wiki:512-8procs-per-node-licallo

8 procs -> 1850 s -> 14800 s-monoproc

16 procs -> 966 -> 15456 s-monoproc

32 procs -> 514 s -> 16448 s-monoproc

64 procs -> 312 s -> 19968 s-monoproc

128 procs -> 223 s -> 28544 s-monoproc

256 procs -> 221 s -> 56576 s-monoproc

512 procs -> 97 s -> 49664 s-monoproc

 ---------------------------------------------
   512 Processor run, global<512,512,512>
   for 100 time steps
main timer : (real:0:1:47,user:0:1:1,sys:0:0:40)[clk:10758]
	loop : (real:0:1:37,user:0:0:59,sys:0:0:37)[clk:9721]	(100 calls X 9.721000e+01)
	FFT timer : (real:0:1:38,user:0:0:52,sys:0:0:39)[clk:9841]
		planification time : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]
		FFT (out of place) and transposition time : (real:0:1:38,user:0:0:52,sys:0:0:39)[clk:9841]	(509 calls X 1.933399e+01)
			FFT (out of place) only : (real:0:0:12,user:0:0:11,sys:0:0:0)[clk:1219]	(2545 calls X 4.789784e-01)
			FFTW (out of place) Transposition only : (real:0:1:25,user:0:0:40,sys:0:0:38)[clk:8578]	(2036 calls X 4.213163e+00)
	azur::array timer root : (real:0:0:4,user:0:0:4,sys:0:0:0)[clk:487]
		view = expr : (real:0:0:4,user:0:0:4,sys:0:0:0)[clk:487]	(1620 calls X 3.006173e-01)
			fftw3<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(2 calls X 0.000000e+00)
			fftw4<dbl> /= int : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:41]	(204 calls X 2.009804e-01)
			fftw4<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(1 calls X 0.000000e+00)
			fftw3<dbl> id= fftw3<dbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:80]	(606 calls X 1.320132e-01)
			fftw4<dbl> *= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(1 calls X 0.000000e+00)
			fftw4<cdbl> id= fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:85]	(202 calls X 4.207921e-01)
			fftw4<dbl> id= fftw4<dbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:45]	(103 calls X 4.368932e-01)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(1 calls X 0.000000e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]	(1 calls X 1.000000e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(1 calls X 0.000000e+00)
			fftw4<cdbl> *= s2v<basic3<dbl>> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(1 calls X 0.000000e+00)
			fftw4<cdbl> += fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]	(1 calls X 1.000000e+00)
			fftw4<cdbl> id= ((fftw4<cdbl> * s2v<basic3<dbl>>) + (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl))) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(1 calls X 0.0000
00e+00)
			fftw4<cdbl> id= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:49]	(99 calls X 4.949495e-01)
			fftw4<cdbl> -= fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:38]	(99 calls X 3.838384e-01)
			fftw4<cdbl> -= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:52]	(99 calls X 5.252525e-01)
			fftw4<cdbl> id= (s2v<basic3<dbl>> swp(*) (fftw4<cdbl> + (fftw4<cdbl> * dbl))) : (real:0:0:0,user:0:0:1,sys:0:0:0)[clk:95]	(198 calls X 4.797980e-01)
	cubby::field timer root : (real:0:1:28,user:0:0:43,sys:0:0:38)[clk:8851]
		scalar::transpose_blocks_when_received : (real:0:1:25,user:0:0:40,sys:0:0:38)[clk:8574]	(3054 calls X 2.807466e+00)
			scalar::copy_transposed : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:117]	(781824 calls X 1.496500e-04)
		vector::in_place_curl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:49]	(202 calls X 2.425743e-01)
		scalar::local_energy : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:4]	(66 calls X 6.060606e-02)
		vector::vec_prod : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:84]	(202 calls X 4.158416e-01)
		vector::project : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:46]	(101 calls X 4.554456e-01)
		scalar::dealias : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:92]	(606 calls X 1.518152e-01)
  256 Processor run, global<512,512,512>
   for 100 time steps
main timer : (real:0:3:39,user:0:1:57,sys:0:1:26)[clk:21974]
	loop : (real:0:3:31,user:0:1:55,sys:0:1:23)[clk:21134]	(100 calls X 2.113400e+02)
	FFT timer : (real:0:3:19,user:0:1:38,sys:0:1:24)[clk:19919]
		planification time : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]
		FFT (out of place) and transposition time : (real:0:3:19,user:0:1:38,sys:0:1:24)[clk:19919]	(509 calls X 3.913359e+01)
			FFT (out of place) only : (real:0:0:27,user:0:0:26,sys:0:0:0)[clk:2712]	(2545 calls X 1.065619e+00)
			FFTW (out of place) Transposition only : (real:0:2:50,user:0:1:11,sys:0:1:24)[clk:17097]	(2036 calls X 8.397347e+00)
	azur::array timer root : (real:0:0:9,user:0:0:9,sys:0:0:0)[clk:989]
		view = expr : (real:0:0:9,user:0:0:9,sys:0:0:0)[clk:988]	(1620 calls X 6.098765e-01)
			fftw3<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(2 calls X 0.000000e+00)
			fftw4<dbl> /= int : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:108]	(204 calls X 5.294118e-01)
			fftw4<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]	(1 calls X 1.000000e+00)
			fftw3<dbl> id= fftw3<dbl> : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:158]	(606 calls X 2.607261e-01)
			fftw4<dbl> *= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(1 calls X 0.000000e+00)
			fftw4<cdbl> id= fftw4<cdbl> : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:146]	(202 calls X 7.227723e-01)
			fftw4<dbl> id= fftw4<dbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:91]	(103 calls X 8.834952e-01)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]	(1 calls X 1.000000e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]	(1 calls X 1.000000e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(1 calls X 0.000000e+00)
			fftw4<cdbl> *= s2v<basic3<dbl>> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(1 calls X 0.000000e+00)
			fftw4<cdbl> += fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]	(1 calls X 1.000000e+00)
			fftw4<cdbl> id= ((fftw4<cdbl> * s2v<basic3<dbl>>) + (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl))) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(1 calls X 0.0000
00e+00)
			fftw4<cdbl> id= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:87]	(99 calls X 8.787879e-01)
			fftw4<cdbl> -= fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:78]	(99 calls X 7.878788e-01)
			fftw4<cdbl> -= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:1,user:0:0:0,sys:0:0:0)[clk:104]	(99 calls X 1.050505e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> swp(*) (fftw4<cdbl> + (fftw4<cdbl> * dbl))) : (real:0:0:2,user:0:0:2,sys:0:0:0)[clk:212]	(198 calls X 1.070707e+00)
	cubby::field timer root : (real:0:2:57,user:0:1:17,sys:0:1:24)[clk:17722]
		scalar::transpose_blocks_when_received : (real:0:2:50,user:0:1:11,sys:0:1:24)[clk:17095]	(3054 calls X 5.597577e+00)
			scalar::copy_transposed : (real:0:0:4,user:0:0:3,sys:0:0:0)[clk:415]	(390912 calls X 1.061620e-03)
		vector::in_place_curl : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:121]	(202 calls X 5.990099e-01)
		scalar::local_energy : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:10]	(66 calls X 1.515152e-01)
		vector::vec_prod : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:191]	(202 calls X 9.455445e-01)
		vector::project : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:112]	(101 calls X 1.108911e+00)
		scalar::dealias : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:192]	(606 calls X 3.168317e-01)

---------------------------------------------
   128 Processor run, global<512,512,512>
   for 100 time steps
main timer : (real:0:3:50,user:0:2:32,sys:0:1:11)[clk:23065]
	loop : (real:0:3:43,user:0:2:29,sys:0:1:9)[clk:22364]	(100 calls X 2.236400e+02)
	FFT timer : (real:0:3:9,user:0:1:54,sys:0:1:8)[clk:18957]
		planification time : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]
		FFT (out of place) and transposition time : (real:0:3:9,user:0:1:54,sys:0:1:8)[clk:18956]	(509 calls X 3.724165e+01)
			FFT (out of place) only : (real:0:0:54,user:0:0:53,sys:0:0:0)[clk:5480]	(2545 calls X 2.153242e+00)
			FFTW (out of place) Transposition only : (real:0:2:12,user:0:0:57,sys:0:1:8)[clk:13256]	(2036 calls X 6.510806e+00)
	azur::array timer root : (real:0:0:21,user:0:0:20,sys:0:0:1)[clk:2143]
		view = expr : (real:0:0:21,user:0:0:20,sys:0:0:1)[clk:2143]	(1620 calls X 1.322839e+00)
			fftw3<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(2 calls X 0.000000e+00)
			fftw4<dbl> /= int : (real:0:0:2,user:0:0:2,sys:0:0:0)[clk:218]	(204 calls X 1.068627e+00)
			fftw4<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]	(1 calls X 1.000000e+00)
			fftw3<dbl> id= fftw3<dbl> : (real:0:0:3,user:0:0:3,sys:0:0:0)[clk:360]	(606 calls X 5.940594e-01)
			fftw4<dbl> *= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]	(1 calls X 1.000000e+00)
			fftw4<cdbl> id= fftw4<cdbl> : (real:0:0:3,user:0:0:3,sys:0:0:0)[clk:343]	(202 calls X 1.698020e+00)
			fftw4<dbl> id= fftw4<dbl> : (real:0:0:1,user:0:0:0,sys:0:0:1)[clk:179]	(103 calls X 1.737864e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:2]	(1 calls X 2.000000e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:2]	(1 calls X 2.000000e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:2]	(1 calls X 2.000000e+00)
			fftw4<cdbl> *= s2v<basic3<dbl>> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]	(1 calls X 1.000000e+00)
			fftw4<cdbl> += fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:2]	(1 calls X 2.000000e+00)
			fftw4<cdbl> id= ((fftw4<cdbl> * s2v<basic3<dbl>>) + (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl))) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:2]	(1 calls X 2.0000
00e+00)
			fftw4<cdbl> id= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:188]	(99 calls X 1.898990e+00)
			fftw4<cdbl> -= fftw4<cdbl> : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:166]	(99 calls X 1.676768e+00)
			fftw4<cdbl> -= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:2,user:0:0:2,sys:0:0:0)[clk:219]	(99 calls X 2.212121e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> swp(*) (fftw4<cdbl> + (fftw4<cdbl> * dbl))) : (real:0:0:4,user:0:0:4,sys:0:0:0)[clk:456]	(198 calls X 2.303030e+00)
	cubby::field timer root : (real:0:2:25,user:0:1:10,sys:0:1:8)[clk:14501]
		scalar::transpose_blocks_when_received : (real:0:2:12,user:0:0:57,sys:0:1:8)[clk:13256]	(3054 calls X 4.340537e+00)
			scalar::copy_transposed : (real:0:0:8,user:0:0:8,sys:0:0:0)[clk:840]	(195456 calls X 4.297643e-03)
		vector::in_place_curl : (real:0:0:2,user:0:0:2,sys:0:0:0)[clk:239]	(202 calls X 1.183168e+00)
		scalar::local_energy : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:20]	(66 calls X 3.030303e-01)
		vector::vec_prod : (real:0:0:3,user:0:0:3,sys:0:0:0)[clk:371]	(202 calls X 1.836634e+00)
		vector::project : (real:0:0:2,user:0:0:2,sys:0:0:0)[clk:235]	(101 calls X 2.326733e+00)
		scalar::dealias : (real:0:0:3,user:0:0:3,sys:0:0:0)[clk:380]	(606 calls X 6.270627e-01)

   64 Processor run, global<512,512,512>
   for 100 time steps
main timer : (real:0:5:20,user:0:4:17,sys:0:1:0)[clk:32058]
	loop : (real:0:5:12,user:0:4:11,sys:0:0:58)[clk:31217]	(100 calls X 3.121700e+02)
	FFT timer : (real:0:3:59,user:0:3:1,sys:0:0:55)[clk:23956]
		planification time : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]
		FFT (out of place) and transposition time : (real:0:3:59,user:0:3:1,sys:0:0:55)[clk:23956]	(509 calls X 4.706483e+01)
			FFT (out of place) only : (real:0:1:53,user:0:1:53,sys:0:0:0)[clk:11368]	(2545 calls X 4.466798e+00)
			FFTW (out of place) Transposition only : (real:0:2:1,user:0:1:4,sys:0:0:54)[clk:12192]	(2036 calls X 5.988212e+00)
	azur::array timer root : (real:0:0:42,user:0:0:40,sys:0:0:2)[clk:4241]
		view = expr : (real:0:0:42,user:0:0:40,sys:0:0:2)[clk:4241]	(1620 calls X 2.617901e+00)
			fftw3<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:2]	(2 calls X 1.000000e+00)
			fftw4<dbl> /= int : (real:0:0:3,user:0:0:4,sys:0:0:0)[clk:392]	(204 calls X 1.921569e+00)
			fftw4<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:2]	(1 calls X 2.000000e+00)
			fftw3<dbl> id= fftw3<dbl> : (real:0:0:7,user:0:0:7,sys:0:0:0)[clk:707]	(606 calls X 1.166667e+00)
			fftw4<dbl> *= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:3]	(1 calls X 3.000000e+00)
			fftw4<cdbl> id= fftw4<cdbl> : (real:0:0:6,user:0:0:6,sys:0:0:0)[clk:685]	(202 calls X 3.391089e+00)
			fftw4<dbl> id= fftw4<dbl> : (real:0:0:3,user:0:0:1,sys:0:0:2)[clk:372]	(103 calls X 3.611650e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:4]	(1 calls X 4.000000e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:4]	(1 calls X 4.000000e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:4]	(1 calls X 4.000000e+00)
			fftw4<cdbl> *= s2v<basic3<dbl>> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:2]	(1 calls X 2.000000e+00)
			fftw4<cdbl> += fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:4]	(1 calls X 4.000000e+00)
			fftw4<cdbl> id= ((fftw4<cdbl> * s2v<basic3<dbl>>) + (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl))) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:5]	(1 calls X 5.0000
00e+00)
			fftw4<cdbl> id= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:3,user:0:0:3,sys:0:0:0)[clk:379]	(99 calls X 3.828283e+00)
			fftw4<cdbl> -= fftw4<cdbl> : (real:0:0:3,user:0:0:3,sys:0:0:0)[clk:335]	(99 calls X 3.383838e+00)
			fftw4<cdbl> -= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:4,user:0:0:4,sys:0:0:0)[clk:435]	(99 calls X 4.393939e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> swp(*) (fftw4<cdbl> + (fftw4<cdbl> * dbl))) : (real:0:0:9,user:0:0:8,sys:0:0:0)[clk:904]	(198 calls X 4.565657e+00)
	cubby::field timer root : (real:0:2:26,user:0:1:29,sys:0:0:54)[clk:14664]
		scalar::transpose_blocks_when_received : (real:0:2:1,user:0:1:4,sys:0:0:54)[clk:12191]	(3054 calls X 3.991814e+00)
			scalar::copy_transposed : (real:0:0:14,user:0:0:14,sys:0:0:0)[clk:1497]	(97728 calls X 1.531803e-02)
		vector::in_place_curl : (real:0:0:4,user:0:0:4,sys:0:0:0)[clk:462]	(202 calls X 2.287129e+00)
		scalar::local_energy : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:36]	(66 calls X 5.454546e-01)
		vector::vec_prod : (real:0:0:7,user:0:0:7,sys:0:0:0)[clk:723]	(202 calls X 3.579208e+00)
		vector::project : (real:0:0:4,user:0:0:5,sys:0:0:0)[clk:498]	(101 calls X 4.930693e+00)
		scalar::dealias : (real:0:0:7,user:0:0:7,sys:0:0:0)[clk:754]	(606 calls X 1.244224e+00)

  32 Processor run, global<512,512,512>
   for 100 time steps
main timer : (real:0:9:28,user:0:8:6,sys:0:1:21)[clk:56842]
	loop : (real:0:9:14,user:0:7:54,sys:0:1:19)[clk:55442]	(100 calls X 5.544200e+02)
	FFT timer : (real:0:6:49,user:0:5:36,sys:0:1:11)[clk:40931]
		planification time : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]
		FFT (out of place) and transposition time : (real:0:6:49,user:0:5:36,sys:0:1:11)[clk:40931]	(509 calls X 8.041454e+01)
			FFT (out of place) only : (real:0:3:51,user:0:3:51,sys:0:0:0)[clk:23192]	(2545 calls X 9.112770e+00)
			FFTW (out of place) Transposition only : (real:0:2:49,user:0:1:37,sys:0:1:11)[clk:16984]	(2036 calls X 8.341846e+00)
	azur::array timer root : (real:0:1:23,user:0:1:18,sys:0:0:4)[clk:8300]
		view = expr : (real:0:1:23,user:0:1:18,sys:0:0:4)[clk:8300]	(1620 calls X 5.123457e+00)
			fftw3<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:3]	(2 calls X 1.500000e+00)
			fftw4<dbl> /= int : (real:0:0:7,user:0:0:7,sys:0:0:0)[clk:752]	(204 calls X 3.686275e+00)
			fftw4<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:5]	(1 calls X 5.000000e+00)
			fftw3<dbl> id= fftw3<dbl> : (real:0:0:14,user:0:0:14,sys:0:0:0)[clk:1450]	(606 calls X 2.392739e+00)
			fftw4<dbl> *= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:4]	(1 calls X 4.000000e+00)
			fftw4<cdbl> id= fftw4<cdbl> : (real:0:0:13,user:0:0:13,sys:0:0:0)[clk:1303]	(202 calls X 6.450495e+00)
			fftw4<dbl> id= fftw4<dbl> : (real:0:0:7,user:0:0:2,sys:0:0:4)[clk:735]	(103 calls X 7.135922e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:10]	(1 calls X 1.000000e+01)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:9]	(1 calls X 9.000000e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:9]	(1 calls X 9.000000e+00)
			fftw4<cdbl> *= s2v<basic3<dbl>> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:6]	(1 calls X 6.000000e+00)
			fftw4<cdbl> += fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:7]	(1 calls X 7.000000e+00)
			fftw4<cdbl> id= ((fftw4<cdbl> * s2v<basic3<dbl>>) + (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl))) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:11]	(1 calls X 1.1000
00e+01)
			fftw4<cdbl> id= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:7,user:0:0:7,sys:0:0:0)[clk:749]	(99 calls X 7.565657e+00)
			fftw4<cdbl> -= fftw4<cdbl> : (real:0:0:6,user:0:0:6,sys:0:0:0)[clk:663]	(99 calls X 6.696970e+00)
			fftw4<cdbl> -= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:8,user:0:0:8,sys:0:0:0)[clk:841]	(99 calls X 8.494949e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> swp(*) (fftw4<cdbl> + (fftw4<cdbl> * dbl))) : (real:0:0:17,user:0:0:17,sys:0:0:0)[clk:1743]	(198 calls X 8.803030e+00)
	cubby::field timer root : (real:0:3:38,user:0:2:26,sys:0:1:11)[clk:21854]
		scalar::transpose_blocks_when_received : (real:0:2:49,user:0:1:37,sys:0:1:11)[clk:16983]	(3054 calls X 5.560904e+00)
			scalar::copy_transposed : (real:0:0:29,user:0:0:29,sys:0:0:0)[clk:2909]	(48864 calls X 5.953258e-02)
		vector::in_place_curl : (real:0:0:9,user:0:0:9,sys:0:0:0)[clk:904]	(202 calls X 4.475247e+00)
		scalar::local_energy : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:71]	(66 calls X 1.075758e+00)
		vector::vec_prod : (real:0:0:13,user:0:0:13,sys:0:0:0)[clk:1387]	(202 calls X 6.866337e+00)
		vector::project : (real:0:0:10,user:0:0:10,sys:0:0:0)[clk:1015]	(101 calls X 1.004951e+01)
		scalar::dealias : (real:0:0:14,user:0:0:14,sys:0:0:0)[clk:1494]	(606 calls X 2.465347e+00)
  16 Processor run, global<512,512,512>
   for 100 time steps
main timer : (real:0:16:32,user:0:15:10,sys:0:1:21)[clk:99275]
	loop : (real:0:16:6,user:0:14:48,sys:0:1:18)[clk:96658]	(100 calls X 9.665800e+02)
	FFT timer : (real:0:11:21,user:0:10:18,sys:0:1:2)[clk:68169]
		planification time : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]
		FFT (out of place) and transposition time : (real:0:11:21,user:0:10:18,sys:0:1:2)[clk:68169]	(509 calls X 1.339273e+02)
			FFT (out of place) only : (real:0:7:32,user:0:7:31,sys:0:0:0)[clk:45267]	(2545 calls X 1.778664e+01)
			FFTW (out of place) Transposition only : (real:0:3:33,user:0:2:30,sys:0:1:2)[clk:21351]	(2036 calls X 1.048674e+01)
	azur::array timer root : (real:0:2:42,user:0:2:33,sys:0:0:8)[clk:16223]
		view = expr : (real:0:2:42,user:0:2:33,sys:0:0:8)[clk:16223]	(1620 calls X 1.001420e+01)
			fftw3<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:6]	(2 calls X 3.000000e+00)
			fftw4<dbl> /= int : (real:0:0:15,user:0:0:15,sys:0:0:0)[clk:1550]	(204 calls X 7.598039e+00)
			fftw4<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:10]	(1 calls X 1.000000e+01)
			fftw3<dbl> id= fftw3<dbl> : (real:0:0:27,user:0:0:27,sys:0:0:0)[clk:2770]	(606 calls X 4.570957e+00)
			fftw4<dbl> *= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:8]	(1 calls X 8.000000e+00)
			fftw4<cdbl> id= fftw4<cdbl> : (real:0:0:25,user:0:0:25,sys:0:0:0)[clk:2535]	(202 calls X 1.254951e+01)
			fftw4<dbl> id= fftw4<dbl> : (real:0:0:14,user:0:0:5,sys:0:0:8)[clk:1419]	(103 calls X 1.377670e+01)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:16]	(1 calls X 1.600000e+01)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:15]	(1 calls X 1.500000e+01)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:14]	(1 calls X 1.400000e+01)
			fftw4<cdbl> *= s2v<basic3<dbl>> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:11]	(1 calls X 1.100000e+01)
			fftw4<cdbl> += fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:15]	(1 calls X 1.500000e+01)
			fftw4<cdbl> id= ((fftw4<cdbl> * s2v<basic3<dbl>>) + (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl))) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:20]	(1 calls X 2.0000
00e+01)
			fftw4<cdbl> id= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:14,user:0:0:14,sys:0:0:0)[clk:1491]	(99 calls X 1.506061e+01)
			fftw4<cdbl> -= fftw4<cdbl> : (real:0:0:13,user:0:0:13,sys:0:0:0)[clk:1322]	(99 calls X 1.335354e+01)
			fftw4<cdbl> -= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:16,user:0:0:16,sys:0:0:0)[clk:1631]	(99 calls X 1.647475e+01)
			fftw4<cdbl> id= (s2v<basic3<dbl>> swp(*) (fftw4<cdbl> + (fftw4<cdbl> * dbl))) : (real:0:0:33,user:0:0:33,sys:0:0:0)[clk:3389]	(198 calls X 1.711616e+01)
	cubby::field timer root : (real:0:5:9,user:0:4:6,sys:0:1:2)[clk:30909]
		scalar::transpose_blocks_when_received : (real:0:3:33,user:0:2:30,sys:0:1:2)[clk:21351]	(3054 calls X 6.991159e+00)
			scalar::copy_transposed : (real:0:0:56,user:0:0:56,sys:0:0:0)[clk:5611]	(24432 calls X 2.296578e-01)
		vector::in_place_curl : (real:0:0:17,user:0:0:17,sys:0:0:0)[clk:1776]	(202 calls X 8.792079e+00)
		scalar::local_energy : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:137]	(66 calls X 2.075758e+00)
		vector::vec_prod : (real:0:0:26,user:0:0:26,sys:0:0:0)[clk:2618]	(202 calls X 1.296040e+01)
		vector::project : (real:0:0:20,user:0:0:20,sys:0:0:0)[clk:2052]	(101 calls X 2.031683e+01)
		scalar::dealias : (real:0:0:29,user:0:0:29,sys:0:0:0)[clk:2975]	(606 calls X 4.909241e+00)
   8 Processor run, global<512,512,512>
   for 100 time steps
main timer : (real:0:31:36,user:0:30:13,sys:0:1:22)[clk:189657]
	loop : (real:0:30:50,user:0:29:30,sys:0:1:19)[clk:185022]	(100 calls X 1.850220e+03)
	FFT timer : (real:0:21:49,user:0:21:5,sys:0:0:43)[clk:130935]
		planification time : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]
		FFT (out of place) and transposition time : (real:0:21:49,user:0:21:5,sys:0:0:43)[clk:130935]	(509 calls X 2.572397e+02)
			FFT (out of place) only : (real:0:15:27,user:0:15:26,sys:0:0:0)[clk:92727]	(2545 calls X 3.643497e+01)
			FFTW (out of place) Transposition only : (real:0:5:55,user:0:5:12,sys:0:0:43)[clk:35564]	(2036 calls X 1.746758e+01)
	azur::array timer root : (real:0:4:54,user:0:4:36,sys:0:0:17)[clk:29461]
		view = expr : (real:0:4:54,user:0:4:36,sys:0:0:17)[clk:29461]	(1620 calls X 1.818580e+01)
			fftw3<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:12]	(2 calls X 6.000000e+00)
			fftw4<dbl> /= int : (real:0:0:26,user:0:0:26,sys:0:0:0)[clk:2642]	(204 calls X 1.295098e+01)
			fftw4<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:19]	(1 calls X 1.900000e+01)
			fftw3<dbl> id= fftw3<dbl> : (real:0:0:47,user:0:0:47,sys:0:0:0)[clk:4706]	(606 calls X 7.765676e+00)
			fftw4<dbl> *= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:13]	(1 calls X 1.300000e+01)
			fftw4<cdbl> id= fftw4<cdbl> : (real:0:0:47,user:0:0:47,sys:0:0:0)[clk:4738]	(202 calls X 2.345545e+01)
			fftw4<dbl> id= fftw4<dbl> : (real:0:0:27,user:0:0:10,sys:0:0:17)[clk:2779]	(103 calls X 2.698058e+01)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:30]	(1 calls X 3.000000e+01)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * ((fftw4<cdbl> * dbl) + fftw4<cdbl>)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:30]	(1 calls X 3.000000e+01)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:28]	(1 calls X 2.800000e+01)
			fftw4<cdbl> *= s2v<basic3<dbl>> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:20]	(1 calls X 2.000000e+01)
			fftw4<cdbl> += fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:26]	(1 calls X 2.600000e+01)
			fftw4<cdbl> id= ((fftw4<cdbl> * s2v<basic3<dbl>>) + (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl))) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:35]	(1 calls X 3.5000
00e+01)
			fftw4<cdbl> id= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:28,user:0:0:28,sys:0:0:0)[clk:2859]	(99 calls X 2.887879e+01)
			fftw4<cdbl> -= fftw4<cdbl> : (real:0:0:24,user:0:0:24,sys:0:0:0)[clk:2479]	(99 calls X 2.504040e+01)
			fftw4<cdbl> -= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:29,user:0:0:29,sys:0:0:0)[clk:2942]	(99 calls X 2.971717e+01)
			fftw4<cdbl> id= (s2v<basic3<dbl>> swp(*) (fftw4<cdbl> + (fftw4<cdbl> * dbl))) : (real:0:1:1,user:0:1:0,sys:0:0:0)[clk:6102]	(198 calls X 3.081818e+01)
	cubby::field timer root : (real:0:9:3,user:0:8:20,sys:0:0:43)[clk:54354]
		scalar::transpose_blocks_when_received : (real:0:5:55,user:0:5:12,sys:0:0:43)[clk:35562]	(3054 calls X 1.164440e+01)
			scalar::copy_transposed : (real:0:1:49,user:0:1:48,sys:0:0:0)[clk:10920]	(12216 calls X 8.939096e-01)
		vector::in_place_curl : (real:0:0:34,user:0:0:34,sys:0:0:0)[clk:3436]	(202 calls X 1.700990e+01)
		scalar::local_energy : (real:0:0:2,user:0:0:2,sys:0:0:0)[clk:274]	(66 calls X 4.151515e+00)
		vector::vec_prod : (real:0:0:50,user:0:0:50,sys:0:0:0)[clk:5074]	(202 calls X 2.511881e+01)
		vector::project : (real:0:0:40,user:0:0:40,sys:0:0:0)[clk:4096]	(101 calls X 4.055445e+01)
		scalar::dealias : (real:0:0:59,user:0:0:59,sys:0:0:0)[clk:5910]	(606 calls X 9.752475e+00)

Last modified 9 years ago Last modified on Sep 29, 2011 2:47:39 PM