wiki:Titane

On Titane(CCRT) for release 1481, 32 cpus for a 2563

max number of allocated scalars: 39
 ---------------------------------------------
   32 Processor run, global<256,256,256>
   for 100 time steps
main timer : (real:0:1:57,user:0:1:52,sys:0:0:3)[clk:11750]
	loop : (real:0:1:15,user:0:1:10,sys:0:0:2)[clk:7549]	(100 calls X 7.549000e+01)
	FFT timer : (real:0:1:38,user:0:1:35,sys:0:0:0)[clk:9843]
		FFT and transposition time : (real:0:1:38,user:0:1:35,sys:0:0:0)[clk:9843]	(512 calls X 1.922461e+01)
			FFT only : (real:0:0:14,user:0:0:14,sys:0:0:0)[clk:1419]	(4302 calls X 3.298466e-01)
		planification time : (real:0:0:40,user:0:0:39,sys:0:0:0)[clk:4001]
	azur::array timer root : (real:0:0:11,user:0:0:10,sys:0:0:0)[clk:1178]
		view = expr : (real:0:0:11,user:0:0:10,sys:0:0:0)[clk:1178]	(2380 calls X 4.949580e-01)
			basic3<flt> id= (basic3<int> + flt) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:0]	(2 calls X 0.000000e+00)
			fftw4<cdbl> id= cdbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:40]	(106 calls X 3.773585e-01)
			fftw4<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:2]	(4 calls X 5.000000e-01)
			fftw3<dbl> id= fftw3<dbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:3]	(9 calls X 3.333333e-01)
			fftw3<dbl> *= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]	(6 calls X 1.666667e-01)
			fftw3<dbl> id= dbl : (real:0:0:1,user:0:0:0,sys:0:0:0)[clk:109]	(516 calls X 2.112403e-01)
			fftw3<dbl> /= dbl : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:103]	(618 calls X 1.666667e-01)
			fftw4<cdbl> id= fftw4<cdbl> : (real:0:0:3,user:0:0:3,sys:0:0:0)[clk:317]	(406 calls X 7.807882e-01)
			fftw4<dbl> id= fftw4<dbl> : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:146]	(205 calls X 7.121951e-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:2]	(2 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:2]	(2 calls X 1.000000e+00)
			fftw4<cdbl> *= s2v<basic3<dbl>> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:2]	(2 calls X 1.000000e+00)
			fftw4<cdbl> += fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]	(2 calls X 5.000000e-01)
			fftw4<cdbl> id= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:106]	(100 calls X 1.060000e+00)
			fftw4<cdbl> -= fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:75]	(100 calls X 7.500000e-01)
			fftw4<cdbl> -= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:102]	(100 calls X 1.020000e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> swp(*) (fftw4<cdbl> + (fftw4<cdbl> * dbl))) : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:166]	(200 calls X 8.300000e-01)
	cubby::field timer root : (real:0:0:47,user:0:0:45,sys:0:0:0)[clk:4777]
		scalar::transpose_blocks_when_received : (real:0:0:42,user:0:0:39,sys:0:0:0)[clk:4215]	(3072 calls X 1.372070e+00)
			scalar::copy_transposed : (real:0:0:3,user:0:0:2,sys:0:0:0)[clk:300]	(49152 calls X 6.103516e-03)
		vector::in_place_curl : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:118]	(204 calls X 5.784314e-01)
		vector::vec_prod : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:151]	(204 calls X 7.401960e-01)
		vector::project : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:64]	(102 calls X 6.274510e-01)
		scalar::dealias : (real:0:0:1,user:0:0:1,sys:0:0:0)[clk:199]	(612 calls X 3.251634e-01)
		scalar::local_energy : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:30]	(66 calls X 4.545455e-01)

On Titane(CCRT) for release 1481, 32 cpus for a 5123

max number of allocated scalars: 39
 ---------------------------------------------
   32 Processor run, global<512,512,512>
   for 100 time steps
main timer : (real:0:13:59,user:0:13:34,sys:0:0:22)[clk:83967]
	loop : (real:0:9:10,user:0:8:49,sys:0:0:19)[clk:55058]	(100 calls X 5.505800e+02)
	FFT timer : (real:0:11:23,user:0:11:17,sys:0:0:4)[clk:68334]
		FFT and transposition time : (real:0:11:23,user:0:11:17,sys:0:0:4)[clk:68334]	(512 calls X 1.334648e+02)
			FFT only : (real:0:2:4,user:0:2:4,sys:0:0:0)[clk:12455]	(4302 calls X 2.895165e+00)
		planification time : (real:0:4:27,user:0:4:25,sys:0:0:1)[clk:26761]
	azur::array timer root : (real:0:1:37,user:0:1:31,sys:0:0:6)[clk:9788]
		view = expr : (real:0:1:37,user:0:1:31,sys:0:0:6)[clk:9788]	(2380 calls X 4.112605e+00)
			basic3<flt> id= (basic3<int> + flt) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:1]	(2 calls X 5.000000e-01)
			fftw4<cdbl> id= cdbl : (real:0:0:3,user:0:0:3,sys:0:0:0)[clk:388]	(106 calls X 3.660377e+00)
			fftw4<dbl> id= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:17]	(4 calls X 4.250000e+00)
			fftw3<dbl> id= fftw3<dbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:21]	(9 calls X 2.333333e+00)
			fftw3<dbl> *= dbl : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:9]	(6 calls X 1.500000e+00)
			fftw3<dbl> id= dbl : (real:0:0:7,user:0:0:1,sys:0:0:6)[clk:776]	(516 calls X 1.503876e+00)
			fftw3<dbl> /= dbl : (real:0:0:7,user:0:0:7,sys:0:0:0)[clk:788]	(618 calls X 1.275081e+00)
			fftw4<cdbl> id= fftw4<cdbl> : (real:0:0:27,user:0:0:26,sys:0:0:0)[clk:2703]	(406 calls X 6.657636e+00)
			fftw4<dbl> id= fftw4<dbl> : (real:0:0:12,user:0:0:12,sys:0:0:0)[clk:1252]	(205 calls X 6.107317e+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:16]	(2 calls X 8.000000e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> * (fftw4<cdbl> * dbl)) : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:16]	(2 calls X 8.000000e+00)
			fftw4<cdbl> *= s2v<basic3<dbl>> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:12]	(2 calls X 6.000000e+00)
			fftw4<cdbl> += fftw4<cdbl> : (real:0:0:0,user:0:0:0,sys:0:0:0)[clk:13]	(2 calls X 6.500000e+00)
			fftw4<cdbl> id= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:8,user:0:0:8,sys:0:0:0)[clk:822]	(100 calls X 8.220000e+00)
			fftw4<cdbl> -= fftw4<cdbl> : (real:0:0:6,user:0:0:6,sys:0:0:0)[clk:677]	(100 calls X 6.770000e+00)
			fftw4<cdbl> -= ((fftw4<cdbl> * dbl) * s2v<basic3<dbl>>) : (real:0:0:7,user:0:0:7,sys:0:0:0)[clk:796]	(100 calls X 7.960000e+00)
			fftw4<cdbl> id= (s2v<basic3<dbl>> swp(*) (fftw4<cdbl> + (fftw4<cdbl> * dbl))) : (real:0:0:14,user:0:0:14,sys:0:0:0)[clk:1479]	(200 calls X 7.395000e+00)
	cubby::field timer root : (real:0:5:18,user:0:5:14,sys:0:0:2)[clk:31871]
		scalar::transpose_blocks_when_received : (real:0:4:33,user:0:4:29,sys:0:0:2)[clk:27393]	(3072 calls X 8.916992e+00)
			scalar::copy_transposed : (real:0:0:25,user:0:0:25,sys:0:0:0)[clk:2556]	(49152 calls X 5.200195e-02)
		vector::in_place_curl : (real:0:0:9,user:0:0:9,sys:0:0:0)[clk:917]	(204 calls X 4.495098e+00)
		vector::vec_prod : (real:0:0:12,user:0:0:12,sys:0:0:0)[clk:1241]	(204 calls X 6.083333e+00)
		vector::project : (real:0:0:5,user:0:0:5,sys:0:0:0)[clk:537]	(102 calls X 5.264706e+00)
		scalar::dealias : (real:0:0:15,user:0:0:15,sys:0:0:0)[clk:1558]	(612 calls X 2.545752e+00)
		scalar::local_energy : (real:0:0:2,user:0:0:2,sys:0:0:0)[clk:225]	(66 calls X 3.409091e+00)


Last modified 10 years ago Last modified on Aug 17, 2010 6:32:27 PM