[RC5] rc5->des keyrate/blocksize/time ->weirdness

Marc Sissom msissom at dnaent.com
Thu Jan 15 10:27:28 EST 1998


The combination of these things does not compute.

The des benchmark says the box is going through keys
at nearly twice the rate of rc5.

The rates reported by the client while operating are
nearly twice the rates reported on rc5.

	rc5 = >600Kks
	des = >1Mks

The des block size was set at 2^28 from the start for
comparison.

The time required to complete a 2^28 des block should be
about 1/2 the time required for an rc5 block.

It is not. It is roughly equal to the time/block of rc5.

	rc5 = >7min/block
	des = >8min/block

The number of blocks per day should be about twice that
of rc5.

It is not. It is roughly equal to the blocks/day of rc5.

Is the block size selected/real off by a factor of two?
Do the benchmark/timing routines only count every other
key? Am I really going ~4x as fast on blocks that are really
~4x as big, but only counting half of the keys?

--
Marc Sissom                       http://www.dnaent.com
Design Engineer                     voice: 972/644-3301
DNA Enterprises, Inc.                 fax: 972/644-6338

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



More information about the rc5 mailing list