time_mp12.c running 
compute 0: running  
compute 0: allocating space for 4*65536 elements
compute 4: running  
compute 5: running  
compute 5: allocating space for 4*65536 elements
compute 2: running  
compute 2: allocating space for 4*65536 elements
compute 4: allocating space for 4*65536 elements
           running 128 FFT and IFFT of length 65536
compute 7: running  
compute 7: allocating space for 4*65536 elements
compute 8: running  
           running 128 FFT and IFFT of length 65536
compute 8: allocating space for 4*65536 elements
compute 11: running  
compute 1: running  
compute 1: allocating space for 4*65536 elements
compute 3: running  
compute 3: allocating space for 4*65536 elements
compute 6: running  
compute 10: running  
compute 10: allocating space for 4*65536 elements
compute 11: allocating space for 4*65536 elements
compute 6: allocating space for 4*65536 elements
compute 9: running  
compute 9: allocating space for 4*65536 elements
           running 128 FFT and IFFT of length 65536
           running 128 FFT and IFFT of length 65536
           running 128 FFT and IFFT of length 65536
           running 128 FFT and IFFT of length 65536
           running 128 FFT and IFFT of length 65536
           running 128 FFT and IFFT of length 65536
           running 128 FFT and IFFT of length 65536
           running 128 FFT and IFFT of length 65536
           running 128 FFT and IFFT of length 65536
           running 128 FFT and IFFT of length 65536
bd(0,65536)=2,0.000287621,2,0.000383495 
bd(0,65536)=2,0.00076699,2,0.000862864 
bd(0,65536)=2,0.00115049,2,0.00124636 
bd(0,65536)=2,0.000862864,2,0.000958738 
bd(0,65536)=2,0.000671117,2,0.00076699 
bd(0,65536)=2,0.00105461,2,0.00115049 
bd(0,65536)=2,0.000191748,2,0.000287621 
bd(0,65536)=2,0.000958738,2,0.00105461 
bd(0,65536)=2,9.58738e-05,2,0.000191748 
bd(0,65536)=2,0.000479369,2,0.000575243 
bd(0,65536)=2,0.000575243,2,0.000671117 
bd(0,65536)=2,0.000383495,2,0.000479369 
bf(0,65536)=8.58993e+09,1.23532e+06,8.58993e+09,1.6471e+06 
bf(0,65536)=8.58993e+09,3.2942e+06,8.58993e+09,3.70597e+06 
bf(0,65536)=8.58993e+09,823550,8.58993e+09,1.23532e+06 
bf(0,65536)=8.58993e+09,4.11775e+06,8.58993e+09,4.52952e+06 
bf(0,65536)=8.58993e+09,4.9413e+06,8.58993e+09,5.35307e+06 
bf(0,65536)=8.58993e+09,3.70597e+06,8.58993e+09,4.11775e+06 
bf(0,65536)=8.58993e+09,2.47065e+06,8.58993e+09,2.88242e+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 
bf(0,65536)=8.58993e+09,2.88242e+06,8.58993e+09,3.2942e+06 
bf(0,65536)=8.58993e+09,4.52952e+06,8.58993e+09,4.9413e+06 
bf(0,65536)=8.58993e+09,1.6471e+06,8.58993e+09,2.05887e+06 
bi(0,65536)=4.29497e+09,1.23532e+06,4.52728e-06,-2.78578e-06 
bi(0,65536)=4.29497e+09,3.2942e+06,4.52711e-06,-2.78613e-06 
bi(0,65536)=4.29497e+09,823550,4.52944e-06,-2.78626e-06 
bi(0,65536)=4.29497e+09,4.11775e+06,4.52991e-06,-2.78479e-06 
bi(0,65536)=4.29497e+09,2.47065e+06,4.5277e-06,-2.78535e-06 
bi(0,65536)=4.29497e+09,4.9413e+06,4.52759e-06,-2.78474e-06 
bi(0,65536)=4.29497e+09,3.70597e+06,4.53025e-06,-2.78647e-06 
bi(0,65536)=4.29497e+09,2.05887e+06,4.529e-06,-2.78475e-06 
bi(0,65536)=4.29497e+09,411775,4.53002e-06,-2.78459e-06 
bi(0,65536)=4.29497e+09,1.6471e+06,4.52906e-06,-2.78376e-06 
bi(0,65536)=4.29497e+09,2.88242e+06,4.53096e-06,-2.78577e-06 
bi(0,65536)=4.29497e+09,4.52952e+06,4.53037e-06,-2.78507e-06 
bd(127,65536)=1.99992,0.0129426,1.99992,0.0130385 
bf(127,65536)=8.58961e+09,5.55881e+07,8.58961e+09,5.59998e+07 
bi(127,65536)=4.29464e+09,5.55881e+07,4.52442e-06,-2.78587e-06 
bd(127,65536)=1.99992,0.0123674,1.99992,0.0124633 
bd(127,65536)=1.99992,0.0131343,1.99992,0.0132302 
bd(127,65536)=1.99992,0.0124633,1.99992,0.0125591 
bd(127,65536)=1.99992,0.0125591,1.99992,0.012655 
bd(127,65536)=1.99992,0.012655,1.99992,0.0127509 
bd(127,65536)=1.99992,0.0127509,1.99992,0.0128467 
bf(127,65536)=8.58961e+09,5.31176e+07,8.58961e+09,5.35294e+07 
bf(127,65536)=8.58961e+09,5.35293e+07,8.58961e+09,5.39411e+07 
bf(127,65536)=8.58961e+09,5.64115e+07,8.58961e+09,5.68233e+07 
bf(127,65536)=8.58961e+09,5.39411e+07,8.58961e+09,5.43529e+07 
bf(127,65536)=8.58961e+09,5.43528e+07,8.58961e+09,5.47646e+07 
bf(127,65536)=8.58961e+09,5.47646e+07,8.58961e+09,5.51763e+07 
bi(127,65536)=4.29464e+09,5.31176e+07,4.53293e-06,-2.78657e-06 
bi(127,65536)=4.29464e+09,5.35293e+07,4.53526e-06,-2.78368e-06 
bi(127,65536)=4.29464e+09,5.64115e+07,4.53894e-06,-2.78213e-06 
bi(127,65536)=4.29464e+09,5.39411e+07,4.53763e-06,-2.7836e-06 
bi(127,65536)=4.29464e+09,5.43528e+07,4.52314e-06,-2.78553e-06 
bi(127,65536)=4.29464e+09,5.47646e+07,4.53554e-06,-2.78508e-06 
bd(127,65536)=1.99992,0.0133261,1.99992,0.0134219 
bd(127,65536)=1.99992,0.0130385,1.99992,0.0131343 
bf(127,65536)=8.58961e+09,5.7235e+07,8.58961e+09,5.76468e+07 
bf(127,65536)=8.58961e+09,5.59998e+07,8.58961e+09,5.64116e+07 
bi(127,65536)=4.29464e+09,5.7235e+07,4.53798e-06,-2.78191e-06 
bi(127,65536)=4.29464e+09,5.59998e+07,4.53661e-06,-2.78444e-06 
bd(127,65536)=1.99992,0.0122715,1.99992,0.0123674 
bf(127,65536)=8.58961e+09,5.27059e+07,8.58961e+09,5.31176e+07 
bi(127,65536)=4.29464e+09,5.27059e+07,4.51976e-06,-2.78348e-06 
bd(127,65536)=1.99992,0.0128467,1.99992,0.0129426 
bd(127,65536)=1.99992,0.0132302,1.99992,0.0133261 
bf(127,65536)=8.58961e+09,5.51763e+07,8.58961e+09,5.55881e+07 
bf(127,65536)=8.58961e+09,5.68233e+07,8.58961e+09,5.7235e+07 
bi(127,65536)=4.29464e+09,5.51763e+07,4.52363e-06,-2.7861e-06 
bi(127,65536)=4.29464e+09,5.68233e+07,4.53732e-06,-2.78269e-06 
total CPU time is 342.970000 seconds 
wall time is 29.000000 seconds 
average number of processors used = 11.826552 
time_mp12.c exiting