
Sat Sep 12 12:24:51 EDT 2015
numactl --interleave=all ../testing/testing_zheevd -JN -N 123 -N 1234 --range 10:90:10 --range 100:900:100 --range 1000:10000:1000 --lapack
% MAGMA 1.7.0  compiled for CUDA capability >= 3.5, 32-bit magma_int_t, 64-bit pointer.
% CUDA runtime 7000, driver 7000. OpenMP threads 16. MKL 11.2.2, MKL threads 16. 
% device 0: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 1: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 2: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% Sat Sep 12 12:24:57 2015
% Usage: ../testing/testing_zheevd [options] [-h|--help]

% jobz = No vectors, uplo = Lower
%   N   CPU Time (sec)   GPU Time (sec)
%======================================
  123      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

 1234      0.28             0.31
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   10      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   20      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   30      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   40      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   50      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   60      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   70      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   80      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   90      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

  100      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

  200      0.01             0.01
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

  300      0.01             0.01
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

  400      0.02             0.02
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

  500      0.04             0.04
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

  600      0.05             0.05
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

  700      0.07             0.07
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

  800      0.10             0.10
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

  900      0.13             0.13
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

 1000      0.16             0.16
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

 2000      0.80             0.82
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

 3000      2.51             2.03
    | S_magma - S_lapack | / |S| = 3.17e-19   ok

 4000      6.04             3.90
    | S_magma - S_lapack | / |S| = 2.41e-18   ok

 5000      9.41             6.62
    | S_magma - S_lapack | / |S| = 1.19e-19   ok

 6000     15.73            10.26
    | S_magma - S_lapack | / |S| = 5.56e-19   ok

 7000     23.73            15.06
    | S_magma - S_lapack | / |S| = 1.25e-19   ok

 8000     36.43            21.08
    | S_magma - S_lapack | / |S| = 1.08e-19   ok

 9000     48.41            28.74
    | S_magma - S_lapack | / |S| = 9.17e-19   ok

10000     63.89            37.79
    | S_magma - S_lapack | / |S| = 1.19e-18   ok

Sat Sep 12 12:30:52 EDT 2015

Sat Sep 12 12:30:52 EDT 2015
numactl --interleave=all ../testing/testing_zheevd -JV -N 123 -N 1234 --range 10:90:10 --range 100:900:100 --range 1000:10000:1000 --lapack
% MAGMA 1.7.0  compiled for CUDA capability >= 3.5, 32-bit magma_int_t, 64-bit pointer.
% CUDA runtime 7000, driver 7000. OpenMP threads 16. MKL 11.2.2, MKL threads 16. 
% device 0: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 1: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 2: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% Sat Sep 12 12:30:58 2015
% Usage: ../testing/testing_zheevd [options] [-h|--help]

% jobz = Vectors needed, uplo = Lower
%   N   CPU Time (sec)   GPU Time (sec)
%======================================
  123      0.00             0.01
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

 1234      0.47             0.32
    | S_magma - S_lapack | / |S| = 1.52e-18   ok

   10      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   20      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   30      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   40      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   50      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   60      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   70      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   80      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

   90      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

  100      0.00             0.00
    | S_magma - S_lapack | / |S| = 0.00e+00   ok

  200      0.01             0.01
    | S_magma - S_lapack | / |S| = 1.11e-17   ok

  300      0.02             0.02
    | S_magma - S_lapack | / |S| = 5.44e-18   ok

  400      0.04             0.03
    | S_magma - S_lapack | / |S| = 4.47e-18   ok

  500      0.06             0.05
    | S_magma - S_lapack | / |S| = 2.15e-18   ok

  600      0.09             0.07
    | S_magma - S_lapack | / |S| = 9.92e-19   ok

  700      0.13             0.09
    | S_magma - S_lapack | / |S| = 1.46e-18   ok

  800      0.17             0.12
    | S_magma - S_lapack | / |S| = 1.39e-18   ok

  900      0.23             0.16
    | S_magma - S_lapack | / |S| = 2.43e-18   ok

 1000      0.30             0.20
    | S_magma - S_lapack | / |S| = 3.57e-19   ok

 2000      1.57             0.95
    | S_magma - S_lapack | / |S| = 1.79e-19   ok

 3000      5.40             2.39
    | S_magma - S_lapack | / |S| = 6.74e-19   ok

 4000     10.83             4.64
    | S_magma - S_lapack | / |S| = 2.23e-19   ok

 5000     20.30             7.91
    | S_magma - S_lapack | / |S| = 5.14e-19   ok

 6000     32.82            12.42
    | S_magma - S_lapack | / |S| = 1.19e-19   ok

 7000     52.75            18.38
    | S_magma - S_lapack | / |S| = 4.37e-20   ok

 8000     63.81            25.90
    | S_magma - S_lapack | / |S| = 5.58e-20   ok

 9000     82.38            35.02
    | S_magma - S_lapack | / |S| = 3.53e-20   ok

10000    109.63            46.07
    | S_magma - S_lapack | / |S| = 2.86e-19   ok

Sat Sep 12 12:40:18 EDT 2015

Sat Sep 12 12:40:18 EDT 2015
numactl --interleave=all ../testing/testing_zheevd_gpu -JN -N 123 -N 1234 --range 10:90:10 --range 100:900:100 --range 1000:10000:1000
% MAGMA 1.7.0  compiled for CUDA capability >= 3.5, 32-bit magma_int_t, 64-bit pointer.
% CUDA runtime 7000, driver 7000. OpenMP threads 16. MKL 11.2.2, MKL threads 16. 
% device 0: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 1: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 2: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% Sat Sep 12 12:40:24 2015
% Usage: ../testing/testing_zheevd_gpu [options] [-h|--help]

% jobz = No vectors, uplo = Lower
%   N   CPU Time (sec)   GPU Time (sec)
%======================================
  123       ---              0.00
 1234       ---              0.26
   10       ---              0.00
   20       ---              0.00
   30       ---              0.00
   40       ---              0.00
   50       ---              0.00
   60       ---              0.00
   70       ---              0.00
   80       ---              0.00
   90       ---              0.00
  100       ---              0.00
  200       ---              0.01
  300       ---              0.01
  400       ---              0.02
  500       ---              0.04
  600       ---              0.05
  700       ---              0.08
  800       ---              0.10
  900       ---              0.13
 1000       ---              0.16
 2000       ---              0.82
 3000       ---              2.04
 4000       ---              3.98
 5000       ---              6.65
 6000       ---             10.23
 7000       ---             15.04
 8000       ---             20.99
 9000       ---             28.68
10000       ---             37.68
Sat Sep 12 12:42:53 EDT 2015

Sat Sep 12 12:42:53 EDT 2015
numactl --interleave=all ../testing/testing_zheevd_gpu -JV -N 123 -N 1234 --range 10:90:10 --range 100:900:100 --range 1000:10000:1000
% MAGMA 1.7.0  compiled for CUDA capability >= 3.5, 32-bit magma_int_t, 64-bit pointer.
% CUDA runtime 7000, driver 7000. OpenMP threads 16. MKL 11.2.2, MKL threads 16. 
% device 0: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 1: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 2: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% Sat Sep 12 12:42:59 2015
% Usage: ../testing/testing_zheevd_gpu [options] [-h|--help]

% jobz = Vectors needed, uplo = Lower
%   N   CPU Time (sec)   GPU Time (sec)
%======================================
  123       ---              0.01
 1234       ---              0.32
   10       ---              0.00
   20       ---              0.00
   30       ---              0.00
   40       ---              0.00
   50       ---              0.00
   60       ---              0.00
   70       ---              0.00
   80       ---              0.00
   90       ---              0.00
  100       ---              0.00
  200       ---              0.01
  300       ---              0.02
  400       ---              0.04
  500       ---              0.05
  600       ---              0.07
  700       ---              0.10
  800       ---              0.13
  900       ---              0.17
 1000       ---              0.24
 2000       ---              0.97
 3000       ---              2.35
 4000       ---              4.58
 5000       ---              7.77
 6000       ---             12.29
 7000       ---             17.88
 8000       ---             25.17
 9000       ---             35.09
10000       ---             46.07
Sat Sep 12 12:45:59 EDT 2015

Sat Sep 12 14:01:49 EDT 2015
numactl --interleave=all ../testing/testing_zheevd -JN -N 123 -N 1234 --range 12000:20000:2000
% MAGMA 1.7.0  compiled for CUDA capability >= 3.5, 32-bit magma_int_t, 64-bit pointer.
% CUDA runtime 7000, driver 7000. OpenMP threads 16. MKL 11.2.2, MKL threads 16. 
% device 0: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 1: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 2: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% Sat Sep 12 14:01:55 2015
% Usage: ../testing/testing_zheevd [options] [-h|--help]

% jobz = No vectors, uplo = Lower
%   N   CPU Time (sec)   GPU Time (sec)
%======================================
  123     ---               0.00
 1234     ---               0.31
12000     ---              61.61
14000     ---              93.11
16000     ---             135.60
18000     ---             189.18
20000     ---             258.83
Sat Sep 12 14:15:21 EDT 2015

Sat Sep 12 14:15:21 EDT 2015
numactl --interleave=all ../testing/testing_zheevd -JV -N 123 -N 1234 --range 12000:20000:2000
% MAGMA 1.7.0  compiled for CUDA capability >= 3.5, 32-bit magma_int_t, 64-bit pointer.
% CUDA runtime 7000, driver 7000. OpenMP threads 16. MKL 11.2.2, MKL threads 16. 
% device 0: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 1: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 2: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% Sat Sep 12 14:15:28 2015
% Usage: ../testing/testing_zheevd [options] [-h|--help]

% jobz = Vectors needed, uplo = Lower
%   N   CPU Time (sec)   GPU Time (sec)
%======================================
  123     ---               0.01
 1234     ---               0.31
12000     ---              76.29
14000     ---             115.62
16000     ---             168.32
18000     ---             238.85
20000     ---             323.71
Sat Sep 12 14:32:12 EDT 2015

Sat Sep 12 14:32:12 EDT 2015
numactl --interleave=all ../testing/testing_zheevd_gpu -JN -N 123 -N 1234 --range 12000:20000:2000
% MAGMA 1.7.0  compiled for CUDA capability >= 3.5, 32-bit magma_int_t, 64-bit pointer.
% CUDA runtime 7000, driver 7000. OpenMP threads 16. MKL 11.2.2, MKL threads 16. 
% device 0: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 1: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 2: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% Sat Sep 12 14:32:18 2015
% Usage: ../testing/testing_zheevd_gpu [options] [-h|--help]

% jobz = No vectors, uplo = Lower
%   N   CPU Time (sec)   GPU Time (sec)
%======================================
  123       ---              0.00
 1234       ---              0.27
12000       ---             61.37
14000       ---             92.66
16000       ---            135.23
18000       ---            188.62
magma_zheevd_gpu returned error -113: cannot allocate memory on GPU device.
20000       ---              0.00
Sat Sep 12 14:41:30 EDT 2015

Sat Sep 12 14:41:30 EDT 2015
numactl --interleave=all ../testing/testing_zheevd_gpu -JV -N 123 -N 1234 --range 12000:20000:2000
% MAGMA 1.7.0  compiled for CUDA capability >= 3.5, 32-bit magma_int_t, 64-bit pointer.
% CUDA runtime 7000, driver 7000. OpenMP threads 16. MKL 11.2.2, MKL threads 16. 
% device 0: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 1: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% device 2: Tesla K40c, 745.0 MHz clock, 11519.6 MB memory, capability 3.5
% Sat Sep 12 14:41:36 2015
% Usage: ../testing/testing_zheevd_gpu [options] [-h|--help]

% jobz = Vectors needed, uplo = Lower
%   N   CPU Time (sec)   GPU Time (sec)
%======================================
  123       ---              0.01
 1234       ---              0.31
12000       ---             75.65
14000       ---            116.57
16000       ---            169.13
18000       ---            239.42
magma_zheevd_gpu returned error -113: cannot allocate memory on GPU device.
20000       ---              0.00
Sat Sep 12 14:53:07 EDT 2015
