time_mp8.c running 
compute 0: running  
compute 0: allocating space for 4*65536 elements
           running 32 FFT and IFFT of length 65536
compute 3: running  
compute 3: allocating space for 4*65536 elements
           running 32 FFT and IFFT of length 65536
compute 2: running  
compute 2: allocating space for 4*65536 elements
           running 32 FFT and IFFT of length 65536
compute 1: running  
compute 5: running  
compute 4: running  
compute 4: allocating space for 4*65536 elements
compute 5: allocating space for 4*65536 elements
compute 7: running  
compute 6: running  
compute 6: allocating space for 4*65536 elements
compute 1: allocating space for 4*65536 elements
compute 7: allocating space for 4*65536 elements
           running 32 FFT and IFFT of length 65536
           running 32 FFT and IFFT of length 65536
           running 32 FFT and IFFT of length 65536
           running 32 FFT and IFFT of length 65536
           running 32 FFT and IFFT of length 65536
bd(0,65536)=2,9.58738e-05,2,0.000191748 
bd(0,65536)=2,0.000383495,2,0.000479369 
bd(0,65536)=2,0.000287621,2,0.000383495 
bd(0,65536)=2,0.000479369,2,0.000575243 
bd(0,65536)=2,0.000575243,2,0.000671117 
bd(0,65536)=2,0.000191748,2,0.000287621 
bd(0,65536)=2,0.000671117,2,0.00076699 
bd(0,65536)=2,0.00076699,2,0.000862864 
bf(0,65536)=8.58993e+09,411775,8.58993e+09,823550 
bf(0,65536)=8.58993e+09,1.23532e+06,8.58993e+09,1.6471e+06 
bi(0,65536)=4.29497e+09,411775,-6.54841e-06,8.87643e-06 
bf(0,65536)=8.58993e+09,2.05887e+06,8.58993e+09,2.47065e+06 
bf(0,65536)=8.58993e+09,2.47065e+06,8.58993e+09,2.88242e+06 
bf(0,65536)=8.58993e+09,823550,8.58993e+09,1.23532e+06 
bf(0,65536)=8.58993e+09,1.6471e+06,8.58993e+09,2.05887e+06 
bi(0,65536)=4.29497e+09,1.23532e+06,-6.55133e-06,8.87866e-06 
bi(0,65536)=4.29497e+09,2.05887e+06,-6.55002e-06,8.87472e-06 
bi(0,65536)=4.29497e+09,2.47065e+06,-6.55251e-06,8.87846e-06 
bi(0,65536)=4.29497e+09,823550,-6.55008e-06,8.87823e-06 
bi(0,65536)=4.29497e+09,1.6471e+06,-6.54895e-06,8.87847e-06 
bf(0,65536)=8.58993e+09,2.88242e+06,8.58993e+09,3.2942e+06 
bf(0,65536)=8.58993e+09,3.2942e+06,8.58993e+09,3.70597e+06 
bi(0,65536)=4.29497e+09,2.88242e+06,-6.54768e-06,8.87849e-06 
bi(0,65536)=4.29497e+09,3.2942e+06,-6.55222e-06,8.8788e-06 
bd(31,65536)=2,0.00306796,2,0.00316383 
bd(31,65536)=2,0.0032597,2,0.00335558 
bf(31,65536)=8.58991e+09,1.31768e+07,8.58991e+09,1.35885e+07 
bf(31,65536)=8.58991e+09,1.40003e+07,8.58991e+09,1.44121e+07 
bi(31,65536)=4.29495e+09,1.31768e+07,-6.5657e-06,8.87786e-06 
bi(31,65536)=4.29495e+09,1.40003e+07,-6.55476e-06,8.87786e-06 
bd(31,65536)=2,0.00345145,2,0.00354732 
bf(31,65536)=8.58991e+09,1.48239e+07,8.58991e+09,1.52356e+07 
bi(31,65536)=4.29495e+09,1.48239e+07,-6.56523e-06,8.87774e-06 
bd(31,65536)=2,0.00354732,2,0.0036432 
bd(31,65536)=2,0.00316383,2,0.0032597 
bd(31,65536)=2,0.00335558,2,0.00345145 
bf(31,65536)=8.58991e+09,1.52356e+07,8.58991e+09,1.56474e+07 
bf(31,65536)=8.58991e+09,1.35885e+07,8.58991e+09,1.40003e+07 
bf(31,65536)=8.58991e+09,1.44121e+07,8.58991e+09,1.48239e+07 
bi(31,65536)=4.29495e+09,1.52356e+07,-6.56397e-06,8.87661e-06 
bi(31,65536)=4.29495e+09,1.35885e+07,-6.56647e-06,8.87995e-06 
bi(31,65536)=4.29495e+09,1.44121e+07,-6.55471e-06,8.87839e-06 
bd(31,65536)=2,0.0036432,2,0.00373907 
bd(31,65536)=2,0.00373907,2,0.00383494 
bf(31,65536)=8.58991e+09,1.56474e+07,8.58991e+09,1.60592e+07 
bf(31,65536)=8.58991e+09,1.60592e+07,8.58991e+09,1.6471e+07 
bi(31,65536)=4.29495e+09,1.56474e+07,-6.55612e-06,8.87748e-06 
bi(31,65536)=4.29495e+09,1.60592e+07,-6.55646e-06,8.87773e-06 
total CPU time is 60.990000 seconds 
wall time is 11.000000 seconds 
average number of processors used = 5.544545 
time_mp8.c exiting