[RC5] dual processor BeOS RC5 benchmarks

Jeffrey Hartgerink jeffrey at scripps.edu
Thu Jul 2 19:07:47 EDT 1998


>>>[05/17/98 23:37:55 GMT] Completed block 64CE39DB:00000000 (1073741824 keys)
>>>                        00:43:22.36 - [412602.57 keys/sec]
>>>[05/17/98 23:37:55 GMT] RC5 1*2^30 Block: 64CE39DA:00000000 ready to process
>>>[05/17/98 23:37:55 GMT] 35 Blocks remain in file 
>>>/boot/beos/rc5des/buff-in.rc5
>>>[05/17/98 23:37:55 GMT] 14 Blocks are in file /boot/beos/rc5des/buff-out.rc5
>>>[05/17/98 23:37:55 GMT] Tot: 977 RC5 blocks 244:21:45.96 - [820527.50 
>>>keys/sec]
>>>                        Tot: 0 DES blocks 244:21:45.96 - [0.00 keys/sec]
>>>
>>>Could it be that this BeBox has dual 133 MHz processors? For some reason 
that
>>>rings a bell... That would perhaps be more in line with other stats?
>
>>Its possible. There were two BeBoxes. The original dual 66MHz 603 
>>followed by a dual 133MHz 603e. From this log its not clear to me if you 
>>were getting 412,602 keys/sec or 820,527 keys/sec. From other numbers 
>>I've seen I'd guess 412kkeys, which would give you about 205kkeys/cpu 
>>which seems reasonable...
>
>Ah. I didn't know there were two. Then this is a dual 133 MHz box. And I 
>propose
>that the keyrate is in fact 820 kkeys/sec for both processors, and 410 
>kkeys/sec
>for one processor. (This BeBox pretty much doesn't get used at all.) But if
>anyone else has access to a dual PowerPC machine, it would be good to get 
>those
>benchmarks as well.

After reconsideration I think I agree with you. Amazing that the old 
BeBox was processing that fast so long ago on mere 133MHz 603e's.

-JEFF
--
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