time_mp8.c running 
compute 1: running  
compute 0: running  
compute 2: running  
compute 1: allocating space for 4*65536 elements
compute 5: running  
compute 0: allocating space for 4*65536 elements
compute 4: running  
compute 4: allocating space for 4*65536 elements
compute 2: allocating space for 4*65536 elements
compute 3: running  
compute 3: allocating space for 4*65536 elements
compute 6: running  
compute 6: allocating space for 4*65536 elements
           running 64 FFT and IFFT of length 65536
compute 5: allocating space for 4*65536 elements
compute 7: running  
compute 7: allocating space for 4*65536 elements
           running 64 FFT and IFFT of length 65536
           running 64 FFT and IFFT of length 65536
           running 64 FFT and IFFT of length 65536
           running 64 FFT and IFFT of length 65536
           running 64 FFT and IFFT of length 65536
           running 64 FFT and IFFT of length 65536
           running 64 FFT and IFFT of length 65536
bd(0,65536)=2,0.000287621,2,0.000383495 
bd(0,65536)=2,0.000191748,2,0.000287621 
bd(0,65536)=2,0.000671117,2,0.00076699 
bd(0,65536)=2,0.000383495,2,0.000479369 
bd(0,65536)=2,0.00076699,2,0.000862864 
bd(0,65536)=2,0.000575243,2,0.000671117 
bd(0,65536)=2,0.000479369,2,0.000575243 
bd(0,65536)=2,9.58738e-05,2,0.000191748 
bf(0,65536)=8.58993e+09,1.23532e+06,8.58993e+09,1.6471e+06 
bf(0,65536)=8.58993e+09,2.88242e+06,8.58993e+09,3.2942e+06 
bf(0,65536)=8.58993e+09,823550,8.58993e+09,1.23532e+06 
bf(0,65536)=8.58993e+09,2.47065e+06,8.58993e+09,2.88242e+06 
bf(0,65536)=8.58993e+09,3.2942e+06,8.58993e+09,3.70597e+06 
bf(0,65536)=8.58993e+09,2.05887e+06,8.58993e+09,2.47065e+06 
bf(0,65536)=8.58993e+09,411775,8.58993e+09,823550 
bi(0,65536)=4.29497e+09,2.88242e+06,4.53096e-06,-2.78577e-06 
bi(0,65536)=4.29497e+09,1.23532e+06,4.52728e-06,-2.78578e-06 
bi(0,65536)=4.29497e+09,2.47065e+06,4.5277e-06,-2.78535e-06 
bi(0,65536)=4.29497e+09,823550,4.52944e-06,-2.78626e-06 
bi(0,65536)=4.29497e+09,2.05887e+06,4.529e-06,-2.78475e-06 
bi(0,65536)=4.29497e+09,3.2942e+06,4.52711e-06,-2.78613e-06 
bi(0,65536)=4.29497e+09,411775,4.53002e-06,-2.78459e-06 
bf(0,65536)=8.58993e+09,1.6471e+06,8.58993e+09,2.05887e+06 
bi(0,65536)=4.29497e+09,1.6471e+06,4.52906e-06,-2.78376e-06 
bd(63,65536)=1.99998,0.00671112,1.99998,0.00680699 
bd(63,65536)=1.99998,0.00661524,1.99998,0.00671112 
bf(63,65536)=8.58985e+09,2.8824e+07,8.58985e+09,2.92358e+07 
bi(63,65536)=4.29489e+09,2.8824e+07,4.51193e-06,-2.77861e-06 
bd(63,65536)=1.99998,0.00651937,1.99998,0.00661525 
bd(63,65536)=1.99998,0.00613588,1.99998,0.00623176 
bd(63,65536)=1.99998,0.00632763,1.99998,0.0064235 
bf(63,65536)=8.58985e+09,2.84123e+07,8.58985e+09,2.8824e+07 
bd(63,65536)=1.99998,0.00680699,1.99998,0.00690286 
bd(63,65536)=1.99998,0.00623176,1.99998,0.00632763 
bi(63,65536)=4.29489e+09,2.84123e+07,4.53747e-06,-2.77703e-06 
bf(63,65536)=8.58985e+09,2.80005e+07,8.58985e+09,2.84123e+07 
bf(63,65536)=8.58985e+09,2.63534e+07,8.58985e+09,2.67652e+07 
bf(63,65536)=8.58985e+09,2.7177e+07,8.58985e+09,2.75887e+07 
bf(63,65536)=8.58985e+09,2.92358e+07,8.58985e+09,2.96476e+07 
bi(63,65536)=4.29489e+09,2.80005e+07,4.50331e-06,-2.77935e-06 
bi(63,65536)=4.29489e+09,2.63534e+07,4.51076e-06,-2.77873e-06 
bi(63,65536)=4.29489e+09,2.7177e+07,4.53717e-06,-2.7765e-06 
bf(63,65536)=8.58985e+09,2.67652e+07,8.58985e+09,2.7177e+07 
bi(63,65536)=4.29489e+09,2.92358e+07,4.51716e-06,-2.77936e-06 
bi(63,65536)=4.29489e+09,2.67652e+07,4.5362e-06,-2.77644e-06 
bd(63,65536)=1.99998,0.0064235,1.99998,0.00651937 
bf(63,65536)=8.58985e+09,2.75887e+07,8.58985e+09,2.80005e+07 
bi(63,65536)=4.29489e+09,2.75887e+07,4.50843e-06,-2.77804e-06 
total CPU time is 113.090000 seconds 
wall time is 17.000000 seconds 
average number of processors used = 6.652353 
time_mp8.c exiting