm. = 0.0871188), norm. avg. (of 17) = 0.0659377 Benchmarking for array size = 165375: 0. CWP (min N) (N=180180): elapsed time t=1.28574 s, 4 iters, t-(init.)=1.18255 s t(norm)=0.103123, mflops=48.4858 1. CWP (best N) (N=180180): elapsed time t=1.28594 s, 4 iters, t-(init.)=1.18268 s t(norm)=0.103135, mflops=48.4804 2. FFTPACK (f2c): elapsed time t=1.31299 s, 1 iters, t-(init.)=1.28978 s t(norm)=0.449897, mflops=11.1137 (err=3.7e-14) FFTW_MEASURE plan: (cost = 2.753610e-01) FFTW_TWIDDLE 9 FFTW_TWIDDLE 7 FFTW_TWIDDLE 7 FFTW_TWIDDLE 5 FFTW_TWIDDLE 5 FFTW_NOTW 15 3. FFTW: elapsed time t=1.09538 s, 4 iters, t-(init.)=1.00094 s t(norm)=0.0872864, mflops=57.2827 (err=3.7e-14) FFTW_ESTIMATE plan: (cost = 8.367975e+06) FFTW_TWIDDLE 7 FFTW_TWIDDLE 5 FFTW_TWIDDLE 5 FFTW_TWIDDLE 7 FFTW_TWIDDLE 9 FFTW_NOTW 15 4. FFTW_ESTIMATE: elapsed time t=1.12885 s, 4 iters, t-(init.)=1.03445 s t(norm)=0.090208, mflops=55.4275 (err=3.7e-14) 5. Frigo-old: elapsed time t=1.31759 s, 1 iters, t-(init.)=1.29444 s t(norm)=0.451523, mflops=11.0736 (err=3.7e-14) 6. GSL: elapsed time t=1.12989 s, 2 iters, t-(init.)=1.08293 s t(norm)=0.188873, mflops=26.4729 (err=3.7e-14) 7. NAPACK (f2c): elapsed time t=1.93952 s, 1 iters, t-(init.)=1.91678 s t(norm)=0.668604, mflops=7.47827 (err=1.6e-11) 8. Nielsen: elapsed time t=1.81387 s, 2 iters, t-(init.)=1.76667 s t(norm)=0.308122, mflops=16.2273 (err=1.6e-12) 9. Singleton (f2c): elapsed time t=1.21633 s, 2 iters, t-(init.)=1.17107 s t(norm)=0.204244, mflops=24.4806 (err=5.6e-14) 10. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). 11. Valkenburg: elapsed time t=2.68528 s, 1 iters, t-(init.)=2.66239 s t(norm)=0.928683, mflops=5.38397 (err=3.6e-14) Top mflops for N=165375 = 57.2827 Normalized results and averages for N=165375: fft 0: mflops = 48.4858 (norm. = 0.84643), norm. avg. (of 18) = 0.721284 fft 1: mflops = 48.4804 (norm. = 0.846335), norm. avg. (of 18) = 0.746774 fft 2: mflops = 11.1137 (norm. = 0.194014), norm. avg. (of 18) = 0.215529 fft 3: mflops = 57.2827 (norm. = 1), norm. avg. (of 18) = 0.939219 fft 4: mflops = 55.4275 (norm. = 0.967613), norm. avg. (of 18) = 0.932947 fft 5: mflops = 11.0736 (norm. = 0.193315), norm. avg. (of 18) = 0.202343 fft 6: mflops = 26.4729 (norm. = 0.462145), norm. avg. (of 18) = 0.391087 fft 7: mflops = 7.47827 (norm. = 0.13055), norm. avg. (of 18) = 0.103491 fft 8: mflops = 16.2273 (norm. = 0.283285), norm. avg. (of 18) = 0.191609 fft 9: mflops = 24.4806 (norm. = 0.427364), norm. avg. (of 18) = 0.426304 fft 10: mflops = -1 (norm. = -0.0174573), norm. avg. (of 12) = 0.171746 fft 11: mflops = 5.38397 (norm. = 0.0939894), norm. avg. (of 18) = 0.0674961 ------------------------------------------------------ @@@@ bench.3d.p2.log Benchmarking for sizes: 4x4x4 (0.00128174 MB) 8x8x8 (0.00830078 MB) 16x16x16 (0.0633545 MB) 32x32x32 (0.501587 MB) 64x64x64 (4.00305 MB) 256x64x32 (8.01184 MB) 16x1024x64 (16.047 MB) Maximum array size N = 1048576 Benchmarking FFTs: 0. FFTW 1. HARM (f2c) 2. NR (C) 3. PDA (f2c) 4. Singleton (f2c) 5. Temperton (f2c) Computing normalized averages (6 transforms). Benchmarking for array size = 4x4x4 (power of 2): 0. FFTW: elapsed time t=1.58706 s, 131072 iters, t-(init.)=1.45734 s t(norm)=0.0289546, mflops=172.684 (err=1.9e-16) 1. Skipping fft (all dimensions must be > 4 for HARM). 2. NR (C): elapsed time t=1.032 s, 32768 iters, t-(init.)=0.999562 s t(norm)=0.0794381, mflops=62.9421 (err=2.3e-16) 3. PDA (f2c): elapsed time t=1.30846 s, 8192 iters, t-(init.)=1.30029 s t(norm)=0.413353, mflops=12.0962 (err=2.8e-16) 4. Singleton (f2c): elapsed time t=1.13893 s, 65536 iters, t-(init.)=1.0741 s t(norm)=0.0426808, mflops=117.149 (err=1.9e-16) 5. Temperton (f2c): elapsed time t=1.90723 s, 32768 iters, t-(init.)=1.87471 s t(norm)=0.148988, mflops=33.5597 (err=1.9e-16) Top mflops for N=64 = 172.684 Normalized results and averages for N=64: fft 0: mflops = 172.684 (norm. = 1), norm. avg. (of 1) = 1 fft 1: mflops = -1 (norm. = -0.00579093), norm. avg. (of 0) = -1 fft 2: mflops = 62.9421 (norm. = 0.364493), norm. avg. (of 1) = 0.364493 fft 3: mflops = 12.0962 (norm. = 0.0700483), norm. avg. (of 1) = 0.0700483 fft 4: mflops = 117.149 (norm. = 0.678399), norm. avg. (of 1) = 0.678399 fft 5: mflops = 33.5597 (norm. = 0.194342), norm. avg. (of 1) = 0.194342 Benchmarking for array size = 8x8x8 (power of 2): 0. FFTW: elapsed time t=1.94461 s, 16384 iters, t-(init.)=1.81799 s t(norm)=0.0240802, mflops=207.64 (err=3.8e-16) 1. HARM (f2c): elapsed time t=1.23067 s, 2048 iters, t-(init.)=1.21483 s t(norm)=0.128728, mflops=38.8417 (err=3.6e-16) 2. NR (C): elapsed time t=1.13018 s, 4096 iters, t-(init.)=1.09849 s t(norm)=0.0582001, mflops=85.9105 (err=2.9e-16) 3. PDA (f2c): elapsed time t=1.19019 s, 1024 iters, t-(init.)=1.18222 s t(norm)=0.250544, mflops=19.9565 (err=3.1e-16) 4. Singleton (f2c): elapsed time t=1.9563 s, 8192 iters, t-(init.)=1.89304 s t(norm)=0.0501484, mflops=99.704 (err=3.1e-16) 5. Temperton (f2c): elapsed time t=1.34059 s, 2048 iters, t-(init.)=1.32475 s t(norm)=0.140375, mflops=35.6188 (err=3.7e-16) Top mflops for N=512 = 207.64 Normalized results and averages for N=512: fft 0: mflops = 207.64 (norm. = 1), norm. avg. (of 2) = 1 fft 1: mflops = 38.8417 (norm. = 0.187063), norm. avg. (of 1) = 0.187063 fft 2: mflops = 85.9105 (norm. = 0.413748), norm. avg. (of 2) = 0.389121 fft 3: mflops = 19.9565 (norm. = 0.0961114), norm. avg. (of 2) = 0.0830798 fft 4: mflops = 99.704 (norm. = 0.480178), norm. avg. (of 2) = 0.579289 fft 5: mflops = 35.6188 (norm. = 0.171541), norm. avg. (of 2) = 0.182942 Benchmarking for array size = 16x16x16 (power of 2): 0. FFTW: elapsed time t=1.83787 s, 1024 iters, t-(init.)=1.66402 s t(norm)=0.0330611, mflops=151.235 (err=4.1e-16) 1. HARM (f2c): elapsed time t=1.58069 s, 256 iters, t-(init.)=1.53717 s t(norm)=0.122163, mflops=40.9289 (err=4.0e-16) 2. NR (C): elapsed time t=1.38962 s, 256 iters, t-(init.)=1.34617 s t(norm)=0.106984, mflops=46.7358 (err=4.7e-16) 3. PDA (f2c): elapsed time t=1.23558 s, 128 iters, t-(init.)=1.21382 s t(norm)=0.192931, mflops=25.916 (err=3.8e-16) 4. Singleton (f2c): elapsed time t=1.82472 s, 512 iters, t-(init.)=1.73765 s t(norm)=0.069048, mflops=72.4134 (err=4.7e-16) 5. Temperton (f2c): elapsed time t=1.61957 s, 256 iters, t-(init.)=1.57612 s t(norm)=0.125259, mflops=39.9174 (err=4.1e-16) Top mflops for N=4096 = 151.235 Normalized results and averages for N=4096: fft 0: mflops = 151.235 (norm. = 1), norm. avg. (of 3) = 1 fft 1: mflops = 40.9289 (norm. = 0.270631), norm. avg. (of 2) = 0.228847 fft 2: mflops = 46.7358 (norm. = 0.309028), norm. avg. (of 3) = 0.362423 fft 3: mflops = 25.916 (norm. = 0.171362), norm. avg. (of 3) = 0.112507 fft 4: mflops = 72.4134 (norm. = 0.478813), norm. avg. (of 3) = 0.545797 fft 5: mflops = 39.9174 (norm. = 0.263943), norm. avg. (of 3) = 0.209942 Benchmarking for array size = 32x32x32 (power of 2): 0. FFTW: elapsed time t=1.11628 s, 64 iters, t-(init.)=1.02559 s t(norm)=0.0326028, mflops=153.361 (err=4.8e-16) 1. HARM (f2c): elapsed time t=1.0389 s, 16 iters, t-(init.)=1.01527 s t(norm)=0.129098, mflops=38.7303 (err=4.8e-16) 2. NR (C): elapsed time t=1.78434 s, 32 iters, t-(init.)=1.73855 s t(norm)=0.110534, mflops=45.235 (err=6.0e-16) 3. PDA (f2c): elapsed time t=1.63037 s, 16 iters, t-(init.)=1.60741 s t(norm)=0.204392, mflops=24.4628 (err=4.5e-16) 4. Singleton (f2c): elapsed time t=1.27911 s, 32 iters, t-(init.)=1.23361 s t(norm)=0.0784308, mflops=63.7505 (err=4.9e-16) 5. Temperton (f2c): elapsed time t=1.20403 s, 16 iters, t-(init.)=1.18109 s t(norm)=0.150183, mflops=33.2926 (err=5.1e-16) Top mflops for N=32768 = 153.361 Normalized results and averages for N=32768: fft 0: mflops = 153.361 (norm. = 1), norm. avg. (of 4) = 1 fft 1: mflops = 38.7303 (norm. = 0.252543), norm. avg. (of 3) = 0.236746 fft 2: mflops = 45.235 (norm. = 0.294957), norm. avg. (of 4) = 0.345557 fft 3: mflops = 24.4628 (norm. = 0.159511), norm. avg. (of 4) = 0.124258 fft 4: mflops = 63.7505 (norm. = 0.415688), norm. avg. (of 4) = 0.51327 fft 5: mflops = 33.2926 (norm. = 0.217086), norm. avg. (of 4) = 0.211728 Benchmarking for array size = 64x64x64 (power of 2): 0. FFTW: elapsed time t=1.46216 s, 4 iters, t-(init.)=1.31233 s t(norm)=0.0695296, mflops=71.9118 (err=1.0e-15) 1. HARM (f2c): elapsed time t=1.78977 s, 2 iters, t-(init.)=1.71444 s t(norm)=0.181668, mflops=27.5227 (err=1.0e-15) 2. NR (C): elapsed time t=1.62168 s, 1 iters, t-(init.)=1.58414 s t(norm)=0.335722, mflops=14.8933 (err=1.0e-15) 3. PDA (f2c): elapsed time t=1.16862 s, 1 iters, t-(init.)=1.13145 s t(norm)=0.239787, mflops=20.8519 (err=1.0e-15) 4. Singleton (f2c): elapsed time t=1.92981 s, 2 iters, t-(init.)=1.85443 s t(norm)=0.196503, mflops=25.4449 (err=1.4e-15) 5. Temperton (f2c): elapsed time t=1.96269 s, 2 iters, t-(init.)=1.88785 s t(norm)=0.200044, mflops=24.9945 (err=9.9e-16) Top mflops for N=262144 = 71.9118 Normalized results and averages for N=262144: fft 0: mflops = 71.9118 (norm. = 1), norm. avg. (of 5) = 1 fft 1: mflops = 27.5227 (norm. = 0.382728), norm. avg. (of 4) = 0.273241 fft 2: mflops = 14.8933 (norm. = 0.207104), norm. avg. (of 5) = 0.317866 fft 3: mflops = 20.8519 (norm. = 0.289964), norm. avg. (of 5) = 0.157399 fft 4: mflops = 25.4449 (norm. = 0.353835), norm. avg. (of 5) = 0.481383 fft 5: mflops = 24.9945 (norm. = 0.347571), norm. avg. (of 5) = 0.238897 Benchmarking for array size = 256x64x32 (power of 2): 0. FFTW: elapsed time t=1.60169 s, 2 iters, t-(init.)=1.45177 s t(norm)=0.0728694, mflops=68.616 (err=9.2e-16) 1. HARM (f2c): elapsed time t=1.95493 s, 1 iters, t-(init.)=1.87968 s t(norm)=0.188695, mflops=26.4978 (err=9.4e-16) 2. NR (C): elapsed time t=3.44968 s, 1 iters, t-(init.)=3.37454 s t(norm)=0.338759, mflops=14.7597 (err=9.6e-16) 3. PDA (f2c): elapsed time t=2.37462 s, 1 iters, t-(init.)=2.30023 s t(norm)=0.230913, mflops=21.6532 (err=8.8e-16) 4. Singleton (f2c): elapsed time t=2.15723 s, 1 iters, t-(init.)=2.08217 s t(norm)=0.209022, mflops=23.9209 (err=1.3e-15) 5. Temperton (f2c): elapsed time t=2.12177 s, 1 iters, t-(init.)=2.04706 s t(norm)=0.205498, mflops=24.3311 (err=9.2e-16) Top mflops for N=524288 = 68.616 Normalized results and averages for N=524288: fft 0: mflops = 68.616 (norm. = 1), norm. avg. (of 6) = 1 fft 1: mflops = 26.4978 (norm. = 0.386175), norm. avg. (of 5) = 0.295828 fft 2: mflops = 14.7597 (norm. = 0.215106), norm. avg. (of 6) = 0.30074 fft 3: mflops = 21.6532 (norm. = 0.315571), norm. avg. (of 6) = 0.183761 fft 4: mflops = 23.9209 (norm. = 0.34862), norm. avg. (of 6) = 0.459256 fft 5: mflops = 24.3311 (norm. = 0.354598), norm. avg. (of 6) = 0.25818 Benchmarking for array size = 16x1024x64 (power of 2): 0. FFTW: elapsed time t=1.95878 s, 1 iters, t-(init.)=1.809 s t(norm)=0.08626, mflops=57.9643 (err=1.2e-15) 1. HARM (f2c): elapsed time t=4.10236 s, 1 iters, t-(init.)=3.95197 s t(norm)=0.188444, mflops=26.533 (err=1.2e-15) 2. NR (C): elapsed time t=7.34251 s, 1 iters, t-(init.)=7.19224 s t(norm)=0.342953, mflops=14.5793 (err=1.3e-15) 3. PDA (f2c): elapsed time t=5.76021 s, 1 iters, t-(init.)=5.61041 s t(norm)=0.267525, mflops=18.6898 (err=1.2e-15) 4. Singleton (f2c): elapsed time t=4.52599 s, 1 iters, t-(init.)=4.37545 s t(norm)=0.208638, mflops=23.965 (err=1.7e-15) 5. Skipping fft (Temperton can't handle dimensions > 256). Top mflops for N=1048576 = 57.9643 Normalized results and averages for N=1048576: fft 0: mflops = 57.9643 (norm. = 1), norm. avg. (of 7) = 1 fft 1: mflops = 26.533 (norm. = 0.457748), norm. avg. (of 6) = 0.322815 fft 2: mflops = 14.5793 (norm. = 0.251521), norm. avg. (of 7) = 0.293708 fft 3: mflops = 18.6898 (norm. = 0.322437), norm. avg. (of 7) = 0.203572 fft 4: mflops = 23.965 (norm. = 0.413444), norm. avg. (of 7) = 0.452711 fft 5: mflops = -1 (norm. = -0.017252), norm. avg. (of 6) = 0.25818 ------------------------------------------------------ @@@@ bench.3d.np2.log Benchmarking for sizes: 5x5x5 (0.0022583 MB) 6x6x6 (0.00369263 MB) 7x7x7 (0.00567627 MB) 9x9x9 (0.0116577 MB) 10x10x10 (0.0158386 MB) 11x11x11 (0.0209351 MB) 12x12x12 (0.0270386 MB) 13x13x13 (0.0342407 MB) 14x14x14 (0.0426331 MB) 15x15x15 (0.0523071 MB) 24x25x28 (0.257751 MB) 48x48x48 (1.68982 MB) 49x49x49 (1.79755 MB) 60x60x60 (3.29877 MB) 72x60x56 (3.69482 MB) 75x75x75 (6.44086 MB) 80x80x80 (7.81628 MB) 84x84x84 (9.04791 MB) 96x96x96 (13.5045 MB) 105x105x105 (17.6689 MB) Maximum array size N = 1157625 Benchmarking FFTs: 0. FFTW 1. PDA (f2c) 2. Singleton (f2c) 3. Temperton (f2c) Computing normalized averages (4 transforms). Benchmarking for array size = 5x5x5: 0. FFTW: elapsed time t=1.42782 s, 32768 iters, t-(init.)=1.36539 s t(norm)=0.047855, mflops=104.482 (err=2.4e-16) 1. PDA (f2c): elapsed time t=1.27209 s, 4096 iters, t-(init.)=1.26447 s t(norm)=0.354544, mflops=14.1026 (err=2.1e-16) 2. Singleton (f2c): elapsed time t=1.05877 s, 32768 iters, t-(init.)=0.99626 s t(norm)=0.0349175, mflops=143.195 (err=3.1e-16) 3. Temperton (f2c): elapsed time t=1.1366 s, 8192 iters, t-(init.)=1.12096 s t(norm)=0.157153, mflops=31.8162 (err=2.4e-16) Top mflops for N=125 = 143.195 Normalized results and averages for N=125: fft 0: mflops = 104.482 (norm. = 0.729651), norm. avg. (of 1) = 0.729651 fft 1: mflops = 14.1026 (norm. = 0.0984856), norm. avg. (of 1) = 0.0984856 fft 2: mflops = 143.195 (norm. = 1), norm. avg. (of 1) = 1 fft 3: mflops = 31.8162 (norm. = 0.222188), norm. avg. (of 1) = 0.222188 Benchmarking for array size = 6x6x6: 0. FFTW: elapsed time t=1.90732 s, 32768 iters, t-(init.)=1.80001 s t(norm)=0.0327941, mflops=152.467 (err=3.0e-16) 1. PDA (f2c): elapsed time t=1.13863 s, 2048 iters, t-(init.)=1.13191 s t(norm)=0.329953, mflops=15.1537 (err=3.7e-16) 2. Singleton (f2c): elapsed time t=1.59159 s, 16384 iters, t-(init.)=1.53793 s t(norm)=0.0560385, mflops=89.2244 (err=3.1e-16) 3. Temperton (f2c): elapsed time t=1.13946 s, 4096 iters, t-(init.)=1.12602 s t(norm)=0.164118, mflops=30.4658 (err=3.2e-16) Top mflops for N=216 = 152.467 Normalized results and averages for N=216: fft 0: mflops = 152.467 (norm. = 1), norm. avg. (of 2) = 0.864825 fft 1: mflops = 15.1537 (norm. = 0.0993901), norm. avg. (of 2) = 0.0989378 fft 2: mflops = 89.2244 (norm. = 0.585206), norm. avg. (of 2) = 0.792603 fft 3: mflops = 30.4658 (norm. = 0.19982), norm. avg. (of 2) = 0.211004 Benchmarking for array size = 7x7x7: 0. FFTW: elapsed time t=1.15101 s, 8192 iters, t-(init.)=1.10847 s t(norm)=0.0468406, mflops=106.745 (err=4.0e-16) 1. PDA (f2c): elapsed time t=1.6858 s, 1024 iters, t-(init.)=1.6805 s t(norm)=0.568102, mflops=8.80123 (err=4.0e-16) 2. Singleton (f2c): elapsed time t=1.65025 s, 8192 iters, t-(init.)=1.60773 s t(norm)=0.0679377, mflops=73.5968 (err=4.9e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=343 = 106.745 Normalized results and averages for N=343: fft 0: mflops = 106.745 (norm. = 1), norm. avg. (of 3) = 0.909884 fft 1: mflops = 8.80123 (norm. = 0.082451), norm. avg. (of 3) = 0.0934422 fft 2: mflops = 73.5968 (norm. = 0.689464), norm. avg. (of 3) = 0.758223 fft 3: mflops = -1 (norm. = -0.00936812), norm. avg. (of 2) = 0.211004 Benchmarking for array size = 9x9x9: 0. FFTW: elapsed time t=1.15468 s, 4096 iters, t-(init.)=1.10962 s t(norm)=0.0390764, mflops=127.954 (err=5.4e-16) 1. PDA (f2c): elapsed time t=1.87916 s, 1024 iters, t-(init.)=1.86791 s t(norm)=0.263123, mflops=19.0025 (err=5.2e-16) 2. Singleton (f2c): elapsed time t=1.4437 s, 4096 iters, t-(init.)=1.39862 s t(norm)=0.0492541, mflops=101.514 (err=4.9e-16) 3. Temperton (f2c): elapsed time t=1.98587 s, 2048 iters, t-(init.)=1.96334 s t(norm)=0.138283, mflops=36.1578 (err=5.8e-16) Top mflops for N=729 = 127.954 Normalized results and averages for N=729: fft 0: mflops = 127.954 (norm. = 1), norm. avg. (of 4) = 0.932413 fft 1: mflops = 19.0025 (norm. = 0.14851), norm. avg. (of 4) = 0.107209 fft 2: mflops = 101.514 (norm. = 0.793363), norm. avg. (of 4) = 0.767008 fft 3: mflops = 36.1578 (norm. = 0.282583), norm. avg. (of 3) = 0.234864 Benchmarking for array size = 10x10x10: 0. FFTW: elapsed time t=1.40332 s, 4096 iters, t-(init.)=1.34158 s t(norm)=0.0328659, mflops=152.133 (err=3.8e-16) 1. PDA (f2c): elapsed time t=1.21307 s, 512 iters, t-(init.)=1.20533 s t(norm)=0.236224, mflops=21.1664 (err=4.2e-16) 2. Singleton (f2c): elapsed time t=1.94691 s, 4096 iters, t-(init.)=1.88523 s t(norm)=0.0461841, mflops=108.262 (err=4.4e-16) 3. Temperton (f2c): elapsed time t=1.548 s, 1024 iters, t-(init.)=1.53255 s t(norm)=0.150177, mflops=33.2941 (err=3.6e-16) Top mflops for N=1000 = 152.133 Normalized results and averages for N=1000: fft 0: mflops = 152.133 (norm. = 1), norm. avg. (of 5) = 0.94593 fft 1: mflops = 21.1664 (norm. = 0.13913), norm. avg. (of 5) = 0.113593 fft 2: mflops = 108.262 (norm. = 0.711628), norm. avg. (of 5) = 0.755932 fft 3: mflops = 33.2941 (norm. = 0.218848), norm. avg. (of 4) = 0.23086 Benchmarking for array size = 11x11x11: 0. FFTW: elapsed time t=1.75053 s, 2048 iters, t-(init.)=1.70943 s t(norm)=0.0604251, mflops=82.747 (err=4.0e-16) 1. PDA (f2c): elapsed time t=1.02117 s, 128 iters, t-(init.)=1.0183 s t(norm)=0.575922, mflops=8.68174 (err=4.8e-16) 2. Singleton (f2c): elapsed time t=1.06144 s, 1024 iters, t-(init.)=1.04087 s t(norm)=0.0735859, mflops=67.9478 (err=6.4e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=1331 = 82.747 Normalized results and averages for N=1331: fft 0: mflops = 82.747 (norm. = 1), norm. avg. (of 6) = 0.954942 fft 1: mflops = 8.68174 (norm. = 0.104919), norm. avg. (of 6) = 0.112148 fft 2: mflops = 67.9478 (norm. = 0.821151), norm. avg. (of 6) = 0.766802 fft 3: mflops = -1 (norm. = -0.012085), norm. avg. (of 4) = 0.23086 Benchmarking for array size = 12x12x12: 0. FFTW: elapsed time t=1.96146 s, 4096 iters, t-(init.)=1.85458 s t(norm)=0.0243633, mflops=205.227 (err=3.8e-16) 1. PDA (f2c): elapsed time t=1.01431 s, 256 iters, t-(init.)=1.00753 s t(norm)=0.211772, mflops=23.6103 (err=3.8e-16) 2. Singleton (f2c): elapsed time t=1.8938 s, 2048 iters, t-(init.)=1.84031 s t(norm)=0.0483517, mflops=103.409 (err=4.0e-16) 3. Temperton (f2c): elapsed time t=1.06317 s, 512 iters, t-(init.)=1.04976 s t(norm)=0.110325, mflops=45.3208 (err=3.8e-16) Top mflops for N=1728 = 205.227 Normalized results and averages for N=1728: fft 0: mflops = 205.227 (norm. = 1), norm. avg. (of 7) = 0.961379 fft 1: mflops = 23.6103 (norm. = 0.115045), norm. avg. (of 7) = 0.112562 fft 2: mflops = 103.409 (norm. = 0.503877), norm. avg. (of 7) = 0.729241 fft 3: mflops = 45.3208 (norm. = 0.220833), norm. avg. (of 5) = 0.228854 Benchmarking for array size = 13x13x13: 0. FFTW: elapsed time t=1.78174 s, 1024 iters, t-(init.)=1.71141 s t(norm)=0.0685252, mflops=72.9659 (err=4.1e-16) 1. PDA (f2c): elapsed time t=1.88523 s, 128 iters, t-(init.)=1.87635 s t(norm)=0.601034, mflops=8.31899 (err=7.2e-16) 2. Singleton (f2c): elapsed time t=1.02787 s, 512 iters, t-(init.)=0.992666 s t(norm)=0.0794929, mflops=62.8987 (err=4.3e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=2197 = 72.9659 Normalized results and averages for N=2197: fft 0: mflops = 72.9659 (norm. = 1), norm. avg. (of 8) = 0.966206 fft 1: mflops = 8.31899 (norm. = 0.114012), norm. avg. (of 8) = 0.112743 fft 2: mflops = 62.8987 (norm. = 0.862029), norm. avg. (of 8) = 0.74584 fft 3: mflops = -1 (norm. = -0.013705), norm. avg. (of 5) = 0.228854 Benchmarking for array size = 14x14x14: 0. FFTW: elapsed time t=1.5672 s, 1024 iters, t-(init.)=1.45055 s t(norm)=0.0451965, mflops=110.628 (err=3.9e-16) 1. PDA (f2c): elapsed time t=1.50862 s, 128 iters, t-(init.)=1.49405 s t(norm)=0.372413, mflops=13.4259 (err=3.8e-16) 2. Singleton (f2c): elapsed time t=1.33809 s, 512 iters, t-(init.)=1.27987 s t(norm)=0.0797568, mflops=62.6906 (err=4.6e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=2744 = 110.628 Normalized results and averages for N=2744: fft 0: mflops = 110.628 (norm. = 1), norm. avg. (of 9) = 0.969961 fft 1: mflops = 13.4259 (norm. = 0.121361), norm. avg. (of 9) = 0.1137 fft 2: mflops = 62.6906 (norm. = 0.56668), norm. avg. (of 9) = 0.725933 fft 3: mflops = -1 (norm. = -0.00903931), norm. avg. (of 5) = 0.228854 Benchmarking for array size = 15x15x15: 0. FFTW: elapsed time t=1.73988 s, 1024 iters, t-(init.)=1.59651 s t(norm)=0.0394136, mflops=126.86 (err=4.6e-16) 1. PDA (f2c): elapsed time t=1.07941 s, 128 iters, t-(init.)=1.06151 s t(norm)=0.209646, mflops=23.8497 (err=4.5e-16) 2. Singleton (f2c): elapsed time t=1.35627 s, 512 iters, t-(init.)=1.2846 s t(norm)=0.0634266, mflops=78.8312 (err=4.8e-16) 3. Temperton (f2c): elapsed time t=1.38008 s, 256 iters, t-(init.)=1.34429 s t(norm)=0.132748, mflops=37.6654 (err=4.6e-16) Top mflops for N=3375 = 126.86 Normalized results and averages for N=3375: fft 0: mflops = 126.86 (norm. = 1), norm. avg. (of 10) = 0.972965 fft 1: mflops = 23.8497 (norm. = 0.188001), norm. avg. (of 10) = 0.12113 fft 2: mflops = 78.8312 (norm. = 0.621405), norm. avg. (of 10) = 0.71548 fft 3: mflops = 37.6654 (norm. = 0.296906), norm. avg. (of 6) = 0.240196 Benchmarking for array size = 24x25x28: 0. FFTW: elapsed time t=1.79754 s, 128 iters, t-(init.)=1.70827 s t(norm)=0.0565965, mflops=88.3447 (err=5.0e-16) 1. PDA (f2c): elapsed time t=1.72512 s, 32 iters, t-(init.)=1.70271 s t(norm)=0.225648, mflops=22.1584 (err=4.4e-16) 2. Singleton (f2c): elapsed time t=1.33562 s, 64 iters, t-(init.)=1.2909 s t(norm)=0.0855373, mflops=58.4541 (err=5.6e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=16800 = 88.3447 Normalized results and averages for N=16800: fft 0: mflops = 88.3447 (norm. = 1), norm. avg. (of 11) = 0.975423 fft 1: mflops = 22.1584 (norm. = 0.250817), norm. avg. (of 11) = 0.13292 fft 2: mflops = 58.4541 (norm. = 0.661659), norm. avg. (of 11) = 0.710587 fft 3: mflops = -1 (norm. = -0.0113193), norm. avg. (of 6) = 0.240196 Benchmarking for array size = 48x48x48: 0. FFTW: elapsed time t=1.06174 s, 8 iters, t-(init.)=0.935623 s t(norm)=0.0631169, mflops=79.2181 (err=7.1e-16) 1. PDA (f2c): elapsed time t=1.59409 s, 4 iters, t-(init.)=1.53119 s t(norm)=0.206588, mflops=24.2028 (err=7.1e-16) 2. Singleton (f2c): elapsed time t=1.41689 s, 4 iters, t-(init.)=1.3533 s t(norm)=0.182587, mflops=27.3842 (err=8.2e-16) 3. Temperton (f2c): elapsed time t=1.27948 s, 4 iters, t-(init.)=1.21668 s t(norm)=0.164154, mflops=30.4593 (err=7.6e-16) Top mflops for N=110592 = 79.2181 Normalized results and averages for N=110592: fft 0: mflops = 79.2181 (norm. = 1), norm. avg. (of 12) = 0.977471 fft 1: mflops = 24.2028 (norm. = 0.305521), norm. avg. (of 12) = 0.147304 fft 2: mflops = 27.3842 (norm. = 0.345682), norm. avg. (of 12) = 0.680179 fft 3: mflops = 30.4593 (norm. = 0.384499), norm. avg. (of 7) = 0.260811 Benchmarking for array size = 49x49x49: 0. FFTW: elapsed time t=1.30829 s, 8 iters, t-(init.)=1.17414 s t(norm)=0.0740615, mflops=67.5114 (err=8.7e-16) 1. PDA (f2c): elapsed time t=1.50947 s, 2 iters, t-(init.)=1.47628 s t(norm)=0.372478, mflops=13.4236 (err=8.8e-16) 2. Singleton (f2c): elapsed time t=1.48385 s, 4 iters, t-(init.)=1.41644 s t(norm)=0.178691, mflops=27.9813 (err=1.1e-15) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=117649 = 67.5114 Normalized results and averages for N=117649: fft 0: mflops = 67.5114 (norm. = 1), norm. avg. (of 13) = 0.979204 fft 1: mflops = 13.4236 (norm. = 0.198835), norm. avg. (of 13) = 0.151268 fft 2: mflops = 27.9813 (norm. = 0.414467), norm. avg. (of 13) = 0.659739 fft 3: mflops = -1 (norm. = -0.0148123), norm. avg. (of 7) = 0.260811 Benchmarking for array size = 60x60x60: 0. FFTW: elapsed time t=1.05283 s, 4 iters, t-(init.)=0.929294 s t(norm)=0.0606959, mflops=82.3779 (err=4.9e-16) 1. PDA (f2c): elapsed time t=1.60129 s, 2 iters, t-(init.)=1.53957 s t(norm)=0.201111, mflops=24.8619 (err=5.0e-16) 2. Singleton (f2c): elapsed time t=1.92789 s, 2 iters, t-(init.)=1.86713 s t(norm)=0.243899, mflops=20.5002 (err=6.0e-16) 3. Temperton (f2c): elapsed time t=1.36909 s, 2 iters, t-(init.)=1.30736 s t(norm)=0.170778, mflops=29.2777 (err=4.7e-16) Top mflops for N=216000 = 82.3779 Normalized results and averages for N=216000: fft 0: mflops = 82.3779 (norm. = 1), norm. avg. (of 14) = 0.980689 fft 1: mflops = 24.8619 (norm. = 0.301803), norm. avg. (of 14) = 0.16202 fft 2: mflops = 20.5002 (norm. = 0.248856), norm. avg. (of 14) = 0.63039 fft 3: mflops = 29.2777 (norm. = 0.355407), norm. avg. (of 8) = 0.272635 Benchmarking for array size = 72x60x56: 0. FFTW: elapsed time t=1.21414 s, 4 iters, t-(init.)=1.0757 s t(norm)=0.0621568, mflops=80.4417 (err=5.7e-16) 1. PDA (f2c): elapsed time t=1.06218 s, 1 iters, t-(init.)=1.0274 s t(norm)=0.237464, mflops=21.0558 (err=6.1e-16) 2. Singleton (f2c): elapsed time t=1.12495 s, 1 iters, t-(init.)=1.09002 s t(norm)=0.251939, mflops=19.8461 (err=7.0e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=241920 = 80.4417 Normalized results and averages for N=241920: fft 0: mflops = 80.4417 (norm. = 1), norm. avg. (of 15) = 0.981977 fft 1: mflops = 21.0558 (norm. = 0.261753), norm. avg. (of 15) = 0.168669 fft 2: mflops = 19.8461 (norm. = 0.246714), norm. avg. (of 15) = 0.604812 fft 3: mflops = -1 (norm. = -0.0124314), norm. avg. (of 8) = 0.272635 Benchmarking for array size = 75x75x75: 0. FFTW: elapsed time t=1.09877 s, 2 iters, t-(init.)=0.977608 s t(norm)=0.0620046, mflops=80.6392 (err=9.0e-16) 1. PDA (f2c): elapsed time t=1.67768 s, 1 iters, t-(init.)=1.61724 s t(norm)=0.205146, mflops=24.3729 (err=9.5e-16) 2. Singleton (f2c): elapsed time t=1.64669 s, 1 iters, t-(init.)=1.5859 s t(norm)=0.201171, mflops=24.8545 (err=1.3e-15) 3. Temperton (f2c): elapsed time t=1.36199 s, 1 iters, t-(init.)=1.30145 s t(norm)=0.165088, mflops=30.2868 (err=1.1e-15) Top mflops for N=421875 = 80.6392 Normalized results and averages for N=421875: fft 0: mflops = 80.6392 (norm. = 1), norm. avg. (of 16) = 0.983103 fft 1: mflops = 24.3729 (norm. = 0.302246), norm. avg. (of 16) = 0.177017 fft 2: mflops = 24.8545 (norm. = 0.308219), norm. avg. (of 16) = 0.586275 fft 3: mflops = 30.2868 (norm. = 0.375585), norm. avg. (of 9) = 0.284074 Benchmarking for array size = 80x80x80: 0. FFTW: elapsed time t=1.32916 s, 2 iters, t-(init.)=1.18234 s t(norm)=0.0608796, mflops=82.1293 (err=1.5e-15) 1. PDA (f2c): elapsed time t=1.95665 s, 1 iters, t-(init.)=1.88333 s t(norm)=0.193948, mflops=25.7801 (err=1.5e-15) 2. Singleton (f2c): elapsed time t=1.89603 s, 1 iters, t-(init.)=1.82265 s t(norm)=0.187699, mflops=26.6384 (err=2.3e-15) 3. Temperton (f2c): elapsed time t=1.76004 s, 1 iters, t-(init.)=1.6866 s t(norm)=0.173689, mflops=28.7871 (err=1.5e-15) Top mflops for N=512000 = 82.1293 Normalized results and averages for N=512000: fft 0: mflops = 82.1293 (norm. = 1), norm. avg. (of 17) = 0.984097 fft 1: mflops = 25.7801 (norm. = 0.313896), norm. avg. (of 17) = 0.185069 fft 2: mflops = 26.6384 (norm. = 0.324346), norm. avg. (of 17) = 0.570867 fft 3: mflops = 28.7871 (norm. = 0.350509), norm. avg. (of 10) = 0.290718 Benchmarking for array size = 84x84x84: 0. FFTW: elapsed time t=1.51525 s, 2 iters, t-(init.)=1.34564 s t(norm)=0.0591944, mflops=84.4675 (err=7.6e-16) 1. PDA (f2c): elapsed time t=3.07528 s, 1 iters, t-(init.)=2.99053 s t(norm)=0.263106, mflops=19.0038 (err=6.9e-16) 2. Singleton (f2c): elapsed time t=3.08728 s, 1 iters, t-(init.)=3.0026 s t(norm)=0.264168, mflops=18.9274 (err=8.6e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=592704 = 84.4675 Normalized results and averages for N=592704: fft 0: mflops = 84.4675 (norm. = 1), norm. avg. (of 18) = 0.984981 fft 1: mflops = 19.0038 (norm. = 0.224983), norm. avg. (of 18) = 0.187287 fft 2: mflops = 18.9274 (norm. = 0.224079), norm. avg. (of 18) = 0.551601 fft 3: mflops = -1 (norm. = -0.0118389), norm. avg. (of 10) = 0.290718 Benchmarking for array size = 96x96x96: 0. FFTW: elapsed time t=1.38902 s, 1 iters, t-(init.)=1.26254 s t(norm)=0.0722368, mflops=69.2168 (err=8.1e-16) 1. PDA (f2c): elapsed time t=4.12696 s, 1 iters, t-(init.)=4.00084 s t(norm)=0.228909, mflops=21.8427 (err=7.7e-16) 2. Singleton (f2c): elapsed time t=4.56895 s, 1 iters, t-(init.)=4.4422 s t(norm)=0.254162, mflops=19.6725 (err=8.2e-16) 3. Temperton (f2c): elapsed time t=3.7068 s, 1 iters, t-(init.)=3.58013 s t(norm)=0.204838, mflops=24.4095 (err=8.9e-16) Top mflops for N=884736 = 69.2168 Normalized results and averages for N=884736: fft 0: mflops = 69.2168 (norm. = 1), norm. avg. (of 19) = 0.985771 fft 1: mflops = 21.8427 (norm. = 0.31557), norm. avg. (of 19) = 0.194038 fft 2: mflops = 19.6725 (norm. = 0.284216), norm. avg. (of 19) = 0.537528 fft 3: mflops = 24.4095 (norm. = 0.352653), norm. avg. (of 11) = 0.296348 Benchmarking for array size = 105x105x105: 0. FFTW: elapsed time t=1.57036 s, 1 iters, t-(init.)=1.40454 s t(norm)=0.0602347, mflops=83.0086 (err=7.9e-16) 1. PDA (f2c): elapsed time t=6.3491 s, 1 iters, t-(init.)=6.18334 s t(norm)=0.265177, mflops=18.8553 (err=8.1e-16) 2. Singleton (f2c): elapsed time t=5.05882 s, 1 iters, t-(init.)=4.89348 s t(norm)=0.209861, mflops=23.8253 (err=9.7e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=1157625 = 83.0086 Normalized results and averages for N=1157625: fft 0: mflops = 83.0086 (norm. = 1), norm. avg. (of 20) = 0.986483 fft 1: mflops = 18.8553 (norm. = 0.227149), norm. avg. (of 20) = 0.195694 fft 2: mflops = 23.8253 (norm. = 0.287022), norm. avg. (of 20) = 0.525003 fft 3: mflops = -1 (norm. = -0.0120469), norm. avg. (of 11) = 0.296348 ------------------------------------------------------ @@@@ bench.1d.p2.dat N, Arndt DIF, Arndt DIT, Arndt Split-Radix, Arndt 4-step, Beauregard, Bergland, CWP (min N), CWP (best N), Edelblute, FFTPACK (f2c), FFTW, FFTW_ESTIMATE, Frigo-old, Green, GSL, GSL DIT, GSL DIF, Krukar, Mayer (Buneman), Mayer (simple), Mayer (lookup), NAPACK (f2c), Nielsen, NR (C), Ooura (C), QFT, Ransom, Singleton (f2c), Temperton (f2c), Valkenburg 2, 28.5862, 26.3211, 17.5715, 1.29453, 4.22336, 6.27342, 4.92384, 4.63188, , 7.44625, 30.2156, 30.5592, 46.6506, , 12.1544, 7.4657, 7.06768, 27.9894, , , , 3.03506, 2.19631, 7.98445, 23.9516, , , 5.8306, 3.22521, 7.74321 4, 66.4683, 62.9489, 26.9228, 5.48645, 9.455, 22.2035, 18.5601, 8.6958, 25.1136, 19.0252, 93.2842, 94.1145, 136.362, , 31.4681, 14.5933, 14.1035, 73.3308, 34.0143, 36.3355, 32.2259, 6.79772, 8.12387, 14.935, 53.0756, , 4.77127, 20.0676, 10.181, 8.16247 8, 100.789, 97.7494, 33.162, 7.58482, 12.9724, 34.5267, 43.3435, 26.0217, 26.4559, 27.747, 147.686, 148.379, 195.783, 73.1947, 45.8866, 25.2005, 24.3722, 94.9407, 55.0564, 57.4894, 53.0467, 10.6476, 18.586, 25.259, 89.4922, , 5.7975, 22.5124, 14.6087, 8.59502 16, 58.8298, 58.3652, 39.5539, 14.1667, 14.4737, 53.5865, 76.0729, 48.6963, 29.2205, 38.6045, 193.812, 194.217, 215.357, 102.499, 66.8721, 36.828, 36.1727, 107.281, 53.123, 63.7331, 62.5997, 15.2046, 18.9242, 37.3437, 118.298, 69.5045, 17.8152, 58.5696, 21.0061, 8.92262 32, 69.6508, 68.8314, 45.4134, 17.2335, 15.0504, 77.4072, 76.1762, 89.1857, 32.5512, 33.5498, 212.07, 212.262, 217.236, 139.545, 62.4503, 47.9818, 48.0595, 108.493, 59.9298, 75.1523, 75.99, 17.8974, 27.354, 49.6591, 127.141, 61.6402, 18.5857, 75.3301, 20.2178, 9.19647 64, 70.0931, 69.0416, 50.9597, 24.7007, 15.184, 90.2107, 81.3766, 101.102, 36.2078, 38.6684, 229.441, 181.269, 151.388, 182.855, 74.4128, 56.2988, 57.479, 108.609, 61.4833, 79.9767, 81.877, 20.9029, 34.9027, 59.6272, 143.058, 57.7795, 34.9388, 103.442, 25.8875, 9.39328 128, 77.2289, 76.1131, 56.2036, 25.0495, 15.1243, 95.7867, 93.985, 134.996, 39.9361, 40.0799, 198.809, 196.978, 168.936, 174.429, 77.2461, 62.0861, 64.3814, 78.858, 66.0958, 87.0846, 89.7782, 21.7374, 33.0848, 67.3477, 141.543, 55.6055, 33.4728, 98.7099, 25.0502, 9.48511 256, 80.9588, 79.5256, 60.8919, 28.0732, 15.0846, 110.501, 109.342, 138.047, 43.5161, 42.9764, 210.854, 205.407, 177.61, 190.322, 85.2977, 65.9676, 69.2149, 78.5577, 68.6872, 90.1702, 93.1681, 23.4428, 37.1519, 72.6623, 151.747, 54.149, 48.0707, 127.601, 27.3067, 9.59164 512, 85.3049, 83.8527, 64.0751, 29.9316, 15.0278, 119.01, 111.348, 138.388, 46.5124, 37.1315, 216.444, 201.079, 178.546, 205.28, 76.5837, 67.9879, 72.4205, 83.0876, 72.9989, 95.3748, 98.5942, 23.4863, 40.7527, 76.407, 148.337, 52.1423, 45.2381, 129.345, 24.8033, 9.67502 1024, 89.1178, 87.295, 67.9782, 34.0227, 14.9289, 117.575, 113.979, 113.988, 49.8589, 36.7353, 156.671, 152.148, 130.214, 192.037, 72.3858, 69.484, 74.9168, 59.595, 75.6202, 97.5233, 100.618, 23.9296, 37.5194, 78.8863, 156.413, 46.7601, 58.1845, 139.829, 27.9877, 9.49882 2048, 90.0212, 87.2071, 67.5471, 33.03, 14.7517, 121.853, 95.7916, 108.378, 50.6956, 34.7521, 139.643, 136.301, 101.651, 164.155, 58.4371, 68.3464, 73.733, 55.9116, 78.2742, 99.8613, 97.2346, 18.6962, 35.7837, 77.9729, 131.499, 43.1652, 50.9234, 124.087, 25.918, 8.94274 4096, 46.2636, 46.5056, 36.1368, 30.8303, 13.6339, 86.7673, 83.7384, 95.3086, 31.0462, 36.4204, 145.131, 126.395, 104.33, 115.836, 63.1756, 44.0067, 43.4867, 52.3454, 75.8416, 95.1722, 86.3904, 19.3444, 30.8403, 47.3837, 100.534, 39.9075, 55.1059, 76.9726, 25.8423, 8.67075 8192, 48.0038, 48.383, 35.3077, 28.5817, 13.5837, 80.6878, 86.5611, 91.9022, 30.7455, 32.3604, 127.508, 122.42, 95.2416, 105.782, 55.0173, 43.6654, 43.3796, , 47.8898, 54.0042, 52.2059, 18.9415, 28.6245, 46.9943, 95.5998, 33.9447, 49.3491, 72.7143, 23.7243, 8.46056 16384, 45.7249, 46.0014, 35.5172, 34.1521, 13.5577, 85.109, 87.028, 87.0032, 31.1969, 30.0344, 92.1477, 91.9081, 64.2536, 101.24, 47.9896, 43.7756, 43.5295, , 46.5799, 51.9054, 49.9241, 18.879, 29.7349, 47.0502, 99.9509, 25.191, 60.4006, 76.2592, 25.5511, 8.13105 32768, 46.1331, 46.1392, 34.1736, 30.3158, 13.1797, 85.303, 82.7726, 82.6906, 30.3638, 21.0633, 75.6086, 70.1322, 44.9932, 91.4179, 28.635, 42.2937, 41.9951, , 46.5488, 51.4719, 46.3537, 10.0506, 25.7247, 45.454, 84.8736, 20.9449, 51.8003, 65.6677, 22.1804, 7.09208 65536, 16.8862, 16.9221, 13.2129, 25.1799, 10.6655, 36.3954, 57.0505, 57.0274, 12.6448, 20.004, 66.0367, 54.1654, 36.3899, 42.5065, 26.3295, 16.5445, 16.4907, , 41.9353, 46.0471, 37.5654, 10.4604, 14.4764, 16.9171, 42.0353, 18.6563, 37.1928, 29.1749, 17.0871, 6.08752 131072, 17.2056, 17.124, 12.7049, 19.7234, 10.6037, 37.1454, 54.9524, 54.9327, 12.1963, 17.5352, 60.6251, 51.5181, 33.8983, 39.4111, 23.4549, 16.1665, 16.1932, , 17.7376, 18.3356, 17.5811, 10.1975, 14.4809, 16.4858, 40.3315, 15.1258, 31.5302, 27.4707, 15.8039, 5.87292 Norm. Avg., 0.404961, 0.396754, 0.273616, 0.173381, 0.0957894, 0.502972, 0.529158, 0.559483, 0.215077, 0.208649, 0.903887, 0.850863, 0.775115, 0.795937, 0.351027, 0.282845, 0.287712, 0.438193, 0.373894, 0.445489, 0.427098, 0.110929, 0.175408, 0.304637, 0.677077, 0.263808, 0.288561, 0.476891, 0.15142, 0.065255 ------------------------------------------------------ @@@@ bench.1d.np2.dat N, CWP (min N), CWP (best N), FFTPACK (f2c), FFTW, FFTW_ESTIMATE, Frigo-old, GSL, NAPACK (f2c), Nielsen, Singleton (f2c), Temperton (f2c), Valkenburg 6, 26.3621, 16.8238, 20.9305, 106.818, 107.403, 20.8051, 31.6794, 9.2743, 7.18557, 16.893, 10.1579, 8.57692 9, 43.3376, 31.0041, 25.2481, 105.338, 105.627, 17.9146, 31.2348, 11.7322, 11.2089, 30.1285, 14.9185, 8.68284 12, 57.3039, 46.6645, 31.7597, 165.788, 166.223, 31.3845, 48.203, 12.6205, 14.7552, 32.0687, 19.4421, 8.89667 15, 63.4421, 63.5165, 31.7913, 128.526, 128.773, 20.9626, 32.2157, 8.70951, 17.1439, 35.8379, 19.8691, 7.86138 18, 64.4511, 57.1006, 24.9832, 104.808, 99.9848, 20.7226, 52.4599, 14.5014, 13.5364, 43.6264, 17.5751, 8.98888 24, 88.6147, 83.98, 29.2842, 140.932, 141.031, 40.1085, 69.8785, 16.4453, 22.5711, 42.6549, 22.3604, 9.16231 36, 100.391, 100.407, 30.9777, 143.832, 143.948, 25.9783, 75.4493, 17.7714, 20.7804, 65.1761, 25.6462, 9.22452 80, 126.499, 133.153, 37.6756, 162.199, 162.235, 49.2507, 52.6069, 12.5443, 36.5929, 95.2597, 29.1777, 8.7849 108, 103.859, 132.303, 34.6989, 149.935, 149.972, 23.8581, 73.5014, 19.7377, 24.1599, 70.6789, 27.3037, 9.35229 210, 138.472, 138.503, 25.7518, 124.648, 121.944, 23.9394, 51.2324, 10.2294, 30.1654, 58.3331, , 7.38719 504, 144.257, 144.241, 25.7988, 151.092, 135.589, 28.4945, 71.2154, 13.3049, 29.5455, 69.5751, , 8.20954 1000, 100.447, 144.234, 31.9242, 118.385, 118.493, 29.3943, 40.384, 11.5689, 42.3616, 92.1167, 27.4404, 7.84538 1960, 127.959, 127.939, 20.1246, 105.454, 99.6319, 26.7667, 41.5372, 9.57935, 30.6834, 70.2286, , 6.80745 4725, 87.9334, 112.119, 23.9625, 82.9898, 100.165, 18.6623, 42.1501, 10.3933, 25.7527, 55.9199, , 7.21201 10368, 92.4196, 100.646, 29.5449, 97.9864, 100.144, 26.8526, 59.8257, 17.9654, 25.4658, 60.2281, 25.41, 8.08811 27000, 100.307, 100.213, 21.7116, 66.4032, 67.2174, 17.2105, 30.5852, 9.32195, 25.8273, 56.1894, 24.5607, 6.61189 75600, 58.854, 58.8585, 15.4211, 67.1017, 62.7368, 15.3975, 26.2336, 8.24202, 17.6819, 25.2262, , 5.84581 165375, 48.4858, 48.4804, 11.1137, 57.2827, 55.4275, 11.0736, 26.4729, 7.47827, 16.2273, 24.4806, , 5.38397 Norm. Avg., 0.721284, 0.746774, 0.215529, 0.939219, 0.932947, 0.202343, 0.391087, 0.103491, 0.191609, 0.426304, 0.171746, 0.0674961 ------------------------------------------------------ @@@@ bench.3d.p2.dat Array Dimensions, FFTW, HARM (f2c), NR (C), PDA (f2c), Singleton (f2c), Temperton (f2c) 4x4x4, 172.684, , 62.9421, 12.0962, 117.149, 33.5597 8x8x8, 207.64, 38.8417, 85.9105, 19.9565, 99.704, 35.6188 16x16x16, 151.235, 40.9289, 46.7358, 25.916, 72.4134, 39.9174 32x32x32, 153.361, 38.7303, 45.235, 24.4628, 63.7505, 33.2926 64x64x64, 71.9118, 27.5227, 14.8933, 20.8519, 25.4449, 24.9945 256x64x32, 68.616, 26.4978, 14.7597, 21.6532, 23.9209, 24.3311 16x1024x64, 57.9643, 26.533, 14.5793, 18.6898, 23.965, Norm. Avg., 1, 0.322815, 0.293708, 0.203572, 0.452711, 0.25818 ------------------------------------------------------ @@@@ bench.3d.np2.dat Array Dimensions, FFTW, PDA (f2c), Singleton (f2c), Temperton (f2c) 5x5x5, 104.482, 14.1026, 143.195, 31.8162 6x6x6, 152.467, 15.1537, 89.2244, 30.4658 7x7x7, 106.745, 8.80123, 73.5968, 9x9x9, 127.954, 19.0025, 101.514, 36.1578 10x10x10, 152.133, 21.1664, 108.262, 33.2941 11x11x11, 82.747, 8.68174, 67.9478, 12x12x12, 205.227, 23.6103, 103.409, 45.3208 13x13x13, 72.9659, 8.31899, 62.8987, 14x14x14, 110.628, 13.4259, 62.6906, 15x15x15, 126.86, 23.8497, 78.8312, 37.6654 24x25x28, 88.3447, 22.1584, 58.4541, 48x48x48, 79.2181, 24.2028, 27.3842, 30.4593 49x49x49, 67.5114, 13.4236, 27.9813, 60x60x60, 82.3779, 24.8619, 20.5002, 29.2777 72x60x56, 80.4417, 21.0558, 19.8461, 75x75x75, 80.6392, 24.3729, 24.8545, 30.2868 80x80x80, 82.1293, 25.7801, 26.6384, 28.7871 84x84x84, 84.4675, 19.0038, 18.9274, 96x96x96, 69.2168, 21.8427, 19.6725, 24.4095 105x105x105, 83.0086, 18.8553, 23.8253, Norm. Avg., 0.986483, 0.195694, 0.525003, 0.296348 @@@@ end