Nodeスペック
| Company |
HP |
| Product |
Z8 G4 Workstation |
| CPU |
Gold 6132 @ 2.60GHz |
| Core |
28Core/Node (14Core/1CPU) |
| Memory |
64GByte |
| OS |
CentOS Linux release 7.4.1708 x64 |
| compiler |
gcc バージョン 4.8.5 20150623 |
結果性能値
| 実行時Core数 |
結果値(MFlops) |
| 1 Core実行時 |
2248.22 |
| 28 Core実行時 |
30782.27 |
実行結果ログ
single Core 実行結果
################################################
1Core
For example:
Grid-size= XS (32x32x64)
S (64x64x128)
M (128x128x256)
L (256x256x512)
XL (512x512x1024)
Grid-size =
mimax = 128 mjmax = 128 mkmax = 256
imax = 127 jmax = 127 kmax =255
Start rehearsal measurement process.
Measure the performance in 3 times.
MFLOPS: 2281.903612 time(s): 0.180251 1.733593e-03
Now, start the actual measurement process.
The loop will be excuted in 998 times
This will take about one minute.
Wait for a while
cpu : 60.861774 sec.
Loop executed for 998 times
Gosa : 7.562597e-04
MFLOPS measured : 2248.224406
Score based on Pentium III 600MHz using Fortran 77: 27.139358
################################################
Max-Core OpenMP並列実行結果
################################################
28Core
For example:
Grid-size= XS (32x32x64)
S (64x64x128)
M (128x128x256)
L (256x256x512)
XL (512x512x1024)
Grid-size =
mimax = 128 mjmax = 128 mkmax = 256
imax = 127 jmax = 127 kmax =255
Start rehearsal measurement process.
Measure the performance in 3 times.
MFLOPS: 5984.336379 time(s): 0.068732 1.693730e-03
Now, start the actual measurement process.
The loop will be excuted in 2618 times
This will take about one minute.
Wait for a while
cpu : 11.660648 sec.
Loop executed for 2618 times
Gosa : 3.790309e-04
MFLOPS measured : 30782.272653
Score based on Pentium III 600MHz using Fortran 77: 371.587067
################################################
特記事項
なし
Post Views: 481