time_mp8.c running 
compute 0: running  
compute 0: allocating space for 4*65536 elements
compute 3: running  
compute 2: running  
compute 1: running  
compute 1: allocating space for 4*65536 elements
compute 2: allocating space for 4*65536 elements
compute 3: allocating space for 4*65536 elements
           running 64 FFT and IFFT of length 65536
compute 4: running  
compute 4: allocating space for 4*65536 elements
           running 64 FFT and IFFT of length 65536
           running 64 FFT and IFFT of length 65536
compute 5: running  
compute 5: 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
compute 6: running  
compute 6: 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
bd(0,65536)=2,9.58738e-05,2,0.000191748 
bd(0,65536)=2,0.000287621,2,0.000383495 
bd(0,65536)=2,0.000575243,2,0.000671117 
bd(0,65536)=2,0.000383495,2,0.000479369 
bd(0,65536)=2,0.000191748,2,0.000287621 
bd(0,65536)=2,0.00076699,2,0.000862864 
bd(0,65536)=2,0.000479369,2,0.000575243 
bd(0,65536)=2,0.000671117,2,0.00076699 
bf(0,65536)=65536,18.8496,65536,-7.36558e-11 
bf(0,65536)=65536,6.28319,65536,-7.36914e-11 
bf(0,65536)=65536,31.4159,65536,-7.36759e-11 
bf(0,65536)=65536,43.9823,65536,-7.36871e-11 
bf(0,65536)=65536,12.5664,65536,-7.36969e-11 
bf(0,65536)=65536,37.6991,65536,-7.36612e-11 
bf(0,65536)=65536,25.1327,65536,-7.36194e-11 
bf(0,65536)=65536,50.2655,65536,-7.36114e-11 
bi(0,65536)=2,0.000479369,2,0.000575243 
bi(0,65536)=2,0.000287621,2,0.000383495 
bi(0,65536)=2,0.000671117,2,0.00076699 
bi(0,65536)=2,9.58738e-05,2,0.000191748 
bi(0,65536)=2,0.000191748,2,0.000287621 
bi(0,65536)=2,0.00076699,2,0.000862864 
bi(0,65536)=2,0.000383495,2,0.000479369 
bi(0,65536)=2,0.000575243,2,0.000671117 
bd(63,65536)=1.99998,0.00651937,1.99998,0.00661525 
bf(63,65536)=65534.8,427.254,65536,-7.36373e-11 
bd(63,65536)=1.99998,0.00671112,1.99998,0.00680699 
bi(63,65536)=1.99998,0.00651937,1.99998,0.00661525 
bf(63,65536)=65534.8,439.82,65536,-7.35996e-11 
bi(63,65536)=1.99998,0.00671112,1.99998,0.00680699 
bd(63,65536)=1.99998,0.00632763,1.99998,0.0064235 
bf(63,65536)=65534.8,414.687,65536,-7.36414e-11 
bd(63,65536)=1.99998,0.00613588,1.99998,0.00623176 
bi(63,65536)=1.99998,0.00632763,1.99998,0.0064235 
bf(63,65536)=65534.8,402.121,65536,-7.35841e-11 
bi(63,65536)=1.99998,0.00613588,1.99998,0.00623176 
bd(63,65536)=1.99998,0.0064235,1.99998,0.00651937 
bd(63,65536)=1.99998,0.00661524,1.99998,0.00671112 
bf(63,65536)=65534.8,420.971,65536,-7.36098e-11 
bf(63,65536)=65534.8,433.537,65536,-7.35787e-11 
bd(63,65536)=1.99998,0.00623176,1.99998,0.00632763 
bd(63,65536)=1.99998,0.00680699,1.99998,0.00690286 
bi(63,65536)=1.99998,0.0064235,1.99998,0.00651937 
bi(63,65536)=1.99998,0.00661524,1.99998,0.00671112 
bf(63,65536)=65534.8,408.404,65536,-7.3592e-11 
bf(63,65536)=65534.8,446.103,65536,-7.37058e-11 
bi(63,65536)=1.99998,0.00623176,1.99998,0.00632763 
bi(63,65536)=1.99998,0.00680699,1.99998,0.00690286 
total CPU time is 37.070000 seconds 
wall time is 5.000000 seconds 
average number of processors used = 7.414000 
time_mp8.c exiting