Версія даної теми для друку

Натисніть сюди для перегляду даної теми у оригінальному форматі

Розподілені обчислення в Україні _ OGR _ OGR-26 Client Benchmark

Автор: cosmo_vk Oct 26 2008, 19:20

507 клиент, Q6600@3.15GHz
[Oct 26 17:18:45 UTC] OGR-NG: using core #0 (FLEGE 2.0).
[Oct 26 17:19:04 UTC] OGR-NG: Benchmark for core #0 (FLEGE 2.0)
0.00:00:16.11 [23,470,381 nodes/sec]
[Oct 26 17:19:04 UTC] OGR-NG: using core #1 (rt-asm-generic).
[Oct 26 17:19:23 UTC] OGR-NG: Benchmark for core #1 (rt-asm-generic)
0.00:00:17.09 [30,830,411 nodes/sec]

реальных данных еще не ловил.

Автор: Death Oct 26 2008, 21:55

Атлон 2500

[Oct 26 19:52:58 UTC] OGR-NG: using core #0 (FLEGE 2.0).
[Oct 26 19:53:18 UTC] OGR-NG: Benchmark for core #0 (FLEGE 2.0)
0.00:00:16.65 [12,790,007 nodes/sec]
[Oct 26 19:53:18 UTC] OGR-NG: using core #1 (rt-asm-generic).
[Oct 26 19:53:37 UTC] OGR-NG: Benchmark for core #1 (rt-asm-generic)
0.00:00:16.39 [13,765,241 nodes/sec]

Они в плане написали что наваяли новое ядро АДУПУ то есть FLEGE!

The OGR node rate for these new clients may appear to be slower than those for the OGR-25p2 project. This isn't a cause for concern. The effective search rate for the overall project is actually more efficient as these new clients are using an improved algorithm. The new algorithm is named FLEGE (Feiri-Levet Enhanced GARSP Engine). It has been developed by Didier Levet and Michael Feiri over the course of the past few months. We are especially grateful to them for this Herculean effort. In technical terms, the number of elements in the 'choose lookup table' has been increased from 48K to 2M elements. Although this will slightly increase the size of the dnetc binary, this optimization will significantly reduce the number of nodes that we have to search through, sometimes a node improvement of ten-fold or more.

Автор: Death Nov 4 2008, 15:28

Celeron 2GHz

[Nov 04 11:52:37 UTC] Automatic processor type detection found
an Intel Pentium 4/D/4-M/Celeron/Xeon processor.
[Nov 04 11:52:37 UTC] OGR-NG: using core #1 (rt-asm-generic).
[Nov 04 11:52:37 UTC] OGR-NG: Loaded 26/2-10-9-13-27 (1.70 Gnodes done)
[Nov 04 11:52:37 UTC] OGR-NG: 24 packets remain in buff-in.og2
[Nov 04 11:52:37 UTC] OGR-NG: 0 packets are in buff-out.og2
[Nov 04 11:52:37 UTC] 1 cruncher has been started.
[Nov 04 11:52:38 UTC] The keyserver says: OGR-P2 is closed.
[Nov 04 11:52:46 UTC] OGR-NG: using core #0 (FLEGE 2.0).
[Nov 04 11:53:05 UTC] OGR-NG: Benchmark for core #0 (FLEGE 2.0)
0.00:00:17.17 [9,120,260 nodes/sec]
[Nov 04 11:53:05 UTC] OGR-NG: using core #1 (rt-asm-generic).
[Nov 04 11:53:25 UTC] OGR-NG: Benchmark for core #1 (rt-asm-generic)
0.00:00:17.11 [8,757,677 nodes/sec]

Будьте внимательны

Автор: egorio Dec 15 2008, 14:18

На днях загорелся идеей протестить новое ядро огра у себя.

Коровка - C2Q Q6600 3200 mhz

Win XP x64 (.507) показала вот такое:

Automatic processor type detection found an Intel Core 2/Xeon processor.
OGR-NG: using core #1 (rt-asm-generic).
OGR-NG: Benchmark for core #1 (rt-asm-generic) 0.00:00:16.37 [32,251,968 nodes/sec]
RC5-72: using core #10 (GO 2-pipe alt).
RC5-72: Benchmark for core #10 (GO 2-pipe alt) 0.00:00:16.57 [12,061,951 keys/sec]

Ubuntu 8.10 x64 (.507) показала вот такое:

OGR-NG: using core #0
OGR-NG: Benchmark for core #0 (FLEGE-64 2.0) 0.00:00:16.66 [41,795,918 nodes/sec]
Automatic processor type detection found an Intel Core 2 processor.
RC5-72: using core #1 (KBE-64 3-pipe).
RC5-72: Benchmark for core #1 (KBE-64 3-pipe) 0.00:00:16.85 [10,784,336 keys/sec]

Автор: Burzum Dec 15 2008, 14:21

а можна те саме, тільки по всіх ядрах?

Автор: egorio Dec 15 2008, 14:38

Вот, тест по всем ядрам:

Ubuntu 8.10 x64 (.507)

CODE

[Dec 15 12:35:46 UTC] OGR-NG: Benchmark for core #0 (FLEGE-64 2.0)
0.00:00:16.13 [41,283,794 nodes/sec]

Win XP x64 (.507)

CODE

[Dec 15 12:47:06 UTC] OGR-NG: using core #0 (FLEGE 2.0).
[Dec 15 12:47:26 UTC] OGR-NG: Benchmark for core #0 (FLEGE 2.0)
0.00:00:16.70 [24,266,145 nodes/sec]
[Dec 15 12:47:26 UTC] OGR-NG: using core #1 (rt-asm-generic).
[Dec 15 12:47:44 UTC] OGR-NG: Benchmark for core #1 (rt-asm-generic)
0.00:00:16.62 [31,782,735 nodes/sec]

Автор: Death Dec 23 2008, 21:43

dnetc v2.9102-508-GTR-08122211 for Win32 (WindowsNT 5.1).
Using email address (distributed.net ID) 'satan@nebesa.com'

[Dec 23 19:40:55 UTC] Automatic processor type detection found
an AMD Athlon XP/MP or Sempron (Thoroughbred) processor.
[Dec 23 19:40:55 UTC] OGR-NG: using core #0 (FLEGE 2.0).
[Dec 23 19:41:15 UTC] OGR-NG: Benchmark for core #0 (FLEGE 2.0)
0.00:00:17.07 [13,277,147 nodes/sec]
[Dec 23 19:41:15 UTC] OGR-NG: using core #1 (rt-asm-generic).
[Dec 23 19:41:34 UTC] OGR-NG: Benchmark for core #1 (rt-asm-generic)
0.00:00:16.92 [13,979,522 nodes/sec]
[Dec 23 19:41:34 UTC] OGR-NG: using core #2 (rt-asm-mmx).
[Dec 23 19:41:55 UTC] OGR-NG: Benchmark for core #2 (rt-asm-mmx)
0.00:00:16.56 [17,192,025 nodes/sec]

ВСем ставить обязательно! +20%!!