<> factor of 60 :-)  Even a 386DX/16 would likely fair well against a
<> MicroVAX II with the dhrystone benchmark. But I've a feeling that float
<
<	the 386DX blows the uVax-II out of the water.

Really?  

<Ummm, not really.  Both are hobbled by 'crippled' bus structures - the
<	uVax-II by the multiplexed Qbus and the 386 by the ISA bus (which
<	BTW is faster than the Qbus ;)).

Not really the ISA bus runs at a bus clock of 8mhz and the Q-bus is not so 
limited.  For some items like DMA q-bus is actaully faster and can do 
things like linked list DMA.

<The "PC" (386) would be able to use more current SCSI devices (but the
<thought of a Cheetah drive hooked up to a 386 wobbles the mind ;-)) 
<whereas the uVax-II could not for the most part.

Kidding me?  Put a CMD or other scsi controller in a Q-bus vaxen and watch 
it go.  Better yet a Kelsi (ra8x series interface) and whach out.

Of course a later VAX like the 3400 with the Cvax and RZ series scsi were 
even faster still.

<If you stuffed a 80387 chip into the 386 system you were far ahead
<of the uVax-II in FP.  The uVax-II can't even do BCD math faster than
<a 386 because DEC left out the decimal math instruction set.  Sigh.

All things considered the 386 was over five years later than the MV-II
and while it can crank numbers faster running multi users it was still
in the same class or slower.

Actually PC class 386s were as hobbled or far worse than Microvax-IIs
as they used the same MFM disks with controllers that were clearly 
slower than the RQDX3.  In 1993 when I was testing things the eithernet
controllers that 3000 series vaxen were using were clearly faster than 
anythng in the 386/33 or 486/33s at that time for sustained data rates.

<For 'raw' cpu power a 386DX/33 is equal to a (get this) a VAX-8650 
<(what we used to call "big iron").  It was a real suprise/awakening
<years ago when I benched a 386/33 and it came out faster than a 8650.
<Now for sure a 8650 could move a *LOT* more I/O over multiple busses, 
<but CPU wise (and if YOU're the only user) the 386 is faster than any 
<VAX up thru the 8650.

An 8650 was what 1986 technology?  Typically supported dozens if not
hundreds of users with clustering, fast disks, networking interfaces
and I have yet to see the 386 do any of that.  Raw CPU power is not a 
real measure of system performance.  We are still comparing apples and 
oranges.

To me a 386 running netBSD and a half dozen users on terminals doing 
wordprocessing, spread sheets and other typical office apps would 
show the differences between that and a MicroVAX-II better.  Then we could 
up the pot and give those users a DWT (decwindows/xwindows) terminal off 
an eithernet and see what VAX and X86 performance compares while serving 
that load.

The only machines I run single user on are PCs, PDP-11(rt-11) and all 
but one of my z80 boxen and they respond fast all of them.  But when I 
crak up background jobs on those than can I can see the difference.  Even 
my 486 box nearly stops under winders(single user!) when printing.  When I 
run something like the vaxen queueing a print job is not a show stopper,
nor copying over the network and generally (underVMS) there are two to 
three logged in and doing work.  Now I've just gotten linux (long story 
why) up on a 386/33 with an IDE 420 meg drive and it seems to compare 
to the VS2000 I have with a RD54 and ultrix but then I havn't pressed 
the linux yet and I suspect the PC format will make itself known as 
less capable despite having a superfast 386.  Why?  To much sluggy IO
in the PC, DMA is not used for a lot of stuff and the cpu spends time in 
loops doing PIO(no fault of *nix) never minding the work it has to do 
to manage the video. 

Raw cpu power is far from the best indicator.


Allison