OT Linux (RE: [rescue] OT: Stuffed Proliant?)

[Dave McGuire]

On December 22, Joshua D Boyd wrote:
> Besides, lack of rotate isn't all that bad.  Instead of rotating left by 12 
> bits, you shift left by 12, shift right by 20, then sum the two shifts.  The
> two shifts can be done simultaneously on a super-pipelined processor, so you
> need 3 cycles to do a rotate instead of one.  While this seems bad, I find it
> hard to believe that this is the sole reason for distributed net to be slower
> on SPARCs than intel boxes.  We loose 2 cylces on a rotate.  So what.  We
> make it up by doing less loads.

  Well, that's what the distributed.net people say.  And the rotate
instruction /no rotate instruction performance difference holds true
for every processor for which there's a distributed.net client.

  That's all the info I need...if it's not enough for you, grab the
sources and try it.

      -Dave

-- 
Dave McGuire
St. Petersburg, FL         "Less talk.  More synthohol." --Lt. Worf