[RC5] Re: [HARDWARE] Solaris on SPARC keyrate

Thord Nilson thordn at stacken.kth.se
Fri Oct 15 18:18:31 EDT 1999


On Fri, 15 Oct 1999, Aaron Kramer wrote:

> 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 hardware' to majordomo at lists.distributed.net
> 

You are probably confusing the result with the DES benchmark.
On a 250 MHz ultra-sparc i get: 414 kkeys/sek for RC5 and 4.9 Mkeys/sec
for DES.

/Thord.

merlin>./rc5des -benchmark

RC5DES v2.7103.427 client - a project of distributed.net
Copyright 1997-1999 distributed.net
Please visit http://www.distributed.net/ for up-to-date contest
information.
Start the client with '-help' for a list of valid command line options.

[Oct 15 15:14:50 UTC] Benchmarking RC5 with 1*2^23 tests (8388608 keys):    
[Oct 15 15:14:50 UTC] Completed in 0.00:00:20.22 [414,693.60 keys/sec]
[Oct 15 15:14:50 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 0.01:26:18.48.
[Oct 15 15:14:57 UTC] Benchmarking DES with 1*2^25 tests (33554432 keys):    
[Oct 15 15:14:57 UTC] Completed in 0.00:00:06.78 [4,947,018.89 keys/sec]
[Oct 15 15:14:57 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 0.00:07:14.09.
merlin>

--------------------------------------------
!  Thord Nilson  !  thordn at stacken.kth.se  !
--------------------------------------------

--
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