[RC5] lost packet after restart....

Dead J. Dona unholy_undead at hotmail.com
Fri Dec 13 13:05:32 EST 2002


> must restart blocks from different platforms or cores.  This is why its
> telling you that the block was started with another core/platform.

Thank you for explanation. This situation really confused me.
When it takes 6-7 hours to process one block (P166 at work :) it's very sad
to lose 40%.

> The block must be restarted if the core changes because different
> cores procede through the block differently, using different counting,
etc.
> Until cores stablize and cores are once again hardcoded based on
> cpu-ID, expect that the microbench mark may differ from time to time
> causing the client to use a different core.

[Nov 18 08:41:22 UTC] RC5-72: using core #0 (ANSI 4-pipe).
[Nov 18 08:41:44 UTC] RC5-72: Benchmark for core #0 (ANSI 4-pipe)
                      0.00:00:17.60 [33,665 keys/sec]
[Nov 18 08:41:44 UTC] RC5-72: using core #1 (ANSI 2-pipe).
[Nov 18 08:42:04 UTC] RC5-72: Benchmark for core #1 (ANSI 2-pipe)
                      0.00:00:16.64 [79,937 keys/sec]
[Nov 18 08:42:04 UTC] RC5-72: using core #2 (ANSI 1-pipe).
[Nov 18 08:42:24 UTC] RC5-72: Benchmark for core #2 (ANSI 1-pipe)
                      0.00:00:16.67 [84,000 keys/sec]
[Nov 18 08:42:24 UTC] RC5-72: using core #3 (SES 1-pipe).
[Nov 18 08:42:43 UTC] RC5-72: Benchmark for core #3 (SES 1-pipe)
                      0.00:00:16.95 [144,000 keys/sec]
[Nov 18 08:42:43 UTC] RC5-72: using core #4 (SES 2-pipe).
[Nov 18 08:43:03 UTC] RC5-72: Benchmark for core #4 (SES 2-pipe)
                      0.00:00:16.89 [146,152 keys/sec]
[Nov 18 08:43:03 UTC] RC5-72: using core #5 (DG 2-pipe).
[Nov 18 08:43:23 UTC] RC5-72: Benchmark for core #5 (DG 2-pipe)
                      0.00:00:16.75 [170,344 keys/sec]
[Nov 18 08:43:23 UTC] RC5-72: using core #6 (DG 3-pipe).
[Nov 18 08:43:42 UTC] RC5-72: Benchmark for core #6 (DG 3-pipe)
                      0.00:00:16.69 [164,982 keys/sec]
[Nov 18 08:43:42 UTC] RC5-72: using core #7 (DG 3-pipe alt).
[Nov 18 08:44:02 UTC] RC5-72: Benchmark for core #7 (DG 3-pipe alt)
                      0.00:00:16.75 [174,313 keys/sec]

OOOOPS!!!! Stupid dumb!!!! (Me).
At home on P3 620MHz 4th core is really faster nearly at 10%.
But why'd I think that here on P166 fourth core is fastest??? Dammit!
Thank's again...

--
To unsubscribe, send 'unsubscribe rc5' to majordomo at lists.distributed.net
rc5-digest subscribers replace rc5 with rc5-digest



More information about the rc5 mailing list