[RC5] C DES core

christ fool at dfw.net
Fri Jan 23 01:54:01 EST 1998


>Date: Thu, 22 Jan 1998 13:24:07 -0800 (PST)
>From: Mary Conner <trif at serv.net>


>fast as they are expecting?  I estimate that a generic DES core would
>have got us 5% people committed to doing DES with a client that would
>produce crappy stats.  The vast majority of people participating are not
>like the people on this mailing list, they run for stats and stats only
>and could care less for the overall goal.

stats aside, i can tell you that my contribution to the DES effort was
hampered...precisely how much, i havent calculated, but i'd say that about
95% is probably an accurate figure.  thankfully, deschall came along and
i'm now throwing approx 10Mkeys/s (from ~40 machines, most with severely
!optimized cores, much better than 0kkeys/s) into the effort that way.
i personally could care less about stats, but not much less.
i do care that i wasted so many cycles before clients were available for
fully 50 machines that aren't x86. (sparc, rs6000, mips, alpha)
i'm not trying to complain about the d.net effort; i'm a happy and con-
tinuing participant for the long haul, but i think part of the reason x86
clients are so important is because a lot of other clients have been
neglected, and people without an x86 focus in their domain are losing
interest---until deschall came out, i'd been waiting months for a client
to run on my non-ppc rs/6000s...all 35 of them.  i hope i won't, but am
willing to bet that i still will be, once DES is over.

my message to the developers:  take a c core, and take offers for comp-
ilation accounts seriously.  you've already lost probably a Gkey from me
alone already (rc5).  if the i386 clients are being worried about, then
worry about other cpu's that arent even as comitragically underpowered.


>The cold hard truth is that most of the people out there were recruited
>with and care about one thing---STATS, and they have zero commitment
>to the d.net cause.

let's not be too pessimistic; i think a lot of people have a little more
than 0 commitment to the cause.  i can certainly say that is the truth
for the 5 major contributors to our top100 rc5 team.

anyway, i'm sorry if that was too much whining...i just want the effort
to be able to reach its full potential.

thanks for listening, and thanks to the d.net crew for persisting.

--
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