timet_mp4.c running 
_POSIX_THREAD_CPUTIME is available
t.tv_nesc = 2000000 
compute 0: running  
compute 0: allocating space for 4*65536 elements
compute 3: running  
           running 64 FFT and IFFT of length 65536
compute 3: allocating space for 4*65536 elements
compute 1: running  
compute 2: running  
compute 1: allocating space for 4*65536 elements
           running 64 FFT and IFFT of length 65536
compute 2: 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)=2,0.000383495,2,0.000479369 
bd(0,65536)=2,0.000191748,2,0.000287621 
bd(0,65536)=2,0.000287621,2,0.000383495 
bf(0,65536)=65536,12.5664,65536,-6.84304e-12 
bf(0,65536)=65536,6.28319,65536,-6.85848e-12 
bf(0,65536)=65536,18.8496,65536,-6.84481e-12 
bf(0,65536)=65536,25.1327,65536,-6.84614e-12 
bi(0,65536)=2,0.000191748,2,0.000287621 
bi(0,65536)=2,9.58738e-05,2,0.000191748 
bi(0,65536)=2,0.000287621,2,0.000383495 
bi(0,65536)=2,0.000383495,2,0.000479369 
bd(63,65536)=1.99998,0.00632763,1.99998,0.0064235 
bd(63,65536)=1.99998,0.00613588,1.99998,0.00623176 
bd(63,65536)=1.99998,0.00623176,1.99998,0.00632763 
bd(63,65536)=1.99998,0.0064235,1.99998,0.00651937 
bf(63,65536)=65534.8,414.687,65536,-6.88545e-12 
bf(63,65536)=65534.8,402.121,65536,-6.89814e-12 
bf(63,65536)=65534.8,408.404,65536,-6.88812e-12 
bf(63,65536)=65534.8,420.971,65536,-6.8937e-12 
bi(63,65536)=1.99998,0.00632763,1.99998,0.0064235 
t.tv_nesc = 363000000 
thread 2, pidtime=0.359000 seconds
bi(63,65536)=1.99998,0.00613588,1.99998,0.00623176 
t.tv_nesc = 363000000 
thread 0, pidtime=0.361000 seconds
bi(63,65536)=1.99998,0.00623176,1.99998,0.00632763 
t.tv_nesc = 383000000 
thread 1, pidtime=0.379000 seconds
bi(63,65536)=1.99998,0.0064235,1.99998,0.00651937 
t.tv_nesc = 384000000 
thread 3, pidtime=0.382000 seconds
t.tv_nesc = 384000000 
main pidtime=0.382000 seconds
total CPU time is 24.380000 seconds 
wall time is 6.000000 seconds 
average number of processors used = 4.063333 
timet_mp4.c exiting