To: benchfft@theory.lcs.mit.edu Subject: SUBMIT ------------------- @@SUBMIT@@ @ submitter = John Spicer @ submitter email = spicerj@islandnet.com @ submitter organization = Dragon Electronics @ computer manufacturer = Apple @ computer model = PowerMac 6500 @ CPU manufacturer = Motorola @ CPU model = PowerPC 603ev @ CPU speed = 250 MHz @ RAM = 32 MB @ L2 cache size = 1 MB @ operating system = MacOS 8 @ C compiler = Metrowerks Codewarrior Pro 2 @ C compiler flags = all @ Fortran compiler = NONE @ Fortran compiler flags = NONE @ remarks = @ 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=1.13214 s, 2097152 iters, t-(init.)=0.943327 s t(norm)=0.224907, mflops=22.2314 (err=1.7e-17) 1. Arndt DIT: elapsed time t=1.19228 s, 2097152 iters, t-(init.)=1.00287 s t(norm)=0.239104, mflops=20.9114 (err=1.7e-17) 2. Arndt Split-Radix: elapsed time t=1.58936 s, 2097152 iters, t-(init.)=1.39931 s t(norm)=0.333623, mflops=14.987 (err=1.7e-17) 3. Arndt 4-step: elapsed time t=1.72628 s, 131072 iters, t-(init.)=1.71448 s t(norm)=6.54021, mflops=0.764501 (err=1.7e-17) 4. Beauregard: elapsed time t=1.6967 s, 524288 iters, t-(init.)=1.64836 s t(norm)=1.572, mflops=3.18066 (err=1.7e-17) 5. Bergland: elapsed time t=1.21427 s, 524288 iters, t-(init.)=1.16489 s t(norm)=1.11093, mflops=4.50075 (err=1.7e-17) 6. CWP (min N): elapsed time t=1.30944 s, 524288 iters, t-(init.)=1.26227 s t(norm)=1.2038, mflops=4.15353 7. CWP (best N) (N=3): elapsed time t=1.41273 s, 524288 iters, t-(init.)=1.3547 s t(norm)=1.29194, mflops=3.87015 8. Skipping fft (Edelblute can't handle N <= 2). 9. FFTPACK (f2c): elapsed time t=1.79146 s, 1048576 iters, t-(init.)=1.69716 s t(norm)=0.809269, mflops=6.17842 (err=1.7e-17) FFTW_MEASURE plan: (cost = 5.150375e-07) FFTW_NOTW 2 10. FFTW: elapsed time t=1.27376 s, 1048576 iters, t-(init.)=1.17955 s t(norm)=0.562453, mflops=8.88963 (err=1.7e-17) FFTW_ESTIMATE plan: (cost = 1.820000e+02) FFTW_NOTW 2 11. FFTW_ESTIMATE: elapsed time t=1.27282 s, 1048576 iters, t-(init.)=1.17831 s t(norm)=0.561861, mflops=8.899 (err=1.7e-17) 12. Frigo-old: elapsed time t=1.66254 s, 4194304 iters, t-(init.)=1.28282 s t(norm)=0.152924, mflops=32.6961 (err=1.7e-17) 13. Skipping fft (Green can't handle this size.). 14. GSL: elapsed time t=1.27795 s, 1048576 iters, t-(init.)=1.18331 s t(norm)=0.564244, mflops=8.86142 (err=1.7e-17) 15. GSL DIT: elapsed time t=1.2469 s, 524288 iters, t-(init.)=1.19974 s t(norm)=1.14416, mflops=4.37 (err=1.7e-17) 16. GSL DIF: elapsed time t=1.2859 s, 524288 iters, t-(init.)=1.23868 s t(norm)=1.18129, mflops=4.23265 (err=1.7e-17) 17. Krukar: elapsed time t=1.20155 s, 2097152 iters, t-(init.)=1.01316 s t(norm)=0.241557, mflops=20.699 (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=1.21005 s, 262144 iters, t-(init.)=1.18657 s t(norm)=2.26321, mflops=2.20925 (err=1.7e-17) 22. Nielsen: elapsed time t=1.61203 s, 262144 iters, t-(init.)=1.58857 s t(norm)=3.02995, mflops=1.65019 (err=1.7e-17) 23. NR (C): elapsed time t=1.90773 s, 1048576 iters, t-(init.)=1.8132 s t(norm)=0.8646, mflops=5.78302 (err=1.7e-17) 24. Ooura (C): elapsed time t=1.38049 s, 2097152 iters, t-(init.)=1.19203 s t(norm)=0.284202, mflops=17.5931 (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=1.224 s, 524288 iters, t-(init.)=1.17685 s t(norm)=1.12233, mflops=4.45501 (err=1.7e-17) 28. Temperton (f2c): elapsed time t=2.00047 s, 524288 iters, t-(init.)=1.9532 s t(norm)=1.86272, mflops=2.68425 (err=1.7e-17) 29. Valkenburg: elapsed time t=1.7993 s, 1048576 iters, t-(init.)=1.70454 s t(norm)=0.812786, mflops=6.15168 (err=1.7e-17) Top mflops for N=2 = 32.6961 Normalized results and averages for N=2: fft 0: mflops = 22.2314 (norm. = 0.679942), norm. avg. (of 1) = 0.679942 fft 1: mflops = 20.9114 (norm. = 0.639571), norm. avg. (of 1) = 0.639571 fft 2: mflops = 14.987 (norm. = 0.458373), norm. avg. (of 1) = 0.458373 fft 3: mflops = 0.764501 (norm. = 0.0233821), norm. avg. (of 1) = 0.0233821 fft 4: mflops = 3.18066 (norm. = 0.0972796), norm. avg. (of 1) = 0.0972796 fft 5: mflops = 4.50075 (norm. = 0.137654), norm. avg. (of 1) = 0.137654 fft 6: mflops = 4.15353 (norm. = 0.127035), norm. avg. (of 1) = 0.127035 fft 7: mflops = 3.87015 (norm. = 0.118367), norm. avg. (of 1) = 0.118367 fft 8: mflops = -1 (norm. = -0.0305847), norm. avg. (of 0) = -1 fft 9: mflops = 6.17842 (norm. = 0.188965), norm. avg. (of 1) = 0.188965 fft 10: mflops = 8.88963 (norm. = 0.271887), norm. avg. (of 1) = 0.271887 fft 11: mflops = 8.899 (norm. = 0.272173), norm. avg. (of 1) = 0.272173 fft 12: mflops = 32.6961 (norm. = 1), norm. avg. (of 1) = 1 fft 13: mflops = -1 (norm. = -0.0305847), norm. avg. (of 0) = -1 fft 14: mflops = 8.86142 (norm. = 0.271024), norm. avg. (of 1) = 0.271024 fft 15: mflops = 4.37 (norm. = 0.133655), norm. avg. (of 1) = 0.133655 fft 16: mflops = 4.23265 (norm. = 0.129454), norm. avg. (of 1) = 0.129454 fft 17: mflops = 20.699 (norm. = 0.633074), norm. avg. (of 1) = 0.633074 fft 18: mflops = -1 (norm. = -0.0305847), norm. avg. (of 0) = -1 fft 19: mflops = -1 (norm. = -0.0305847), norm. avg. (of 0) = -1 fft 20: mflops = -1 (norm. = -0.0305847), norm. avg. (of 0) = -1 fft 21: mflops = 2.20925 (norm. = 0.0675694), norm. avg. (of 1) = 0.0675694 fft 22: mflops = 1.65019 (norm. = 0.0504706), norm. avg. (of 1) = 0.0504706 fft 23: mflops = 5.78302 (norm. = 0.176872), norm. avg. (of 1) = 0.176872 fft 24: mflops = 17.5931 (norm. = 0.538081), norm. avg. (of 1) = 0.538081 fft 25: mflops = -1 (norm. = -0.0305847), norm. avg. (of 0) = -1 fft 26: mflops = -1 (norm. = -0.0305847), norm. avg. (of 0) = -1 fft 27: mflops = 4.45501 (norm. = 0.136255), norm. avg. (of 1) = 0.136255 fft 28: mflops = 2.68425 (norm. = 0.0820969), norm. avg. (of 1) = 0.0820969 fft 29: mflops = 6.15168 (norm. = 0.188147), norm. avg. (of 1) = 0.188147 Benchmarking for array size = 4 (power of 2): 0. Arndt DIF: elapsed time t=2.00048 s, 2097152 iters, t-(init.)=1.72628 s t(norm)=0.102894, mflops=48.5935 (err=1.3e-16) 1. Arndt DIT: elapsed time t=1.03955 s, 1048576 iters, t-(init.)=0.902438 s t(norm)=0.107579, mflops=46.4775 (err=1.3e-16) 2. Arndt Split-Radix: elapsed time t=1.01954 s, 524288 iters, t-(init.)=0.951002 s t(norm)=0.226737, mflops=22.052 (err=1.3e-16) 3. Arndt 4-step: elapsed time t=1.41288 s, 131072 iters, t-(init.)=1.39562 s t(norm)=1.33096, mflops=3.75668 (err=1.3e-16) 4. Beauregard: elapsed time t=1.52646 s, 262144 iters, t-(init.)=1.49218 s t(norm)=0.711528, mflops=7.02713 (err=5.3e-17) 5. Bergland: elapsed time t=1.36869 s, 524288 iters, t-(init.)=1.29805 s t(norm)=0.30948, mflops=16.1561 (err=5.3e-17) 6. CWP (min N): elapsed time t=1.43546 s, 524288 iters, t-(init.)=1.36689 s t(norm)=0.325892, mflops=15.3425 7. CWP (best N) (N=15): elapsed time t=1.52455 s, 262144 iters, t-(init.)=1.43138 s t(norm)=0.682534, mflops=7.32565 8. Edelblute: elapsed time t=1.13209 s, 524288 iters, t-(init.)=1.06123 s t(norm)=0.253018, mflops=19.7614 (err=1.3e-16) 9. FFTPACK (f2c): elapsed time t=1.36426 s, 524288 iters, t-(init.)=1.29571 s t(norm)=0.308921, mflops=16.1854 (err=5.3e-17) FFTW_MEASURE plan: (cost = 6.621246e-07) FFTW_NOTW 4 10. FFTW: elapsed time t=1.43198 s, 1048576 iters, t-(init.)=1.29491 s t(norm)=0.154365, mflops=32.3907 (err=5.3e-17) FFTW_ESTIMATE plan: (cost = 3.176000e+02) FFTW_NOTW 4 11. FFTW_ESTIMATE: elapsed time t=1.43223 s, 1048576 iters, t-(init.)=1.29513 s t(norm)=0.154391, mflops=32.3852 (err=5.3e-17) 12. Frigo-old: elapsed time t=1.10699 s, 2097152 iters, t-(init.)=0.832571 s t(norm)=0.0496251, mflops=100.755 (err=5.3e-17) 13. Skipping fft (Green can't handle this size.). 14. GSL: elapsed time t=1.93419 s, 1048576 iters, t-(init.)=1.79693 s t(norm)=0.214211, mflops=23.3415 (err=5.3e-17) 15. GSL DIT: elapsed time t=1.28889 s, 262144 iters, t-(init.)=1.2546 s t(norm)=0.598238, mflops=8.35787 (err=6.4e-17) 16. GSL DIF: elapsed time t=1.26568 s, 262144 iters, t-(init.)=1.23128 s t(norm)=0.587121, mflops=8.51614 (err=6.4e-17) 17. Krukar: elapsed time t=1.74289 s, 2097152 iters, t-(init.)=1.46899 s t(norm)=0.0875586, mflops=57.1046 (err=5.3e-17) 18. Mayer (Buneman): elapsed time t=1.87563 s, 1048576 iters, t-(init.)=1.7343 s t(norm)=0.206744, mflops=24.1844 (err=1.3e-16) 19. Mayer (simple): elapsed time t=1.7586 s, 1048576 iters, t-(init.)=1.6208 s t(norm)=0.193214, mflops=25.878 20. Mayer (lookup): elapsed time t=1.94929 s, 1048576 iters, t-(init.)=1.81225 s t(norm)=0.216038, mflops=23.1441 (err=1.3e-16) 21. NAPACK (f2c): elapsed time t=1.06354 s, 131072 iters, t-(init.)=1.04626 s t(norm)=0.997788, mflops=5.01108 (err=5.3e-17) 22. Nielsen: elapsed time t=1.73145 s, 262144 iters, t-(init.)=1.69593 s t(norm)=0.808681, mflops=6.18291 (err=1.3e-16) 23. NR (C): elapsed time t=1.96891 s, 524288 iters, t-(init.)=1.89972 s t(norm)=0.452928, mflops=11.0393 (err=6.4e-17) 24. Ooura (C): elapsed time t=1.20934 s, 1048576 iters, t-(init.)=1.07198 s t(norm)=0.12779, mflops=39.1268 (err=5.3e-17) 25. Skipping fft (QFT requires N >= 16). 26. Ransom: elapsed time t=1.935 s, 131072 iters, t-(init.)=1.91728 s t(norm)=1.82846, mflops=2.73454 (err=2.4e-16) 27. Singleton (f2c): elapsed time t=1.44059 s, 524288 iters, t-(init.)=1.3719 s t(norm)=0.327088, mflops=15.2864 (err=5.3e-17) 28. Temperton (f2c): elapsed time t=1.22747 s, 262144 iters, t-(init.)=1.19302 s t(norm)=0.568876, mflops=8.78926 (err=5.3e-17) 29. Valkenburg: elapsed time t=1.60263 s, 262144 iters, t-(init.)=1.56834 s t(norm)=0.747841, mflops=6.68591 (err=5.3e-17) Top mflops for N=4 = 100.755 Normalized results and averages for N=4: fft 0: mflops = 48.5935 (norm. = 0.482291), norm. avg. (of 2) = 0.581117 fft 1: mflops = 46.4775 (norm. = 0.46129), norm. avg. (of 2) = 0.55043 fft 2: mflops = 22.052 (norm. = 0.218867), norm. avg. (of 2) = 0.33862 fft 3: mflops = 3.75668 (norm. = 0.0372851), norm. avg. (of 2) = 0.0303336 fft 4: mflops = 7.02713 (norm. = 0.0697444), norm. avg. (of 2) = 0.083512 fft 5: mflops = 16.1561 (norm. = 0.16035), norm. avg. (of 2) = 0.149002 fft 6: mflops = 15.3425 (norm. = 0.152274), norm. avg. (of 2) = 0.139654 fft 7: mflops = 7.32565 (norm. = 0.0727072), norm. avg. (of 2) = 0.0955373 fft 8: mflops = 19.7614 (norm. = 0.196133), norm. avg. (of 1) = 0.196133 fft 9: mflops = 16.1854 (norm. = 0.16064), norm. avg. (of 2) = 0.174803 fft 10: mflops = 32.3907 (norm. = 0.321478), norm. avg. (of 2) = 0.296682 fft 11: mflops = 32.3852 (norm. = 0.321424), norm. avg. (of 2) = 0.296799 fft 12: mflops = 100.755 (norm. = 1), norm. avg. (of 2) = 1 fft 13: mflops = -1 (norm. = -0.00992502), norm. avg. (of 0) = -1 fft 14: mflops = 23.3415 (norm. = 0.231665), norm. avg. (of 2) = 0.251344 fft 15: mflops = 8.35787 (norm. = 0.082952), norm. avg. (of 2) = 0.108304 fft 16: mflops = 8.51614 (norm. = 0.0845228), norm. avg. (of 2) = 0.106989 fft 17: mflops = 57.1046 (norm. = 0.566765), norm. avg. (of 2) = 0.599919 fft 18: mflops = 24.1844 (norm. = 0.240031), norm. avg. (of 1) = 0.240031 fft 19: mflops = 25.878 (norm. = 0.25684), norm. avg. (of 1) = 0.25684 fft 20: mflops = 23.1441 (norm. = 0.229706), norm. avg. (of 1) = 0.229706 fft 21: mflops = 5.01108 (norm. = 0.0497351), norm. avg. (of 2) = 0.0586522 fft 22: mflops = 6.18291 (norm. = 0.0613655), norm. avg. (of 2) = 0.055918 fft 23: mflops = 11.0393 (norm. = 0.109565), norm. avg. (of 2) = 0.143219 fft 24: mflops = 39.1268 (norm. = 0.388334), norm. avg. (of 2) = 0.463207 fft 25: mflops = -1 (norm. = -0.00992502), norm. avg. (of 0) = -1 fft 26: mflops = 2.73454 (norm. = 0.0271404), norm. avg. (of 1) = 0.0271404 fft 27: mflops = 15.2864 (norm. = 0.151718), norm. avg. (of 2) = 0.143987 fft 28: mflops = 8.78926 (norm. = 0.0872336), norm. avg. (of 2) = 0.0846652 fft 29: mflops = 6.68591 (norm. = 0.0663578), norm. avg. (of 2) = 0.127253 Benchmarking for array size = 8 (power of 2): 0. Arndt DIF: elapsed time t=1.90319 s, 1048576 iters, t-(init.)=1.68037 s t(norm)=0.0667718, mflops=74.8819 (err=1.1e-16) 1. Arndt DIT: elapsed time t=1.95133 s, 1048576 iters, t-(init.)=1.72843 s t(norm)=0.0686816, mflops=72.7997 (err=1.1e-16) 2. Arndt Split-Radix: elapsed time t=1.2387 s, 262144 iters, t-(init.)=1.18282 s t(norm)=0.188004, mflops=26.5952 (err=7.7e-17) 3. Arndt 4-step: elapsed time t=1.57321 s, 65536 iters, t-(init.)=1.55917 s t(norm)=0.991292, mflops=5.04392 (err=9.0e-17) 4. Beauregard: elapsed time t=1.6995 s, 131072 iters, t-(init.)=1.67152 s t(norm)=0.531361, mflops=9.40979 (err=1.5e-16) 5. Bergland: elapsed time t=1.25183 s, 262144 iters, t-(init.)=1.19514 s t(norm)=0.189962, mflops=26.321 (err=1.6e-16) 6. CWP (min N): elapsed time t=1.90207 s, 524288 iters, t-(init.)=1.79045 s t(norm)=0.142292, mflops=35.139 7. CWP (best N) (N=15): elapsed time t=1.52494 s, 262144 iters, t-(init.)=1.4319 s t(norm)=0.227594, mflops=21.9689 8. Edelblute: elapsed time t=1.59696 s, 262144 iters, t-(init.)=1.54013 s t(norm)=0.244798, mflops=20.425 (err=8.3e-17) 9. FFTPACK (f2c): elapsed time t=1.39036 s, 262144 iters, t-(init.)=1.33464 s t(norm)=0.212135, mflops=23.5699 (err=1.5e-16) FFTW_MEASURE plan: (cost = 1.211151e-06) FFTW_NOTW 8 10. FFTW: elapsed time t=1.22489 s, 524288 iters, t-(init.)=1.1124 s t(norm)=0.0884058, mflops=56.5573 (err=1.4e-16) FFTW_ESTIMATE plan: (cost = 4.688000e+02) FFTW_NOTW 8 11. FFTW_ESTIMATE: elapsed time t=1.22473 s, 524288 iters, t-(init.)=1.11248 s t(norm)=0.0884116, mflops=56.5536 (err=1.4e-16) 12. Frigo-old: elapsed time t=1.05107 s, 1048576 iters, t-(init.)=0.828351 s t(norm)=0.0329157, mflops=151.903 (err=1.4e-16) 13. Green: elapsed time t=1.16536 s, 524288 iters, t-(init.)=1.05393 s t(norm)=0.0837586, mflops=59.6954 (err=1.4e-16) 14. GSL: elapsed time t=1.86652 s, 524288 iters, t-(init.)=1.75502 s t(norm)=0.139477, mflops=35.8483 (err=1.4e-16) 15. GSL DIT: elapsed time t=1.06515 s, 131072 iters, t-(init.)=1.03728 s t(norm)=0.329743, mflops=15.1633 (err=1.5e-16) 16. GSL DIF: elapsed time t=1.05934 s, 131072 iters, t-(init.)=1.03134 s t(norm)=0.327855, mflops=15.2506 (err=1.6e-16) 17. Krukar: elapsed time t=1.80007 s, 1048576 iters, t-(init.)=1.57633 s t(norm)=0.0626377, mflops=79.8241 (err=1.5e-16) 18. Mayer (Buneman): elapsed time t=1.68052 s, 524288 iters, t-(init.)=1.56569 s t(norm)=0.12443, mflops=40.1832 (err=1.1e-16) 19. Mayer (simple): elapsed time t=1.60386 s, 524288 iters, t-(init.)=1.49171 s t(norm)=0.118551, mflops=42.176 20. Mayer (lookup): elapsed time t=1.691 s, 524288 iters, t-(init.)=1.5782 s t(norm)=0.125424, mflops=39.8647 (err=1.1e-16) 21. NAPACK (f2c): elapsed time t=1.98909 s, 131072 iters, t-(init.)=1.96086 s t(norm)=0.623339, mflops=8.02131 (err=1.7e-16) 22. Nielsen: elapsed time t=1.11979 s, 131072 iters, t-(init.)=1.09177 s t(norm)=0.347066, mflops=14.4065 (err=7.5e-16) 23. NR (C): elapsed time t=1.72241 s, 262144 iters, t-(init.)=1.66535 s t(norm)=0.2647, mflops=18.8893 (err=1.6e-16) 24. Ooura (C): elapsed time t=1.0152 s, 524288 iters, t-(init.)=0.903678 s t(norm)=0.0718179, mflops=69.6206 (err=1.5e-16) 25. Skipping fft (QFT requires N >= 16). 26. Ransom: elapsed time t=1.15599 s, 32768 iters, t-(init.)=1.14901 s t(norm)=1.46105, mflops=3.42221 (err=3.1e-16) 27. Singleton (f2c): elapsed time t=1.88993 s, 262144 iters, t-(init.)=1.83427 s t(norm)=0.29155, mflops=17.1497 (err=1.4e-16) 28. Temperton (f2c): elapsed time t=1.28906 s, 131072 iters, t-(init.)=1.26108 s t(norm)=0.400886, mflops=12.4724 (err=1.4e-16) 29. Valkenburg: elapsed time t=1.1202 s, 65536 iters, t-(init.)=1.10616 s t(norm)=0.70328, mflops=7.10954 (err=1.4e-16) Top mflops for N=8 = 151.903 Normalized results and averages for N=8: fft 0: mflops = 74.8819 (norm. = 0.492958), norm. avg. (of 3) = 0.551731 fft 1: mflops = 72.7997 (norm. = 0.479251), norm. avg. (of 3) = 0.526704 fft 2: mflops = 26.5952 (norm. = 0.17508), norm. avg. (of 3) = 0.284106 fft 3: mflops = 5.04392 (norm. = 0.0332048), norm. avg. (of 3) = 0.0312907 fft 4: mflops = 9.40979 (norm. = 0.061946), norm. avg. (of 3) = 0.0763233 fft 5: mflops = 26.321 (norm. = 0.173275), norm. avg. (of 3) = 0.157093 fft 6: mflops = 35.139 (norm. = 0.231325), norm. avg. (of 3) = 0.170211 fft 7: mflops = 21.9689 (norm. = 0.144625), norm. avg. (of 3) = 0.1119 fft 8: mflops = 20.425 (norm. = 0.134461), norm. avg. (of 2) = 0.165297 fft 9: mflops = 23.5699 (norm. = 0.155164), norm. avg. (of 3) = 0.168257 fft 10: mflops = 56.5573 (norm. = 0.372325), norm. avg. (of 3) = 0.321897 fft 11: mflops = 56.5536 (norm. = 0.372301), norm. avg. (of 3) = 0.321966 fft 12: mflops = 151.903 (norm. = 1), norm. avg. (of 3) = 1 fft 13: mflops = 59.6954 (norm. = 0.392983), norm. avg. (of 1) = 0.392983 fft 14: mflops = 35.8483 (norm. = 0.235994), norm. avg. (of 3) = 0.246228 fft 15: mflops = 15.1633 (norm. = 0.0998224), norm. avg. (of 3) = 0.105477 fft 16: mflops = 15.2506 (norm. = 0.100397), norm. avg. (of 3) = 0.104791 fft 17: mflops = 79.8241 (norm. = 0.525494), norm. avg. (of 3) = 0.575111 fft 18: mflops = 40.1832 (norm. = 0.264532), norm. avg. (of 2) = 0.252282 fft 19: mflops = 42.176 (norm. = 0.277651), norm. avg. (of 2) = 0.267245 fft 20: mflops = 39.8647 (norm. = 0.262435), norm. avg. (of 2) = 0.24607 fft 21: mflops = 8.02131 (norm. = 0.0528054), norm. avg. (of 3) = 0.0567033 fft 22: mflops = 14.4065 (norm. = 0.0948399), norm. avg. (of 3) = 0.068892 fft 23: mflops = 18.8893 (norm. = 0.124351), norm. avg. (of 3) = 0.136929 fft 24: mflops = 69.6206 (norm. = 0.458322), norm. avg. (of 3) = 0.461579 fft 25: mflops = -1 (norm. = -0.00658314), norm. avg. (of 0) = -1 fft 26: mflops = 3.42221 (norm. = 0.0225289), norm. avg. (of 2) = 0.0248346 fft 27: mflops = 17.1497 (norm. = 0.112899), norm. avg. (of 3) = 0.133624 fft 28: mflops = 12.4724 (norm. = 0.0821074), norm. avg. (of 3) = 0.0838126 fft 29: mflops = 7.10954 (norm. = 0.0468031), norm. avg. (of 3) = 0.100436 Benchmarking for array size = 16 (power of 2): 0. Arndt DIF: elapsed time t=1.95569 s, 262144 iters, t-(init.)=1.8566 s t(norm)=0.110662, mflops=45.1826 (err=1.9e-16) 1. Arndt DIT: elapsed time t=2.00002 s, 262144 iters, t-(init.)=1.90142 s t(norm)=0.113334, mflops=44.1175 (err=1.9e-16) 2. Arndt Split-Radix: elapsed time t=1.4011 s, 131072 iters, t-(init.)=1.35173 s t(norm)=0.161139, mflops=31.0292 (err=1.5e-16) 3. Arndt 4-step: elapsed time t=1.05561 s, 32768 iters, t-(init.)=1.04313 s t(norm)=0.497403, mflops=10.0522 (err=2.0e-16) 4. Beauregard: elapsed time t=1.02346 s, 32768 iters, t-(init.)=1.01095 s t(norm)=0.482058, mflops=10.3722 (err=2.3e-16) 5. Bergland: elapsed time t=1.05722 s, 131072 iters, t-(init.)=1.00731 s t(norm)=0.120081, mflops=41.6386 (err=2.6e-16) 6. CWP (min N): elapsed time t=1.52701 s, 262144 iters, t-(init.)=1.42838 s t(norm)=0.0851381, mflops=58.7281 7. CWP (best N) (N=28): elapsed time t=1.11078 s, 131072 iters, t-(init.)=1.02934 s t(norm)=0.122707, mflops=40.74738. Edelblute: elapsed time t=1.932 58 s, 131072 iters, t-(init.)=1.88165 s t(norm)=0.22431, mflops=22.2906 (err=1.6e-16) 9. FFTPACK (f2c): elapsed time t=1.3139 s, 131072 iters, t-(init.)=1.26465 s t(norm)=0.150758, mflops=33.1658 (err=2.1e-16) FFTW_MEASURE plan: (cost = 2.406372e-06) FFTW_NOTW 16 10. FFTW: elapsed time t=1.73396 s, 524288 iters, t-(init.)=1.53683 s t(norm)=0.0458012, mflops=109.167 (err=2.2e-16) FFTW_ESTIMATE plan: (cost = 4.256000e+02) FFTW_NOTW 16 11. FFTW_ESTIMATE: elapsed time t=1.73542 s, 524288 iters, t-(init.)=1.53838 s t(norm)=0.0458471, mflops=109.058 (err=2.2e-16) 12. Frigo-old: elapsed time t=1.20065 s, 524288 iters, t-(init.)=1.00365 s t(norm)=0.0299111, mflops=167.162 (err=2.2e-16) 13. Green: elapsed time t=1.10606 s, 262144 iters, t-(init.)=1.00757 s t(norm)=0.0600556, mflops=83.2562 (err=2.6e-16) 14. GSL: elapsed time t=1.69017 s, 262144 iters, t-(init.)=1.59044 s t(norm)=0.0947978, mflops=52.7438 (err=2.1e-16) 15. GSL DIT: elapsed time t=1.81621 s, 131072 iters, t-(init.)=1.76695 s t(norm)=0.210637, mflops=23.7375 (err=3.1e-16) 16. GSL DIF: elapsed time t=1.7988 s, 131072 iters, t-(init.)=1.74959 s t(norm)=0.208568, mflops=23.973 (err=2.5e-16) 17. Krukar: elapsed time t=1.00416 s, 262144 iters, t-(init.)=0.90489 s t(norm)=0.0539356, mflops=92.7031 (err=1.7e-16) 18. Mayer (Buneman): elapsed time t=1.06823 s, 131072 iters, t-(init.)=1.01834 s t(norm)=0.121395, mflops=41.1878 (err=2.3e-16) 19. Mayer (simple): elapsed time t=1.75147 s, 262144 iters, t-(init.)=1.65291 s t(norm)=0.098521, mflops=50.7506 20. Mayer (lookup): elapsed time t=1.777 s, 262144 iters, t-(init.)=1.67825 s t(norm)=0.100032, mflops=49.9841 (err=2.1e-16) 21. NAPACK (f2c): elapsed time t=1.84527 s, 65536 iters, t-(init.)=1.82039 s t(norm)=0.434016, mflops=11.5203 (err=2.7e-16) 22. Nielsen: elapsed time t=1.41303 s, 65536 iters, t-(init.)=1.38829 s t(norm)=0.330993, mflops=15.106 (err=1.8e-16) 23. NR (C): elapsed time t=1.52215 s, 131072 iters, t-(init.)=1.47289 s t(norm)=0.175582, mflops=28.4768 (err=2.9e-16) 24. Ooura (C): elapsed time t=1.94382 s, 524288 iters, t-(init.)=1.74657 s t(norm)=0.052052, mflops=96.0578 (err=2.5e-16) 25. QFT: elapsed time t=1.12651 s, 131072 iters, t-(init.)=1.07717 s t(norm)=0.128409, mflops=38.9381 (err=1.4e-16) 26. Ransom: elapsed time t=1.7979 s, 65536 iters, t-(init.)=1.7729 s t(norm)=0.422692, mflops=11.829 (err=5.0e-16) 27. Singleton (f2c): elapsed time t=1.94685 s, 262144 iters, t-(init.)=1.8482 s t(norm)=0.110161, mflops=45.3881 (err=2.0e-16) 28. Temperton (f2c): elapsed time t=1.19955 s, 65536 iters, t-(init.)=1.17494 s t(norm)=0.280128, mflops=17.849 (err=2.1e-16) 29. Valkenburg: elapsed time t=1.4228 s, 32768 iters, t-(init.)=1.41046 s t(norm)=0.672559, mflops=7.43429 (err=2.5e-16) Top mflops for N=16 = 167.162 Normalized results and averages for N=16: fft 0: mflops = 45.1826 (norm. = 0.270292), norm. avg. (of 4) = 0.481371 fft 1: mflops = 44.1175 (norm. = 0.263921), norm. avg. (of 4) = 0.461008 fft 2: mflops = 31.0292 (norm. = 0.185623), norm. avg. (of 4) = 0.259486 fft 3: mflops = 10.0522 (norm. = 0.0601345), norm. avg. (of 4) = 0.0385016 fft 4: mflops = 10.3722 (norm. = 0.0620488), norm. avg. (of 4) = 0.0727547 fft 5: mflops = 41.6386 (norm. = 0.249091), norm. avg. (of 4) = 0.180093 fft 6: mflops = 58.7281 (norm. = 0.351325), norm. avg. (of 4) = 0.21549 fft 7: mflops = 40.7473 (norm. = 0.243759), norm. avg. (of 4) = 0.144865 fft 8: mflops = 22.2906 (norm. = 0.133347), norm. avg. (of 3) = 0.154647 fft 9: mflops = 33.1658 (norm. = 0.198405), norm. avg. (of 4) = 0.175794 fft 10: mflops = 109.167 (norm. = 0.653063), norm. avg. (of 4) = 0.404688 fft 11: mflops = 109.058 (norm. = 0.652409), norm. avg. (of 4) = 0.404577 fft 12: mflops = 167.162 (norm. = 1), norm. avg. (of 4) = 1 fft 13: mflops = 83.2562 (norm. = 0.498057), norm. avg. (of 2) = 0.44552 fft 14: mflops = 52.7438 (norm. = 0.315525), norm. avg. (of 4) = 0.263552 fft 15: mflops = 23.7375 (norm. = 0.142003), norm. avg. (of 4) = 0.114608 fft 16: mflops = 23.973 (norm. = 0.143412), norm. avg. (of 4) = 0.114447 fft 17: mflops = 92.7031 (norm. = 0.55457), norm. avg. (of 4) = 0.569976 fft 18: mflops = 41.1878 (norm. = 0.246395), norm. avg. (of 3) = 0.250319 fft 19: mflops = 50.7506 (norm. = 0.303601), norm. avg. (of 3) = 0.279364 fft 20: mflops = 49.9841 (norm. = 0.299016), norm. avg. (of 3) = 0.263719 fft 21: mflops = 11.5203 (norm. = 0.068917), norm. avg. (of 4) = 0.0597567 fft 22: mflops = 15.106 (norm. = 0.0903677), norm. avg. (of 4) = 0.0742609 fft 23: mflops = 28.4768 (norm. = 0.170354), norm. avg. (of 4) = 0.145286 fft 24: mflops = 96.0578 (norm. = 0.574639), norm. avg. (of 4) = 0.489844 fft 25: mflops = 38.9381 (norm. = 0.232936), norm. avg. (of 1) = 0.232936 fft 26: mflops = 11.829 (norm. = 0.0707634), norm. avg. (of 3) = 0.0401442 fft 27: mflops = 45.3881 (norm. = 0.271521), norm. avg. (of 4) = 0.168098 fft 28: mflops = 17.849 (norm. = 0.106776), norm. avg. (of 4) = 0.0895536 fft 29: mflops = 7.43429 (norm. = 0.0444736), norm. avg. (of 4) = 0.0864455 Benchmarking for array size = 32 (power of 2): 0. Arndt DIF: elapsed time t=1.04027 s, 65536 iters, t-(init.)=0.994136 s t(norm)=0.0948082, mflops=52.7381 (err=2.4e-16) 1. Arndt DIT: elapsed time t=1.05323 s, 65536 iters, t-(init.)=1.00702 s t(norm)=0.0960366, mflops=52.0635 (err=2.7e-16) 2. Arndt Split-Radix: elapsed time t=1.53474 s, 65536 iters, t-(init.)=1.48843 s t(norm)=0.141948, mflops=35.2242 (err=3.0e-16) 3. Arndt 4-step: elapsed time t=1.10624 s, 16384 iters, t-(init.)=1.09456 s t(norm)=0.417542, mflops=11.9748 (err=2.4e-16) 4. Beauregard: elapsed time t=1.24081 s, 16384 iters, t-(init.)=1.22927 s t(norm)=0.468929, mflops=10.6626 (err=2.5e-16) 5. Bergland: elapsed time t=1.85989 s, 131072 iters, t-(init.)=1.76714 s t(norm)=0.0842636, mflops=59.3376 (err=2.6e-16) 6. CWP (min N) (N=33): elapsed time t=1.7757 s, 131072 iters, t-(init.)=1.68021 s t(norm)=0.0801189, mflops=62.4073 7. CWP (best N) (N=35): elapsed time t=1.49124 s, 131072 iters, t-(init.)=1.39084 s t(norm)=0.0663206, mflops=75.3913 8. Edelblute: elapsed time t=1.08887 s, 32768 iters, t-(init.)=1.0655 s t(norm)=0.203228, mflops=24.6029 (err=2.9e-16) 9. FFTPACK (f2c): elapsed time t=1.87841 s, 65536 iters, t-(init.)=1.83227 s t(norm)=0.174739, mflops=28.614 (err=2.3e-16) FFTW_MEASURE plan: (cost = 5.420288e-06) FFTW_NOTW 32 10. FFTW: elapsed time t=1.66543 s, 262144 iters, t-(init.)=1.48063 s t(norm)=0.035301, mflops=141.639 (err=2.4e-16) FFTW_ESTIMATE plan: (cost = 3.200000e+01) FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.6658 s, 262144 iters, t-(init.)=1.47998 s t(norm)=0.0352856, mflops=141.701 (err=2.4e-16) 12. Frigo-old: elapsed time t=1.39981 s, 262144 iters, t-(init.)=1.21533 s t(norm)=0.0289758, mflops=172.558 (err=2.1e-16) 13. Green: elapsed time t=1.03633 s, 131072 iters, t-(init.)=0.944346 s t(norm)=0.0450299, mflops=111.037 (err=2.4e-16) 14. GSL: elapsed time t=1.06946 s, 65536 iters, t-(init.)=1.02307 s t(norm)=0.0975672, mflops=51.2467 (err=2.3e-16) 15. GSL DIT: elapsed time t=1.64631 s, 65536 iters, t-(init.)=1.60013 s t(norm)=0.152601, mflops=32.7653 (err=3.1e-16) 16. GSL DIF: elapsed time t=1.60796 s, 65536 iters, t-(init.)=1.56196 s t(norm)=0.14896, mflops=33.5659 (err=3.2e-16) 17. Krukar: elapsed time t=1.27052 s, 131072 iters, t-(init.)=1.17804 s t(norm)=0.0561732, mflops=89.0104 (err=2.7e-16) 18. Mayer (Buneman): elapsed time t=1.17135 s, 65536 iters, t-(init.)=1.12486 s t(norm)=0.107275, mflops=46.6093 (err=2.8e-16) 19. Mayer (simple): elapsed time t=1.82707 s, 131072 iters, t-(init.)=1.73417 s t(norm)=0.0826916, mflops=60.4657 20. Mayer (lookup): elapsed time t=1.81073 s, 131072 iters, t-(init.)=1.71864 s t(norm)=0.0819511, mflops=61.012 (err=2.6e-16) 21. NAPACK (f2c): elapsed time t=1.90614 s, 32768 iters, t-(init.)=1.883 s t(norm)=0.359153, mflops=13.9216 (err=6.4e-16) 22. Nielsen: elapsed time t=1.20719 s, 32768 iters, t-(init.)=1.18412 s t(norm)=0.225854, mflops=22.1382 (err=1.1e-15) 23. NR (C): elapsed time t=1.41749 s, 65536 iters, t-(init.)=1.37128 s t(norm)=0.130775, mflops=38.2336 (err=2.9e-16) 24. Ooura (C): elapsed time t=1.09764 s, 131072 iters, t-(init.)=1.00532 s t(norm)=0.0479376, mflops=104.302 (err=2.5e-16) 25. QFT: elapsed time t=1.27913 s, 65536 iters, t-(init.)=1.23312 s t(norm)=0.1176, mflops=42.5172 (err=2.8e-16) 26. Ransom: elapsed time t=1.05613 s, 16384 iters, t-(init.)=1.04451 s t(norm)=0.39845, mflops=12.5486 (err=7.4e-16) 27. Singleton (f2c): elapsed time t=1.89177 s, 131072 iters, t-(init.)=1.79973 s t(norm)=0.0858177, mflops=58.263 (err=2.3e-16) 28. Temperton (f2c): elapsed time t=1.565 s, 32768 iters, t-(init.)=1.54183 s t(norm)=0.29408, mflops=17.0022 (err=2.6e-16) 29. Valkenburg: elapsed time t=1.71878 s, 16384 iters, t-(init.)=1.7074 s t(norm)=0.651323, mflops=7.67668 (err=2.8e-16) Top mflops for N=32 = 172.558 Normalized results and averages for N=32: fft 0: mflops = 52.7381 (norm. = 0.305625), norm. avg. (of 5) = 0.446222 fft 1: mflops = 52.0635 (norm. = 0.301716), norm. avg. (of 5) = 0.42915 fft 2: mflops = 35.2242 (norm. = 0.20413), norm. avg. (of 5) = 0.248414 fft 3: mflops = 11.9748 (norm. = 0.0693961), norm. avg. (of 5) = 0.0446805 fft 4: mflops = 10.6626 (norm. = 0.0617915), norm. avg. (of 5) = 0.0705621 fft 5: mflops = 59.3376 (norm. = 0.343871), norm. avg. (of 5) = 0.212848 fft 6: mflops = 62.4073 (norm. = 0.36166), norm. avg. (of 5) = 0.244724 fft 7: mflops = 75.3913 (norm. = 0.436905), norm. avg. (of 5) = 0.203273 fft 8: mflops = 24.6029 (norm. = 0.142578), norm. avg. (of 4) = 0.15163 fft 9: mflops = 28.614 (norm. = 0.165823), norm. avg. (of 5) = 0.1738 fft 10: mflops = 141.639 (norm. = 0.820821), norm. avg. (of 5) = 0.487915 fft 11: mflops = 141.701 (norm. = 0.821179), norm. avg. (of 5) = 0.487897 fft 12: mflops = 172.558 (norm. = 1), norm. avg. (of 5) = 1 fft 13: mflops = 111.037 (norm. = 0.643479), norm. avg. (of 3) = 0.511506 fft 14: mflops = 51.2467 (norm. = 0.296983), norm. avg. (of 5) = 0.270238 fft 15: mflops = 32.7653 (norm. = 0.18988), norm. avg. (of 5) = 0.129662 fft 16: mflops = 33.5659 (norm. = 0.19452), norm. avg. (of 5) = 0.130461 fft 17: mflops = 89.0104 (norm. = 0.515829), norm. avg. (of 5) = 0.559146 fft 18: mflops = 46.6093 (norm. = 0.270108), norm. avg. (of 4) = 0.255266 fft 19: mflops = 60.4657 (norm. = 0.350408), norm. avg. (of 4) = 0.297125 fft 20: mflops = 61.012 (norm. = 0.353574), norm. avg. (of 4) = 0.286183 fft 21: mflops = 13.9216 (norm. = 0.0806781), norm. avg. (of 5) = 0.063941 fft 22: mflops = 22.1382 (norm. = 0.128295), norm. avg. (of 5) = 0.0850677 fft 23: mflops = 38.2336 (norm. = 0.22157), norm. avg. (of 5) = 0.160542 fft 24: mflops = 104.302 (norm. = 0.604448), norm. avg. (of 5) = 0.512765 fft 25: mflops = 42.5172 (norm. = 0.246394), norm. avg. (of 2) = 0.239665 fft 26: mflops = 12.5486 (norm. = 0.0727212), norm. avg. (of 4) = 0.0482885 fft 27: mflops = 58.263 (norm. = 0.337644), norm. avg. (of 5) = 0.202007 fft 28: mflops = 17.0022 (norm. = 0.0985303), norm. avg. (of 5) = 0.0913489 fft 29: mflops = 7.67668 (norm. = 0.0444876), norm. avg. (of 5) = 0.0780539 Benchmarking for array size = 64 (power of 2): 0. Arndt DIF: elapsed time t=1.22008 s, 32768 iters, t-(init.)=1.17554 s t(norm)=0.0934234, mflops=53.5198 (err=5.0e-16) 1. Arndt DIT: elapsed time t=1.25018 s, 32768 iters, t-(init.)=1.20564 s t(norm)=0.0958159, mflops=52.1834 (err=4.9e-16) 2. Arndt Split-Radix: elapsed time t=1.64711 s, 32768 iters, t-(init.)=1.60247 s t(norm)=0.127353, mflops=39.2611 (err=4.5e-16) 3. Arndt 4-step: elapsed time t=1.83113 s, 16384 iters, t-(init.)=1.80887 s t(norm)=0.287513, mflops=17.3905 (err=4.9e-16) 4. Beauregard: elapsed time t=1.48115 s, 8192 iters, t-(init.)=1.47 s t(norm)=0.467301, mflops=10.6997 (err=4.5e-16) 5. Bergland: elapsed time t=1.89929 s, 65536 iters, t-(init.)=1.81019 s t(norm)=0.0719306, mflops=69.5114 (err=5.5e-16) 6. CWP (min N) (N=65): elapsed time t=1.98898 s, 65536 iters, t-(init.)=1.89868 s t(norm)=0.0754467, mflops=66.272 7. CWP (best N) (N=84): elapsed time t=1.60998 s, 65536 iters, t-(init.)=1.49426 s t(norm)=0.0593765, mflops=84.2084 8. Edelblute: elapsed time t=1.17735 s, 16384 iters, t-(init.)=1.15501 s t(norm)=0.183585, mflops=27.2354 (err=4.6e-16) 9. FFTPACK (f2c): elapsed time t=1.94202 s, 32768 iters, t-(init.)=1.89744 s t(norm)=0.150795, mflops=33.1576 (err=4.4e-16) FFTW_MEASURE plan: (cost = 1.211646e-05) FFTW_NOTW 64 10. FFTW: elapsed time t=1.93266 s, 131072 iters, t-(init.)=1.75473 s t(norm)=0.0348634, mflops=143.417 (err=4.4e-16) FFTW_ESTIMATE plan: (cost = 7.680000e+02) FFTW_TWIDDLE 2 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.05088 s, 65536 iters, t-(init.)=0.961639 s t(norm)=0.0382121, mflops=130.849 (err=4.7e-16) 12. Frigo-old: elapsed time t=1.13537 s, 65536 iters, t-(init.)=1.04624 s t(norm)=0.041574, mflops=120.267 (err=4.5e-16) 13. Green: elapsed time t=1.92418 s, 131072 iters, t-(init.)=1.74634 s t(norm)=0.0346966, mflops=144.106 (err=4.6e-16) 14. GSL: elapsed time t=1.0758 s, 32768 iters, t-(init.)=1.03121 s t(norm)=0.0819529, mflops=61.0107 (err=4.4e-16) 15. GSL DIT: elapsed time t=1.60873 s, 32768 iters, t-(init.)=1.56416 s t(norm)=0.124309, mflops=40.2225 (err=4.6e-16) 16. GSL DIF: elapsed time t=1.54978 s, 32768 iters, t-(init.)=1.50534 s t(norm)=0.119634, mflops=41.7942 (err=4.9e-16) 17. Krukar: elapsed time t=1.33697 s, 32768 iters, t-(init.)=1.29248 s t(norm)=0.102717, mflops=48.6772 (err=5.2e-16) 18. Mayer (Buneman): elapsed time t=1.33511 s, 32768 iters, t-(init.)=1.2899 s t(norm)=0.102512, mflops=48.7746 (err=4.8e-16) 19. Mayer (simple): elapsed time t=2.00079 s, 65536 iters, t-(init.)=1.91166 s t(norm)=0.0759625, mflops=65.8219 20. Mayer (lookup): elapsed time t=1.96226 s, 65536 iters, t-(init.)=1.87327 s t(norm)=0.0744369, mflops=67.171 (err=4.5e-16) 21. NAPACK (f2c): elapsed time t=1.93691 s, 16384 iters, t-(init.)=1.9145 s t(norm)=0.304302, mflops=16.431 (err=1.1e-15) 22. Nielsen: elapsed time t=1.12406 s, 16384 iters, t-(init.)=1.10184 s t(norm)=0.175133, mflops=28.5497 (err=1.9e-15) 23. NR (C): elapsed time t=1.40337 s, 32768 iters, t-(init.)=1.35885 s t(norm)=0.107992, mflops=46.2998 (err=4.4e-16) 24. Ooura (C): elapsed time t=1.14765 s, 65536 iters, t-(init.)=1.05863 s t(norm)=0.042066, mflops=118.861 (err=5.4e-16) 25. QFT: elapsed time t=1.49862 s, 32768 iters, t-(init.)=1.45379 s t(norm)=0.115537, mflops=43.2763 (err=4.9e-16) 26. Ransom: elapsed time t=1.25836 s, 16384 iters, t-(init.)=1.2359 s t(norm)=0.196441, mflops=25.453 (err=9.1e-16) 27. Singleton (f2c): elapsed time t=1.64251 s, 65536 iters, t-(init.)=1.55333 s t(norm)=0.0617238, mflops=81.006 (err=6.5e-16) 28. Temperton (f2c): elapsed time t=1.46777 s, 16384 iters, t-(init.)=1.44536 s t(norm)=0.229734, mflops=21.7643 (err=4.7e-16) 29. Valkenburg: elapsed time t=1.00408 s, 4096 iters, t-(init.)=0.998207 s t(norm)=0.634643, mflops=7.87845 (err=6.0e-16) Top mflops for N=64 = 144.106 Normalized results and averages for N=64: fft 0: mflops = 53.5198 (norm. = 0.371391), norm. avg. (of 6) = 0.43375 fft 1: mflops = 52.1834 (norm. = 0.362117), norm. avg. (of 6) = 0.417978 fft 2: mflops = 39.2611 (norm. = 0.272445), norm. avg. (of 6) = 0.25242 fft 3: mflops = 17.3905 (norm. = 0.120679), norm. avg. (of 6) = 0.0573469 fft 4: mflops = 10.6997 (norm. = 0.0742489), norm. avg. (of 6) = 0.0711765 fft 5: mflops = 69.5114 (norm. = 0.482362), norm. avg. (of 6) = 0.257767 fft 6: mflops = 66.272 (norm. = 0.459882), norm. avg. (of 6) = 0.280583 fft 7: mflops = 84.2084 (norm. = 0.584349), norm. avg. (of 6) = 0.266785 fft 8: mflops = 27.2354 (norm. = 0.188995), norm. avg. (of 5) = 0.159103 fft 9: mflops = 33.1576 (norm. = 0.230091), norm. avg. (of 6) = 0.183181 fft 10: mflops = 143.417 (norm. = 0.995217), norm. avg. (of 6) = 0.572465 fft 11: mflops = 130.849 (norm. = 0.908), norm. avg. (of 6) = 0.557914 fft 12: mflops = 120.267 (norm. = 0.834574), norm. avg. (of 6) = 0.972429 fft 13: mflops = 144.106 (norm. = 1), norm. avg. (of 4) = 0.63363 fft 14: mflops = 61.0107 (norm. = 0.423372), norm. avg. (of 6) = 0.295761 fft 15: mflops = 40.2225 (norm. = 0.279117), norm. avg. (of 6) = 0.154572 fft 16: mflops = 41.7942 (norm. = 0.290023), norm. avg. (of 6) = 0.157055 fft 17: mflops = 48.6772 (norm. = 0.337787), norm. avg. (of 6) = 0.522253 fft 18: mflops = 48.7746 (norm. = 0.338463), norm. avg. (of 5) = 0.271906 fft 19: mflops = 65.8219 (norm. = 0.45676), norm. avg. (of 5) = 0.329052 fft 20: mflops = 67.171 (norm. = 0.466121), norm. avg. (of 5) = 0.32217 fft 21: mflops = 16.431 (norm. = 0.11402), norm. avg. (of 6) = 0.0722876 fft 22: mflops = 28.5497 (norm. = 0.198116), norm. avg. (of 6) = 0.103909 fft 23: mflops = 46.2998 (norm. = 0.321289), norm. avg. (of 6) = 0.187334 fft 24: mflops = 118.861 (norm. = 0.824813), norm. avg. (of 6) = 0.564773 fft 25: mflops = 43.2763 (norm. = 0.300308), norm. avg. (of 3) = 0.259879 fft 26: mflops = 25.453 (norm. = 0.176626), norm. avg. (of 5) = 0.073956 fft 27: mflops = 81.006 (norm. = 0.562127), norm. avg. (of 6) = 0.262027 fft 28: mflops = 21.7643 (norm. = 0.15103), norm. avg. (of 6) = 0.101296 fft 29: mflops = 7.87845 (norm. = 0.0546711), norm. avg. (of 6) = 0.0741568 Benchmarking for array size = 128 (power of 2): 0. Arndt DIF: elapsed time t=1.29019 s, 16384 iters, t-(init.)=1.2465 s t(norm)=0.0849113, mflops=58.885 (err=4.0e-16) 1. Arndt DIT: elapsed time t=1.31406 s, 16384 iters, t-(init.)=1.27028 s t(norm)=0.0865308, mflops=57.7829 (err=4.1e-16) 2. Arndt Split-Radix: elapsed time t=1.74533 s, 16384 iters, t-(init.)=1.70117 s t(norm)=0.115883, mflops=43.147 (err=4.4e-16) 3. Arndt 4-step: elapsed time t=1.04607 s, 4096 iters, t-(init.)=1.03496 s t(norm)=0.282003, mflops=17.7303 (err=4.0e-16) 4. Beauregard: elapsed time t=1.73576 s, 4096 iters, t-(init.)=1.72492 s t(norm)=0.470003, mflops=10.6382 (err=4.1e-16) 5. Bergland: elapsed time t=1.01766 s, 16384 iters, t-(init.)=0.973795 s t(norm)=0.0663345, mflops=75.3755 (err=4.3e-16) 6. CWP (min N) (N=130): elapsed time t=1.01295 s, 16384 iters, t-(init.)=0.968584 s t(norm)=0.0659795, mflops=75.7811 7. CWP (best N) (N=140): elapsed time t=1.39875 s, 32768 iters, t-(init.)=1.30329 s t(norm)=0.0443897, mflops=112.639 8. Edelblute: elapsed time t=1.24291 s, 8192 iters, t-(init.)=1.22101 s t(norm)=0.166349, mflops=30.0573 (err=4.1e-16) 9. FFTPACK (f2c): elapsed time t=1.09314 s, 8192 iters, t-(init.)=1.071 s t(norm)=0.145912, mflops=34.2671 (err=4.1e-16) FFTW_MEASURE plan: (cost = 3.116748e-05) FFTW_TWIDDLE 4 FFTW_NOTW 32 10. FFTW: elapsed time t=1.09843 s, 32768 iters, t-(init.)=1.01095 s t(norm)=0.0344327, mflops=145.211 (err=4.2e-16) FFTW_ESTIMATE plan: (cost = 1.075200e+03) FFTW_TWIDDLE 4 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.09824 s, 32768 iters, t-(init.)=1.01081 s t(norm)=0.0344278, mflops=145.231 (err=4.2e-16) 12. Frigo-old: elapsed time t=1.17806 s, 32768 iters, t-(init.)=1.09057 s t(norm)=0.0371444, mflops=134.61 (err=4.4e-16) 13. Green: elapsed time t=1.13055 s, 32768 iters, t-(init.)=1.04318 s t(norm)=0.0355305, mflops=140.724 (err=4.4e-16) 14. GSL: elapsed time t=1.19643 s, 16384 iters, t-(init.)=1.15287 s t(norm)=0.0785328, mflops=63.6676 (err=4.2e-16) 15. GSL DIT: elapsed time t=1.65691 s, 16384 iters, t-(init.)=1.61322 s t(norm)=0.109892, mflops=45.4991 (err=4.3e-16) 16. GSL DIF: elapsed time t=1.56361 s, 16384 iters, t-(init.)=1.51992 s t(norm)=0.103536, mflops=48.2923 (err=4.6e-16) 17. Krukar: elapsed time t=1.76184 s, 8192 iters, t-(init.)=1.7398 s t(norm)=0.237029, mflops=21.0945 (err=4.6e-16) 18. Mayer (Buneman): elapsed time t=1.43352 s, 16384 iters, t-(init.)=1.38962 s t(norm)=0.0946601, mflops=52.8206 (err=4.0e-16) 19. Mayer (simple): elapsed time t=1.06294 s, 16384 iters, t-(init.)=1.01906 s t(norm)=0.0694182, mflops=72.0272 20. Mayer (lookup): elapsed time t=1.03694 s, 16384 iters, t-(init.)=0.993267 s t(norm)=0.0676609, mflops=73.8979 (err=4.3e-16) 21. NAPACK (f2c): elapsed time t=1.07294 s, 4096 iters, t-(init.)=1.06179 s t(norm)=0.289314, mflops=17.2823 (err=1.2e-15) 22. Nielsen: elapsed time t=1.36819 s, 8192 iters, t-(init.)=1.34617 s t(norm)=0.183401, mflops=27.2627 (err=1.3e-15) 23. NR (C): elapsed time t=1.44104 s, 16384 iters, t-(init.)=1.39737 s t(norm)=0.0951882, mflops=52.5275 (err=4.4e-16) 24. Ooura (C): elapsed time t=1.34737 s, 32768 iters, t-(init.)=1.25883 s t(norm)=0.0428757, mflops=116.616 (err=4.1e-16) 25. QFT: elapsed time t=1.74336 s, 16384 iters, t-(init.)=1.69962 s t(norm)=0.115777, mflops=43.1864 (err=4.6e-16) 26. Ransom: elapsed time t=1.48268 s, 8192 iters, t-(init.)=1.46076 s t(norm)=0.199013, mflops=25.124 (err=1.1e-15) 27. Singleton (f2c): elapsed time t=1.99203 s, 32768 iters, t-(init.)=1.90446 s t(norm)=0.0648655, mflops=77.0826 (err=5.3e-16) 28. Temperton (f2c): elapsed time t=1.06299 s, 4096 iters, t-(init.)=1.05197 s t(norm)=0.28664, mflops=17.4435 (err=4.4e-16) 29. Valkenburg: elapsed time t=1.16415 s, 2048 iters, t-(init.)=1.15861 s t(norm)=0.631393, mflops=7.919 (err=4.8e-16) Top mflops for N=128 = 145.231 Normalized results and averages for N=128: fft 0: mflops = 58.885 (norm. = 0.405457), norm. avg. (of 7) = 0.429708 fft 1: mflops = 57.7829 (norm. = 0.397868), norm. avg. (of 7) = 0.415105 fft 2: mflops = 43.147 (norm. = 0.297092), norm. avg. (of 7) = 0.258801 fft 3: mflops = 17.7303 (norm. = 0.122083), norm. avg. (of 7) = 0.0665949 fft 4: mflops = 10.6382 (norm. = 0.0732503), norm. avg. (of 7) = 0.0714728 fft 5: mflops = 75.3755 (norm. = 0.519003), norm. avg. (of 7) = 0.295087 fft 6: mflops = 75.7811 (norm. = 0.521796), norm. avg. (of 7) = 0.315042 fft 7: mflops = 112.639 (norm. = 0.775582), norm. avg. (of 7) = 0.339471 fft 8: mflops = 30.0573 (norm. = 0.206961), norm. avg. (of 6) = 0.167079 fft 9: mflops = 34.2671 (norm. = 0.235949), norm. avg. (of 7) = 0.19072 fft 10: mflops = 145.211 (norm. = 0.999859), norm. avg. (of 7) = 0.633521 fft 11: mflops = 145.231 (norm. = 1), norm. avg. (of 7) = 0.62107 fft 12: mflops = 134.61 (norm. = 0.926865), norm. avg. (of 7) = 0.96592 fft 13: mflops = 140.724 (norm. = 0.968966), norm. avg. (of 5) = 0.700697 fft 14: mflops = 63.6676 (norm. = 0.438388), norm. avg. (of 7) = 0.316136 fft 15: mflops = 45.4991 (norm. = 0.313287), norm. avg. (of 7) = 0.177245 fft 16: mflops = 48.2923 (norm. = 0.33252), norm. avg. (of 7) = 0.182121 fft 17: mflops = 21.0945 (norm. = 0.145247), norm. avg. (of 7) = 0.468395 fft 18: mflops = 52.8206 (norm. = 0.3637), norm. avg. (of 6) = 0.287205 fft 19: mflops = 72.0272 (norm. = 0.495948), norm. avg. (of 6) = 0.356868 fft 20: mflops = 73.8979 (norm. = 0.508829), norm. avg. (of 6) = 0.35328 fft 21: mflops = 17.2823 (norm. = 0.118998), norm. avg. (of 7) = 0.0789605 fft 22: mflops = 27.2627 (norm. = 0.187719), norm. avg. (of 7) = 0.115882 fft 23: mflops = 52.5275 (norm. = 0.361682), norm. avg. (of 7) = 0.21224 fft 24: mflops = 116.616 (norm. = 0.802969), norm. avg. (of 7) = 0.598801 fft 25: mflops = 43.1864 (norm. = 0.297363), norm. avg. (of 4) = 0.26925 fft 26: mflops = 25.124 (norm. = 0.172993), norm. avg. (of 6) = 0.0904622 fft 27: mflops = 77.0826 (norm. = 0.530758), norm. avg. (of 7) = 0.300417 fft 28: mflops = 17.4435 (norm. = 0.120108), norm. avg. (of 7) = 0.103983 fft 29: mflops = 7.919 (norm. = 0.0545268), norm. avg. (of 7) = 0.0713525 Benchmarking for array size = 256 (power of 2): 0. Arndt DIF: elapsed time t=1.40872 s, 8192 iters, t-(init.)=1.36527 s t(norm)=0.0813764, mflops=61.4429 (err=6.7e-16) 1. Arndt DIT: elapsed time t=1.45202 s, 8192 iters, t-(init.)=1.40869 s t(norm)=0.0839646, mflops=59.5489 (err=7.1e-16) 2. Arndt Split-Radix: elapsed time t=1.86914 s, 8192 iters, t-(init.)=1.82568 s t(norm)=0.108819, mflops=45.9479 (err=7.4e-16) 3. Arndt 4-step: elapsed time t=1.05027 s, 2048 iters, t-(init.)=1.03939 s t(norm)=0.247809, mflops=20.1768 (err=7.2e-16) 4. Beauregard: elapsed time t=1.99649 s, 2048 iters, t-(init.)=1.98561 s t(norm)=0.473405, mflops=10.5618 (err=7.8e-16) 5. Bergland: elapsed time t=1.02407 s, 8192 iters, t-(init.)=0.980676 s t(norm)=0.0584528, mflops=85.539 (err=8.3e-16) 6. CWP (min N) (N=260): elapsed time t=1.99341 s, 16384 iters, t-(init.)=1.90523 s t(norm)=0.0567802, mflops=88.0589 7. CWP (best N) (N=280): elapsed time t=1.54361 s, 16384 iters, t-(init.)=1.44872 s t(norm)=0.0431751, mflops=115.807 8. Edelblute: elapsed time t=1.31078 s, 4096 iters, t-(init.)=1.28914 s t(norm)=0.153678, mflops=32.5356 (err=7.0e-16) 9. FFTPACK (f2c): elapsed time t=1.17175 s, 4096 iters, t-(init.)=1.14997 s t(norm)=0.137087, mflops=36.4731 (err=7.8e-16) FFTW_MEASURE plan: (cost = 7.911621e-05) FFTW_TWIDDLE 8 FFTW_NOTW 32 10. FFTW: elapsed time t=1.22862 s, 16384 iters, t-(init.)=1.14196 s t(norm)=0.0340331, mflops=146.916 (err=8.1e-16) FFTW_ESTIMATE plan: (cost = 9.216000e+02) FFTW_TWIDDLE 8 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.22916 s, 16384 iters, t-(init.)=1.14216 s t(norm)=0.034039, mflops=146.89 (err=8.1e-16) 12. Frigo-old: elapsed time t=1.27698 s, 16384 iters, t-(init.)=1.1903 s t(norm)=0.0354739, mflops=140.949 (err=8.0e-16) 13. Green: elapsed time t=1.20242 s, 16384 iters, t-(init.)=1.11576 s t(norm)=0.0332521, mflops=150.366 (err=7.6e-16) 14. GSL: elapsed time t=1.25423 s, 8192 iters, t-(init.)=1.21068 s t(norm)=0.0721623, mflops=69.2882 (err=7.8e-16) 15. GSL DIT: elapsed time t=1.77802 s, 8192 iters, t-(init.)=1.73468 s t(norm)=0.103395, mflops=48.3583 (err=7.7e-16) 16. GSL DIF: elapsed time t=1.63876 s, 8192 iters, t-(init.)=1.59547 s t(norm)=0.0950977, mflops=52.5775 (err=8.3e-16) 17. Krukar: elapsed time t=1.44364 s, 4096 iters, t-(init.)=1.422 s t(norm)=0.169516, mflops=29.4958 (err=7.7e-16) 18. Mayer (Buneman): elapsed time t=1.5528 s, 8192 iters, t-(init.)=1.50923 s t(norm)=0.0899574, mflops=55.5819 (err=7.0e-16) 19. Mayer (simple): elapsed time t=1.15073 s, 8192 iters, t-(init.)=1.10707 s t(norm)=0.0659863, mflops=75.7733 20. Mayer (lookup): elapsed time t=1.12217 s, 8192 iters, t-(init.)=1.07868 s t(norm)=0.0642945, mflops=77.7672 (err=7.1e-16) 21. NAPACK (f2c): elapsed time t=1.14166 s, 2048 iters, t-(init.)=1.13057 s t(norm)=0.269548, mflops=18.5496 (err=3.6e-15) 22. Nielsen: elapsed time t=1.39504 s, 4096 iters, t-(init.)=1.37278 s t(norm)=0.163648, mflops=30.5533 (err=3.4e-15) 23. NR (C): elapsed time t=1.5372 s, 8192 iters, t-(init.)=1.49374 s t(norm)=0.0890337, mflops=56.1585 (err=8.6e-16) 24. Ooura (C): elapsed time t=1.41429 s, 16384 iters, t-(init.)=1.32747 s t(norm)=0.0395617, mflops=126.385 (err=7.9e-16) 25. QFT: elapsed time t=1.12683 s, 4096 iters, t-(init.)=1.10459 s t(norm)=0.131677, mflops=37.9717 (err=9.5e-16) 26. Ransom: elapsed time t=1.15043 s, 4096 iters, t-(init.)=1.12813 s t(norm)=0.134484, mflops=37.1791 (err=1.7e-15) 27. Singleton (f2c): elapsed time t=1.73861 s, 16384 iters, t-(init.)=1.65199 s t(norm)=0.049233, mflops=101.558 (err=1.3e-15) 28. Temperton (f2c): elapsed time t=1.89924 s, 4096 iters, t-(init.)=1.87751 s t(norm)=0.223817, mflops=22.3397 (err=7.5e-16) 29. Valkenburg: elapsed time t=1.32243 s, 1024 iters, t-(init.)=1.31696 s t(norm)=0.627975, mflops=7.9621 (err=7.4e-16) Top mflops for N=256 = 150.366 Normalized results and averages for N=256: fft 0: mflops = 61.4429 (norm. = 0.408621), norm. avg. (of 8) = 0.427072 fft 1: mflops = 59.5489 (norm. = 0.396025), norm. avg. (of 8) = 0.41272 fft 2: mflops = 45.9479 (norm. = 0.305573), norm. avg. (of 8) = 0.264648 fft 3: mflops = 20.1768 (norm. = 0.134184), norm. avg. (of 8) = 0.0750436 fft 4: mflops = 10.5618 (norm. = 0.0702402), norm. avg. (of 8) = 0.0713187 fft 5: mflops = 85.539 (norm. = 0.56887), norm. avg. (of 8) = 0.32931 fft 6: mflops = 88.0589 (norm. = 0.585628), norm. avg. (of 8) = 0.348866 fft 7: mflops = 115.807 (norm. = 0.770168), norm. avg. (of 8) = 0.393308 fft 8: mflops = 32.5356 (norm. = 0.216375), norm. avg. (of 7) = 0.174122 fft 9: mflops = 36.4731 (norm. = 0.242561), norm. avg. (of 8) = 0.1972 fft 10: mflops = 146.916 (norm. = 0.977051), norm. avg. (of 8) = 0.676463 fft 11: mflops = 146.89 (norm. = 0.976882), norm. avg. (of 8) = 0.665546 fft 12: mflops = 140.949 (norm. = 0.937369), norm. avg. (of 8) = 0.962351 fft 13: mflops = 150.366 (norm. = 1), norm. avg. (of 6) = 0.750581 fft 14: mflops = 69.2882 (norm. = 0.460796), norm. avg. (of 8) = 0.334218 fft 15: mflops = 48.3583 (norm. = 0.321603), norm. avg. (of 8) = 0.19529 fft 16: mflops = 52.5775 (norm. = 0.349663), norm. avg. (of 8) = 0.203064 fft 17: mflops = 29.4958 (norm. = 0.196159), norm. avg. (of 8) = 0.434366 fft 18: mflops = 55.5819 (norm. = 0.369643), norm. avg. (of 7) = 0.298982 fft 19: mflops = 75.7733 (norm. = 0.503924), norm. avg. (of 7) = 0.377876 fft 20: mflops = 77.7672 (norm. = 0.517184), norm. avg. (of 7) = 0.376695 fft 21: mflops = 18.5496 (norm. = 0.123362), norm. avg. (of 8) = 0.0845108 fft 22: mflops = 30.5533 (norm. = 0.203192), norm. avg. (of 8) = 0.126796 fft 23: mflops = 56.1585 (norm. = 0.373478), norm. avg. (of 8) = 0.232395 fft 24: mflops = 126.385 (norm. = 0.840512), norm. avg. (of 8) = 0.629015 fft 25: mflops = 37.9717 (norm. = 0.252527), norm. avg. (of 5) = 0.265906 fft 26: mflops = 37.1791 (norm. = 0.247257), norm. avg. (of 7) = 0.112861 fft 27: mflops = 101.558 (norm. = 0.675403), norm. avg. (of 8) = 0.347291 fft 28: mflops = 22.3397 (norm. = 0.148568), norm. avg. (of 8) = 0.109556 fft 29: mflops = 7.9621 (norm. = 0.0529513), norm. avg. (of 8) = 0.0690523 Benchmarking for array size = 512 (power of 2): 0. Arndt DIF: elapsed time t=1.48999 s, 4096 iters, t-(init.)=1.44637 s t(norm)=0.0766315, mflops=65.2473 (err=6.7e-16) 1. Arndt DIT: elapsed time t=1.52472 s, 4096 iters, t-(init.)=1.48151 s t(norm)=0.0784932, mflops=63.6998 (err=6.2e-16) 2. Arndt Split-Radix: elapsed time t=1.96543 s, 4096 iters, t-(init.)=1.92192 s t(norm)=0.101827, mflops=49.1028 (err=6.5e-16) 3. Arndt 4-step: elapsed time t=1.12482 s, 1024 iters, t-(init.)=1.11373 s t(norm)=0.236029, mflops=21.1838 (err=6.3e-16) 4. Beauregard: elapsed time t=1.13347 s, 512 iters, t-(init.)=1.12797 s t(norm)=0.478094, mflops=10.4582 (err=6.8e-16) 5. Bergland: elapsed time t=1.07298 s, 4096 iters, t-(init.)=1.02961 s t(norm)=0.0545506, mflops=91.658 (err=7.2e-16) 6. CWP (min N) (N=520): elapsed time t=1.09176 s, 4096 iters, t-(init.)=1.04783 s t(norm)=0.0555163, mflops=90.0636 7. CWP (best N) (N=560): elapsed time t=1.79618 s, 8192 iters, t-(init.)=1.70097 s t(norm)=0.0450604, mflops=110.962 8. Edelblute: elapsed time t=1.36761 s, 2048 iters, t-(init.)=1.34568 s t(norm)=0.142593, mflops=35.0647 (err=6.2e-16) 9. FFTPACK (f2c): elapsed time t=1.10357 s, 1024 iters, t-(init.)=1.09263 s t(norm)=0.231559, mflops=21.5928 (err=6.4e-16) FFTW_MEASURE plan: (cost = 3.834375e-04) FFTW_TWIDDLE 16 FFTW_NOTW 32 10. FFTW: elapsed time t=1.57109 s, 4096 iters, t-(init.)=1.52763 s t(norm)=0.0809369, mflops=61.7766 (err=6.5e-16) FFTW_ESTIMATE plan: (cost = 1.843200e+03) FFTW_TWIDDLE 16 FFTW_NOTW 32 11. FFTW_ESTIMATE: elapsed time t=1.623 s, 4096 iters, t-(init.)=1.57914 s t(norm)=0.083666, mflops=59.7615 (err=6.5e-16) 12. Frigo-old: elapsed time t=1.66786 s, 4096 iters, t-(init.)=1.62422 s t(norm)=0.0860542, mflops=58.1029 (err=6.3e-16) 13. Green: elapsed time t=1.25814 s, 8192 iters, t-(init.)=1.17129 s t(norm)=0.0310286, mflops=161.142 (err=6.2e-16) 14. GSL: elapsed time t=1.29567 s, 2048 iters, t-(init.)=1.27385 s t(norm)=0.134982, mflops=37.0419 (err=6.4e-16) 15. GSL DIT: elapsed time t=1.93561 s, 4096 iters, t-(init.)=1.89225 s t(norm)=0.100255, mflops=49.8727 (err=9.0e-16) 16. GSL DIF: elapsed time t=1.74956 s, 4096 iters, t-(init.)=1.706 s t(norm)=0.0903871, mflops=55.3176 (err=7.8e-16) 17. Krukar: elapsed time t=1.98533 s, 2048 iters, t-(init.)=1.96354 s t(norm)=0.208065, mflops=24.031 (err=6.9e-16) 18. Mayer (Buneman): elapsed time t=1.64527 s, 4096 iters, t-(init.)=1.60183 s t(norm)=0.0848682, mflops=58.9149 (err=6.5e-16) 19. Mayer (simple): elapsed time t=1.22538 s, 4096 iters, t-(init.)=1.1818 s t(norm)=0.0626138, mflops=79.8546 20. Mayer (lookup): elapsed time t=1.19869 s, 4096 iters, t-(init.)=1.15513 s t(norm)=0.0612008, mflops=81.6982 (err=6.5e-16) 21. NAPACK (f2c): elapsed time t=1.47518 s, 1024 iters, t-(init.)=1.46423 s t(norm)=0.310311, mflops=16.1129 (err=6.7e-15) 22. Nielsen: elapsed time t=1.64314 s, 2048 iters, t-(init.)=1.62141 s t(norm)=0.171811, mflops=29.1017 (err=3.2e-15) 23. NR (C): elapsed time t=1.65808 s, 4096 iters, t-(init.)=1.61423 s t(norm)=0.085525, mflops=58.4624 (err=7.1e-16) 24. Ooura (C): elapsed time t=1.64552 s, 8192 iters, t-(init.)=1.55839 s t(norm)=0.0412833, mflops=121.114 (err=6.9e-16) 25. QFT: elapsed time t=1.12244 s, 1024 iters, t-(init.)=1.11158 s t(norm)=0.235575, mflops=21.2247 (err=9.5e-16) 26. Ransom: elapsed time t=1.35957 s, 2048 iters, t-(init.)=1.33776 s t(norm)=0.141754, mflops=35.2723 (err=1.5e-15) 27. Singleton (f2c): elapsed time t=1.93358 s, 8192 iters, t-(init.)=1.84686 s t(norm)=0.048925, mflops=102.197 (err=8.4e-16) 28. Temperton (f2c): elapsed time t=1.21067 s, 1024 iters, t-(init.)=1.19947 s t(norm)=0.254201, mflops=19.6695 (err=6.4e-16) 29. Valkenburg: elapsed time t=1.64589 s, 512 iters, t-(init.)=1.64038 s t(norm)=0.695285, mflops=7.1913 (err=7.4e-16) Top mflops for N=512 = 161.142 Normalized results and averages for N=512: fft 0: mflops = 65.2473 (norm. = 0.404906), norm. avg. (of 9) = 0.424609 fft 1: mflops = 63.6998 (norm. = 0.395303), norm. avg. (of 9) = 0.410785 fft 2: mflops = 49.1028 (norm. = 0.304718), norm. avg. (of 9) = 0.2691 fft 3: mflops = 21.1838 (norm. = 0.131461), norm. avg. (of 9) = 0.0813122 fft 4: mflops = 10.4582 (norm. = 0.0649006), norm. avg. (of 9) = 0.0706056 fft 5: mflops = 91.658 (norm. = 0.568804), norm. avg. (of 9) = 0.35592 fft 6: mflops = 90.0636 (norm. = 0.55891), norm. avg. (of 9) = 0.372204 fft 7: mflops = 110.962 (norm. = 0.6886), norm. avg. (of 9) = 0.426118 fft 8: mflops = 35.0647 (norm. = 0.217602), norm. avg. (of 8) = 0.179557 fft 9: mflops = 21.5928 (norm. = 0.133999), norm. avg. (of 9) = 0.190177 fft 10: mflops = 61.7766 (norm. = 0.383368), norm. avg. (of 9) = 0.643896 fft 11: mflops = 59.7615 (norm. = 0.370863), norm. avg. (of 9) = 0.632803 fft 12: mflops = 58.1029 (norm. = 0.36057), norm. avg. (of 9) = 0.895486 fft 13: mflops = 161.142 (norm. = 1), norm. avg. (of 7) = 0.786212 fft 14: mflops = 37.0419 (norm. = 0.229872), norm. avg. (of 9) = 0.322624 fft 15: mflops = 49.8727 (norm. = 0.309496), norm. avg. (of 9) = 0.20798 fft 16: mflops = 55.3176 (norm. = 0.343285), norm. avg. (of 9) = 0.218644 fft 17: mflops = 24.031 (norm. = 0.14913), norm. avg. (of 9) = 0.402673 fft 18: mflops = 58.9149 (norm. = 0.365609), norm. avg. (of 8) = 0.30731 fft 19: mflops = 79.8546 (norm. = 0.495555), norm. avg. (of 8) = 0.392586 fft 20: mflops = 81.6982 (norm. = 0.506996), norm. avg. (of 8) = 0.392983 fft 21: mflops = 16.1129 (norm. = 0.0999918), norm. avg. (of 9) = 0.0862309 fft 22: mflops = 29.1017 (norm. = 0.180597), norm. avg. (of 9) = 0.132774 fft 23: mflops = 58.4624 (norm. = 0.362801), norm. avg. (of 9) = 0.246885 fft 24: mflops = 121.114 (norm. = 0.751602), norm. avg. (of 9) = 0.642636 fft 25: mflops = 21.2247 (norm. = 0.131714), norm. avg. (of 6) = 0.24354 fft 26: mflops = 35.2723 (norm. = 0.21889), norm. avg. (of 8) = 0.126115 fft 27: mflops = 102.197 (norm. = 0.634207), norm. avg. (of 9) = 0.37917 fft 28: mflops = 19.6695 (norm. = 0.122063), norm. avg. (of 9) = 0.110946 fft 29: mflops = 7.1913 (norm. = 0.0446272), norm. avg. (of 9) = 0.0663384 Benchmarking for array size = 1024 (power of 2): 0. Arndt DIF: elapsed time t=1.89961 s, 2048 iters, t-(init.)=1.85056 s t(norm)=0.0882418, mflops=56.6625 (err=1.0e-15) 1. Arndt DIT: elapsed time t=1.03177 s, 1024 iters, t-(init.)=1.0075 s t(norm)=0.0960823, mflops=52.0387 (err=1.0e-15) 2. Arndt Split-Radix: elapsed time t=1.30094 s, 1024 iters, t-(init.)=1.27585 s t(norm)=0.121674, mflops=41.0933 (err=1.0e-15) 3. Arndt 4-step: elapsed time t=1.33062 s, 512 iters, t-(init.)=1.31809 s t(norm)=0.251406, mflops=19.8882 (err=1.0e-15) 4. Beauregard: elapsed time t=1.33564 s, 256 iters, t-(init.)=1.32901 s t(norm)=0.506978, mflops=9.86236 (err=1.1e-15) 5. Bergland: elapsed time t=1.53244 s, 2048 iters, t-(init.)=1.48306 s t(norm)=0.0707179, mflops=70.7035 (err=1.1e-15) 6. CWP (min N) (N=1040): elapsed time t=1.50021 s, 2048 iters, t-(init.)=1.42006 s t(norm)=0.0677135, mflops=73.8405 7. CWP (best N) (N=1040): elapsed time t=1.50325 s, 2048 iters, t-(init.)=1.42266 s t(norm)=0.0678377, mflops=73.7053 8. Edelblute: elapsed time t=1.73407 s, 1024 iters, t-(init.)=1.70963 s t(norm)=0.163043, mflops=30.6667 (err=1.0e-15) 9. FFTPACK (f2c): elapsed time t=1.82673 s, 512 iters, t-(init.)=1.81402 s t(norm)=0.345997, mflops=14.451 (err=1.1e-15) FFTW_MEASURE plan: (cost = 1.235734e-03) FFTW_TWIDDLE 8 FFTW_TWIDDLE 8 FFTW_NOTW 16 10. FFTW: elapsed time t=1.35329 s, 1024 iters, t-(init.)=1.3278 s t(norm)=0.126629, mflops=39.4855 (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=1.3545 s, 1024 iters, t-(init.)=1.32995 s t(norm)=0.126834, mflops=39.4215 (err=1.1e-15) 12. Frigo-old: elapsed time t=1.8462 s, 1024 iters, t-(init.)=1.82105 s t(norm)=0.173669, mflops=28.7904 (err=1.1e-15) 13. Green: elapsed time t=1.25528 s, 2048 iters, t-(init.)=1.2061 s t(norm)=0.0575116, mflops=86.939 (err=1.1e-15) 14. GSL: elapsed time t=1.34973 s, 512 iters, t-(init.)=1.33698 s t(norm)=0.255009, mflops=19.6072 (err=1.1e-15) 15. GSL DIT: elapsed time t=1.23485 s, 1024 iters, t-(init.)=1.20976 s t(norm)=0.115372, mflops=43.3382 (err=1.3e-15) 16. GSL DIF: elapsed time t=1.1455 s, 1024 iters, t-(init.)=1.12133 s t(norm)=0.106938, mflops=46.7559 (err=1.4e-15) 17. Krukar: elapsed time t=1.31596 s, 512 iters, t-(init.)=1.30363 s t(norm)=0.248647, mflops=20.1088 (err=1.1e-15) 18. Mayer (Buneman): elapsed time t=1.86652 s, 2048 iters, t-(init.)=1.81717 s t(norm)=0.0866494, mflops=57.7038 (err=1.0e-15) 19. Mayer (simple): elapsed time t=1.40316 s, 2048 iters, t-(init.)=1.35378 s t(norm)=0.0645535, mflops=77.4552 20. Mayer (lookup): elapsed time t=1.7221 s, 2048 iters, t-(init.)=1.67194 s t(norm)=0.0797243, mflops=62.7162 (err=1.0e-15) 21. NAPACK (f2c): elapsed time t=1.5272 s, 256 iters, t-(init.)=1.52102 s t(norm)=0.580223, mflops=8.61737 (err=1.6e-14) 22. Nielsen: elapsed time t=1.3871 s, 512 iters, t-(init.)=1.3743 s t(norm)=0.262128, mflops=19.0747 (err=7.2e-15) 23. NR (C): elapsed time t=1.05749 s, 1024 iters, t-(init.)=1.03216 s t(norm)=0.0984348, mflops=50.795 (err=1.2e-15) 24. Ooura (C): elapsed time t=1.3876 s, 2048 iters, t-(init.)=1.33868 s t(norm)=0.0638335, mflops=78.3288 (err=1.1e-15) 25. QFT: elapsed time t=1.64206 s, 512 iters, t-(init.)=1.6296 s t(norm)=0.310822, mflops=16.0864 (err=1.4e-15) 26. Ransom: elapsed time t=1.43756 s, 1024 iters, t-(init.)=1.41256 s t(norm)=0.134712, mflops=37.1162 (err=2.1e-15) 27. Singleton (f2c): elapsed time t=1.25538 s, 2048 iters, t-(init.)=1.20561 s t(norm)=0.0574881, mflops=86.9745 (err=1.6e-15) 28. Temperton (f2c): elapsed time t=1.57981 s, 512 iters, t-(init.)=1.56709 s t(norm)=0.298899, mflops=16.7281 (err=1.1e-15) 29. Valkenburg: elapsed time t=1.11341 s, 128 iters, t-(init.)=1.11032 s t(norm)=0.847104, mflops=5.90246 (err=1.1e-15) Top mflops for N=1024 = 86.9745 Normalized results and averages for N=1024: fft 0: mflops = 56.6625 (norm. = 0.651484), norm. avg. (of 10) = 0.447297 fft 1: mflops = 52.0387 (norm. = 0.598321), norm. avg. (of 10) = 0.429538 fft 2: mflops = 41.0933 (norm. = 0.472476), norm. avg. (of 10) = 0.289438 fft 3: mflops = 19.8882 (norm. = 0.228666), norm. avg. (of 10) = 0.0960476 fft 4: mflops = 9.86236 (norm. = 0.113394), norm. avg. (of 10) = 0.0748844 fft 5: mflops = 70.7035 (norm. = 0.812922), norm. avg. (of 10) = 0.40162 fft 6: mflops = 73.8405 (norm. = 0.84899), norm. avg. (of 10) = 0.419882 fft 7: mflops = 73.7053 (norm. = 0.847436), norm. avg. (of 10) = 0.46825 fft 8: mflops = 30.6667 (norm. = 0.352594), norm. avg. (of 9) = 0.198783 fft 9: mflops = 14.451 (norm. = 0.166152), norm. avg. (of 10) = 0.187775 fft 10: mflops = 39.4855 (norm. = 0.45399), norm. avg. (of 10) = 0.624906 fft 11: mflops = 39.4215 (norm. = 0.453253), norm. avg. (of 10) = 0.614848 fft 12: mflops = 28.7904 (norm. = 0.331021), norm. avg. (of 10) = 0.83904 fft 13: mflops = 86.939 (norm. = 0.999592), norm. avg. (of 8) = 0.812885 fft 14: mflops = 19.6072 (norm. = 0.225436), norm. avg. (of 10) = 0.312906 fft 15: mflops = 43.3382 (norm. = 0.498286), norm. avg. (of 10) = 0.23701 fft 16: mflops = 46.7559 (norm. = 0.537582), norm. avg. (of 10) = 0.250538 fft 17: mflops = 20.1088 (norm. = 0.231203), norm. avg. (of 10) = 0.385526 fft 18: mflops = 57.7038 (norm. = 0.663456), norm. avg. (of 9) = 0.346882 fft 19: mflops = 77.4552 (norm. = 0.89055), norm. avg. (of 9) = 0.447915 fft 20: mflops = 62.7162 (norm. = 0.721087), norm. avg. (of 9) = 0.429439 fft 21: mflops = 8.61737 (norm. = 0.0990793), norm. avg. (of 10) = 0.0875157 fft 22: mflops = 19.0747 (norm. = 0.219313), norm. avg. (of 10) = 0.141428 fft 23: mflops = 50.795 (norm. = 0.584022), norm. avg. (of 10) = 0.280598 fft 24: mflops = 78.3288 (norm. = 0.900595), norm. avg. (of 10) = 0.668432 fft 25: mflops = 16.0864 (norm. = 0.184955), norm. avg. (of 7) = 0.235171 fft 26: mflops = 37.1162 (norm. = 0.426748), norm. avg. (of 9) = 0.159519 fft 27: mflops = 86.9745 (norm. = 1), norm. avg. (of 10) = 0.441253 fft 28: mflops = 16.7281 (norm. = 0.192333), norm. avg. (of 10) = 0.119085 fft 29: mflops = 5.90246 (norm. = 0.0678643), norm. avg. (of 10) = 0.066491 Benchmarking for array size = 2048 (power of 2): 0. Arndt DIF: elapsed time t=1.32234 s, 128 iters, t-(init.)=1.26135 s t(norm)=0.437423, mflops=11.4306 (err=1.4e-15) 1. Arndt DIT: elapsed time t=1.3477 s, 128 iters, t-(init.)=1.28715 s t(norm)=0.446373, mflops=11.2014 (err=1.4e-15) 2. Arndt Split-Radix: elapsed time t=1.77255 s, 128 iters, t-(init.)=1.71166 s t(norm)=0.593587, mflops=8.42336 (err=1.4e-15) 3. Arndt 4-step: elapsed time t=1.16579 s, 128 iters, t-(init.)=1.105 s t(norm)=0.383205, mflops=13.0478 (err=1.4e-15) 4. Beauregard: elapsed time t=1.92554 s, 128 iters, t-(init.)=1.86475 s t(norm)=0.64668, mflops=7.7318 (err=1.5e-15) 5. Bergland: elapsed time t=1.37935 s, 256 iters, t-(init.)=1.25619 s t(norm)=0.217818, mflops=22.9549 (err=1.5e-15) 6. CWP (min N) (N=2145): elapsed time t=1.60556 s, 512 iters, t-(init.)=1.35124 s t(norm)=0.117149, mflops=42.6806 7. CWP (best N) (N=2184): elapsed time t=1.62485 s, 512 iters, t-(init.)=1.36603 s t(norm)=0.118432, mflops=42.2184 8. Edelblute: elapsed time t=1.87277 s, 128 iters, t-(init.)=1.81221 s t(norm)=0.628456, mflops=7.95601 (err=1.4e-15) 9. FFTPACK (f2c): elapsed time t=1.96878 s, 256 iters, t-(init.)=1.84716 s t(norm)=0.320289, mflops=15.6109 (err=1.5e-15) FFTW_MEASURE plan: (cost = 2.759031e-03) FFTW_TWIDDLE 4 FFTW_TWIDDLE 4 FFTW_TWIDDLE 4 FFTW_NOTW 32 10. FFTW: elapsed time t=1.4696 s, 512 iters, t-(init.)=1.22658 s t(norm)=0.106342, mflops=47.0182 (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=1.763 s, 512 iters, t-(init.)=1.52025 s t(norm)=0.131802, mflops=37.9356 (err=1.5e-15) 12. Frigo-old: elapsed time t=1.23323 s, 256 iters, t-(init.)=1.11174 s t(norm)=0.192771, mflops=25.9375 (err=1.5e-15) 13. Green: elapsed time t=1.24697 s, 256 iters, t-(init.)=1.12485 s t(norm)=0.195045, mflops=25.6352 (err=1.5e-15) 14. GSL: elapsed time t=1.46645 s, 256 iters, t-(init.)=1.3451 s t(norm)=0.233234, mflops=21.4377 (err=1.5e-15) 15. GSL DIT: elapsed time t=1.3316 s, 128 iters, t-(init.)=1.27012 s t(norm)=0.440467, mflops=11.3516 (err=2.1e-15) 16. GSL DIF: elapsed time t=1.35745 s, 128 iters, t-(init.)=1.29685 s t(norm)=0.449737, mflops=11.1176 (err=2.2e-15) 17. Krukar: elapsed time t=1.74732 s, 256 iters, t-(init.)=1.62552 s t(norm)=0.281857, mflops=17.7395 (err=1.5e-15) 18. Mayer (Buneman): elapsed time t=1.43983 s, 512 iters, t-(init.)=1.19671 s t(norm)=0.103752, mflops=48.1918 (err=1.4e-15) 19. Mayer (simple): elapsed time t=1.16372 s, 512 iters, t-(init.)=0.921325 s t(norm)=0.0798767, mflops=62.5965 20. Mayer (lookup): elapsed time t=1.58343 s, 512 iters, t-(init.)=1.34054 s t(norm)=0.116222, mflops=43.0212 (err=1.4e-15) 21. NAPACK (f2c): elapsed time t=1.81122 s, 128 iters, t-(init.)=1.75044 s t(norm)=0.607036, mflops=8.23674 (err=1.5e-14) 22. Nielsen: elapsed time t=1.28723 s, 128 iters, t-(init.)=1.22648 s t(norm)=0.425333, mflops=11.7555 (err=1.2e-14) 23. NR (C): elapsed time t=1.29111 s, 128 iters, t-(init.)=1.22959 s t(norm)=0.426411, mflops=11.7258 (err=1.6e-15) 24. Ooura (C): elapsed time t=1.08632 s, 256 iters, t-(init.)=0.964844 s t(norm)=0.167299, mflops=29.8865 (err=1.4e-15) 25. QFT: elapsed time t=1.09779 s, 128 iters, t-(init.)=1.03698 s t(norm)=0.359614, mflops=13.9038 (err=1.9e-15) 26. Ransom: elapsed time t=1.7601 s, 256 iters, t-(init.)=1.63864 s t(norm)=0.284132, mflops=17.5975 (err=2.6e-15) 27. Singleton (f2c): elapsed time t=1.82764 s, 256 iters, t-(init.)=1.70611 s t(norm)=0.295832, mflops=16.9015 (err=2.0e-15) 28. Temperton (f2c): elapsed time t=1.21389 s, 128 iters, t-(init.)=1.15328 s t(norm)=0.399948, mflops=12.5016 (err=1.5e-15) 29. Valkenburg: elapsed time t=1.3531 s, 64 iters, t-(init.)=1.32268 s t(norm)=0.917388, mflops=5.45026 (err=1.5e-15) Top mflops for N=2048 = 62.5965 Normalized results and averages for N=2048: fft 0: mflops = 11.4306 (norm. = 0.182607), norm. avg. (of 11) = 0.423234 fft 1: mflops = 11.2014 (norm. = 0.178946), norm. avg. (of 11) = 0.406757 fft 2: mflops = 8.42336 (norm. = 0.134566), norm. avg. (of 11) = 0.275358 fft 3: mflops = 13.0478 (norm. = 0.208444), norm. avg. (of 11) = 0.106265 fft 4: mflops = 7.7318 (norm. = 0.123518), norm. avg. (of 11) = 0.0793057 fft 5: mflops = 22.9549 (norm. = 0.366713), norm. avg. (of 11) = 0.398447 fft 6: mflops = 42.6806 (norm. = 0.681837), norm. avg. (of 11) = 0.443697 fft 7: mflops = 42.2184 (norm. = 0.674454), norm. avg. (of 11) = 0.486996 fft 8: mflops = 7.95601 (norm. = 0.1271), norm. avg. (of 10) = 0.191615 fft 9: mflops = 15.6109 (norm. = 0.249389), norm. avg. (of 11) = 0.193376 fft 10: mflops = 47.0182 (norm. = 0.751132), norm. avg. (of 11) = 0.636381 fft 11: mflops = 37.9356 (norm. = 0.606034), norm. avg. (of 11) = 0.614047 fft 12: mflops = 25.9375 (norm. = 0.414361), norm. avg. (of 11) = 0.800433 fft 13: mflops = 25.6352 (norm. = 0.409531), norm. avg. (of 9) = 0.768068 fft 14: mflops = 21.4377 (norm. = 0.342475), norm. avg. (of 11) = 0.315594 fft 15: mflops = 11.3516 (norm. = 0.181345), norm. avg. (of 11) = 0.23195 fft 16: mflops = 11.1176 (norm. = 0.177608), norm. avg. (of 11) = 0.243908 fft 17: mflops = 17.7395 (norm. = 0.283395), norm. avg. (of 11) = 0.376241 fft 18: mflops = 48.1918 (norm. = 0.76988), norm. avg. (of 10) = 0.389182 fft 19: mflops = 62.5965 (norm. = 1), norm. avg. (of 10) = 0.503124 fft 20: mflops = 43.0212 (norm. = 0.687278), norm. avg. (of 10) = 0.455223 fft 21: mflops = 8.23674 (norm. = 0.131585), norm. avg. (of 11) = 0.091522 fft 22: mflops = 11.7555 (norm. = 0.187798), norm. avg. (of 11) = 0.145643 fft 23: mflops = 11.7258 (norm. = 0.187323), norm. avg. (of 11) = 0.272119 fft 24: mflops = 29.8865 (norm. = 0.477448), norm. avg. (of 11) = 0.651069 fft 25: mflops = 13.9038 (norm. = 0.222118), norm. avg. (of 8) = 0.233539 fft 26: mflops = 17.5975 (norm. = 0.281125), norm. avg. (of 10) = 0.171679 fft 27: mflops = 16.9015 (norm. = 0.270007), norm. avg. (of 11) = 0.425685 fft 28: mflops = 12.5016 (norm. = 0.199718), norm. avg. (of 11) = 0.126415 fft 29: mflops = 5.45026 (norm. = 0.0870698), norm. avg. (of 11) = 0.0683618 Benchmarking for array size = 4096 (power of 2): 0. Arndt DIF: elapsed time t=1.66961 s, 64 iters, t-(init.)=1.60419 s t(norm)=0.50996, mflops=9.80469 (err=2.5e-15) 1. Arndt DIT: elapsed time t=1.67779 s, 64 iters, t-(init.)=1.61224 s t(norm)=0.512519, mflops=9.75574 (err=2.5e-15) 2. Arndt Split-Radix: elapsed time t=1.09577 s, 32 iters, t-(init.)=1.06369 s t(norm)=0.676275, mflops=7.39345 (err=2.5e-15) 3. Arndt 4-step: elapsed time t=1.23374 s, 64 iters, t-(init.)=1.16957 s t(norm)=0.371796, mflops=13.4482 (err=2.5e-15) 4. Beauregard: elapsed time t=1.08193 s, 32 iters, t-(init.)=1.05007 s t(norm)=0.667615, mflops=7.48935 (err=2.6e-15) 5. Bergland: elapsed time t=1.4571 s, 128 iters, t-(init.)=1.32808 s t(norm)=0.211093, mflops=23.6863 (err=2.5e-15) 6. CWP (min N) (N=4290): elapsed time t=1.06774 s, 128 iters, t-(init.)=0.93372 s t(norm)=0.148411, mflops=33.6903 7. CWP (best N) (N=4368): elapsed time t=1.83391 s, 256 iters, t-(init.)=1.56236 s t(norm)=0.124165, mflops=40.269 8. Edelblute: elapsed time t=1.14663 s, 32 iters, t-(init.)=1.11439 s t(norm)=0.708509, mflops=7.05707 (err=2.5e-15) 9. FFTPACK (f2c): elapsed time t=1.12795 s, 64 iters, t-(init.)=1.06373 s t(norm)=0.338152, mflops=14.7863 (err=2.6e-15) FFTW_MEASURE plan: (cost = 6.806500e-03) FFTW_TWIDDLE 2 FFTW_TWIDDLE 4 FFTW_TWIDDLE 16 FFTW_NOTW 32 10. FFTW: elapsed time t=1.82873 s, 256 iters, t-(init.)=1.57256 s t(norm)=0.124976, mflops=40.0077 (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=1.87018 s, 256 iters, t-(init.)=1.61387 s t(norm)=0.128259, mflops=38.9837 (err=2.6e-15) 12. Frigo-old: elapsed time t=1.3764 s, 128 iters, t-(init.)=1.24783 s t(norm)=0.198337, mflops=25.2096 (err=2.6e-15) 13. Green: elapsed time t=1.31348 s, 128 iters, t-(init.)=1.18532 s t(norm)=0.188402, mflops=26.539 (err=2.6e-15) 14. GSL: elapsed time t=1.5657 s, 128 iters, t-(init.)=1.43733 s t(norm)=0.228458, mflops=21.8859 (err=2.6e-15) 15. GSL DIT: elapsed time t=1.56021 s, 64 iters, t-(init.)=1.4953 s t(norm)=0.475342, mflops=10.5187 (err=3.0e-15) 16. GSL DIF: elapsed time t=1.56706 s, 64 iters, t-(init.)=1.50279 s t(norm)=0.477725, mflops=10.4663 (err=3.1e-15) 17. Krukar: elapsed time t=1.96861 s, 128 iters, t-(init.)=1.84018 s t(norm)=0.292489, mflops=17.0947 (err=2.6e-15) 18. Mayer (Buneman): elapsed time t=1.25587 s, 64 iters, t-(init.)=1.19185 s t(norm)=0.37888, mflops=13.1968 (err=2.5e-15) 19. Mayer (simple): elapsed time t=1.19431 s, 64 iters, t-(init.)=1.13023 s t(norm)=0.359292, mflops=13.9163 20. Mayer (lookup): elapsed time t=1.25256 s, 64 iters, t-(init.)=1.18827 s t(norm)=0.377741, mflops=13.2366 (err=2.5e-15) 21. NAPACK (f2c): elapsed time t=1.95569 s, 64 iters, t-(init.)=1.89157 s t(norm)=0.601314, mflops=8.31512 (err=4.7e-14) 22. Nielsen: elapsed time t=1.35039 s, 64 iters, t-(init.)=1.28593 s t(norm)=0.408786, mflops=12.2313 (err=2.2e-14) 23. NR (C): elapsed time t=1.52435 s, 64 iters, t-(init.)=1.4599 s t(norm)=0.46409, mflops=10.7738 (err=2.6e-15) 24. Ooura (C): elapsed time t=1.17906 s, 128 iters, t-(init.)=1.04993 s t(norm)=0.166882, mflops=29.9614 (err=2.5e-15) 25. QFT: elapsed time t=1.42194 s, 64 iters, t-(init.)=1.35659 s t(norm)=0.43125, mflops=11.5942 (err=3.1e-15) 26. Ransom: elapsed time t=1.41858 s, 128 iters, t-(init.)=1.28929 s t(norm)=0.204927, mflops=24.3989 (err=3.1e-15) 27. Singleton (f2c): elapsed time t=1.68117 s, 128 iters, t-(init.)=1.5515 s t(norm)=0.246605, mflops=20.2754 (err=3.8e-15) 28. Temperton (f2c): elapsed time t=1.27307 s, 64 iters, t-(init.)=1.20886 s t(norm)=0.384287, mflops=13.0111 (err=2.6e-15) 29. Valkenburg: elapsed time t=1.55424 s, 32 iters, t-(init.)=1.52214 s t(norm)=0.967752, mflops=5.16661 (err=2.5e-15) Top mflops for N=4096 = 40.269 Normalized results and averages for N=4096: fft 0: mflops = 9.80469 (norm. = 0.24348), norm. avg. (of 12) = 0.408255 fft 1: mflops = 9.75574 (norm. = 0.242265), norm. avg. (of 12) = 0.393049 fft 2: mflops = 7.39345 (norm. = 0.183602), norm. avg. (of 12) = 0.267712 fft 3: mflops = 13.4482 (norm. = 0.33396), norm. avg. (of 12) = 0.12524 fft 4: mflops = 7.48935 (norm. = 0.185983), norm. avg. (of 12) = 0.0881955 fft 5: mflops = 23.6863 (norm. = 0.588202), norm. avg. (of 12) = 0.41426 fft 6: mflops = 33.6903 (norm. = 0.836631), norm. avg. (of 12) = 0.476441 fft 7: mflops = 40.269 (norm. = 1), norm. avg. (of 12) = 0.529746 fft 8: mflops = 7.05707 (norm. = 0.175248), norm. avg. (of 11) = 0.190127 fft 9: mflops = 14.7863 (norm. = 0.367187), norm. avg. (of 12) = 0.207861 fft 10: mflops = 40.0077 (norm. = 0.993512), norm. avg. (of 12) = 0.666142 fft 11: mflops = 38.9837 (norm. = 0.968082), norm. avg. (of 12) = 0.64355 fft 12: mflops = 25.2096 (norm. = 0.62603), norm. avg. (of 12) = 0.785899 fft 13: mflops = 26.539 (norm. = 0.659043), norm. avg. (of 10) = 0.757165 fft 14: mflops = 21.8859 (norm. = 0.543492), norm. avg. (of 12) = 0.334585 fft 15: mflops = 10.5187 (norm. = 0.261212), norm. avg. (of 12) = 0.234388 fft 16: mflops = 10.4663 (norm. = 0.259909), norm. avg. (of 12) = 0.245241 fft 17: mflops = 17.0947 (norm. = 0.424512), norm. avg. (of 12) = 0.380264 fft 18: mflops = 13.1968 (norm. = 0.327716), norm. avg. (of 11) = 0.383594 fft 19: mflops = 13.9163 (norm. = 0.345583), norm. avg. (of 11) = 0.488802 fft 20: mflops = 13.2366 (norm. = 0.328704), norm. avg. (of 11) = 0.443721 fft 21: mflops = 8.31512 (norm. = 0.206489), norm. avg. (of 12) = 0.101103 fft 22: mflops = 12.2313 (norm. = 0.303741), norm. avg. (of 12) = 0.158818 fft 23: mflops = 10.7738 (norm. = 0.267545), norm. avg. (of 12) = 0.271738 fft 24: mflops = 29.9614 (norm. = 0.744031), norm. avg. (of 12) = 0.658816 fft 25: mflops = 11.5942 (norm. = 0.287919), norm. avg. (of 9) = 0.239582 fft 26: mflops = 24.3989 (norm. = 0.605899), norm. avg. (of 11) = 0.211154 fft 27: mflops = 20.2754 (norm. = 0.503499), norm. avg. (of 12) = 0.43217 fft 28: mflops = 13.0111 (norm. = 0.323105), norm. avg. (of 12) = 0.142806 fft 29: mflops = 5.16661 (norm. = 0.128302), norm. avg. (of 12) = 0.0733569 Benchmarking for array size = 8192 (power of 2): 0. Arndt DIF: elapsed time t=1.73521 s, 32 iters, t-(init.)=1.67233 s t(norm)=0.490725, mflops=10.189 (err=3.0e-15) 1. Arndt DIT: elapsed time t=1.75855 s, 32 iters, t-(init.)=1.69549 s t(norm)=0.49752, mflops=10.0498 (err=3.0e-15) 2. Arndt Split-Radix: elapsed time t=1.18668 s, 16 iters, t-(init.)=1.15521 s t(norm)=0.677964, mflops=7.37502 (err=3.0e-15) 3. Arndt 4-step: elapsed time t=1.56561 s, 32 iters, t-(init.)=1.50257 s t(norm)=0.440913, mflops=11.3401 (err=2.9e-15) 4. Beauregard: elapsed time t=1.16912 s, 16 iters, t-(init.)=1.13754 s t(norm)=0.667598, mflops=7.48954 (err=2.9e-15) 5. Bergland: elapsed time t=1.70255 s, 64 iters, t-(init.)=1.57694 s t(norm)=0.231367, mflops=21.6107 (err=2.9e-15) 6. CWP (min N) (N=8580): elapsed time t=1.0793 s, 64 iters, t-(init.)=0.946206 s t(norm)=0.138827, mflops=36.0162 7. CWP (best N) (N=9240): elapsed time t=1.10571 s, 64 iters, t-(init.)=0.960026 s t(norm)=0.140854, mflops=35.4977 8. Edelblute: elapsed time t=1.23723 s, 16 iters, t-(init.)=1.20546 s t(norm)=0.707456, mflops=7.06758 (err=3.0e-15) 9. FFTPACK (f2c): elapsed time t=1.45205 s, 32 iters, t-(init.)=1.38881 s t(norm)=0.407531, mflops=12.269 (err=2.9e-15) FFTW_MEASURE plan: (cost = 1.616775e-02) FFTW_TWIDDLE 4 FFTW_TWIDDLE 4 FFTW_TWIDDLE 16 FFTW_NOTW 32 10. FFTW: elapsed time t=1.0956 s, 64 iters, t-(init.)=0.969562 s t(norm)=0.142253, mflops=35.1486 (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=1.15821 s, 64 iters, t-(init.)=1.0319 s t(norm)=0.151399, mflops=33.0252 (err=2.9e-15) 12. Frigo-old: elapsed time t=1.55554 s, 64 iters, t-(init.)=1.42922 s t(norm)=0.209694, mflops=23.8443 (err=2.9e-15) 13. Green: elapsed time t=1.51404 s, 64 iters, t-(init.)=1.38886 s t(norm)=0.203772, mflops=24.5372 (err=2.9e-15) 14. GSL: elapsed time t=1.10888 s, 32 iters, t-(init.)=1.04566 s t(norm)=0.306837, mflops=16.2953 (err=2.9e-15) 15. GSL DIT: elapsed time t=1.66256 s, 32 iters, t-(init.)=1.59987 s t(norm)=0.469462, mflops=10.6505 (err=3.6e-15) 16. GSL DIF: elapsed time t=1.66226 s, 32 iters, t-(init.)=1.59802 s t(norm)=0.46892, mflops=10.6628 (err=3.6e-15) 17. Skipping fft (Krukar can't handle N > 4096). 18. Mayer (Buneman): elapsed time t=1.33076 s, 32 iters, t-(init.)=1.26773 s t(norm)=0.372001, mflops=13.4408 (err=2.9e-15) 19. Mayer (simple): elapsed time t=1.2758 s, 32 iters, t-(init.)=1.21259 s t(norm)=0.35582, mflops=14.052 20. Mayer (lookup): elapsed time t=1.34859 s, 32 iters, t-(init.)=1.28558 s t(norm)=0.377239, mflops=13.2542 (err=3.0e-15) 21. NAPACK (f2c): elapsed time t=1.28339 s, 16 iters, t-(init.)=1.25144 s t(norm)=0.73444, mflops=6.80791 (err=4.3e-14) 22. Nielsen: elapsed time t=1.81459 s, 32 iters, t-(init.)=1.75012 s t(norm)=0.513552, mflops=9.73612 (err=1.1e-14) 23. NR (C): elapsed time t=1.6207 s, 32 iters, t-(init.)=1.55634 s t(norm)=0.456691, mflops=10.9483 (err=3.0e-15) 24. Ooura (C): elapsed time t=1.30772 s, 64 iters, t-(init.)=1.18221 s t(norm)=0.173453, mflops=28.8262 (err=2.9e-15) 25. QFT: elapsed time t=1.86498 s, 32 iters, t-(init.)=1.80143 s t(norm)=0.528608, mflops=9.45881 (err=4.0e-15) 26. Ransom: elapsed time t=1.8192 s, 64 iters, t-(init.)=1.69245 s t(norm)=0.248314, mflops=20.1358 (err=4.1e-15) 27. Singleton (f2c): elapsed time t=1.89307 s, 64 iters, t-(init.)=1.7666 s t(norm)=0.259193, mflops=19.2906 (err=4.4e-15) 28. Temperton (f2c): elapsed time t=1.48627 s, 32 iters, t-(init.)=1.42354 s t(norm)=0.41772, mflops=11.9697 (err=2.9e-15) 29. Valkenburg: elapsed time t=1.81711 s, 16 iters, t-(init.)=1.78537 s t(norm)=1.04779, mflops=4.77193 (err=2.9e-15) Top mflops for N=8192 = 36.0162 Normalized results and averages for N=8192: fft 0: mflops = 10.189 (norm. = 0.282901), norm. avg. (of 13) = 0.398612 fft 1: mflops = 10.0498 (norm. = 0.279037), norm. avg. (of 13) = 0.384279 fft 2: mflops = 7.37502 (norm. = 0.20477), norm. avg. (of 13) = 0.26287 fft 3: mflops = 11.3401 (norm. = 0.314861), norm. avg. (of 13) = 0.139826 fft 4: mflops = 7.48954 (norm. = 0.207949), norm. avg. (of 13) = 0.0974073 fft 5: mflops = 21.6107 (norm. = 0.600027), norm. avg. (of 13) = 0.42855 fft 6: mflops = 36.0162 (norm. = 1), norm. avg. (of 13) = 0.516715 fft 7: mflops = 35.4977 (norm. = 0.985605), norm. avg. (of 13) = 0.564812 fft 8: mflops = 7.06758 (norm. = 0.196234), norm. avg. (of 12) = 0.190636 fft 9: mflops = 12.269 (norm. = 0.340653), norm. avg. (of 13) = 0.218075 fft 10: mflops = 35.1486 (norm. = 0.975911), norm. avg. (of 13) = 0.68997 fft 11: mflops = 33.0252 (norm. = 0.916955), norm. avg. (of 13) = 0.664581 fft 12: mflops = 23.8443 (norm. = 0.662044), norm. avg. (of 13) = 0.776372 fft 13: mflops = 24.5372 (norm. = 0.681283), norm. avg. (of 11) = 0.750267 fft 14: mflops = 16.2953 (norm. = 0.452444), norm. avg. (of 13) = 0.343651 fft 15: mflops = 10.6505 (norm. = 0.295714), norm. avg. (of 13) = 0.239106 fft 16: mflops = 10.6628 (norm. = 0.296056), norm. avg. (of 13) = 0.24915 fft 17: mflops = -1 (norm. = -0.0277653), norm. avg. (of 12) = 0.380264 fft 18: mflops = 13.4408 (norm. = 0.373188), norm. avg. (of 12) = 0.382727 fft 19: mflops = 14.052 (norm. = 0.390159), norm. avg. (of 12) = 0.480582 fft 20: mflops = 13.2542 (norm. = 0.368007), norm. avg. (of 12) = 0.437411 fft 21: mflops = 6.80791 (norm. = 0.189024), norm. avg. (of 13) = 0.107866 fft 22: mflops = 9.73612 (norm. = 0.270326), norm. avg. (of 13) = 0.167395 fft 23: mflops = 10.9483 (norm. = 0.303983), norm. avg. (of 13) = 0.274218 fft 24: mflops = 28.8262 (norm. = 0.800368), norm. avg. (of 13) = 0.669705 fft 25: mflops = 9.45881 (norm. = 0.262627), norm. avg. (of 10) = 0.241886 fft 26: mflops = 20.1358 (norm. = 0.559075), norm. avg. (of 12) = 0.240147 fft 27: mflops = 19.2906 (norm. = 0.53561), norm. avg. (of 13) = 0.440127 fft 28: mflops = 11.9697 (norm. = 0.332344), norm. avg. (of 13) = 0.157386 fft 29: mflops = 4.77193 (norm. = 0.132494), norm. avg. (of 13) = 0.0779059 Benchmarking for array size = 16384 (power of 2): 0. Arndt DIF: elapsed time t=1.09184 s, 8 iters, t-(init.)=1.0552 s t(norm)=0.57504, mflops=8.69505 (err=5.6e-15) 1. Arndt DIT: elapsed time t=1.11674 s, 8 iters, t-(init.)=1.0802 s t(norm)=0.588662, mflops=8.49384 (err=5.6e-15) 2. Arndt Split-Radix: elapsed time t=1.41849 s, 8 iters, t-(init.)=1.3822 s t(norm)=0.75324, mflops=6.63799 (err=5.6e-15) 3. Arndt 4-step: elapsed time t=1.3839 s, 16 iters, t-(init.)=1.31066 s t(norm)=0.357127, mflops=14.0006 (err=5.6e-15) 4. Beauregard: elapsed time t=1.33303 s, 8 iters, t-(init.)=1.2961 s t(norm)=0.706318, mflops=7.07897 (err=5.7e-15) 5. Bergland: elapsed time t=1.99326 s, 32 iters, t-(init.)=1.84714 s t(norm)=0.251653, mflops=19.8686 (err=5.7e-15) 6. CWP (min N) (N=17160): elapsed time t=1.20353 s, 32 iters, t-(init.)=1.05039 s t(norm)=0.143105, mflops=34.9395 7. CWP (best N) (N=17160): elapsed time t=1.20386 s, 32 iters, t-(init.)=1.05115 s t(norm)=0.143208, mflops=34.9143 8. Edelblute: elapsed time t=1.4692 s, 8 iters, t-(init.)=1.4322 s t(norm)=0.780485, mflops=6.40627 (err=5.6e-15) 9. FFTPACK (f2c): elapsed time t=1.81701 s, 16 iters, t-(init.)=1.74361 s t(norm)=0.475097, mflops=10.5242 (err=5.7e-15) FFTW_MEASURE plan: (cost = 4.070400e-02) FFTW_TWIDDLE 32 FFTW_TWIDDLE 16 FFTW_NOTW 32 10. FFTW: elapsed time t=1.27796 s, 32 iters, t-(init.)=1.13138 s t(norm)=0.154138, mflops=32.4384 (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=1.50662 s, 32 iters, t-(init.)=1.35976 s t(norm)=0.185252, mflops=26.9902 (err=5.7e-15) 12. Frigo-old: elapsed time t=1.08209 s, 16 iters, t-(init.)=1.00908 s t(norm)=0.274952, mflops=18.185 (err=5.7e-15) 13. Green: elapsed time t=1.99656 s, 32 iters, t-(init.)=1.85044 s t(norm)=0.252102, mflops=19.8333 (err=5.7e-15) 14. GSL: elapsed time t=1.26399 s, 16 iters, t-(init.)=1.19093 s t(norm)=0.324503, mflops=15.4082 (err=5.7e-15) 15. GSL DIT: elapsed time t=1.01344 s, 8 iters, t-(init.)=0.976854 s t(norm)=0.532343, mflops=9.39244 (err=6.3e-15) 16. GSL DIF: elapsed time t=1.01243 s, 8 iters, t-(init.)=0.975607 s t(norm)=0.531664, mflops=9.40444 (err=6.4e-15) 17. Skipping fft (Krukar can't handle N > 4096). 18. Mayer (Buneman): elapsed time t=1.61652 s, 16 iters, t-(init.)=1.54259 s t(norm)=0.420322, mflops=11.8957 (err=5.6e-15) 19. Mayer (simple): elapsed time t=1.5543 s, 16 iters, t-(init.)=1.48089 s t(norm)=0.40351, mflops=12.3913 20. Mayer (lookup): elapsed time t=1.64538 s, 16 iters, t-(init.)=1.57228 s t(norm)=0.428412, mflops=11.671 (err=5.6e-15) 21. NAPACK (f2c): elapsed time t=1.46409 s, 8 iters, t-(init.)=1.42708 s t(norm)=0.777698, mflops=6.42923 (err=2.3e-13) 22. Nielsen: elapsed time t=1.06362 s, 8 iters, t-(init.)=1.02665 s t(norm)=0.559481, mflops=8.93685 (err=1.3e-13) 23. NR (C): elapsed time t=1.98478 s, 16 iters, t-(init.)=1.91151 s t(norm)=0.520845, mflops=9.59979 (err=5.6e-15) 24. Ooura (C): elapsed time t=1.49452 s, 32 iters, t-(init.)=1.34748 s t(norm)=0.183579, mflops=27.2362 (err=5.7e-15) 25. QFT: elapsed time t=1.13447 s, 8 iters, t-(init.)=1.09719 s t(norm)=0.59792, mflops=8.36232 (err=7.0e-15) 26. Ransom: elapsed time t=1.59651 s, 32 iters, t-(init.)=1.45039 s t(norm)=0.197601, mflops=25.3036 (err=6.0e-15) 27. Singleton (f2c): elapsed time t=1.07806 s, 16 iters, t-(init.)=1.00449 s t(norm)=0.273703, mflops=18.268 (err=8.5e-15) 28. Temperton (f2c): elapsed time t=1.64523 s, 16 iters, t-(init.)=1.57005 s t(norm)=0.427805, mflops=11.6876 (err=5.7e-15) 29. Valkenburg: elapsed time t=1.10454 s, 4 iters, t-(init.)=1.08595 s t(norm)=1.18359, mflops=4.22445 (err=5.7e-15) Top mflops for N=16384 = 34.9395 Normalized results and averages for N=16384: fft 0: mflops = 8.69505 (norm. = 0.24886), norm. avg. (of 14) = 0.387916 fft 1: mflops = 8.49384 (norm. = 0.243102), norm. avg. (of 14) = 0.374195 fft 2: mflops = 6.63799 (norm. = 0.189985), norm. avg. (of 14) = 0.257664 fft 3: mflops = 14.0006 (norm. = 0.400711), norm. avg. (of 14) = 0.158461 fft 4: mflops = 7.07897 (norm. = 0.202606), norm. avg. (of 14) = 0.104922 fft 5: mflops = 19.8686 (norm. = 0.568658), norm. avg. (of 14) = 0.438557 fft 6: mflops = 34.9395 (norm. = 1), norm. avg. (of 14) = 0.551235 fft 7: mflops = 34.9143 (norm. = 0.99928), norm. avg. (of 14) = 0.595845 fft 8: mflops = 6.40627 (norm. = 0.183353), norm. avg. (of 13) = 0.190076 fft 9: mflops = 10.5242 (norm. = 0.301211), norm. avg. (of 14) = 0.224014 fft 10: mflops = 32.4384 (norm. = 0.928417), norm. avg. (of 14) = 0.707002 fft 11: mflops = 26.9902 (norm. = 0.772485), norm. avg. (of 14) = 0.672289 fft 12: mflops = 18.185 (norm. = 0.52047), norm. avg. (of 14) = 0.758093 fft 13: mflops = 19.8333 (norm. = 0.567646), norm. avg. (of 12) = 0.735048 fft 14: mflops = 15.4082 (norm. = 0.440995), norm. avg. (of 14) = 0.350604 fft 15: mflops = 9.39244 (norm. = 0.26882), norm. avg. (of 14) = 0.241228 fft 16: mflops = 9.40444 (norm. = 0.269164), norm. avg. (of 14) = 0.25058 fft 17: mflops = -1 (norm. = -0.0286209), norm. avg. (of 12) = 0.380264 fft 18: mflops = 11.8957 (norm. = 0.340464), norm. avg. (of 13) = 0.379476 fft 19: mflops = 12.3913 (norm. = 0.354649), norm. avg. (of 13) = 0.470895 fft 20: mflops = 11.671 (norm. = 0.334035), norm. avg. (of 13) = 0.429459 fft 21: mflops = 6.42923 (norm. = 0.18401), norm. avg. (of 14) = 0.113305 fft 22: mflops = 8.93685 (norm. = 0.255781), norm. avg. (of 14) = 0.173709 fft 23: mflops = 9.59979 (norm. = 0.274755), norm. avg. (of 14) = 0.274256 fft 24: mflops = 27.2362 (norm. = 0.779525), norm. avg. (of 14) = 0.677549 fft 25: mflops = 8.36232 (norm. = 0.239337), norm. avg. (of 11) = 0.241654 fft 26: mflops = 25.3036 (norm. = 0.724211), norm. avg. (of 13) = 0.277383 fft 27: mflops = 18.268 (norm. = 0.522846), norm. avg. (of 14) = 0.446035 fft 28: mflops = 11.6876 (norm. = 0.334509), norm. avg. (of 14) = 0.170037 fft 29: mflops = 4.22445 (norm. = 0.120907), norm. avg. (of 14) = 0.0809774 Benchmarking for array size = 32768 (power of 2): 0. Arndt DIF: elapsed time t=1.33447 s, 4 iters, t-(init.)=1.29464 s t(norm)=0.658486, mflops=7.59317 (err=5.2e-15) 1. Arndt DIT: elapsed time t=1.35455 s, 4 iters, t-(init.)=1.31475 s t(norm)=0.668714, mflops=7.47703 (err=5.2e-15) 2. Arndt Split-Radix: elapsed time t=1.74125 s, 4 iters, t-(init.)=1.70167 s t(norm)=0.865513, mflops=5.77692 (err=5.2e-15) 3. Arndt 4-step: elapsed time t=1.9271 s, 8 iters, t-(init.)=1.84714 s t(norm)=0.469752, mflops=10.6439 (err=5.2e-15) 4. Beauregard: elapsed time t=1.48674 s, 4 iters, t-(init.)=1.44715 s t(norm)=0.73606, mflops=6.79292 (err=5.2e-15) 5. Bergland: elapsed time t=1.17213 s, 8 iters, t-(init.)=1.09208 s t(norm)=0.27773, mflops=18.0031 (err=5.2e-15) 6. CWP (min N) (N=34320): elapsed time t=1.31498 s, 16 iters, t-(init.)=1.14614 s t(norm)=0.145739, mflops=34.3079 7. CWP (best N) (N=34320): elapsed time t=1.31557 s, 16 iters, t-(init.)=1.14713 s t(norm)=0.145865, mflops=34.2783 8. Edelblute: elapsed time t=1.79237 s, 4 iters, t-(init.)=1.75254 s t(norm)=0.89139, mflops=5.60921 (err=5.2e-15) 9. FFTPACK (f2c): elapsed time t=1.20174 s, 4 iters, t-(init.)=1.1613 s t(norm)=0.590669, mflops=8.46497 (err=5.2e-15) FFTW_MEASURE plan: (cost = 1.097840e-01) FFTW_TWIDDLE 64 FFTW_TWIDDLE 16 FFTW_NOTW 32 10. FFTW: elapsed time t=1.81829 s, 16 iters, t-(init.)=1.65799 s t(norm)=0.210824, mflops=23.7165 (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=1.97901 s, 16 iters, t-(init.)=1.81844 s t(norm)=0.231227, mflops=21.6237 (err=5.2e-15) 12. Frigo-old: elapsed time t=1.38021 s, 8 iters, t-(init.)=1.30003 s t(norm)=0.330614, mflops=15.1234 (err=5.2e-15) 13. Green: elapsed time t=1.1657 s, 8 iters, t-(init.)=1.08573 s t(norm)=0.276116, mflops=18.1083 (err=5.2e-15) 14. GSL: elapsed time t=1.64795 s, 8 iters, t-(init.)=1.56791 s t(norm)=0.398741, mflops=12.5395 (err=5.2e-15) 15. GSL DIT: elapsed time t=1.23772 s, 4 iters, t-(init.)=1.19781 s t(norm)=0.609239, mflops=8.20696 (err=5.9e-15) 16. GSL DIF: elapsed time t=1.24149 s, 4 iters, t-(init.)=1.20146 s t(norm)=0.611092, mflops=8.18207 (err=6.0e-15) 17. Skipping fft (Krukar can't handle N > 4096). 18. Mayer (Buneman): elapsed time t=1.89954 s, 8 iters, t-(init.)=1.81918 s t(norm)=0.462641, mflops=10.8075 (err=5.2e-15) 19. Mayer (simple): elapsed time t=1.82691 s, 8 iters, t-(init.)=1.74752 s t(norm)=0.444417, mflops=11.2507 20. Mayer (lookup): elapsed time t=1.98547 s, 8 iters, t-(init.)=1.90561 s t(norm)=0.484621, mflops=10.3173 (err=5.2e-15) 21. NAPACK (f2c): elapsed time t=1.70221 s, 4 iters, t-(init.)=1.66184 s t(norm)=0.845256, mflops=5.91537 (err=5.6e-13) 22. Nielsen: elapsed time t=1.30892 s, 4 iters, t-(init.)=1.26875 s t(norm)=0.645317, mflops=7.74813 (err=2.3e-13) 23. NR (C): elapsed time t=1.21306 s, 4 iters, t-(init.)=1.1731 s t(norm)=0.596669, mflops=8.37986 (err=5.3e-15) 24. Ooura (C): elapsed time t=1.79729 s, 16 iters, t-(init.)=1.63765 s t(norm)=0.208237, mflops=24.0111 (err=5.2e-15) 25. QFT: elapsed time t=1.32549 s, 4 iters, t-(init.)=1.28478 s t(norm)=0.653471, mflops=7.65144 (err=7.5e-15) 26. Ransom: elapsed time t=1.13786 s, 8 iters, t-(init.)=1.05801 s t(norm)=0.269067, mflops=18.5828 (err=6.4e-15) 27. Singleton (f2c): elapsed time t=1.72756 s, 8 iters, t-(init.)=1.64776 s t(norm)=0.419048, mflops=11.9318 (err=7.2e-15) 28. Temperton (f2c): elapsed time t=1.13978 s, 4 iters, t-(init.)=1.09976 s t(norm)=0.559368, mflops=8.93866 (err=5.2e-15) 29. Valkenburg: elapsed time t=1.37265 s, 2 iters, t-(init.)=1.35231 s t(norm)=1.37565, mflops=3.63466 (err=5.2e-15) Top mflops for N=32768 = 34.3079 Normalized results and averages for N=32768: fft 0: mflops = 7.59317 (norm. = 0.221324), norm. avg. (of 15) = 0.376809 fft 1: mflops = 7.47703 (norm. = 0.217939), norm. avg. (of 15) = 0.363778 fft 2: mflops = 5.77692 (norm. = 0.168385), norm. avg. (of 15) = 0.251712 fft 3: mflops = 10.6439 (norm. = 0.310247), norm. avg. (of 15) = 0.16858 fft 4: mflops = 6.79292 (norm. = 0.197999), norm. avg. (of 15) = 0.111127 fft 5: mflops = 18.0031 (norm. = 0.52475), norm. avg. (of 15) = 0.444304 fft 6: mflops = 34.3079 (norm. = 1), norm. avg. (of 15) = 0.581153 fft 7: mflops = 34.2783 (norm. = 0.999138), norm. avg. (of 15) = 0.622732 fft 8: mflops = 5.60921 (norm. = 0.163496), norm. avg. (of 14) = 0.188177 fft 9: mflops = 8.46497 (norm. = 0.246735), norm. avg. (of 15) = 0.225528 fft 10: mflops = 23.7165 (norm. = 0.691282), norm. avg. (of 15) = 0.705954 fft 11: mflops = 21.6237 (norm. = 0.630285), norm. avg. (of 15) = 0.669488 fft 12: mflops = 15.1234 (norm. = 0.440813), norm. avg. (of 15) = 0.736941 fft 13: mflops = 18.1083 (norm. = 0.527818), norm. avg. (of 13) = 0.719107 fft 14: mflops = 12.5395 (norm. = 0.365498), norm. avg. (of 15) = 0.351597 fft 15: mflops = 8.20696 (norm. = 0.239215), norm. avg. (of 15) = 0.241094 fft 16: mflops = 8.18207 (norm. = 0.238489), norm. avg. (of 15) = 0.249774 fft 17: mflops = -1 (norm. = -0.0291478), norm. avg. (of 12) = 0.380264 fft 18: mflops = 10.8075 (norm. = 0.315016), norm. avg. (of 14) = 0.374872 fft 19: mflops = 11.2507 (norm. = 0.327933), norm. avg. (of 14) = 0.460683 fft 20: mflops = 10.3173 (norm. = 0.300727), norm. avg. (of 14) = 0.420264 fft 21: mflops = 5.91537 (norm. = 0.17242), norm. avg. (of 15) = 0.117246 fft 22: mflops = 7.74813 (norm. = 0.225841), norm. avg. (of 15) = 0.177184 fft 23: mflops = 8.37986 (norm. = 0.244254), norm. avg. (of 15) = 0.272256 fft 24: mflops = 24.0111 (norm. = 0.69987), norm. avg. (of 15) = 0.679037 fft 25: mflops = 7.65144 (norm. = 0.223023), norm. avg. (of 12) = 0.240102 fft 26: mflops = 18.5828 (norm. = 0.541646), norm. avg. (of 14) = 0.296259 fft 27: mflops = 11.9318 (norm. = 0.347786), norm. avg. (of 15) = 0.439485 fft 28: mflops = 8.93866 (norm. = 0.260542), norm. avg. (of 15) = 0.176071 fft 29: mflops = 3.63466 (norm. = 0.105942), norm. avg. (of 15) = 0.0826418 Benchmarking for array size = 65536 (power of 2): 0. Arndt DIF: elapsed time t=1.63006 s, 2 iters, t-(init.)=1.58794 s t(norm)=0.757188, mflops=6.60338 (err=1.6e-14) 1. Arndt DIT: elapsed time t=1.65037 s, 2 iters, t-(init.)=1.6086 s t(norm)=0.767038, mflops=6.51858 (err=1.6e-14) 2. Arndt Split-Radix: elapsed time t=1.02704 s, 1 iters, t-(init.)=1.006 s t(norm)=0.959393, mflops=5.21163 (err=1.6e-14) 3. Arndt 4-step: elapsed time t=1.85194 s, 4 iters, t-(init.)=1.76757 s t(norm)=0.421422, mflops=11.8646 (err=1.6e-14) 4. Beauregard: elapsed time t=1.63321 s, 2 iters, t-(init.)=1.5907 s t(norm)=0.758507, mflops=6.5919 (err=1.6e-14) 5. Bergland: elapsed time t=1.45598 s, 4 iters, t-(init.)=1.37187 s t(norm)=0.327079, mflops=15.2868 (err=1.6e-14) 6. CWP (min N) (N=72072): elapsed time t=1.55121 s, 8 iters, t-(init.)=1.36587 s t(norm)=0.162824, mflops=30.708 7. CWP (best N) (N=72072): elapsed time t=1.5498 s, 8 iters, t-(init.)=1.36456 s t(norm)=0.162669, mflops=30.7373 8. Edelblute: elapsed time t=1.05765 s, 1 iters, t-(init.)=1.03662 s t(norm)=0.988603, mflops=5.05764 (err=1.6e-14) 9. FFTPACK (f2c): elapsed time t=1.418 s, 2 iters, t-(init.)=1.37616 s t(norm)=0.656202, mflops=7.6196 (err=1.6e-14) FFTW_MEASURE plan: (cost = 2.593620e-01) FFTW_TWIDDLE 16 FFTW_TWIDDLE 4 FFTW_TWIDDLE 16 FFTW_NOTW 64 10. FFTW: elapsed time t=1.05503 s, 4 iters, t-(init.)=0.970618 s t(norm)=0.231413, mflops=21.6064 (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=1.14087 s, 4 iters, t-(init.)=1.05637 s t(norm)=0.251858, mflops=19.8525 (err=1.6e-14) 12. Frigo-old: elapsed time t=1.5899 s, 4 iters, t-(init.)=1.5057 s t(norm)=0.358987, mflops=13.9281 (err=1.6e-14) 13. Green: elapsed time t=1.4371 s, 4 iters, t-(init.)=1.35321 s t(norm)=0.322631, mflops=15.4976 (err=1.6e-14) 14. GSL: elapsed time t=1.80041 s, 4 iters, t-(init.)=1.71595 s t(norm)=0.409115, mflops=12.2215 (err=1.6e-14) 15. GSL DIT: elapsed time t=1.40603 s, 2 iters, t-(init.)=1.36396 s t(norm)=0.650388, mflops=7.68772 (err=1.7e-14) 16. GSL DIF: elapsed time t=1.4078 s, 2 iters, t-(init.)=1.36519 s t(norm)=0.650972, mflops=7.68082 (err=1.8e-14) 17. Skipping fft (Krukar can't handle N > 4096). 18. Mayer (Buneman): elapsed time t=1.25907 s, 2 iters, t-(init.)=1.21698 s t(norm)=0.580302, mflops=8.6162 (err=1.6e-14) 19. Mayer (simple): elapsed time t=1.22678 s, 2 iters, t-(init.)=1.18455 s t(norm)=0.564837, mflops=8.85211 20. Mayer (lookup): elapsed time t=1.30141 s, 2 iters, t-(init.)=1.25929 s t(norm)=0.600475, mflops=8.32674 (err=1.6e-14) 21. NAPACK (f2c): elapsed time t=1.76537 s, 2 iters, t-(init.)=1.7229 s t(norm)=0.821541, mflops=6.08612 (err=8.7e-13) 22. Nielsen: elapsed time t=1.59828 s, 2 iters, t-(init.)=1.55635 s t(norm)=0.742124, mflops=6.73742 (err=2.6e-13) 23. NR (C): elapsed time t=1.38218 s, 2 iters, t-(init.)=1.33987 s t(norm)=0.6389, mflops=7.82595 (err=1.6e-14) 24. Ooura (C): elapsed time t=1.17934 s, 4 iters, t-(init.)=1.09512 s t(norm)=0.261096, mflops=19.15 (err=1.6e-14) 25. QFT: elapsed time t=1.64391 s, 2 iters, t-(init.)=1.60098 s t(norm)=0.763406, mflops=6.54959 (err=1.9e-14) 26. Ransom: elapsed time t=1.27371 s, 4 iters, t-(init.)=1.18935 s t(norm)=0.283564, mflops=17.6327 (err=1.7e-14) 27. Singleton (f2c): elapsed time t=1.6754 s, 4 iters, t-(init.)=1.59087 s t(norm)=0.379293, mflops=13.1824 (err=2.4e-14) 28. Temperton (f2c): elapsed time t=1.26739 s, 2 iters, t-(init.)=1.2248 s t(norm)=0.584032, mflops=8.56118 (err=1.6e-14) 29. Valkenburg: elapsed time t=1.58471 s, 1 iters, t-(init.)=1.56321 s t(norm)=1.49079, mflops=3.35392 (err=1.6e-14) Top mflops for N=65536 = 30.7373 Normalized results and averages for N=65536: fft 0: mflops = 6.60338 (norm. = 0.214833), norm. avg. (of 16) = 0.366686 fft 1: mflops = 6.51858 (norm. = 0.212074), norm. avg. (of 16) = 0.354297 fft 2: mflops = 5.21163 (norm. = 0.169554), norm. avg. (of 16) = 0.246577 fft 3: mflops = 11.8646 (norm. = 0.386), norm. avg. (of 16) = 0.182169 fft 4: mflops = 6.5919 (norm. = 0.214459), norm. avg. (of 16) = 0.117585 fft 5: mflops = 15.2868 (norm. = 0.497338), norm. avg. (of 16) = 0.447618 fft 6: mflops = 30.708 (norm. = 0.999047), norm. avg. (of 16) = 0.607271 fft 7: mflops = 30.7373 (norm. = 1), norm. avg. (of 16) = 0.646311 fft 8: mflops = 5.05764 (norm. = 0.164544), norm. avg. (of 15) = 0.186601 fft 9: mflops = 7.6196 (norm. = 0.247894), norm. avg. (of 16) = 0.226926 fft 10: mflops = 21.6064 (norm. = 0.702936), norm. avg. (of 16) = 0.705765 fft 11: mflops = 19.8525 (norm. = 0.645876), norm. avg. (of 16) = 0.668013 fft 12: mflops = 13.9281 (norm. = 0.453133), norm. avg. (of 16) = 0.719203 fft 13: mflops = 15.4976 (norm. = 0.504195), norm. avg. (of 14) = 0.703757 fft 14: mflops = 12.2215 (norm. = 0.397612), norm. avg. (of 16) = 0.354473 fft 15: mflops = 7.68772 (norm. = 0.250111), norm. avg. (of 16) = 0.241657 fft 16: mflops = 7.68082 (norm. = 0.249886), norm. avg. (of 16) = 0.249781 fft 17: mflops = -1 (norm. = -0.0325338), norm. avg. (of 12) = 0.380264 fft 18: mflops = 8.6162 (norm. = 0.280317), norm. avg. (of 15) = 0.368568 fft 19: mflops = 8.85211 (norm. = 0.287993), norm. avg. (of 15) = 0.44917 fft 20: mflops = 8.32674 (norm. = 0.2709), norm. avg. (of 15) = 0.410307 fft 21: mflops = 6.08612 (norm. = 0.198004), norm. avg. (of 16) = 0.122293 fft 22: mflops = 6.73742 (norm. = 0.219194), norm. avg. (of 16) = 0.17981 fft 23: mflops = 7.82595 (norm. = 0.254608), norm. avg. (of 16) = 0.271153 fft 24: mflops = 19.15 (norm. = 0.623022), norm. avg. (of 16) = 0.675536 fft 25: mflops = 6.54959 (norm. = 0.213083), norm. avg. (of 13) = 0.238023 fft 26: mflops = 17.6327 (norm. = 0.573659), norm. avg. (of 15) = 0.314752 fft 27: mflops = 13.1824 (norm. = 0.428874), norm. avg. (of 16) = 0.438822 fft 28: mflops = 8.56118 (norm. = 0.278527), norm. avg. (of 16) = 0.182474 fft 29: mflops = 3.35392 (norm. = 0.109116), norm. avg. (of 16) = 0.0842964 Benchmarking for array size = 131072 (power of 2): 0. Arndt DIF: elapsed time t=2.18423 s, 1 iters, t-(init.)=2.14132 s t(norm)=0.960997, mflops=5.20293 (err=3.9e-14) 1. Arndt DIT: elapsed time t=2.22425 s, 1 iters, t-(init.)=2.18232 s t(norm)=0.979397, mflops=5.10518 (err=3.9e-14) 2. Arndt Split-Radix: elapsed time t=2.75496 s, 1 iters, t-(init.)=2.71246 s t(norm)=1.21732, mflops=4.10739 (err=3.9e-14) 3. Arndt 4-step: elapsed time t=1.32469 s, 1 iters, t-(init.)=1.28246 s t(norm)=0.575551, mflops=8.68733 (err=3.9e-14) 4. Beauregard: elapsed time t=1.7568 s, 1 iters, t-(init.)=1.71442 s t(norm)=0.769412, mflops=6.49847 (err=3.8e-14) 5. Bergland: elapsed time t=1.90034 s, 2 iters, t-(init.)=1.81576 s t(norm)=0.407446, mflops=12.2716 (err=3.9e-14) 6. CWP (min N) (N=144144): elapsed time t=1.58103 s, 4 iters, t-(init.)=1.3952 s t(norm)=0.156537, mflops=31.9414 7. CWP (best N) (N=144144): elapsed time t=1.58128 s, 4 iters, t-(init.)=1.39533 s t(norm)=0.156552, mflops=31.9382 8. Edelblute: elapsed time t=2.8048 s, 1 iters, t-(init.)=2.76234 s t(norm)=1.2397, mflops=4.03322 (err=3.9e-14) 9. FFTPACK (f2c): elapsed time t=1.5818 s, 1 iters, t-(init.)=1.53989 s t(norm)=0.691085, mflops=7.235 (err=3.8e-14) FFTW_MEASURE plan: (cost = 6.132320e-01) FFTW_TWIDDLE 64 FFTW_TWIDDLE 4 FFTW_TWIDDLE 4 FFTW_TWIDDLE 4 FFTW_NOTW 32 10. FFTW: elapsed time t=1.2852 s, 2 iters, t-(init.)=1.20064 s t(norm)=0.269416, mflops=18.5587 (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=1.31614 s, 2 iters, t-(init.)=1.2312 s t(norm)=0.276274, mflops=18.098 (err=3.8e-14) 12. Frigo-old: elapsed time t=1.89352 s, 2 iters, t-(init.)=1.80882 s t(norm)=0.405888, mflops=12.3187 (err=3.8e-14) 13. Green: elapsed time t=1.9249 s, 2 iters, t-(init.)=1.84079 s t(norm)=0.413062, mflops=12.1047 (err=3.8e-14) 14. GSL: elapsed time t=1.04027 s, 1 iters, t-(init.)=0.998159 s t(norm)=0.447962, mflops=11.1617 (err=3.8e-14) 15. GSL DIT: elapsed time t=1.95961 s, 1 iters, t-(init.)=1.9173 s t(norm)=0.860463, mflops=5.81082 (err=4.0e-14) 16. GSL DIF: elapsed time t=1.96051 s, 1 iters, t-(init.)=1.91832 s t(norm)=0.860921, mflops=5.80774 (err=4.2e-14) 17. Skipping fft (Krukar can't handle N > 4096). 18. Mayer (Buneman): elapsed time t=1.39871 s, 1 iters, t-(init.)=1.35618 s t(norm)=0.608639, mflops=8.21505 (err=3.9e-14) 19. Mayer (simple): elapsed time t=1.34623 s, 1 iters, t-(init.)=1.30384 s t(norm)=0.585147, mflops=8.54487 20. Mayer (lookup): elapsed time t=1.45117 s, 1 iters, t-(init.)=1.40927 s t(norm)=0.632465, mflops=7.90557 (err=3.9e-14) 21. NAPACK (f2c): elapsed time t=1.9447 s, 1 iters, t-(init.)=1.90246 s t(norm)=0.853802, mflops=5.85616 (err=2.0e-12) 22. Nielsen: elapsed time t=1.92836 s, 1 iters, t-(init.)=1.88607 s t(norm)=0.846445, mflops=5.90706 (err=9.2e-13) 23. NR (C): elapsed time t=1.93492 s, 1 iters, t-(init.)=1.89294 s t(norm)=0.849531, mflops=5.8856 (err=3.9e-14) 24. Ooura (C): elapsed time t=1.29252 s, 2 iters, t-(init.)=1.20801 s t(norm)=0.271071, mflops=18.4453 (err=3.9e-14) 25. QFT: elapsed time t=2.11954 s, 1 iters, t-(init.)=2.07668 s t(norm)=0.93199, mflops=5.36486 (err=4.1e-14) 26. Ransom: elapsed time t=1.57234 s, 2 iters, t-(init.)=1.48784 s t(norm)=0.333863, mflops=14.9762 (err=3.9e-14) 27. Singleton (f2c): elapsed time t=1.24545 s, 1 iters, t-(init.)=1.20332 s t(norm)=0.540037, mflops=9.25863 (err=5.7e-14) 28. Temperton (f2c): elapsed time t=1.69525 s, 1 iters, t-(init.)=1.65308 s t(norm)=0.741883, mflops=6.73961 (err=3.8e-14) 29. Valkenburg: elapsed time t=3.57859 s, 1 iters, t-(init.)=3.5363 s t(norm)=1.58705, mflops=3.1505 (err=3.9e-14) Top mflops for N=131072 = 31.9414 Normalized results and averages for N=131072: fft 0: mflops = 5.20293 (norm. = 0.16289), norm. avg. (of 17) = 0.354698 fft 1: mflops = 5.10518 (norm. = 0.15983), norm. avg. (of 17) = 0.342857 fft 2: mflops = 4.10739 (norm. = 0.128592), norm. avg. (of 17) = 0.239637 fft 3: mflops = 8.68733 (norm. = 0.271978), norm. avg. (of 17) = 0.187452 fft 4: mflops = 6.49847 (norm. = 0.20345), norm. avg. (of 17) = 0.122636 fft 5: mflops = 12.2716 (norm. = 0.384191), norm. avg. (of 17) = 0.443887 fft 6: mflops = 31.9414 (norm. = 1), norm. avg. (of 17) = 0.630373 fft 7: mflops = 31.9382 (norm. = 0.999903), norm. avg. (of 17) = 0.66711 fft 8: mflops = 4.03322 (norm. = 0.12627), norm. avg. (of 16) = 0.182831 fft 9: mflops = 7.235 (norm. = 0.226509), norm. avg. (of 17) = 0.226902 fft 10: mflops = 18.5587 (norm. = 0.581023), norm. avg. (of 17) = 0.698428 fft 11: mflops = 18.098 (norm. = 0.5666), norm. avg. (of 17) = 0.662047 fft 12: mflops = 12.3187 (norm. = 0.385665), norm. avg. (of 17) = 0.699583 fft 13: mflops = 12.1047 (norm. = 0.378967), norm. avg. (of 15) = 0.682104 fft 14: mflops = 11.1617 (norm. = 0.349443), norm. avg. (of 17) = 0.354177 fft 15: mflops = 5.81082 (norm. = 0.181922), norm. avg. (of 17) = 0.238144 fft 16: mflops = 5.80774 (norm. = 0.181825), norm. avg. (of 17) = 0.245783 fft 17: mflops = -1 (norm. = -0.0313074), norm. avg. (of 12) = 0.380264 fft 18: mflops = 8.21505 (norm. = 0.257192), norm. avg. (of 16) = 0.361607 fft 19: mflops = 8.54487 (norm. = 0.267517), norm. avg. (of 16) = 0.437817 fft 20: mflops = 7.90557 (norm. = 0.247503), norm. avg. (of 16) = 0.400131 fft 21: mflops = 5.85616 (norm. = 0.183341), norm. avg. (of 17) = 0.125884 fft 22: mflops = 5.90706 (norm. = 0.184934), norm. avg. (of 17) = 0.180111 fft 23: mflops = 5.8856 (norm. = 0.184263), norm. avg. (of 17) = 0.266042 fft 24: mflops = 18.4453 (norm. = 0.577476), norm. avg. (of 17) = 0.669768 fft 25: mflops = 5.36486 (norm. = 0.16796), norm. avg. (of 14) = 0.233019 fft 26: mflops = 14.9762 (norm. = 0.468866), norm. avg. (of 16) = 0.324384 fft 27: mflops = 9.25863 (norm. = 0.289863), norm. avg. (of 17) = 0.43006 fft 28: mflops = 6.73961 (norm. = 0.210999), norm. avg. (of 17) = 0.184152 fft 29: mflops = 3.1505 (norm. = 0.0986338), norm. avg. (of 17) = 0.0851398 ------------------------------------------------------ @@@@ 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=1.89039 s, 524288 iters, t-(init.)=1.80011 s t(norm)=0.221372, mflops=22.5864 1. CWP (best N) (N=15): elapsed time t=1.52562 s, 262144 iters, t-(init.)=1.4322 s t(norm)=0.352256, mflops=14.1942 2. FFTPACK (f2c): elapsed time t=1.56753 s, 262144 iters, t-(init.)=1.52257 s t(norm)=0.374484, mflops=13.3517 (err=1.7e-16) FFTW_MEASURE plan: (cost = 1.047058e-06) FFTW_NOTW 6 3. FFTW: elapsed time t=1.13939 s, 524288 iters, t-(init.)=1.04956 s t(norm)=0.129072, mflops=38.738 (err=1.3e-16) FFTW_ESTIMATE plan: (cost = 4.116000e+02) FFTW_NOTW 6 4. FFTW_ESTIMATE: elapsed time t=1.13922 s, 524288 iters, t-(init.)=1.04864 s t(norm)=0.128958, mflops=38.7722 (err=1.3e-16) 5. Frigo-old: elapsed time t=1.02385 s, 131072 iters, t-(init.)=1.00109 s t(norm)=0.492443, mflops=10.1534 (err=3.2e-16) 6. GSL: elapsed time t=1.20752 s, 262144 iters, t-(init.)=1.16241 s t(norm)=0.2859, mflops=17.4886 (err=1.3e-16) 7. NAPACK (f2c): elapsed time t=1.11685 s, 65536 iters, t-(init.)=1.10555 s t(norm)=1.08766, mflops=4.59702 (err=2.3e-16) 8. Nielsen: elapsed time t=1.17554 s, 65536 iters, t-(init.)=1.16432 s t(norm)=1.14548, mflops=4.36497 (err=2.7e-16) 9. Singleton (f2c): elapsed time t=1.6061 s, 262144 iters, t-(init.)=1.56098 s t(norm)=0.383929, mflops=13.0232 (err=1.3e-16) 10. Temperton (f2c): elapsed time t=1.19664 s, 131072 iters, t-(init.)=1.17383 s t(norm)=0.577418, mflops=8.65924 (err=1.2e-16) 11. Valkenburg: elapsed time t=1.56636 s, 65536 iters, t-(init.)=1.55516 s t(norm)=1.52999, mflops=3.268 (err=2.1e-16) Top mflops for N=6 = 38.7722 Normalized results and averages for N=6: fft 0: mflops = 22.5864 (norm. = 0.582541), norm. avg. (of 1) = 0.582541 fft 1: mflops = 14.1942 (norm. = 0.366093), norm. avg. (of 1) = 0.366093 fft 2: mflops = 13.3517 (norm. = 0.344363), norm. avg. (of 1) = 0.344363 fft 3: mflops = 38.738 (norm. = 0.999119), norm. avg. (of 1) = 0.999119 fft 4: mflops = 38.7722 (norm. = 1), norm. avg. (of 1) = 1 fft 5: mflops = 10.1534 (norm. = 0.261875), norm. avg. (of 1) = 0.261875 fft 6: mflops = 17.4886 (norm. = 0.451062), norm. avg. (of 1) = 0.451062 fft 7: mflops = 4.59702 (norm. = 0.118565), norm. avg. (of 1) = 0.118565 fft 8: mflops = 4.36497 (norm. = 0.11258), norm. avg. (of 1) = 0.11258 fft 9: mflops = 13.0232 (norm. = 0.335891), norm. avg. (of 1) = 0.335891 fft 10: mflops = 8.65924 (norm. = 0.223336), norm. avg. (of 1) = 0.223336 fft 11: mflops = 3.268 (norm. = 0.0842871), norm. avg. (of 1) = 0.0842871 Benchmarking for array size = 9: 0. CWP (min N): elapsed time t=1.14676 s, 262144 iters, t-(init.)=1.0856 s t(norm)=0.145158, mflops=34.4453 1. CWP (best N) (N=15): elapsed time t=1.52473 s, 262144 iters, t-(init.)=1.43097 s t(norm)=0.191338, mflops=26.1318 2. FFTPACK (f2c): elapsed time t=1.09399 s, 131072 iters, t-(init.)=1.06337 s t(norm)=0.28437, mflops=17.5827 (err=2.8e-16) FFTW_MEASURE plan: (cost = 1.797852e-06) FFTW_NOTW 9 3. FFTW: elapsed time t=1.55329 s, 524288 iters, t-(init.)=1.43067 s t(norm)=0.0956484, mflops=52.2748 (err=1.4e-16) FFTW_ESTIMATE plan: (cost = 4.851000e+02) FFTW_NOTW 9 4. FFTW_ESTIMATE: elapsed time t=1.5519 s, 524288 iters, t-(init.)=1.42978 s t(norm)=0.0955892, mflops=52.3072 (err=1.4e-16) 5. Frigo-old: elapsed time t=1.00702 s, 65536 iters, t-(init.)=0.991669 s t(norm)=0.53039, mflops=9.42703 (err=3.1e-16) 6. GSL: elapsed time t=1.05844 s, 131072 iters, t-(init.)=1.02779 s t(norm)=0.274855, mflops=18.1914 (err=1.4e-16) 7. NAPACK (f2c): elapsed time t=1.63941 s, 65536 iters, t-(init.)=1.62405 s t(norm)=0.868618, mflops=5.75627 (err=5.8e-16) 8. Nielsen: elapsed time t=1.46873 s, 65536 iters, t-(init.)=1.45333 s t(norm)=0.777309, mflops=6.43245 (err=4.5e-16) 9. Singleton (f2c): elapsed time t=1.67517 s, 262144 iters, t-(init.)=1.61407 s t(norm)=0.215819, mflops=23.1675 (err=1.7e-16) 10. Temperton (f2c): elapsed time t=1.64699 s, 131072 iters, t-(init.)=1.61613 s t(norm)=0.432191, mflops=11.569 (err=1.7e-16) 11. Valkenburg: elapsed time t=1.47078 s, 32768 iters, t-(init.)=1.46311 s t(norm)=1.56507, mflops=3.19474 (err=2.6e-16) Top mflops for N=9 = 52.3072 Normalized results and averages for N=9: fft 0: mflops = 34.4453 (norm. = 0.65852), norm. avg. (of 2) = 0.62053 fft 1: mflops = 26.1318 (norm. = 0.499584), norm. avg. (of 2) = 0.432838 fft 2: mflops = 17.5827 (norm. = 0.336143), norm. avg. (of 2) = 0.340253 fft 3: mflops = 52.2748 (norm. = 0.999381), norm. avg. (of 2) = 0.99925 fft 4: mflops = 52.3072 (norm. = 1), norm. avg. (of 2) = 1 fft 5: mflops = 9.42703 (norm. = 0.180224), norm. avg. (of 2) = 0.221049 fft 6: mflops = 18.1914 (norm. = 0.347781), norm. avg. (of 2) = 0.399421 fft 7: mflops = 5.75627 (norm. = 0.110047), norm. avg. (of 2) = 0.114306 fft 8: mflops = 6.43245 (norm. = 0.122974), norm. avg. (of 2) = 0.117777 fft 9: mflops = 23.1675 (norm. = 0.442913), norm. avg. (of 2) = 0.389402 fft 10: mflops = 11.569 (norm. = 0.221173), norm. avg. (of 2) = 0.222255 fft 11: mflops = 3.19474 (norm. = 0.0610764), norm. avg. (of 2) = 0.0726818 Benchmarking for array size = 12: 0. CWP (min N): elapsed time t=1.22548 s, 262144 iters, t-(init.)=1.1483 s t(norm)=0.101824, mflops=49.1044 1. CWP (best N) (N=15): elapsed time t=1.5268 s, 262144 iters, t-(init.)=1.43342 s t(norm)=0.127106, mflops=39.3372 2. FFTPACK (f2c): elapsed time t=1.26755 s, 131072 iters, t-(init.)=1.22908 s t(norm)=0.217975, mflops=22.9384 (err=1.9e-16) FFTW_MEASURE plan: (cost = 1.829712e-06) FFTW_NOTW 12 3. FFTW: elapsed time t=1.44316 s, 524288 iters, t-(init.)=1.28872 s t(norm)=0.0571379, mflops=87.5076 (err=1.3e-16) FFTW_ESTIMATE plan: (cost = 4.920000e+02) FFTW_NOTW 12 4. FFTW_ESTIMATE: elapsed time t=1.44358 s, 524288 iters, t-(init.)=1.28891 s t(norm)=0.0571462, mflops=87.4949 (err=1.3e-16) 5. Frigo-old: elapsed time t=1.77437 s, 131072 iters, t-(init.)=1.73559 s t(norm)=0.307802, mflops=16.2442 (err=2.3e-16) 6. GSL: elapsed time t=1.38525 s, 131072 iters, t-(init.)=1.34659 s t(norm)=0.238813, mflops=20.9369 (err=1.5e-16) 7. NAPACK (f2c): elapsed time t=1.38626 s, 32768 iters, t-(init.)=1.37655 s t(norm)=0.976505, mflops=5.1203 (err=4.2e-16) 8. Nielsen: elapsed time t=1.75366 s, 65536 iters, t-(init.)=1.73423 s t(norm)=0.615123, mflops=8.12846 (err=4.8e-16) 9. Singleton (f2c): elapsed time t=1.18034 s, 131072 iters, t-(init.)=1.14177 s t(norm)=0.20249, mflops=24.6926 (err=1.9e-16) 10. Temperton (f2c): elapsed time t=1.72433 s, 131072 iters, t-(init.)=1.68454 s t(norm)=0.298749, mflops=16.7365 (err=1.2e-16) 11. Valkenburg: elapsed time t=1.03927 s, 16384 iters, t-(init.)=1.03425 s t(norm)=1.46737, mflops=3.40746 (err=1.9e-16) Top mflops for N=12 = 87.5076 Normalized results and averages for N=12: fft 0: mflops = 49.1044 (norm. = 0.561145), norm. avg. (of 3) = 0.600735 fft 1: mflops = 39.3372 (norm. = 0.449529), norm. avg. (of 3) = 0.438402 fft 2: mflops = 22.9384 (norm. = 0.262131), norm. avg. (of 3) = 0.314213 fft 3: mflops = 87.5076 (norm. = 1), norm. avg. (of 3) = 0.9995 fft 4: mflops = 87.4949 (norm. = 0.999856), norm. avg. (of 3) = 0.999952 fft 5: mflops = 16.2442 (norm. = 0.185632), norm. avg. (of 3) = 0.209244 fft 6: mflops = 20.9369 (norm. = 0.239258), norm. avg. (of 3) = 0.346033 fft 7: mflops = 5.1203 (norm. = 0.0585127), norm. avg. (of 3) = 0.0957084 fft 8: mflops = 8.12846 (norm. = 0.0928887), norm. avg. (of 3) = 0.109481 fft 9: mflops = 24.6926 (norm. = 0.282177), norm. avg. (of 3) = 0.353661 fft 10: mflops = 16.7365 (norm. = 0.191257), norm. avg. (of 3) = 0.211922 fft 11: mflops = 3.40746 (norm. = 0.038939), norm. avg. (of 3) = 0.0614342 Benchmarking for array size = 15: 0. CWP (min N): elapsed time t=1.52526 s, 262144 iters, t-(init.)=1.43209 s t(norm)=0.0932195, mflops=53.6369 1. CWP (best N): elapsed time t=1.52529 s, 262144 iters, t-(init.)=1.43215 s t(norm)=0.0932236, mflops=53.6345 2. FFTPACK (f2c): elapsed time t=1.95351 s, 131072 iters, t-(init.)=1.90679 s t(norm)=0.248239, mflops=20.1419 (err=3.6e-16) FFTW_MEASURE plan: (cost = 3.115906e-06) FFTW_NOTW 15 3. FFTW: elapsed time t=1.17509 s, 262144 iters, t-(init.)=1.08179 s t(norm)=0.0704176, mflops=71.005 (err=1.7e-16) FFTW_ESTIMATE plan: (cost = 4.485000e+02) FFTW_NOTW 15 4. FFTW_ESTIMATE: elapsed time t=1.17539 s, 262144 iters, t-(init.)=1.0821 s t(norm)=0.0704375, mflops=70.9849 (err=1.7e-16) 5. Frigo-old: elapsed time t=1.60406 s, 65536 iters, t-(init.)=1.58082 s t(norm)=0.411603, mflops=12.1476 (err=2.7e-16) 6. GSL: elapsed time t=1.98021 s, 131072 iters, t-(init.)=1.93338 s t(norm)=0.251701, mflops=19.8648 (err=1.9e-16) 7. NAPACK (f2c): elapsed time t=1.45021 s, 16384 iters, t-(init.)=1.44431 s t(norm)=1.50424, mflops=3.32394 (err=9.4e-16) 8. Nielsen: elapsed time t=1.04426 s, 32768 iters, t-(init.)=1.03255 s t(norm)=0.5377, mflops=9.29886 (err=4.5e-15) 9. Singleton (f2c): elapsed time t=1.4182 s, 131072 iters, t-(init.)=1.37156 s t(norm)=0.178559, mflops=28.0019 (err=2.0e-16) 10. Temperton (f2c): elapsed time t=1.15138 s, 65536 iters, t-(init.)=1.12794 s t(norm)=0.293688, mflops=17.0249 (err=2.5e-16) 11. Valkenburg: elapsed time t=1.72717 s, 16384 iters, t-(init.)=1.72023 s t(norm)=1.79161, mflops=2.79079 (err=2.5e-16) Top mflops for N=15 = 71.005 Normalized results and averages for N=15: fft 0: mflops = 53.6369 (norm. = 0.755396), norm. avg. (of 4) = 0.6394 fft 1: mflops = 53.6345 (norm. = 0.755363), norm. avg. (of 4) = 0.517642 fft 2: mflops = 20.1419 (norm. = 0.283668), norm. avg. (of 4) = 0.306576 fft 3: mflops = 71.005 (norm. = 1), norm. avg. (of 4) = 0.999625 fft 4: mflops = 70.9849 (norm. = 0.999717), norm. avg. (of 4) = 0.999893 fft 5: mflops = 12.1476 (norm. = 0.171081), norm. avg. (of 4) = 0.199703 fft 6: mflops = 19.8648 (norm. = 0.279767), norm. avg. (of 4) = 0.329467 fft 7: mflops = 3.32394 (norm. = 0.0468127), norm. avg. (of 4) = 0.0834845 fft 8: mflops = 9.29886 (norm. = 0.130961), norm. avg. (of 4) = 0.114851 fft 9: mflops = 28.0019 (norm. = 0.394366), norm. avg. (of 4) = 0.363837 fft 10: mflops = 17.0249 (norm. = 0.239771), norm. avg. (of 4) = 0.218884 fft 11: mflops = 2.79079 (norm. = 0.0393041), norm. avg. (of 4) = 0.0559017 Benchmarking for array size = 18: 0. CWP (min N): elapsed time t=1.95082 s, 262144 iters, t-(init.)=1.84144 s t(norm)=0.0935874, mflops=53.426 1. CWP (best N) (N=28): elapsed time t=1.11124 s, 131072 iters, t-(init.)=1.02976 s t(norm)=0.104671, mflops=47.7687 2. FFTPACK (f2c): elapsed time t=1.37946 s, 65536 iters, t-(init.)=1.35163 s t(norm)=0.274775, mflops=18.1967 (err=2.6e-16) FFTW_MEASURE plan: (cost = 4.813171e-06) FFTW_TWIDDLE 3 FFTW_NOTW 6 3. FFTW: elapsed time t=1.90517 s, 262144 iters, t-(init.)=1.79595 s t(norm)=0.0912752, mflops=54.7794 (err=1.9e-16) FFTW_ESTIMATE plan: (cost = 1.168200e+03) FFTW_TWIDDLE 2 FFTW_NOTW 9 4. FFTW_ESTIMATE: elapsed time t=1.76779 s, 262144 iters, t-(init.)=1.65853 s t(norm)=0.0842913, mflops=59.3181 (err=2.3e-16) 5. Frigo-old: elapsed time t=1.1371 s, 32768 iters, t-(init.)=1.12331 s t(norm)=0.456721, mflops=10.9476 (err=3.8e-16) 6. GSL: elapsed time t=1.73103 s, 131072 iters, t-(init.)=1.67626 s t(norm)=0.170385, mflops=29.3454 (err=2.4e-16) 7. NAPACK (f2c): elapsed time t=1.04517 s, 16384 iters, t-(init.)=1.03845 s t(norm)=0.844434, mflops=5.92113 (err=6.0e-16) 8. Nielsen: elapsed time t=1.52974 s, 32768 iters, t-(init.)=1.51596 s t(norm)=0.616363, mflops=8.1121 (err=7.7e-16) 9. Singleton (f2c): elapsed time t=1.52112 s, 131072 iters, t-(init.)=1.46651 s t(norm)=0.149064, mflops=33.5425 (err=1.7e-16) 10. Temperton (f2c): elapsed time t=1.72341 s, 65536 iters, t-(init.)=1.69497 s t(norm)=0.344573, mflops=14.5107 (err=2.8e-16) 11. Valkenburg: elapsed time t=1.85029 s, 16384 iters, t-(init.)=1.84346 s t(norm)=1.49904, mflops=3.33546 (err=2.8e-16) Top mflops for N=18 = 59.3181 Normalized results and averages for N=18: fft 0: mflops = 53.426 (norm. = 0.90067), norm. avg. (of 5) = 0.691654 fft 1: mflops = 47.7687 (norm. = 0.805297), norm. avg. (of 5) = 0.575173 fft 2: mflops = 18.1967 (norm. = 0.306765), norm. avg. (of 5) = 0.306614 fft 3: mflops = 54.7794 (norm. = 0.923485), norm. avg. (of 5) = 0.984397 fft 4: mflops = 59.3181 (norm. = 1), norm. avg. (of 5) = 0.999915 fft 5: mflops = 10.9476 (norm. = 0.184558), norm. avg. (of 5) = 0.196674 fft 6: mflops = 29.3454 (norm. = 0.494712), norm. avg. (of 5) = 0.362516 fft 7: mflops = 5.92113 (norm. = 0.0998199), norm. avg. (of 5) = 0.0867515 fft 8: mflops = 8.1121 (norm. = 0.136756), norm. avg. (of 5) = 0.119232 fft 9: mflops = 33.5425 (norm. = 0.565469), norm. avg. (of 5) = 0.404163 fft 10: mflops = 14.5107 (norm. = 0.244626), norm. avg. (of 5) = 0.224033 fft 11: mflops = 3.33546 (norm. = 0.0562301), norm. avg. (of 5) = 0.0559674 Benchmarking for array size = 24: 0. CWP (min N): elapsed time t=1.02588 s, 131072 iters, t-(init.)=0.955145 s t(norm)=0.0662235, mflops=75.5019 1. CWP (best N) (N=28): elapsed time t=1.11067 s, 131072 iters, t-(init.)=1.02902 s t(norm)=0.0713455, mflops=70.0815 2. FFTPACK (f2c): elapsed time t=1.67177 s, 65536 iters, t-(init.)=1.63634 s t(norm)=0.226906, mflops=22.0355 (err=2.4e-16) FFTW_MEASURE plan: (cost = 5.280334e-06) FFTW_TWIDDLE 2 FFTW_NOTW 12 3. FFTW: elapsed time t=1.9722 s, 262144 iters, t-(init.)=1.83046 s t(norm)=0.063456, mflops=78.7948 (err=2.0e-16) FFTW_ESTIMATE plan: (cost = 1.248000e+03) FFTW_TWIDDLE 2 FFTW_NOTW 12 4. FFTW_ESTIMATE: elapsed time t=1.97227 s, 262144 iters, t-(init.)=1.83054 s t(norm)=0.0634587, mflops=78.7914 (err=2.0e-16) 5. Frigo-old: elapsed time t=1.67294 s, 65536 iters, t-(init.)=1.6376 s t(norm)=0.227081, mflops=22.0186 (err=2.7e-16) 6. GSL: elapsed time t=1.04991 s, 65536 iters, t-(init.)=1.01438 s t(norm)=0.14066, mflops=35.5466 (err=2.2e-16) 7. NAPACK (f2c): elapsed time t=1.61948 s, 16384 iters, t-(init.)=1.61065 s t(norm)=0.893378, mflops=5.59674 (err=8.2e-16) 8. Nielsen: elapsed time t=1.53625 s, 32768 iters, t-(init.)=1.51845 s t(norm)=0.421119, mflops=11.8731 (err=1.4e-15) 9. Singleton (f2c): elapsed time t=1.13659 s, 65536 iters, t-(init.)=1.10108 s t(norm)=0.152683, mflops=32.7476 (err=2.2e-16) 10. Temperton (f2c): elapsed time t=1.9154 s, 65536 iters, t-(init.)=1.87994 s t(norm)=0.260686, mflops=19.1802 (err=2.7e-16) 11. Valkenburg: elapsed time t=1.28826 s, 8192 iters, t-(init.)=1.28378 s t(norm)=1.42415, mflops=3.51087 (err=2.9e-16) Top mflops for N=24 = 78.7948 Normalized results and averages for N=24: fft 0: mflops = 75.5019 (norm. = 0.958209), norm. avg. (of 6) = 0.73608 fft 1: mflops = 70.0815 (norm. = 0.889418), norm. avg. (of 6) = 0.627547 fft 2: mflops = 22.0355 (norm. = 0.279657), norm. avg. (of 6) = 0.302121 fft 3: mflops = 78.7948 (norm. = 1), norm. avg. (of 6) = 0.986997 fft 4: mflops = 78.7914 (norm. = 0.999957), norm. avg. (of 6) = 0.999922 fft 5: mflops = 22.0186 (norm. = 0.279442), norm. avg. (of 6) = 0.210469 fft 6: mflops = 35.5466 (norm. = 0.451129), norm. avg. (of 6) = 0.377285 fft 7: mflops = 5.59674 (norm. = 0.0710293), norm. avg. (of 6) = 0.0841312 fft 8: mflops = 11.8731 (norm. = 0.150684), norm. avg. (of 6) = 0.124474 fft 9: mflops = 32.7476 (norm. = 0.415607), norm. avg. (of 6) = 0.406071 fft 10: mflops = 19.1802 (norm. = 0.243419), norm. avg. (of 6) = 0.227264 fft 11: mflops = 3.51087 (norm. = 0.0445572), norm. avg. (of 6) = 0.0540657 Benchmarking for array size = 36: 0. CWP (min N): elapsed time t=1.5681 s, 131072 iters, t-(init.)=1.46514 s t(norm)=0.0600596, mflops=83.2506 1. CWP (best N): elapsed time t=1.56808 s, 131072 iters, t-(init.)=1.46499 s t(norm)=0.0600534, mflops=83.2593 2. FFTPACK (f2c): elapsed time t=1.28223 s, 32768 iters, t-(init.)=1.25655 s t(norm)=0.206037, mflops=24.2675 (err=3.7e-16) FFTW_MEASURE plan: (cost = 8.543701e-06) FFTW_TWIDDLE 3 FFTW_NOTW 12 3. FFTW: elapsed time t=1.53215 s, 131072 iters, t-(init.)=1.42807 s t(norm)=0.0585399, mflops=85.4118 (err=3.5e-16) FFTW_ESTIMATE plan: (cost = 1.803600e+03) FFTW_TWIDDLE 3 FFTW_NOTW 12 4. FFTW_ESTIMATE: elapsed time t=1.53209 s, 131072 iters, t-(init.)=1.42885 s t(norm)=0.0585719, mflops=85.3651 (err=3.5e-16) 5. Frigo-old: elapsed time t=1.10091 s, 16384 iters, t-(init.)=1.0879 s t(norm)=0.356764, mflops=14.0149 (err=4.8e-16) 6. GSL: elapsed time t=1.44031 s, 65536 iters, t-(init.)=1.38886 s t(norm)=0.113866, mflops=43.9114 (err=2.8e-16) 7. NAPACK (f2c): elapsed time t=1.24083 s, 8192 iters, t-(init.)=1.2341 s t(norm)=0.809419, mflops=6.17727 (err=1.0e-15) 8. Nielsen: elapsed time t=1.30979 s, 16384 iters, t-(init.)=1.29688 s t(norm)=0.425298, mflops=11.7565 (err=9.7e-16) 9. Singleton (f2c): elapsed time t=1.26119 s, 65536 iters, t-(init.)=1.20961 s t(norm)=0.0991696, mflops=50.4187 (err=2.7e-16) 10. Temperton (f2c): elapsed time t=1.44819 s, 32768 iters, t-(init.)=1.42237 s t(norm)=0.233225, mflops=21.4385 (err=3.9e-16) 11. Valkenburg: elapsed time t=1.09551 s, 4096 iters, t-(init.)=1.09233 s t(norm)=1.43287, mflops=3.4895 (err=4.0e-16) Top mflops for N=36 = 85.4118 Normalized results and averages for N=36: fft 0: mflops = 83.2506 (norm. = 0.974696), norm. avg. (of 7) = 0.770168 fft 1: mflops = 83.2593 (norm. = 0.974798), norm. avg. (of 7) = 0.677155 fft 2: mflops = 24.2675 (norm. = 0.284124), norm. avg. (of 7) = 0.29955 fft 3: mflops = 85.4118 (norm. = 1), norm. avg. (of 7) = 0.988855 fft 4: mflops = 85.3651 (norm. = 0.999453), norm. avg. (of 7) = 0.999855 fft 5: mflops = 14.0149 (norm. = 0.164086), norm. avg. (of 7) = 0.203843 fft 6: mflops = 43.9114 (norm. = 0.514113), norm. avg. (of 7) = 0.396832 fft 7: mflops = 6.17727 (norm. = 0.0723234), norm. avg. (of 7) = 0.0824443 fft 8: mflops = 11.7565 (norm. = 0.137644), norm. avg. (of 7) = 0.126355 fft 9: mflops = 50.4187 (norm. = 0.590301), norm. avg. (of 7) = 0.432389 fft 10: mflops = 21.4385 (norm. = 0.251002), norm. avg. (of 7) = 0.230655 fft 11: mflops = 3.4895 (norm. = 0.040855), norm. avg. (of 7) = 0.0521784 Benchmarking for array size = 80: 0. CWP (min N): elapsed time t=1.71302 s, 65536 iters, t-(init.)=1.60145 s t(norm)=0.0483164, mflops=103.484 1. CWP (best N) (N=84): elapsed time t=1.60975 s, 65536 iters, t-(init.)=1.49396 s t(norm)=0.0450734, mflops=110.93 2. FFTPACK (f2c): elapsed time t=1.8836 s, 16384 iters, t-(init.)=1.85582 s t(norm)=0.223964, mflops=22.3251 (err=7.7e-16) FFTW_MEASURE plan: (cost = 2.097021e-05) FFTW_TWIDDLE 5 FFTW_NOTW 16 3. FFTW: elapsed time t=1.55585 s, 65536 iters, t-(init.)=1.44508 s t(norm)=0.0435987, mflops=114.682 (err=7.3e-16) FFTW_ESTIMATE plan: (cost = 2.600000e+03) FFTW_TWIDDLE 5 FFTW_NOTW 16 4. FFTW_ESTIMATE: elapsed time t=1.55527 s, 65536 iters, t-(init.)=1.44457 s t(norm)=0.0435832, mflops=114.723 (err=7.3e-16) 5. Frigo-old: elapsed time t=1.23815 s, 16384 iters, t-(init.)=1.2105 s t(norm)=0.146085, mflops=34.2266 (err=7.1e-16) 6. GSL: elapsed time t=1.48313 s, 16384 iters, t-(init.)=1.45555 s t(norm)=0.175658, mflops=28.4643 (err=6.9e-16) 7. NAPACK (f2c): elapsed time t=1.79698 s, 4096 iters, t-(init.)=1.79007 s t(norm)=0.864112, mflops=5.78629 (err=1.1e-15) 8. Nielsen: elapsed time t=1.09174 s, 8192 iters, t-(init.)=1.07778 s t(norm)=0.260137, mflops=19.2206 (err=5.4e-15) 9. Singleton (f2c): elapsed time t=1.15858 s, 32768 iters, t-(init.)=1.10325 s t(norm)=0.066571, mflops=75.1078 (err=1.3e-15) 10. Temperton (f2c): elapsed time t=1.79558 s, 16384 iters, t-(init.)=1.76781 s t(norm)=0.213342, mflops=23.4366 (err=7.0e-16) 11. Valkenburg: elapsed time t=1.12272 s, 2048 iters, t-(init.)=1.11914 s t(norm)=1.08048, mflops=4.62758 (err=8.4e-16) Top mflops for N=80 = 114.723 Normalized results and averages for N=80: fft 0: mflops = 103.484 (norm. = 0.902037), norm. avg. (of 8) = 0.786652 fft 1: mflops = 110.93 (norm. = 0.966938), norm. avg. (of 8) = 0.713377 fft 2: mflops = 22.3251 (norm. = 0.1946), norm. avg. (of 8) = 0.286431 fft 3: mflops = 114.682 (norm. = 0.999645), norm. avg. (of 8) = 0.990204 fft 4: mflops = 114.723 (norm. = 1), norm. avg. (of 8) = 0.999873 fft 5: mflops = 34.2266 (norm. = 0.298341), norm. avg. (of 8) = 0.215655 fft 6: mflops = 28.4643 (norm. = 0.248113), norm. avg. (of 8) = 0.378242 fft 7: mflops = 5.78629 (norm. = 0.050437), norm. avg. (of 8) = 0.0784434 fft 8: mflops = 19.2206 (norm. = 0.167539), norm. avg. (of 8) = 0.131503 fft 9: mflops = 75.1078 (norm. = 0.654687), norm. avg. (of 8) = 0.460176 fft 10: mflops = 23.4366 (norm. = 0.204288), norm. avg. (of 8) = 0.227359 fft 11: mflops = 4.62758 (norm. = 0.040337), norm. avg. (of 8) = 0.0506983 Benchmarking for array size = 108: 0. CWP (min N) (N=110): elapsed time t=1.47552 s, 32768 iters, t-(init.)=1.39993 s t(norm)=0.0585618, mflops=85.3799 1. CWP (best N) (N=112): elapsed time t=1.19715 s, 32768 iters, t-(init.)=1.12054 s t(norm)=0.0468742, mflops=106.668 2. FFTPACK (f2c): elapsed time t=1.05732 s, 8192 iters, t-(init.)=1.03869 s t(norm)=0.173802, mflops=28.7684 (err=4.7e-16) FFTW_MEASURE plan: (cost = 3.167627e-05) FFTW_TWIDDLE 9 FFTW_NOTW 12 3. FFTW: elapsed time t=1.31783 s, 32768 iters, t-(init.)=1.2435 s t(norm)=0.0520182, mflops=96.1202 (err=3.7e-16) FFTW_ESTIMATE plan: (cost = 4.633200e+03) FFTW_TWIDDLE 9 FFTW_NOTW 12 4. FFTW_ESTIMATE: elapsed time t=1.31818 s, 32768 iters, t-(init.)=1.24412 s t(norm)=0.0520438, mflops=96.0728 (err=3.7e-16) 5. Frigo-old: elapsed time t=1.92207 s, 8192 iters, t-(init.)=1.90335 s t(norm)=0.318484, mflops=15.6994 (err=5.5e-16) 6. GSL: elapsed time t=1.44674 s, 16384 iters, t-(init.)=1.40955 s t(norm)=0.117928, mflops=42.3986 (err=4.7e-16) 7. NAPACK (f2c): elapsed time t=1.36154 s, 4096 iters, t-(init.)=1.35198 s t(norm)=0.452447, mflops=11.051 (err=2.7e-15) 8. Nielsen: elapsed time t=1.90807 s, 8192 iters, t-(init.)=1.88946 s t(norm)=0.316159, mflops=15.8148 (err=1.1e-15) 9. Singleton (f2c): elapsed time t=1.12004 s, 16384 iters, t-(init.)=1.08285 s t(norm)=0.0905956, mflops=55.1903 (err=5.1e-16) 10. Temperton (f2c): elapsed time t=1.34924 s, 8192 iters, t-(init.)=1.33053 s t(norm)=0.222635, mflops=22.4583 (err=3.8e-16) 11. Valkenburg: elapsed time t=1.3814 s, 2048 iters, t-(init.)=1.37644 s t(norm)=0.921266, mflops=5.42732 (err=5.2e-16) Top mflops for N=108 = 106.668 Normalized results and averages for N=108: fft 0: mflops = 85.3799 (norm. = 0.800423), norm. avg. (of 9) = 0.788182 fft 1: mflops = 106.668 (norm. = 1), norm. avg. (of 9) = 0.745224 fft 2: mflops = 28.7684 (norm. = 0.2697), norm. avg. (of 9) = 0.284572 fft 3: mflops = 96.1202 (norm. = 0.901112), norm. avg. (of 9) = 0.980305 fft 4: mflops = 96.0728 (norm. = 0.900668), norm. avg. (of 9) = 0.98885 fft 5: mflops = 15.6994 (norm. = 0.147179), norm. avg. (of 9) = 0.208046 fft 6: mflops = 42.3986 (norm. = 0.397481), norm. avg. (of 9) = 0.380379 fft 7: mflops = 11.051 (norm. = 0.103601), norm. avg. (of 9) = 0.0812388 fft 8: mflops = 15.8148 (norm. = 0.148262), norm. avg. (of 9) = 0.133365 fft 9: mflops = 55.1903 (norm. = 0.5174), norm. avg. (of 9) = 0.466535 fft 10: mflops = 22.4583 (norm. = 0.210543), norm. avg. (of 9) = 0.225491 fft 11: mflops = 5.42732 (norm. = 0.0508802), norm. avg. (of 9) = 0.0507185 Benchmarking for array size = 210: 0. CWP (min N): elapsed time t=1.22286 s, 16384 iters, t-(init.)=1.15156 s t(norm)=0.0433863, mflops=115.244 1. CWP (best N): elapsed time t=1.22318 s, 16384 iters, t-(init.)=1.15196 s t(norm)=0.0434016, mflops=115.203 2. FFTPACK (f2c): elapsed time t=1.6293 s, 4096 iters, t-(init.)=1.61142 s t(norm)=0.242849, mflops=20.5889 (err=5.7e-16) FFTW_MEASURE plan: (cost = 8.625195e-05) FFTW_TWIDDLE 3 FFTW_TWIDDLE 7 FFTW_NOTW 10 3. FFTW: elapsed time t=1.67324 s, 16384 iters, t-(init.)=1.60042 s t(norm)=0.0602978, mflops=82.9217 (err=4.6e-16) FFTW_ESTIMATE plan: (cost = 9.324000e+03) FFTW_TWIDDLE 7 FFTW_TWIDDLE 2 FFTW_NOTW 15 4. FFTW_ESTIMATE: elapsed time t=1.65864 s, 16384 iters, t-(init.)=1.58724 s t(norm)=0.0598011, mflops=83.6105 (err=4.6e-16) 5. Frigo-old: elapsed time t=1.9213 s, 4096 iters, t-(init.)=1.90333 s t(norm)=0.286842, mflops=17.4312 (err=5.8e-16) 6. GSL: elapsed time t=1.92577 s, 8192 iters, t-(init.)=1.88992 s t(norm)=0.14241, mflops=35.1098 (err=5.3e-16) 7. NAPACK (f2c): elapsed time t=1.16909 s, 1024 iters, t-(init.)=1.16469 s t(norm)=0.702098, mflops=7.12151 (err=1.4e-14) 8. Nielsen: elapsed time t=1.51572 s, 4096 iters, t-(init.)=1.49775 s t(norm)=0.225718, mflops=22.1515 (err=7.6e-15) 9. Singleton (f2c): elapsed time t=1.43726 s, 8192 iters, t-(init.)=1.40154 s t(norm)=0.105609, mflops=47.3442 (err=6.7e-16) 10. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). 11. Valkenburg: elapsed time t=1.64778 s, 1024 iters, t-(init.)=1.64326 s t(norm)=0.990588, mflops=5.04751 (err=6.5e-16) Top mflops for N=210 = 115.244 Normalized results and averages for N=210: fft 0: mflops = 115.244 (norm. = 1), norm. avg. (of 10) = 0.809364 fft 1: mflops = 115.203 (norm. = 0.999648), norm. avg. (of 10) = 0.770667 fft 2: mflops = 20.5889 (norm. = 0.178655), norm. avg. (of 10) = 0.273981 fft 3: mflops = 82.9217 (norm. = 0.719533), norm. avg. (of 10) = 0.954227 fft 4: mflops = 83.6105 (norm. = 0.725509), norm. avg. (of 10) = 0.962516 fft 5: mflops = 17.4312 (norm. = 0.151255), norm. avg. (of 10) = 0.202367 fft 6: mflops = 35.1098 (norm. = 0.304657), norm. avg. (of 10) = 0.372807 fft 7: mflops = 7.12151 (norm. = 0.0617951), norm. avg. (of 10) = 0.0792944 fft 8: mflops = 22.1515 (norm. = 0.192214), norm. avg. (of 10) = 0.13925 fft 9: mflops = 47.3442 (norm. = 0.410818), norm. avg. (of 10) = 0.460963 fft 10: mflops = -1 (norm. = -0.00867726), norm. avg. (of 9) = 0.225491 fft 11: mflops = 5.04751 (norm. = 0.0437985), norm. avg. (of 10) = 0.0500265 Benchmarking for array size = 504: 0. CWP (min N): elapsed time t=1.64989 s, 8192 iters, t-(init.)=1.56455 s t(norm)=0.0422108, mflops=118.453 1. CWP (best N): elapsed time t=1.64961 s, 8192 iters, t-(init.)=1.5639 s t(norm)=0.0421935, mflops=118.502 2. FFTPACK (f2c): elapsed time t=1.39645 s, 1024 iters, t-(init.)=1.38592 s t(norm)=0.299133, mflops=16.715 (err=9.8e-16) FFTW_MEASURE plan: (cost = 4.064297e-04) FFTW_TWIDDLE 7 FFTW_TWIDDLE 6 FFTW_NOTW 12 3. FFTW: elapsed time t=1.78324 s, 4096 iters, t-(init.)=1.74019 s t(norm)=0.0938993, mflops=53.2485 (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=1.9835 s, 4096 iters, t-(init.)=1.93952 s t(norm)=0.104655, mflops=47.7761 (err=8.8e-16) 5. Frigo-old: elapsed time t=1.3948 s, 1024 iters, t-(init.)=1.3842 s t(norm)=0.29876, mflops=16.7358 (err=1.0e-15) 6. GSL: elapsed time t=1.52763 s, 2048 iters, t-(init.)=1.50601 s t(norm)=0.162526, mflops=30.7644 (err=8.9e-16) 7. NAPACK (f2c): elapsed time t=1.24436 s, 512 iters, t-(init.)=1.23909 s t(norm)=0.53488, mflops=9.34789 (err=4.2e-14) 8. Nielsen: elapsed time t=1.09059 s, 1024 iters, t-(init.)=1.07995 s t(norm)=0.233093, mflops=21.4507 (err=5.8e-15) 9. Singleton (f2c): elapsed time t=1.71988 s, 4096 iters, t-(init.)=1.6759 s t(norm)=0.09043, mflops=55.2914 (err=1.3e-15) 10. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). 11. Valkenburg: elapsed time t=1.01158 s, 256 iters, t-(init.)=1.00889 s t(norm)=0.871024, mflops=5.74037 (err=1.0e-15) Top mflops for N=504 = 118.502 Normalized results and averages for N=504: fft 0: mflops = 118.453 (norm. = 0.999589), norm. avg. (of 11) = 0.826657 fft 1: mflops = 118.502 (norm. = 1), norm. avg. (of 11) = 0.791515 fft 2: mflops = 16.715 (norm. = 0.141053), norm. avg. (of 11) = 0.261896 fft 3: mflops = 53.2485 (norm. = 0.449348), norm. avg. (of 11) = 0.908329 fft 4: mflops = 47.7761 (norm. = 0.403168), norm. avg. (of 11) = 0.911666 fft 5: mflops = 16.7358 (norm. = 0.141228), norm. avg. (of 11) = 0.196809 fft 6: mflops = 30.7644 (norm. = 0.259611), norm. avg. (of 11) = 0.362517 fft 7: mflops = 9.34789 (norm. = 0.078884), norm. avg. (of 11) = 0.0792571 fft 8: mflops = 21.4507 (norm. = 0.181016), norm. avg. (of 11) = 0.143047 fft 9: mflops = 55.2914 (norm. = 0.466587), norm. avg. (of 11) = 0.461474 fft 10: mflops = -1 (norm. = -0.00843869), norm. avg. (of 9) = 0.225491 fft 11: mflops = 5.74037 (norm. = 0.0484412), norm. avg. (of 11) = 0.0498824 Benchmarking for array size = 1000: 0. CWP (min N) (N=1001): elapsed time t=1.52616 s, 2048 iters, t-(init.)=1.47974 s t(norm)=0.072501, mflops=68.9646 1. CWP (best N) (N=1008): elapsed time t=1.10903 s, 2048 iters, t-(init.)=1.06277 s t(norm)=0.0520713, mflops=96.0221 2. FFTPACK (f2c): elapsed time t=1.90999 s, 512 iters, t-(init.)=1.89888 s t(norm)=0.372148, mflops=13.4355 (err=3.1e-15) FFTW_MEASURE plan: (cost = 1.159797e-03) FFTW_TWIDDLE 10 FFTW_TWIDDLE 10 FFTW_NOTW 10 3. FFTW: elapsed time t=1.31885 s, 1024 iters, t-(init.)=1.2963 s t(norm)=0.127026, mflops=39.362 (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=1.32146 s, 1024 iters, t-(init.)=1.2989 s t(norm)=0.127282, mflops=39.283 (err=3.1e-15) 5. Frigo-old: elapsed time t=1.83323 s, 512 iters, t-(init.)=1.82164 s t(norm)=0.357011, mflops=14.0052 (err=3.1e-15) 6. GSL: elapsed time t=1.81632 s, 512 iters, t-(init.)=1.80463 s t(norm)=0.353678, mflops=14.1372 (err=3.1e-15) 7. NAPACK (f2c): elapsed time t=1.06685 s, 128 iters, t-(init.)=1.06399 s t(norm)=0.834093, mflops=5.99454 (err=1.8e-14) 8. Nielsen: elapsed time t=1.15525 s, 512 iters, t-(init.)=1.14361 s t(norm)=0.224129, mflops=22.3086 (err=1.5e-14) 9. Singleton (f2c): elapsed time t=1.64433 s, 2048 iters, t-(init.)=1.59833 s t(norm)=0.0783114, mflops=63.8477 (err=4.7e-15) 10. Temperton (f2c): elapsed time t=1.28339 s, 512 iters, t-(init.)=1.27188 s t(norm)=0.249268, mflops=20.0588 (err=3.0e-15) 11. Valkenburg: elapsed time t=1.27676 s, 128 iters, t-(init.)=1.27386 s t(norm)=0.998617, mflops=5.00693 (err=3.0e-15) Top mflops for N=1000 = 96.0221 Normalized results and averages for N=1000: fft 0: mflops = 68.9646 (norm. = 0.718215), norm. avg. (of 12) = 0.81762 fft 1: mflops = 96.0221 (norm. = 1), norm. avg. (of 12) = 0.808889 fft 2: mflops = 13.4355 (norm. = 0.139921), norm. avg. (of 12) = 0.251732 fft 3: mflops = 39.362 (norm. = 0.409926), norm. avg. (of 12) = 0.866796 fft 4: mflops = 39.283 (norm. = 0.409103), norm. avg. (of 12) = 0.869786 fft 5: mflops = 14.0052 (norm. = 0.145854), norm. avg. (of 12) = 0.192563 fft 6: mflops = 14.1372 (norm. = 0.147228), norm. avg. (of 12) = 0.344576 fft 7: mflops = 5.99454 (norm. = 0.0624287), norm. avg. (of 12) = 0.0778547 fft 8: mflops = 22.3086 (norm. = 0.232328), norm. avg. (of 12) = 0.150487 fft 9: mflops = 63.8477 (norm. = 0.664927), norm. avg. (of 12) = 0.478429 fft 10: mflops = 20.0588 (norm. = 0.208897), norm. avg. (of 10) = 0.223831 fft 11: mflops = 5.00693 (norm. = 0.0521435), norm. avg. (of 12) = 0.0500708 Benchmarking for array size = 1960: 0. CWP (min N) (N=1980): elapsed time t=1.3722 s, 512 iters, t-(init.)=1.136 s t(norm)=0.103506, mflops=48.3062 1. CWP (best N) (N=1980): elapsed time t=1.37174 s, 512 iters, t-(init.)=1.13565 s t(norm)=0.103475, mflops=48.3209 2. FFTPACK (f2c): elapsed time t=1.70503 s, 128 iters, t-(init.)=1.64499 s t(norm)=0.599535, mflops=8.33979 (err=1.5e-15) FFTW_MEASURE plan: (cost = 2.544781e-03) FFTW_TWIDDLE 10 FFTW_TWIDDLE 2 FFTW_TWIDDLE 7 FFTW_NOTW 14 3. FFTW: elapsed time t=1.41427 s, 512 iters, t-(init.)=1.18024 s t(norm)=0.107538, mflops=46.4954 (err=1.4e-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=1.43211 s, 512 iters, t-(init.)=1.19776 s t(norm)=0.109134, mflops=45.8154 (err=1.5e-15) 5. Frigo-old: elapsed time t=1.03386 s, 128 iters, t-(init.)=0.975077 s t(norm)=0.355377, mflops=14.0696 (err=1.5e-15) 6. GSL: elapsed time t=1.68775 s, 256 iters, t-(init.)=1.56927 s t(norm)=0.285969, mflops=17.4844 (err=1.6e-15) 7. NAPACK (f2c): elapsed time t=1.22057 s, 64 iters, t-(init.)=1.19122 s t(norm)=0.868305, mflops=5.75835 (err=1.3e-13) 8. Nielsen: elapsed time t=1.80314 s, 256 iters, t-(init.)=1.6858 s t(norm)=0.307204, mflops=16.2758 (err=1.7e-14) 9. Singleton (f2c): elapsed time t=1.27325 s, 256 iters, t-(init.)=1.15608 s t(norm)=0.210672, mflops=23.7335 (err=2.3e-15) 10. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). 11. Valkenburg: elapsed time t=1.68272 s, 64 iters, t-(init.)=1.65334 s t(norm)=1.20516, mflops=4.14884 (err=1.4e-15) Top mflops for N=1960 = 48.3209 Normalized results and averages for N=1960: fft 0: mflops = 48.3062 (norm. = 0.999695), norm. avg. (of 13) = 0.831626 fft 1: mflops = 48.3209 (norm. = 1), norm. avg. (of 13) = 0.82359 fft 2: mflops = 8.33979 (norm. = 0.172592), norm. avg. (of 13) = 0.245644 fft 3: mflops = 46.4954 (norm. = 0.96222), norm. avg. (of 13) = 0.874136 fft 4: mflops = 45.8154 (norm. = 0.948147), norm. avg. (of 13) = 0.875814 fft 5: mflops = 14.0696 (norm. = 0.291169), norm. avg. (of 13) = 0.200148 fft 6: mflops = 17.4844 (norm. = 0.36184), norm. avg. (of 13) = 0.345904 fft 7: mflops = 5.75835 (norm. = 0.119169), norm. avg. (of 13) = 0.0810327 fft 8: mflops = 16.2758 (norm. = 0.336828), norm. avg. (of 13) = 0.164821 fft 9: mflops = 23.7335 (norm. = 0.491165), norm. avg. (of 13) = 0.479408 fft 10: mflops = -1 (norm. = -0.020695), norm. avg. (of 10) = 0.223831 fft 11: mflops = 4.14884 (norm. = 0.0858601), norm. avg. (of 13) = 0.0528238 Benchmarking for array size = 4725: 0. CWP (min N) (N=5005): elapsed time t=1.08242 s, 128 iters, t-(init.)=0.922567 s t(norm)=0.124971, mflops=40.0093 1. CWP (best N) (N=5040): elapsed time t=1.00775 s, 128 iters, t-(init.)=0.846889 s t(norm)=0.11472, mflops=43.5845 2. FFTPACK (f2c): elapsed time t=1.85975 s, 64 iters, t-(init.)=1.78334 s t(norm)=0.483143, mflops=10.3489 (err=2.4e-15) FFTW_MEASURE plan: (cost = 8.339625e-03) FFTW_TWIDDLE 5 FFTW_TWIDDLE 9 FFTW_TWIDDLE 7 FFTW_NOTW 15 3. FFTW: elapsed time t=1.15237 s, 128 iters, t-(init.)=0.999268 s t(norm)=0.135361, mflops=36.9383 (err=2.3e-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=1.14072 s, 128 iters, t-(init.)=0.987946 s t(norm)=0.133827, mflops=37.3616 (err=2.3e-15) 5. Frigo-old: elapsed time t=1.062 s, 32 iters, t-(init.)=1.02333 s t(norm)=0.554482, mflops=9.01743 (err=2.3e-15) 6. GSL: elapsed time t=1.08723 s, 64 iters, t-(init.)=1.01049 s t(norm)=0.273761, mflops=18.2641 (err=2.4e-15) 7. NAPACK (f2c): elapsed time t=1.54397 s, 32 iters, t-(init.)=1.50544 s t(norm)=0.815709, mflops=6.12964 (err=3.5e-13) 8. Nielsen: elapsed time t=1.42106 s, 64 iters, t-(init.)=1.34406 s t(norm)=0.364133, mflops=13.7312 (err=4.4e-14) 9. Singleton (f2c): elapsed time t=1.10216 s, 64 iters, t-(init.)=1.02571 s t(norm)=0.277886, mflops=17.993 (err=3.3e-15) 10. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). 11. Valkenburg: elapsed time t=1.02579 s, 16 iters, t-(init.)=1.00659 s t(norm)=1.09082, mflops=4.58372 (err=2.3e-15) Top mflops for N=4725 = 43.5845 Normalized results and averages for N=4725: fft 0: mflops = 40.0093 (norm. = 0.91797), norm. avg. (of 14) = 0.837793 fft 1: mflops = 43.5845 (norm. = 1), norm. avg. (of 14) = 0.836191 fft 2: mflops = 10.3489 (norm. = 0.237444), norm. avg. (of 14) = 0.245058 fft 3: mflops = 36.9383 (norm. = 0.847509), norm. avg. (of 14) = 0.872234 fft 4: mflops = 37.3616 (norm. = 0.857222), norm. avg. (of 14) = 0.874486 fft 5: mflops = 9.01743 (norm. = 0.206895), norm. avg. (of 14) = 0.20063 fft 6: mflops = 18.2641 (norm. = 0.41905), norm. avg. (of 14) = 0.351129 fft 7: mflops = 6.12964 (norm. = 0.140638), norm. avg. (of 14) = 0.0852902 fft 8: mflops = 13.7312 (norm. = 0.315049), norm. avg. (of 14) = 0.175552 fft 9: mflops = 17.993 (norm. = 0.41283), norm. avg. (of 14) = 0.474653 fft 10: mflops = -1 (norm. = -0.0229439), norm. avg. (of 10) = 0.223831 fft 11: mflops = 4.58372 (norm. = 0.105168), norm. avg. (of 14) = 0.0565627 Benchmarking for array size = 10368: 0. CWP (min N) (N=10920): elapsed time t=1.37046 s, 64 iters, t-(init.)=1.19513 s t(norm)=0.135017, mflops=37.0323 1. CWP (best N) (N=11088): elapsed time t=1.23629 s, 64 iters, t-(init.)=1.05686 s t(norm)=0.119397, mflops=41.8771 2. FFTPACK (f2c): elapsed time t=1.83929 s, 32 iters, t-(init.)=1.75535 s t(norm)=0.396613, mflops=12.6067 (err=4.7e-15) FFTW_MEASURE plan: (cost = 1.871100e-02) FFTW_TWIDDLE 64 FFTW_TWIDDLE 3 FFTW_TWIDDLE 6 FFTW_NOTW 9 3. FFTW: elapsed time t=1.22446 s, 64 iters, t-(init.)=1.0552 s t(norm)=0.119209, mflops=41.9433 (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=1.43191 s, 64 iters, t-(init.)=1.26313 s t(norm)=0.1427, mflops=35.0386 (err=4.7e-15) 5. Frigo-old: elapsed time t=1.02348 s, 16 iters, t-(init.)=0.981009 s t(norm)=0.44331, mflops=11.2788 (err=4.8e-15) 6. GSL: elapsed time t=1.212 s, 32 iters, t-(init.)=1.12734 s t(norm)=0.254719, mflops=19.6295 (err=4.7e-15) 7. NAPACK (f2c): elapsed time t=1.61605 s, 16 iters, t-(init.)=1.57355 s t(norm)=0.711075, mflops=7.03161 (err=7.8e-14) 8. Nielsen: elapsed time t=1.05422 s, 16 iters, t-(init.)=1.01171 s t(norm)=0.457181, mflops=10.9366 (err=1.1e-14) 9. Singleton (f2c): elapsed time t=1.61977 s, 32 iters, t-(init.)=1.53447 s t(norm)=0.346707, mflops=14.4214 (err=6.7e-15) 10. Temperton (f2c): elapsed time t=1.99212 s, 32 iters, t-(init.)=1.90809 s t(norm)=0.431125, mflops=11.5976 (err=4.7e-15) 11. Valkenburg: elapsed time t=1.28387 s, 8 iters, t-(init.)=1.26244 s t(norm)=1.14098, mflops=4.38222 (err=4.7e-15) Top mflops for N=10368 = 41.9433 Normalized results and averages for N=10368: fft 0: mflops = 37.0323 (norm. = 0.882914), norm. avg. (of 15) = 0.840801 fft 1: mflops = 41.8771 (norm. = 0.998422), norm. avg. (of 15) = 0.847006 fft 2: mflops = 12.6067 (norm. = 0.300566), norm. avg. (of 15) = 0.248759 fft 3: mflops = 41.9433 (norm. = 1), norm. avg. (of 15) = 0.880752 fft 4: mflops = 35.0386 (norm. = 0.835379), norm. avg. (of 15) = 0.871879 fft 5: mflops = 11.2788 (norm. = 0.268906), norm. avg. (of 15) = 0.205182 fft 6: mflops = 19.6295 (norm. = 0.468001), norm. avg. (of 15) = 0.35892 fft 7: mflops = 7.03161 (norm. = 0.167646), norm. avg. (of 15) = 0.0907806 fft 8: mflops = 10.9366 (norm. = 0.260747), norm. avg. (of 15) = 0.181231 fft 9: mflops = 14.4214 (norm. = 0.343831), norm. avg. (of 15) = 0.465931 fft 10: mflops = 11.5976 (norm. = 0.276506), norm. avg. (of 11) = 0.22862 fft 11: mflops = 4.38222 (norm. = 0.10448), norm. avg. (of 15) = 0.0597572 Benchmarking for array size = 27000: 0. CWP (min N) (N=27720): elapsed time t=1.98744 s, 32 iters, t-(init.)=1.72158 s t(norm)=0.135359, mflops=36.9389 1. CWP (best N) (N=27720): elapsed time t=1.98634 s, 32 iters, t-(init.)=1.72041 s t(norm)=0.135266, mflops=36.9641 2. FFTPACK (f2c): elapsed time t=1.37917 s, 8 iters, t-(init.)=1.31447 s t(norm)=0.413398, mflops=12.0949 (err=7.3e-15) FFTW_MEASURE plan: (cost = 7.216000e-02) FFTW_TWIDDLE 10 FFTW_TWIDDLE 10 FFTW_TWIDDLE 10 FFTW_TWIDDLE 3 FFTW_NOTW 9 3. FFTW: elapsed time t=1.1917 s, 16 iters, t-(init.)=1.06203 s t(norm)=0.167004, mflops=29.9394 (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=1.24754 s, 16 iters, t-(init.)=1.11813 s t(norm)=0.175825, mflops=28.4373 (err=7.3e-15) 5. Frigo-old: elapsed time t=1.11176 s, 4 iters, t-(init.)=1.07897 s t(norm)=0.678668, mflops=7.36738 (err=7.3e-15) 6. GSL: elapsed time t=1.0637 s, 8 iters, t-(init.)=0.998479 s t(norm)=0.31402, mflops=15.9225 (err=7.3e-15) 7. NAPACK (f2c): elapsed time t=1.49273 s, 4 iters, t-(init.)=1.46028 s t(norm)=0.918514, mflops=5.44357 (err=1.0e-12) 8. Nielsen: elapsed time t=1.65702 s, 8 iters, t-(init.)=1.59243 s t(norm)=0.500816, mflops=9.9837 (err=2.0e-13) 9. Singleton (f2c): elapsed time t=1.381 s, 8 iters, t-(init.)=1.31692 s t(norm)=0.414168, mflops=12.0724 (err=1.1e-14) 10. Temperton (f2c): elapsed time t=1.54496 s, 8 iters, t-(init.)=1.47955 s t(norm)=0.465318, mflops=10.7453 (err=7.3e-15) 11. Valkenburg: elapsed time t=1.06434 s, 2 iters, t-(init.)=1.04756 s t(norm)=1.31782, mflops=3.79414 (err=7.3e-15) Top mflops for N=27000 = 36.9641 Normalized results and averages for N=27000: fft 0: mflops = 36.9389 (norm. = 0.999317), norm. avg. (of 16) = 0.850709 fft 1: mflops = 36.9641 (norm. = 1), norm. avg. (of 16) = 0.856568 fft 2: mflops = 12.0949 (norm. = 0.327206), norm. avg. (of 16) = 0.253662 fft 3: mflops = 29.9394 (norm. = 0.809959), norm. avg. (of 16) = 0.876327 fft 4: mflops = 28.4373 (norm. = 0.769323), norm. avg. (of 16) = 0.865469 fft 5: mflops = 7.36738 (norm. = 0.199312), norm. avg. (of 16) = 0.204815 fft 6: mflops = 15.9225 (norm. = 0.430757), norm. avg. (of 16) = 0.36341 fft 7: mflops = 5.44357 (norm. = 0.147266), norm. avg. (of 16) = 0.094311 fft 8: mflops = 9.9837 (norm. = 0.270092), norm. avg. (of 16) = 0.186785 fft 9: mflops = 12.0724 (norm. = 0.326597), norm. avg. (of 16) = 0.457223 fft 10: mflops = 10.7453 (norm. = 0.290697), norm. avg. (of 12) = 0.233793 fft 11: mflops = 3.79414 (norm. = 0.102644), norm. avg. (of 16) = 0.0624376 Benchmarking for array size = 75600: 0. CWP (min N) (N=80080): elapsed time t=1.78352 s, 8 iters, t-(init.)=1.57719 s t(norm)=0.160914, mflops=31.0724 1. CWP (best N) (N=80080): elapsed time t=1.78275 s, 8 iters, t-(init.)=1.5771 s t(norm)=0.160905, mflops=31.0743 2. FFTPACK (f2c): elapsed time t=1.47089 s, 2 iters, t-(init.)=1.42234 s t(norm)=0.580461, mflops=8.61384 (err=9.4e-15) FFTW_MEASURE plan: (cost = 2.248620e-01) FFTW_TWIDDLE 16 FFTW_TWIDDLE 9 FFTW_TWIDDLE 7 FFTW_TWIDDLE 5 FFTW_NOTW 15 3. FFTW: elapsed time t=1.88245 s, 8 iters, t-(init.)=1.68718 s t(norm)=0.172135, mflops=29.0469 (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=1.02891 s, 4 iters, t-(init.)=0.931121 s t(norm)=0.189997, mflops=26.3163 (err=9.4e-15) 5. Frigo-old: elapsed time t=1.92197 s, 2 iters, t-(init.)=1.87358 s t(norm)=0.764613, mflops=6.53925 (err=9.4e-15) 6. GSL: elapsed time t=1.76617 s, 4 iters, t-(init.)=1.66883 s t(norm)=0.340527, mflops=14.6831 (err=9.4e-15) 7. NAPACK (f2c): elapsed time t=1.16445 s, 1 iters, t-(init.)=1.14021 s t(norm)=0.930649, mflops=5.37259 (err=5.1e-12) 8. Nielsen: elapsed time t=1.64949 s, 2 iters, t-(init.)=1.60066 s t(norm)=0.653234, mflops=7.65422 (err=4.7e-13) 9. Singleton (f2c): elapsed time t=1.36739 s, 2 iters, t-(init.)=1.32001 s t(norm)=0.538698, mflops=9.28163 (err=1.3e-14) 10. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). 11. Valkenburg: elapsed time t=1.88947 s, 1 iters, t-(init.)=1.86508 s t(norm)=1.52229, mflops=3.28453 (err=9.5e-15) Top mflops for N=75600 = 31.0743 Normalized results and averages for N=75600: fft 0: mflops = 31.0724 (norm. = 0.999941), norm. avg. (of 17) = 0.859487 fft 1: mflops = 31.0743 (norm. = 1), norm. avg. (of 17) = 0.865005 fft 2: mflops = 8.61384 (norm. = 0.277202), norm. avg. (of 17) = 0.255046 fft 3: mflops = 29.0469 (norm. = 0.934758), norm. avg. (of 17) = 0.879764 fft 4: mflops = 26.3163 (norm. = 0.846883), norm. avg. (of 17) = 0.864376 fft 5: mflops = 6.53925 (norm. = 0.21044), norm. avg. (of 17) = 0.205146 fft 6: mflops = 14.6831 (norm. = 0.472517), norm. avg. (of 17) = 0.369828 fft 7: mflops = 5.37259 (norm. = 0.172895), norm. avg. (of 17) = 0.0989336 fft 8: mflops = 7.65422 (norm. = 0.24632), norm. avg. (of 17) = 0.190287 fft 9: mflops = 9.28163 (norm. = 0.298692), norm. avg. (of 17) = 0.447898 fft 10: mflops = -1 (norm. = -0.032181), norm. avg. (of 12) = 0.233793 fft 11: mflops = 3.28453 (norm. = 0.105699), norm. avg. (of 17) = 0.0649824 Benchmarking for array size = 165375: 0. CWP (min N) (N=180180): elapsed time t=1.37961 s, 2 iters, t-(init.)=1.26357 s t(norm)=0.220377, mflops=22.6884 1. CWP (best N) (N=180180): elapsed time t=1.37909 s, 2 iters, t-(init.)=1.26256 s t(norm)=0.2202, mflops=22.7066 2. FFTPACK (f2c): elapsed time t=2.49143 s, 1 iters, t-(init.)=2.43829 s t(norm)=0.850515, mflops=5.87879 (err=3.7e-14) FFTW_MEASURE plan: (cost = 6.754800e-01) FFTW_TWIDDLE 9 FFTW_TWIDDLE 7 FFTW_TWIDDLE 7 FFTW_TWIDDLE 5 FFTW_TWIDDLE 5 FFTW_NOTW 15 3. FFTW: elapsed time t=1.2649 s, 2 iters, t-(init.)=1.15873 s t(norm)=0.202091, mflops=24.7413 (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=1.27358 s, 2 iters, t-(init.)=1.16704 s t(norm)=0.203542, mflops=24.5649 (err=3.7e-14) 5. Frigo-old: elapsed time t=3.10736 s, 1 iters, t-(init.)=3.05423 s t(norm)=1.06536, mflops=4.69323 (err=3.7e-14) 6. GSL: elapsed time t=1.00794 s, 1 iters, t-(init.)=0.954787 s t(norm)=0.333045, mflops=15.013 (err=3.7e-14) 7. NAPACK (f2c): elapsed time t=3.00974 s, 1 iters, t-(init.)=2.95639 s t(norm)=1.03124, mflops=4.84855 (err=1.6e-11) 8. Nielsen: elapsed time t=2.10189 s, 1 iters, t-(init.)=2.04849 s t(norm)=0.714546, mflops=6.99745 (err=1.6e-12) 9. Singleton (f2c): elapsed time t=1.5362 s, 1 iters, t-(init.)=1.48369 s t(norm)=0.517537, mflops=9.66115 (err=5.6e-14) 10. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). 11. Valkenburg: elapsed time t=4.8696 s, 1 iters, t-(init.)=4.81622 s t(norm)=1.67998, mflops=2.97623 (err=3.6e-14) Top mflops for N=165375 = 24.7413 Normalized results and averages for N=165375: fft 0: mflops = 22.6884 (norm. = 0.917024), norm. avg. (of 18) = 0.862683 fft 1: mflops = 22.7066 (norm. = 0.917764), norm. avg. (of 18) = 0.867936 fft 2: mflops = 5.87879 (norm. = 0.237611), norm. avg. (of 18) = 0.254078 fft 3: mflops = 24.7413 (norm. = 1), norm. avg. (of 18) = 0.886444 fft 4: mflops = 24.5649 (norm. = 0.992873), norm. avg. (of 18) = 0.871514 fft 5: mflops = 4.69323 (norm. = 0.189692), norm. avg. (of 18) = 0.204287 fft 6: mflops = 15.013 (norm. = 0.606799), norm. avg. (of 18) = 0.382993 fft 7: mflops = 4.84855 (norm. = 0.19597), norm. avg. (of 18) = 0.104325 fft 8: mflops = 6.99745 (norm. = 0.282825), norm. avg. (of 18) = 0.195428 fft 9: mflops = 9.66115 (norm. = 0.390487), norm. avg. (of 18) = 0.444708 fft 10: mflops = -1 (norm. = -0.0404183), norm. avg. (of 12) = 0.233793 fft 11: mflops = 2.97623 (norm. = 0.120294), norm. avg. (of 18) = 0.0680553 ------------------------------------------------------ @@@@ 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=1.29423 s, 32768 iters, t-(init.)=1.24957 s t(norm)=0.0993067, mflops=50.349 (err=1.9e-16) 1. Skipping fft (all dimensions must be > 4 for HARM). 2. NR (C): elapsed time t=1.32881 s, 32768 iters, t-(init.)=1.2841 s t(norm)=0.102051, mflops=48.995 (err=2.3e-16) 3. PDA (f2c): elapsed time t=1.92906 s, 8192 iters, t-(init.)=1.91803 s t(norm)=0.609724, mflops=8.20043 (err=2.8e-16) 4. Singleton (f2c): elapsed time t=1.44687 s, 65536 iters, t-(init.)=1.35742 s t(norm)=0.0539392, mflops=92.697 (err=1.9e-16) 5. Temperton (f2c): elapsed time t=1.10051 s, 16384 iters, t-(init.)=1.07814 s t(norm)=0.171366, mflops=29.1773 (err=1.9e-16) Top mflops for N=64 = 92.697 Normalized results and averages for N=64: fft 0: mflops = 50.349 (norm. = 0.543157), norm. avg. (of 1) = 0.543157 fft 1: mflops = -1 (norm. = -0.0107878), norm. avg. (of 0) = -1 fft 2: mflops = 48.995 (norm. = 0.52855), norm. avg. (of 1) = 0.52855 fft 3: mflops = 8.20043 (norm. = 0.0884649), norm. avg. (of 1) = 0.0884649 fft 4: mflops = 92.697 (norm. = 1), norm. avg. (of 1) = 1 fft 5: mflops = 29.1773 (norm. = 0.31476), norm. avg. (of 1) = 0.31476 Benchmarking for array size = 8x8x8 (power of 2): 0. FFTW: elapsed time t=1.50588 s, 8192 iters, t-(init.)=1.41779 s t(norm)=0.0375586, mflops=133.125 (err=3.8e-16) 1. HARM (f2c): elapsed time t=1.45771 s, 2048 iters, t-(init.)=1.43597 s t(norm)=0.152161, mflops=32.86 (err=3.6e-16) 2. NR (C): elapsed time t=1.47622 s, 4096 iters, t-(init.)=1.43268 s t(norm)=0.0759064, mflops=65.8706 (err=2.9e-16) 3. PDA (f2c): elapsed time t=1.53429 s, 1024 iters, t-(init.)=1.52318 s t(norm)=0.322804, mflops=15.4893 (err=3.1e-16) 4. Singleton (f2c): elapsed time t=1.22482 s, 4096 iters, t-(init.)=1.18117 s t(norm)=0.0625807, mflops=79.8968 (err=3.1e-16) 5. Temperton (f2c): elapsed time t=1.54645 s, 2048 iters, t-(init.)=1.52458 s t(norm)=0.16155, mflops=30.9501 (err=3.7e-16) Top mflops for N=512 = 133.125 Normalized results and averages for N=512: fft 0: mflops = 133.125 (norm. = 1), norm. avg. (of 2) = 0.771579 fft 1: mflops = 32.86 (norm. = 0.246835), norm. avg. (of 1) = 0.246835 fft 2: mflops = 65.8706 (norm. = 0.494802), norm. avg. (of 2) = 0.511676 fft 3: mflops = 15.4893 (norm. = 0.116351), norm. avg. (of 2) = 0.102408 fft 4: mflops = 79.8968 (norm. = 0.600163), norm. avg. (of 2) = 0.800082 fft 5: mflops = 30.9501 (norm. = 0.232489), norm. avg. (of 2) = 0.273624 Benchmarking for array size = 16x16x16 (power of 2): 0. FFTW: elapsed time t=1.7986 s, 256 iters, t-(init.)=1.54088 s t(norm)=0.122458, mflops=40.8304 (err=4.1e-16) 1. HARM (f2c): elapsed time t=1.71043 s, 128 iters, t-(init.)=1.58229 s t(norm)=0.251499, mflops=19.8808 (err=4.0e-16) 2. NR (C): elapsed time t=1.64118 s, 64 iters, t-(init.)=1.57697 s t(norm)=0.501305, mflops=9.97396 (err=4.7e-16) 3. PDA (f2c): elapsed time t=1.16837 s, 64 iters, t-(init.)=1.10405 s t(norm)=0.350967, mflops=14.2464 (err=3.8e-16) 4. Singleton (f2c): elapsed time t=1.96594 s, 128 iters, t-(init.)=1.83781 s t(norm)=0.292113, mflops=17.1167 (err=4.7e-16) 5. Temperton (f2c): elapsed time t=1.85832 s, 128 iters, t-(init.)=1.73005 s t(norm)=0.274985, mflops=18.1828 (err=4.1e-16) Top mflops for N=4096 = 40.8304 Normalized results and averages for N=4096: fft 0: mflops = 40.8304 (norm. = 1), norm. avg. (of 3) = 0.847719 fft 1: mflops = 19.8808 (norm. = 0.486912), norm. avg. (of 2) = 0.366874 fft 2: mflops = 9.97396 (norm. = 0.244278), norm. avg. (of 3) = 0.422543 fft 3: mflops = 14.2464 (norm. = 0.348915), norm. avg. (of 3) = 0.184577 fft 4: mflops = 17.1167 (norm. = 0.419215), norm. avg. (of 3) = 0.673126 fft 5: mflops = 18.1828 (norm. = 0.445326), norm. avg. (of 3) = 0.330858 Benchmarking for array size = 32x32x32 (power of 2): 0. FFTW: elapsed time t=1.33899 s, 16 iters, t-(init.)=1.17838 s t(norm)=0.149839, mflops=33.3691 (err=4.8e-16) 1. HARM (f2c): elapsed time t=1.28069 s, 8 iters, t-(init.)=1.201 s t(norm)=0.30543, mflops=16.3704 (err=4.8e-16) 2. NR (C): elapsed time t=1.27827 s, 4 iters, t-(init.)=1.23808 s t(norm)=0.629718, mflops=7.94006 (err=6.0e-16) 3. PDA (f2c): elapsed time t=1.77363 s, 8 iters, t-(init.)=1.69425 s t(norm)=0.43087, mflops=11.6044 (err=4.5e-16) 4. Singleton (f2c): elapsed time t=1.84967 s, 8 iters, t-(init.)=1.76988 s t(norm)=0.450105, mflops=11.1085 (err=4.9e-16) 5. Temperton (f2c): elapsed time t=1.72257 s, 8 iters, t-(init.)=1.64254 s t(norm)=0.417721, mflops=11.9697 (err=5.1e-16) Top mflops for N=32768 = 33.3691 Normalized results and averages for N=32768: fft 0: mflops = 33.3691 (norm. = 1), norm. avg. (of 4) = 0.885789 fft 1: mflops = 16.3704 (norm. = 0.490585), norm. avg. (of 3) = 0.408111 fft 2: mflops = 7.94006 (norm. = 0.237947), norm. avg. (of 4) = 0.376394 fft 3: mflops = 11.6044 (norm. = 0.34776), norm. avg. (of 4) = 0.225373 fft 4: mflops = 11.1085 (norm. = 0.332898), norm. avg. (of 4) = 0.588069 fft 5: mflops = 11.9697 (norm. = 0.358707), norm. avg. (of 4) = 0.33782 Benchmarking for array size = 64x64x64 (power of 2): 0. FFTW: elapsed time t=1.99329 s, 2 iters, t-(init.)=1.8246 s t(norm)=0.193342, mflops=25.8609 (err=1.0e-15) 1. HARM (f2c): elapsed time t=1.66907 s, 1 iters, t-(init.)=1.58461 s t(norm)=0.335823, mflops=14.8888 (err=1.0e-15) 2. NR (C): elapsed time t=4.29947 s, 1 iters, t-(init.)=4.21466 s t(norm)=0.893202, mflops=5.59783 (err=1.0e-15) 3. PDA (f2c): elapsed time t=2.33942 s, 1 iters, t-(init.)=2.25474 s t(norm)=0.477842, mflops=10.4637 (err=1.0e-15) 4. Singleton (f2c): elapsed time t=2.63997 s, 1 iters, t-(init.)=2.55578 s t(norm)=0.54164, mflops=9.23122 (err=1.4e-15) 5. Temperton (f2c): elapsed time t=2.13704 s, 1 iters, t-(init.)=2.05234 s t(norm)=0.434948, mflops=11.4956 (err=9.9e-16) Top mflops for N=262144 = 25.8609 Normalized results and averages for N=262144: fft 0: mflops = 25.8609 (norm. = 1), norm. avg. (of 5) = 0.908631 fft 1: mflops = 14.8888 (norm. = 0.575726), norm. avg. (of 4) = 0.450014 fft 2: mflops = 5.59783 (norm. = 0.216459), norm. avg. (of 5) = 0.344407 fft 3: mflops = 10.4637 (norm. = 0.404615), norm. avg. (of 5) = 0.261221 fft 4: mflops = 9.23122 (norm. = 0.356956), norm. avg. (of 5) = 0.541847 fft 5: mflops = 11.4956 (norm. = 0.444517), norm. avg. (of 5) = 0.35916 Benchmarking for array size = 256x64x32 (power of 2): 0. FFTW: elapsed time t=2.12224 s, 1 iters, t-(init.)=1.9521 s t(norm)=0.195965, mflops=25.5148 (err=9.2e-16) 1. HARM (f2c): elapsed time t=3.72793 s, 1 iters, t-(init.)=3.55882 s t(norm)=0.357258, mflops=13.9955 (err=9.4e-16) 2. NR (C): elapsed time t=9.1143 s, 1 iters, t-(init.)=8.94589 s t(norm)=0.898049, mflops=5.56762 (err=9.6e-16) 3. PDA (f2c): elapsed time t=4.89189 s, 1 iters, t-(init.)=4.72274 s t(norm)=0.4741, mflops=10.5463 (err=8.8e-16) 4. Singleton (f2c): elapsed time t=5.98665 s, 1 iters, t-(init.)=5.81693 s t(norm)=0.583943, mflops=8.56248 (err=1.3e-15) 5. Temperton (f2c): elapsed time t=5.10411 s, 1 iters, t-(init.)=4.9349 s t(norm)=0.495398, mflops=10.0929 (err=9.2e-16) Top mflops for N=524288 = 25.5148 Normalized results and averages for N=524288: fft 0: mflops = 25.5148 (norm. = 1), norm. avg. (of 6) = 0.92386 fft 1: mflops = 13.9955 (norm. = 0.548524), norm. avg. (of 5) = 0.469716 fft 2: mflops = 5.56762 (norm. = 0.218212), norm. avg. (of 6) = 0.323375 fft 3: mflops = 10.5463 (norm. = 0.41334), norm. avg. (of 6) = 0.286574 fft 4: mflops = 8.56248 (norm. = 0.335589), norm. avg. (of 6) = 0.50747 fft 5: mflops = 10.0929 (norm. = 0.39557), norm. avg. (of 6) = 0.365228 Benchmarking for array size = 16x1024x64 (power of 2): 0. FFTW: elapsed time t=5.18783 s, 1 iters, t-(init.)=4.84959 s t(norm)=0.231246, mflops=21.622 (err=1.2e-15) 1. HARM (f2c): elapsed time t=7.6192 s, 1 iters, t-(init.)=7.28212 s t(norm)=0.347239, mflops=14.3993 (err=1.2e-15) 2. NR (C): elapsed time t=18.817 s, 1 iters, t-(init.)=18.4802 s t(norm)=0.881206, mflops=5.67404 (err=1.3e-15) 3. PDA (f2c): elapsed time t=11.2298 s, 1 iters, t-(init.)=10.8929 s t(norm)=0.519413, mflops=9.62625 (err=1.2e-15) 4. Singleton (f2c): elapsed time t=11.7429 s, 1 iters, t-(init.)=11.4049 s t(norm)=0.543826, mflops=9.19412 (err=1.7e-15) 5. Skipping fft (Temperton can't handle dimensions > 256). Top mflops for N=1048576 = 21.622 Normalized results and averages for N=1048576: fft 0: mflops = 21.622 (norm. = 1), norm. avg. (of 7) = 0.934737 fft 1: mflops = 14.3993 (norm. = 0.665958), norm. avg. (of 6) = 0.502423 fft 2: mflops = 5.67404 (norm. = 0.262421), norm. avg. (of 7) = 0.314667 fft 3: mflops = 9.62625 (norm. = 0.445207), norm. avg. (of 7) = 0.309236 fft 4: mflops = 9.19412 (norm. = 0.425222), norm. avg. (of 7) = 0.49572 fft 5: mflops = -1 (norm. = -0.0462493), norm. avg. (of 6) = 0.365228 ------------------------------------------------------ @@@@ 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=1.38971 s, 16384 iters, t-(init.)=1.34712 s t(norm)=0.0944293, mflops=52.9497 (err=2.4e-16) 1. PDA (f2c): elapsed time t=1.53304 s, 4096 iters, t-(init.)=1.52217 s t(norm)=0.4268, mflops=11.7151 (err=2.1e-16) 2. Singleton (f2c): elapsed time t=1.29295 s, 32768 iters, t-(init.)=1.20767 s t(norm)=0.0423271, mflops=118.128 (err=3.1e-16) 3. Temperton (f2c): elapsed time t=1.30357 s, 8192 iters, t-(init.)=1.28225 s t(norm)=0.179765, mflops=27.8141 (err=2.4e-16) Top mflops for N=125 = 118.128 Normalized results and averages for N=125: fft 0: mflops = 52.9497 (norm. = 0.448241), norm. avg. (of 1) = 0.448241 fft 1: mflops = 11.7151 (norm. = 0.0991731), norm. avg. (of 1) = 0.0991731 fft 2: mflops = 118.128 (norm. = 1), norm. avg. (of 1) = 1 fft 3: mflops = 27.8141 (norm. = 0.235458), norm. avg. (of 1) = 0.235458 Benchmarking for array size = 6x6x6: 0. FFTW: elapsed time t=1.75753 s, 16384 iters, t-(init.)=1.68429 s t(norm)=0.0613717, mflops=81.4708 (err=3.0e-16) 1. PDA (f2c): elapsed time t=1.36781 s, 2048 iters, t-(init.)=1.3587 s t(norm)=0.396064, mflops=12.6242 (err=3.7e-16) 2. Singleton (f2c): elapsed time t=1.01126 s, 8192 iters, t-(init.)=0.974601 s t(norm)=0.0710244, mflops=70.3983 (err=3.1e-16) 3. Temperton (f2c): elapsed time t=1.33328 s, 4096 iters, t-(init.)=1.3149 s t(norm)=0.191648, mflops=26.0895 (err=3.2e-16) Top mflops for N=216 = 81.4708 Normalized results and averages for N=216: fft 0: mflops = 81.4708 (norm. = 1), norm. avg. (of 2) = 0.724121 fft 1: mflops = 12.6242 (norm. = 0.154954), norm. avg. (of 2) = 0.127063 fft 2: mflops = 70.3983 (norm. = 0.864093), norm. avg. (of 2) = 0.932046 fft 3: mflops = 26.0895 (norm. = 0.320231), norm. avg. (of 2) = 0.277845 Benchmarking for array size = 7x7x7: 0. FFTW: elapsed time t=1.75897 s, 8192 iters, t-(init.)=1.70095 s t(norm)=0.071877, mflops=69.5633 (err=4.0e-16) 1. PDA (f2c): elapsed time t=1.98641 s, 1024 iters, t-(init.)=1.97897 s t(norm)=0.669001, mflops=7.47383 (err=4.0e-16) 2. Singleton (f2c): elapsed time t=1.91524 s, 8192 iters, t-(init.)=1.85736 s t(norm)=0.0784861, mflops=63.7055 (err=4.9e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=343 = 69.5633 Normalized results and averages for N=343: fft 0: mflops = 69.5633 (norm. = 1), norm. avg. (of 3) = 0.81608 fft 1: mflops = 7.47383 (norm. = 0.107439), norm. avg. (of 3) = 0.120522 fft 2: mflops = 63.7055 (norm. = 0.915792), norm. avg. (of 3) = 0.926628 fft 3: mflops = -1 (norm. = -0.0143754), norm. avg. (of 2) = 0.277845 Benchmarking for array size = 9x9x9: 0. FFTW: elapsed time t=1.5543 s, 4096 iters, t-(init.)=1.49137 s t(norm)=0.0525203, mflops=95.2013 (err=5.4e-16) 1. PDA (f2c): elapsed time t=1.15298 s, 512 iters, t-(init.)=1.14493 s t(norm)=0.32256, mflops=15.501 (err=5.2e-16) 2. Singleton (f2c): elapsed time t=1.86934 s, 4096 iters, t-(init.)=1.80675 s t(norm)=0.0636269, mflops=78.5831 (err=4.9e-16) 3. Temperton (f2c): elapsed time t=1.21761 s, 1024 iters, t-(init.)=1.20185 s t(norm)=0.169299, mflops=29.5336 (err=5.8e-16) Top mflops for N=729 = 95.2013 Normalized results and averages for N=729: fft 0: mflops = 95.2013 (norm. = 1), norm. avg. (of 4) = 0.86206 fft 1: mflops = 15.501 (norm. = 0.162823), norm. avg. (of 4) = 0.131097 fft 2: mflops = 78.5831 (norm. = 0.825441), norm. avg. (of 4) = 0.901332 fft 3: mflops = 29.5336 (norm. = 0.310222), norm. avg. (of 3) = 0.288637 Benchmarking for array size = 10x10x10: 0. FFTW: elapsed time t=1.1306 s, 2048 iters, t-(init.)=1.0851 s t(norm)=0.0531652, mflops=94.0466 (err=3.8e-16) 1. PDA (f2c): elapsed time t=1.5981 s, 512 iters, t-(init.)=1.58622 s t(norm)=0.310872, mflops=16.0838 (err=4.2e-16) 2. Singleton (f2c): elapsed time t=1.50103 s, 2048 iters, t-(init.)=1.45558 s t(norm)=0.0713175, mflops=70.109 (err=4.4e-16) 3. Temperton (f2c): elapsed time t=1.05718 s, 512 iters, t-(init.)=1.04602 s t(norm)=0.205002, mflops=24.39 (err=3.6e-16) Top mflops for N=1000 = 94.0466 Normalized results and averages for N=1000: fft 0: mflops = 94.0466 (norm. = 1), norm. avg. (of 5) = 0.889648 fft 1: mflops = 16.0838 (norm. = 0.171019), norm. avg. (of 5) = 0.139082 fft 2: mflops = 70.109 (norm. = 0.745471), norm. avg. (of 5) = 0.87016 fft 3: mflops = 24.39 (norm. = 0.259339), norm. avg. (of 4) = 0.281313 Benchmarking for array size = 11x11x11: 0. FFTW: elapsed time t=1.05659 s, 512 iters, t-(init.)=0.914127 s t(norm)=0.129251, mflops=38.6845 (err=4.0e-16) 1. PDA (f2c): elapsed time t=1.28569 s, 128 iters, t-(init.)=1.24998 s t(norm)=0.70695, mflops=7.07264 (err=4.8e-16) 2. Singleton (f2c): elapsed time t=1.92692 s, 1024 iters, t-(init.)=1.64203 s t(norm)=0.116085, mflops=43.0718 (err=6.4e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=1331 = 43.0718 Normalized results and averages for N=1331: fft 0: mflops = 38.6845 (norm. = 0.898141), norm. avg. (of 6) = 0.891064 fft 1: mflops = 7.07264 (norm. = 0.164206), norm. avg. (of 6) = 0.143269 fft 2: mflops = 43.0718 (norm. = 1), norm. avg. (of 6) = 0.8918 fft 3: mflops = -1 (norm. = -0.0232171), norm. avg. (of 4) = 0.281313 Benchmarking for array size = 12x12x12: 0. FFTW: elapsed time t=1.88424 s, 1024 iters, t-(init.)=1.46395 s t(norm)=0.0769269, mflops=64.9968 (err=3.8e-16) 1. PDA (f2c): elapsed time t=1.51965 s, 256 iters, t-(init.)=1.41456 s t(norm)=0.297325, mflops=16.8166 (err=3.8e-16) 2. Singleton (f2c): elapsed time t=1.29841 s, 256 iters, t-(init.)=1.1933 s t(norm)=0.250819, mflops=19.9347 (err=4.0e-16) 3. Temperton (f2c): elapsed time t=1.09376 s, 256 iters, t-(init.)=0.988327 s t(norm)=0.207736, mflops=24.069 (err=3.8e-16) Top mflops for N=1728 = 64.9968 Normalized results and averages for N=1728: fft 0: mflops = 64.9968 (norm. = 1), norm. avg. (of 7) = 0.906626 fft 1: mflops = 16.8166 (norm. = 0.25873), norm. avg. (of 7) = 0.159763 fft 2: mflops = 19.9347 (norm. = 0.306703), norm. avg. (of 7) = 0.808214 fft 3: mflops = 24.069 (norm. = 0.370311), norm. avg. (of 5) = 0.299112 Benchmarking for array size = 13x13x13: 0. FFTW: elapsed time t=1.99388 s, 512 iters, t-(init.)=1.73494 s t(norm)=0.138935, mflops=35.9882 (err=4.1e-16) 1. PDA (f2c): elapsed time t=1.19476 s, 64 iters, t-(init.)=1.16241 s t(norm)=0.744687, mflops=6.71423 (err=7.2e-16) 2. Singleton (f2c): elapsed time t=1.87715 s, 512 iters, t-(init.)=1.61836 s t(norm)=0.129599, mflops=38.5805 (err=4.3e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=2197 = 38.5805 Normalized results and averages for N=2197: fft 0: mflops = 35.9882 (norm. = 0.932807), norm. avg. (of 8) = 0.909899 fft 1: mflops = 6.71423 (norm. = 0.174032), norm. avg. (of 8) = 0.161547 fft 2: mflops = 38.5805 (norm. = 1), norm. avg. (of 8) = 0.832188 fft 3: mflops = -1 (norm. = -0.0259198), norm. avg. (of 5) = 0.299112 Benchmarking for array size = 14x14x14: 0. FFTW: elapsed time t=1.94733 s, 512 iters, t-(init.)=1.63275 s t(norm)=0.101747, mflops=49.1414 (err=3.9e-16) 1. PDA (f2c): elapsed time t=1.00904 s, 64 iters, t-(init.)=0.969554 s t(norm)=0.483352, mflops=10.3444 (err=3.8e-16) 2. Singleton (f2c): elapsed time t=1.85972 s, 256 iters, t-(init.)=1.70266 s t(norm)=0.212207, mflops=23.5619 (err=4.6e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=2744 = 49.1414 Normalized results and averages for N=2744: fft 0: mflops = 49.1414 (norm. = 1), norm. avg. (of 9) = 0.91991 fft 1: mflops = 10.3444 (norm. = 0.210503), norm. avg. (of 9) = 0.166987 fft 2: mflops = 23.5619 (norm. = 0.479472), norm. avg. (of 9) = 0.792997 fft 3: mflops = -1 (norm. = -0.0203494), norm. avg. (of 5) = 0.299112 Benchmarking for array size = 15x15x15: 0. FFTW: elapsed time t=1.14163 s, 256 iters, t-(init.)=0.936587 s t(norm)=0.0924873, mflops=54.0615 (err=4.6e-16) 1. PDA (f2c): elapsed time t=1.57204 s, 128 iters, t-(init.)=1.46922 s t(norm)=0.290169, mflops=17.2314 (err=4.5e-16) 2. Singleton (f2c): elapsed time t=1.17186 s, 128 iters, t-(init.)=1.06938 s t(norm)=0.211201, mflops=23.6741 (err=4.8e-16) 3. Temperton (f2c): elapsed time t=1.29213 s, 128 iters, t-(init.)=1.18876 s t(norm)=0.234778, mflops=21.2967 (err=4.6e-16) Top mflops for N=3375 = 54.0615 Normalized results and averages for N=3375: fft 0: mflops = 54.0615 (norm. = 1), norm. avg. (of 10) = 0.927919 fft 1: mflops = 17.2314 (norm. = 0.318736), norm. avg. (of 10) = 0.182162 fft 2: mflops = 23.6741 (norm. = 0.43791), norm. avg. (of 10) = 0.757488 fft 3: mflops = 21.2967 (norm. = 0.393934), norm. avg. (of 6) = 0.314916 Benchmarking for array size = 24x25x28: 0. FFTW: elapsed time t=1.05105 s, 32 iters, t-(init.)=0.899585 s t(norm)=0.119216, mflops=41.9407 (err=4.3e-16) 1. PDA (f2c): elapsed time t=1.3126 s, 16 iters, t-(init.)=1.23755 s t(norm)=0.328007, mflops=15.2436 (err=4.4e-16) 2. Singleton (f2c): elapsed time t=1.40162 s, 16 iters, t-(init.)=1.32673 s t(norm)=0.351646, mflops=14.2188 (err=5.6e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=16800 = 41.9407 Normalized results and averages for N=16800: fft 0: mflops = 41.9407 (norm. = 1), norm. avg. (of 11) = 0.934472 fft 1: mflops = 15.2436 (norm. = 0.363455), norm. avg. (of 11) = 0.198643 fft 2: mflops = 14.2188 (norm. = 0.339023), norm. avg. (of 11) = 0.719446 fft 3: mflops = -1 (norm. = -0.0238432), norm. avg. (of 6) = 0.314916 Benchmarking for array size = 48x48x48: 0. FFTW: elapsed time t=1.12008 s, 4 iters, t-(init.)=0.977358 s t(norm)=0.131865, mflops=37.9177 (err=7.1e-16) 1. PDA (f2c): elapsed time t=1.49463 s, 2 iters, t-(init.)=1.42369 s t(norm)=0.384167, mflops=13.0152 (err=7.1e-16) 2. Singleton (f2c): elapsed time t=1.83597 s, 2 iters, t-(init.)=1.76481 s t(norm)=0.476215, mflops=10.4995 (err=8.2e-16) 3. Temperton (f2c): elapsed time t=1.28535 s, 2 iters, t-(init.)=1.21413 s t(norm)=0.327619, mflops=15.2616 (err=7.6e-16) Top mflops for N=110592 = 37.9177 Normalized results and averages for N=110592: fft 0: mflops = 37.9177 (norm. = 1), norm. avg. (of 12) = 0.939932 fft 1: mflops = 13.0152 (norm. = 0.343248), norm. avg. (of 12) = 0.210693 fft 2: mflops = 10.4995 (norm. = 0.276901), norm. avg. (of 12) = 0.682567 fft 3: mflops = 15.2616 (norm. = 0.402494), norm. avg. (of 7) = 0.327427 Benchmarking for array size = 49x49x49: 0. FFTW: elapsed time t=1.1338 s, 4 iters, t-(init.)=0.982316 s t(norm)=0.123924, mflops=40.3474 (err=8.7e-16) 1. PDA (f2c): elapsed time t=1.07629 s, 1 iters, t-(init.)=1.03801 s t(norm)=0.523801, mflops=9.54562 (err=8.8e-16) 2. Singleton (f2c): elapsed time t=1.68808 s, 2 iters, t-(init.)=1.61159 s t(norm)=0.40662, mflops=12.2965 (err=1.1e-15) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=117649 = 40.3474 Normalized results and averages for N=117649: fft 0: mflops = 40.3474 (norm. = 1), norm. avg. (of 13) = 0.944553 fft 1: mflops = 9.54562 (norm. = 0.236586), norm. avg. (of 13) = 0.212685 fft 2: mflops = 12.2965 (norm. = 0.304766), norm. avg. (of 13) = 0.653506 fft 3: mflops = -1 (norm. = -0.0247847), norm. avg. (of 7) = 0.327427 Benchmarking for array size = 60x60x60: 0. FFTW: elapsed time t=1.95004 s, 4 iters, t-(init.)=1.67162 s t(norm)=0.10918, mflops=45.7959 (err=4.9e-16) 1. PDA (f2c): elapsed time t=1.49676 s, 1 iters, t-(init.)=1.42746 s t(norm)=0.372933, mflops=13.4072 (err=5.0e-16) 2. Singleton (f2c): elapsed time t=2.40304 s, 1 iters, t-(init.)=2.33381 s t(norm)=0.609722, mflops=8.20045 (err=6.0e-16) 3. Temperton (f2c): elapsed time t=1.17561 s, 1 iters, t-(init.)=1.10608 s t(norm)=0.288969, mflops=17.3029 (err=4.7e-16) Top mflops for N=216000 = 45.7959 Normalized results and averages for N=216000: fft 0: mflops = 45.7959 (norm. = 1), norm. avg. (of 14) = 0.948514 fft 1: mflops = 13.4072 (norm. = 0.29276), norm. avg. (of 14) = 0.218405 fft 2: mflops = 8.20045 (norm. = 0.179065), norm. avg. (of 14) = 0.619617 fft 3: mflops = 17.3029 (norm. = 0.377826), norm. avg. (of 8) = 0.333727 Benchmarking for array size = 72x60x56: 0. FFTW: elapsed time t=1.2509 s, 2 iters, t-(init.)=1.09521 s t(norm)=0.126568, mflops=39.5043 (err=5.7e-16) 1. PDA (f2c): elapsed time t=1.87728 s, 1 iters, t-(init.)=1.79933 s t(norm)=0.415882, mflops=12.0227 (err=6.1e-16) 2. Singleton (f2c): elapsed time t=2.84535 s, 1 iters, t-(init.)=2.76731 s t(norm)=0.639614, mflops=7.81722 (err=7.0e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=241920 = 39.5043 Normalized results and averages for N=241920: fft 0: mflops = 39.5043 (norm. = 1), norm. avg. (of 15) = 0.951946 fft 1: mflops = 12.0227 (norm. = 0.304338), norm. avg. (of 15) = 0.224133 fft 2: mflops = 7.81722 (norm. = 0.197882), norm. avg. (of 15) = 0.591501 fft 3: mflops = -1 (norm. = -0.0253137), norm. avg. (of 8) = 0.333727 Benchmarking for array size = 75x75x75: 0. FFTW: elapsed time t=1.01196 s, 1 iters, t-(init.)=0.875974 s t(norm)=0.111117, mflops=44.9976 (err=9.0e-16) 1. PDA (f2c): elapsed time t=3.02267 s, 1 iters, t-(init.)=2.88668 s t(norm)=0.366174, mflops=13.6547 (err=9.5e-16) 2. Singleton (f2c): elapsed time t=4.06334 s, 1 iters, t-(init.)=3.92608 s t(norm)=0.498022, mflops=10.0397 (err=1.3e-15) 3. Temperton (f2c): elapsed time t=2.33212 s, 1 iters, t-(init.)=2.19664 s t(norm)=0.278643, mflops=17.9441 (err=1.1e-15) Top mflops for N=421875 = 44.9976 Normalized results and averages for N=421875: fft 0: mflops = 44.9976 (norm. = 1), norm. avg. (of 16) = 0.954949 fft 1: mflops = 13.6547 (norm. = 0.303454), norm. avg. (of 16) = 0.229091 fft 2: mflops = 10.0397 (norm. = 0.223117), norm. avg. (of 16) = 0.568477 fft 3: mflops = 17.9441 (norm. = 0.398779), norm. avg. (of 9) = 0.340955 Benchmarking for array size = 80x80x80: 0. FFTW: elapsed time t=1.56412 s, 1 iters, t-(init.)=1.3999 s t(norm)=0.144163, mflops=34.6829 (err=1.5e-15) 1. PDA (f2c): elapsed time t=3.97855 s, 1 iters, t-(init.)=3.81355 s t(norm)=0.392725, mflops=12.7316 (err=1.5e-15) 2. Singleton (f2c): elapsed time t=4.79788 s, 1 iters, t-(init.)=4.63261 s t(norm)=0.477073, mflops=10.4806 (err=2.3e-15) 3. Temperton (f2c): elapsed time t=3.75701 s, 1 iters, t-(init.)=3.59252 s t(norm)=0.369964, mflops=13.5148 (err=1.5e-15) Top mflops for N=512000 = 34.6829 Normalized results and averages for N=512000: fft 0: mflops = 34.6829 (norm. = 1), norm. avg. (of 17) = 0.957599 fft 1: mflops = 12.7316 (norm. = 0.367085), norm. avg. (of 17) = 0.237208 fft 2: mflops = 10.4806 (norm. = 0.302183), norm. avg. (of 17) = 0.552813 fft 3: mflops = 13.5148 (norm. = 0.389669), norm. avg. (of 10) = 0.345826 Benchmarking for array size = 84x84x84: 0. FFTW: elapsed time t=1.60859 s, 1 iters, t-(init.)=1.41756 s t(norm)=0.124717, mflops=40.0909 (err=7.6e-16) 1. PDA (f2c): elapsed time t=5.18371 s, 1 iters, t-(init.)=4.9917 s t(norm)=0.439168, mflops=11.3852 (err=6.9e-16) 2. Singleton (f2c): elapsed time t=7.58421 s, 1 iters, t-(init.)=7.39345 s t(norm)=0.650473, mflops=7.68671 (err=8.6e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=592704 = 40.0909 Normalized results and averages for N=592704: fft 0: mflops = 40.0909 (norm. = 1), norm. avg. (of 18) = 0.959955 fft 1: mflops = 11.3852 (norm. = 0.283984), norm. avg. (of 18) = 0.239807 fft 2: mflops = 7.68671 (norm. = 0.191732), norm. avg. (of 18) = 0.532753 fft 3: mflops = -1 (norm. = -0.0249433), norm. avg. (of 10) = 0.345826 Benchmarking for array size = 96x96x96: 0. FFTW: elapsed time t=3.35991 s, 1 iters, t-(init.)=3.07537 s t(norm)=0.175958, mflops=28.4159 (err=8.1e-16) 1. PDA (f2c): elapsed time t=8.21707 s, 1 iters, t-(init.)=7.93272 s t(norm)=0.453873, mflops=11.0163 (err=7.7e-16) 2. Singleton (f2c): elapsed time t=12.2624 s, 1 iters, t-(init.)=11.9777 s t(norm)=0.685306, mflops=7.29601 (err=8.2e-16) 3. Temperton (f2c): elapsed time t=8.0473 s, 1 iters, t-(init.)=7.76238 s t(norm)=0.444127, mflops=11.2581 (err=8.9e-16) Top mflops for N=884736 = 28.4159 Normalized results and averages for N=884736: fft 0: mflops = 28.4159 (norm. = 1), norm. avg. (of 19) = 0.962063 fft 1: mflops = 11.0163 (norm. = 0.387681), norm. avg. (of 19) = 0.24759 fft 2: mflops = 7.29601 (norm. = 0.256758), norm. avg. (of 19) = 0.518227 fft 3: mflops = 11.2581 (norm. = 0.396188), norm. avg. (of 11) = 0.350405 Benchmarking for array size = 105x105x105: 0. FFTW: elapsed time t=3.09716 s, 1 iters, t-(init.)=2.72421 s t(norm)=0.11683, mflops=42.7973 (err=7.9e-16) 1. PDA (f2c): elapsed time t=11.2778 s, 1 iters, t-(init.)=10.9037 s t(norm)=0.467614, mflops=10.6926 (err=8.1e-16) 2. Singleton (f2c): elapsed time t=11.932 s, 1 iters, t-(init.)=11.5591 s t(norm)=0.495719, mflops=10.0864 (err=9.7e-16) 3. Skipping fft (Temperton only handles N = 2^m 3^n 5^q). Top mflops for N=1157625 = 42.7973 Normalized results and averages for N=1157625: fft 0: mflops = 42.7973 (norm. = 1), norm. avg. (of 20) = 0.963959 fft 1: mflops = 10.6926 (norm. = 0.249842), norm. avg. (of 20) = 0.247702 fft 2: mflops = 10.0864 (norm. = 0.235677), norm. avg. (of 20) = 0.504099 fft 3: mflops = -1 (norm. = -0.023366), norm. avg. (of 11) = 0.350405 ------------------------------------------------------ @@@@ 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, 22.2314, 20.9114, 14.987, 0.764501, 3.18066, 4.50075, 4.15353, 3.87015, , 6.17842, 8.88963, 8.899, 32.6961, , 8.86142, 4.37, 4.23265, 20.699, , , , 2.20925, 1.65019, 5.78302, 17.5931, , , 4.45501, 2.68425, 6.15168 4, 48.5935, 46.4775, 22.052, 3.75668, 7.02713, 16.1561, 15.3425, 7.32565, 19.7614, 16.1854, 32.3907, 32.3852, 100.755, , 23.3415, 8.35787, 8.51614, 57.1046, 24.1844, 25.878, 23.1441, 5.01108, 6.18291, 11.0393, 39.1268, , 2.73454, 15.2864, 8.78926, 6.68591 8, 74.8819, 72.7997, 26.5952, 5.04392, 9.40979, 26.321, 35.139, 21.9689, 20.425, 23.5699, 56.5573, 56.5536, 151.903, 59.6954, 35.8483, 15.1633, 15.2506, 79.8241, 40.1832, 42.176, 39.8647, 8.02131, 14.4065, 18.8893, 69.6206, , 3.42221, 17.1497, 12.4724, 7.10954 16, 45.1826, 44.1175, 31.0292, 10.0522, 10.3722, 41.6386, 58.7281, 40.7473, 22.2906, 33.1658, 109.167, 109.058, 167.162, 83.2562, 52.7438, 23.7375, 23.973, 92.7031, 41.1878, 50.7506, 49.9841, 11.5203, 15.106, 28.4768, 96.0578, 38.9381, 11.829, 45.3881, 17.849, 7.43429 32, 52.7381, 52.0635, 35.2242, 11.9748, 10.6626, 59.3376, 62.4073, 75.3913, 24.6029, 28.614, 141.639, 141.701, 172.558, 111.037, 51.2467, 32.7653, 33.5659, 89.0104, 46.6093, 60.4657, 61.012, 13.9216, 22.1382, 38.2336, 104.302, 42.5172, 12.5486, 58.263, 17.0022, 7.67668 64, 53.5198, 52.1834, 39.2611, 17.3905, 10.6997, 69.5114, 66.272, 84.2084, 27.2354, 33.1576, 143.417, 130.849, 120.267, 144.106, 61.0107, 40.2225, 41.7942, 48.6772, 48.7746, 65.8219, 67.171, 16.431, 28.5497, 46.2998, 118.861, 43.2763, 25.453, 81.006, 21.7643, 7.87845 128, 58.885, 57.7829, 43.147, 17.7303, 10.6382, 75.3755, 75.7811, 112.639, 30.0573, 34.2671, 145.211, 145.231, 134.61, 140.724, 63.6676, 45.4991, 48.2923, 21.0945, 52.8206, 72.0272, 73.8979, 17.2823, 27.2627, 52.5275, 116.616,43.1864, 25.124, 77.0826, 17.4435, 7.919 256, 61.4429, 59.5489, 45.9479, 20.1768, 10.5618, 85.539, 88.0589, 115.807, 32.5356, 36.4731, 146.916, 146.89, 140.949, 150.366, 69.2882, 48.3583, 52.5775, 29.4958, 55.5819, 75.7733, 77.7672, 18.5496, 30.5533, 56.1585, 126.385, 37.9717, 37.1791, 101.558, 22.3397, 7.9621 512, 65.2473, 63.6998, 49.1028, 21.1838, 10.4582, 91.658, 90.0636, 110.962, 35.0647, 21.5928, 61.7766, 59.7615, 58.1029, 161.142, 37.0419, 49.8727, 55.3176, 24.031, 58.9149, 79.8546, 81.6982, 16.1129, 29.1017, 58.4624, 121.114, 21.2247, 35.2723, 102.197, 19.6695, 7.1913 1024, 56.6625, 52.0387, 41.0933, 19.8882, 9.86236, 70.7035, 73.8405, 73.7053, 30.6667, 14.451, 39.4855, 39.4215, 28.7904, 86.939, 19.6072, 43.3382, 46.7559, 20.1088, 57.7038, 77.4552, 62.7162, 8.61737, 19.0747, 50.795, 78.3288, 16.0864, 37.1162, 86.9745, 16.7281, 5.90246 2048, 11.4306, 11.2014, 8.42336, 13.0478, 7.7318, 22.9549, 42.6806, 42.2184, 7.95601, 15.6109, 47.0182, 37.9356, 25.9375, 25.6352, 21.4377, 11.3516, 11.1176, 17.7395, 48.1918, 62.5965, 43.0212, 8.23674, 11.7555, 11.7258, 29.8865, 13.9038, 17.5975, 16.9015, 12.5016, 5.45026 4096, 9.80469, 9.75574, 7.39345, 13.4482, 7.48935, 23.6863, 33.6903, 40.269, 7.05707, 14.7863, 40.0077, 38.9837, 25.2096, 26.539, 21.8859, 10.5187, 10.4663, 17.0947, 13.1968, 13.9163, 13.2366, 8.31512, 12.2313, 10.7738, 29.9614, 11.5942, 24.3989, 20.2754, 13.0111, 5.16661 8192, 10.189, 10.0498, 7.37502, 11.3401, 7.48954, 21.6107, 36.0162, 35.4977, 7.06758, 12.269, 35.1486, 33.0252, 23.8443, 24.5372, 16.2953, 10.6505, 10.6628, , 13.4408, 14.052, 13.2542, 6.80791, 9.73612, 10.9483, 28.8262, 9.45881, 20.1358, 19.2906, 11.9697, 4.77193 16384, 8.69505, 8.49384, 6.63799, 14.0006, 7.07897, 19.8686, 34.9395, 34.9143, 6.40627, 10.5242, 32.4384, 26.9902, 18.185, 19.8333, 15.4082, 9.39244, 9.40444, , 11.8957, 12.3913, 11.671, 6.42923, 8.93685, 9.59979, 27.2362, 8.36232, 25.3036, 18.268, 11.6876, 4.22445 32768, 7.59317, 7.47703, 5.77692, 10.6439, 6.79292, 18.0031, 34.3079, 34.2783, 5.60921, 8.46497, 23.7165, 21.6237, 15.1234, 18.1083, 12.5395, 8.20696, 8.18207, , 10.8075, 11.2507, 10.3173, 5.91537, 7.74813, 8.37986, 24.0111, 7.65144, 18.5828, 11.9318, 8.93866, 3.63466 65536, 6.60338, 6.51858, 5.21163, 11.8646, 6.5919, 15.2868, 30.708, 30.7373, 5.05764, 7.6196, 21.6064, 19.8525, 13.9281, 15.4976, 12.2215, 7.68772, 7.68082, , 8.6162, 8.85211, 8.32674, 6.08612, 6.73742, 7.82595, 19.15, 6.54959, 17.6327, 13.1824, 8.56118, 3.35392 131072, 5.20293, 5.10518, 4.10739, 8.68733, 6.49847, 12.2716, 31.9414, 31.9382, 4.03322, 7.235, 18.5587, 18.098, 12.3187, 12.1047, 11.1617, 5.81082, 5.80774, , 8.21505, 8.54487, 7.90557, 5.85616, 5.90706, 5.8856, 18.4453, 5.36486, 14.9762, 9.25863, 6.73961, 3.1505 Norm. Avg., 0.354698, 0.342857, 0.239637, 0.187452, 0.122636, 0.443887, 0.630373, 0.66711, 0.182831, 0.226902, 0.698428, 0.662047, 0.699583, 0.682104, 0.354177, 0.238144, 0.245783, 0.380264, 0.361607, 0.437817, 0.400131, 0.125884, 0.180111, 0.266042, 0.669768, 0.233019, 0.324384, 0.43006, 0.184152, 0.0851398 ------------------------------------------------------ @@@@ 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, 22.5864, 14.1942, 13.3517, 38.738, 38.7722, 10.1534, 17.4886, 4.59702, 4.36497, 13.0232, 8.65924, 3.268 9, 34.4453, 26.1318, 17.5827, 52.2748, 52.3072, 9.42703, 18.1914, 5.75627, 6.43245, 23.1675, 11.569, 3.19474 12, 49.1044, 39.3372, 22.9384, 87.5076, 87.4949, 16.2442, 20.9369, 5.1203, 8.12846, 24.6926, 16.7365, 3.40746 15, 53.6369, 53.6345, 20.1419, 71.005, 70.9849, 12.1476, 19.8648, 3.32394, 9.29886, 28.0019, 17.0249, 2.79079 18, 53.426, 47.7687, 18.1967, 54.7794, 59.3181, 10.9476, 29.3454, 5.92113, 8.1121, 33.5425, 14.5107, 3.33546 24, 75.5019, 70.0815, 22.0355, 78.7948, 78.7914, 22.0186, 35.5466, 5.59674, 11.8731, 32.7476, 19.1802, 3.51087 36, 83.2506, 83.2593, 24.2675, 85.4118, 85.3651, 14.0149, 43.9114, 6.17727, 11.7565, 50.4187, 21.4385, 3.4895 80, 103.484, 110.93, 22.3251, 114.682, 114.723, 34.2266, 28.4643, 5.78629, 19.2206, 75.1078, 23.4366, 4.62758 108, 85.3799, 106.668, 28.7684, 96.1202, 96.0728, 15.6994, 42.3986, 11.051, 15.8148, 55.1903, 22.4583, 5.42732 210, 115.244, 115.203, 20.5889, 82.9217, 83.6105, 17.4312, 35.1098, 7.12151, 22.1515, 47.3442, , 5.04751 504, 118.453, 118.502, 16.715, 53.2485, 47.7761, 16.7358, 30.7644, 9.34789, 21.4507, 55.2914, , 5.74037 1000, 68.9646, 96.0221, 13.4355, 39.362, 39.283, 14.0052, 14.1372, 5.99454, 22.3086, 63.8477, 20.0588, 5.00693 1960, 48.3062, 48.3209, 8.33979, 46.4954, 45.8154, 14.0696, 17.4844, 5.75835, 16.2758, 23.7335, , 4.14884 4725, 40.0093, 43.5845, 10.3489, 36.9383, 37.3616, 9.01743, 18.2641, 6.12964, 13.7312, 17.993, , 4.58372 10368, 37.0323, 41.8771, 12.6067, 41.9433, 35.0386, 11.2788, 19.6295, 7.03161, 10.9366, 14.4214, 11.5976, 4.38222 27000, 36.9389, 36.9641, 12.0949, 29.9394, 28.4373, 7.36738, 15.9225, 5.44357, 9.9837, 12.0724, 10.7453, 3.79414 75600, 31.0724, 31.0743, 8.61384, 29.0469, 26.3163, 6.53925, 14.6831, 5.37259, 7.65422, 9.28163, , 3.28453 165375, 22.6884, 22.7066, 5.87879, 24.7413, 24.5649, 4.69323, 15.013, 4.84855, 6.99745, 9.66115, , 2.97623 Norm. Avg., 0.862683, 0.867936, 0.254078, 0.886444, 0.871514, 0.204287, 0.382993, 0.104325, 0.195428, 0.444708, 0.233793, 0.0680553 ------------------------------------------------------ @@@@ bench.3d.p2.dat Array Dimensions, FFTW, HARM (f2c), NR (C), PDA (f2c), Singleton (f2c), Temperton (f2c) 4x4x4, 50.349, , 48.995, 8.20043, 92.697, 29.1773 8x8x8, 133.125, 32.86, 65.8706, 15.4893, 79.8968, 30.9501 16x16x16, 40.8304, 19.8808, 9.97396, 14.2464, 17.1167, 18.1828 32x32x32, 33.3691, 16.3704, 7.94006, 11.6044, 11.1085, 11.9697 64x64x64, 25.8609, 14.8888, 5.59783, 10.4637, 9.23122, 11.4956 256x64x32, 25.5148, 13.9955, 5.56762, 10.5463, 8.56248, 10.0929 16x1024x64, 21.622, 14.3993, 5.67404, 9.62625, 9.19412, Norm. Avg., 0.934737, 0.502423, 0.314667, 0.309236, 0.49572, 0.365228 ------------------------------------------------------ @@@@ bench.3d.np2.dat Array Dimensions, FFTW, PDA (f2c), Singleton (f2c), Temperton (f2c) 5x5x5, 52.9497, 11.7151, 118.128, 27.8141 6x6x6, 81.4708, 12.6242, 70.3983, 26.0895 7x7x7, 69.5633, 7.47383, 63.7055, 9x9x9, 95.2013, 15.501, 78.5831, 29.5336 10x10x10, 94.0466, 16.0838, 70.109, 24.39 11x11x11, 38.6845, 7.07264, 43.0718, 12x12x12, 64.9968, 16.8166, 19.9347, 24.069 13x13x13, 35.9882, 6.71423, 38.5805, 14x14x14, 49.1414, 10.3444, 23.5619, 15x15x15, 54.0615, 17.2314, 23.6741, 21.2967 24x25x28, 41.9407, 15.2436, 14.2188, 48x48x48, 37.9177, 13.0152, 10.4995, 15.2616 49x49x49, 40.3474, 9.54562, 12.2965, 60x60x60, 45.7959, 13.4072, 8.20045, 17.3029 72x60x56, 39.5043, 12.0227, 7.81722, 75x75x75, 44.9976, 13.6547, 10.0397, 17.9441 80x80x80, 34.6829, 12.7316, 10.4806, 13.5148 84x84x84, 40.0909, 11.3852, 7.68671, 96x96x96, 28.4159, 11.0163, 7.29601, 11.2581 105x105x105, 42.7973, 10.6926, 10.0864, Norm. Avg., 0.963959, 0.247702, 0.504099, 0.350405 @@@@ end