In message from Kilian CAVALOTTI <[EMAIL PROTECTED]> (Fri, 18 Apr
2008 16:38:26 -0700):
...
The same benchmark on lower-end hardware (E5345) running Linux (same
4X
DDR IB though), gives roughly 30% better results:
#---------------------------------------------------
# Benchmarking PingPong
# #processes = 2
#---------------------------------------------------
#bytes #repetitions t[usec] Mbytes/sec
0 1000 4.72 0.00
1 1000 4.68 0.20
2 1000 4.64 0.41
4 1000 4.74 0.81
8 1000 4.68 1.63
16 1000 4.78 3.19
32 1000 4.79 6.37
64 1000 4.84 12.61
128 1000 6.12 19.95
256 1000 6.47 37.71
512 1000 7.14 68.40
1024 1000 8.53 114.54
2048 1000 10.81 180.65
4096 1000 14.12 276.58
8192 1000 20.99 372.21
:-)
I may add our results on Supermicro H8DCE/Opteron 246 (also slower
hardware, I think ?) - w/ old Linux (OpenSuSE 10.1) and old OFED
(1.2):
# Benchmarking PingPong
# #processes = 2
#---------------------------------------------------
#bytes #repetitions t[usec] Mbytes/sec
0 1000 3.17 0.00
1 1000 3.21 0.30
2 1000 3.20 0.60
4 1000 3.20 1.19
8 1000 3.20 2.38
16 1000 3.22 4.74
32 1000 3.27 9.32
64 1000 3.44 17.77
128 1000 4.18 29.21
256 1000 4.47 54.62
512 1000 5.15 94.83
1024 1000 6.54 149.29
2048 1000 8.05 242.76
4096 1000 10.93 357.42
8192 1000 16.72 467.14
Also better :-)
Mikhail Kuzminsky
Computer Assistance to Chemical Research Center
Zelinsky Institute of Organic Chemistry
Moscow
_______________________________________________
Beowulf mailing list, Beowulf@beowulf.org
To change your subscription (digest mode or unsubscribe) visit
http://www.beowulf.org/mailman/listinfo/beowulf
