[RC5] Solaris on SPARC keyrate

Peter A. DeNitto denitto at llamas.net
Sun Oct 17 23:39:06 EDT 1999


Remember that it benchmarks not only RC5, but DES as well...

And I shouldn't have to remind you how much easier DES is... (If you need
reminding, look at the last DES contest).

[Oct 18 00:45:26 UTC] Automatic processor detection found 1 processor.
[Oct 18 00:45:42 UTC] Benchmarking RC5 with 1*2^23 tests (8388608 keys):
[Oct 18 00:45:42 UTC] Completed in 0.00:00:15.70 [534,174.94 keys/sec]
[Oct 18 00:45:42 UTC] The preferred RC5 blocksize for this machine should be
                      set to 31 (8*2^28 keys). At the benchmarked keyrate
                      (ie, under ideal conditions) each processor would finish
                      a block of that size in approximately 0.01:07:00.19.
[Oct 18 00:45:49 UTC] Benchmarking DES with 1*2^25 tests (33554432 keys):
[Oct 18 00:45:49 UTC] Completed in 0.00:00:06.61 [5,073,541.05 keys/sec]
[Oct 18 00:45:49 UTC] The preferred DES blocksize for this machine should be
                      set to 31 (8*2^28 keys). At the benchmarked keyrate
                      (ie, under ideal conditions) each processor would finish
                      a block of that size in approximately 0.00:07:03.27.

This is a 267i.  It does 400-540k per sec depending on if I've got X
running, netscape, mxaudio...

The second bench is DES...  And because of the V8 architecture and
bitslicing with the large number of registers, it flys thru DES, but then,
that's not the current contest.... :)

--Pete


On Fri, 15 Oct 1999, Aaron Kramer wrote:

> Date: Fri, 15 Oct 1999 10:48:22 -0400
> From: Aaron Kramer <aaron.kramer at ins.com>
> Reply-To: rc5 at lists.distributed.net
> To: hardware at lists.distributed.net
> Cc: rc5 at lists.distributed.net
> Subject: [RC5] Solaris on SPARC keyrate
> 
> Has anyone else noticed that the benchmark keyrate (./rc5des -benchmark) is
> way, way higher than the actual keyrate?
> 
> Is this a cross-platform thing? Is this expected behavior?
> For example, a single 267MHz Ultra IIi benchmarks at over 4 million keys/s
> (!!) but runs at only 300-400 KKeys/s!
> (or so my cohort tells me!)
> 
> 
> Aaron Kramer, Network Systems Engineer
> International Network Services (INS), Philadelphia, PA
> Pager: 1-800-INS-1-INS
> aaron_kramer at ins.com, NSE, CISSP, ^TLA and FLA TBD$
> "I never metacharacter I didn't like."
> 
> --
> To unsubscribe, send 'unsubscribe rc5' to majordomo at lists.distributed.net
> rc5-digest subscribers replace rc5 with rc5-digest
> 

--
Help Crack Government Encryption - Join Distributed.Net : www.distributed.net
Not all men who drink are poets.  Some of us drink because we aren't poets.

--
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