Quote:
|
Originally Posted by Groth
These big protein like memory bandwidth. An old PC100 using box has slowed 50% or more from the last protein; my top cruncher (with PC3200) has only dropped ~20%.
|
That's interesting; I thought I had heard before that df was *relatively* indifferent to memory bandwidth.
Things do seem to be picking up for me at least--over the last 2h11m, my machine is now averaging 7.84 gens/hour; versus the running average of 6.6 gens/hour between gen 7 and gen 143(current)...so that's looking much more like the 20% drop that was expected.
__________________
Everything aircooled
(I honestly don't know why you guys let me stay a member...
)
Always folding:
WXP Pro:
KD7R + Palomino 1800+
W2K3:
4x P3 Xeon 500 512KB (4 clients)
Linux boxes:
none
Had to put them to use doing *real* work.