time_mp4.c running 
compute 0: running  
compute 2: running  
compute 3: running  
compute 1: running  
compute 0: allocating space for 4*65536 elements
compute 2: allocating space for 4*65536 elements
compute 3: allocating space for 4*65536 elements
compute 1: 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
bd(0,65536)=2,0.000383495,2,0.000479369 
bd(0,65536)=2,9.58738e-05,2,0.000191748 
bd(0,65536)=2,0.000287621,2,0.000383495 
bd(0,65536)=2,0.000191748,2,0.000287621 
bf(0,65536)=65536,25.1327,65536,-1.45622e-10 
bf(0,65536)=65536,6.28319,65536,-1.45661e-10 
bf(0,65536)=65536,12.5664,65536,-1.45672e-10 
bf(0,65536)=65536,18.8496,65536,-1.4567e-10 
bi(0,65536)=2,0.000383495,2,0.000479369 
bi(0,65536)=2,9.58738e-05,2,0.000191748 
bi(0,65536)=2,0.000191748,2,0.000287621 
bi(0,65536)=2,0.000287621,2,0.000383495 
bd(31,65536)=2,0.00335558,2,0.00345145 
bf(31,65536)=65535.7,219.911,65536,-1.45683e-10 
bi(31,65536)=2,0.00335558,2,0.00345145 
bd(31,65536)=2,0.00306796,2,0.00316383 
bf(31,65536)=65535.7,201.062,65536,-1.45666e-10 
bi(31,65536)=2,0.00306796,2,0.00316383 
bd(31,65536)=2,0.00316383,2,0.0032597 
bd(31,65536)=2,0.0032597,2,0.00335558 
bf(31,65536)=65535.7,207.345,65536,-1.45717e-10 
bf(31,65536)=65535.7,213.628,65536,-1.45667e-10 
bi(31,65536)=2,0.00316383,2,0.0032597 
bi(31,65536)=2,0.0032597,2,0.00335558 
total CPU time is 20.430000 seconds 
wall time is 6.000000 seconds 
average number of processors used = 3.405000 
time_mp4.c exiting