<That's fascinating. Take obsolete hardware and architecture (vax), and
Define that, obsolete is when it doesnt do the job.
<>The problems is equivalent hardware. You can't configure a PC
<>like a VAX, they are two different types of machines. A PC
<>is tuned for a single user, while a VAX is tuned for many users.
<
<Amen! Thank you!
You obviously didn't understand, likely don't care to. One observation is
those that claim a narrow pardigm often end up eating it. VAX is not beall
but then again it represents 20 years, in excess of 8 busses (cpu to memory
and primary IO) and one major OS that still is secure and fast. PCs are
an evolving species and wer are not up to the maturity level for even the
OS not minding the hardware.
<Remember, I was just making the observation that the integer performance of
<the vax 8650 is worse than a dx2-66. I think single-user; I run single-use
<machines. The future is single-user with vast network-accessed databases.
All served by big iron with 64 bit cpus, why is merced so hot to beat
Alpha.
<Again, with -equivalent hardware- it certainly would.
Ok. find a PC that you can cluster. Set it up in minimal time using an
out of box OS.
<having given up on Big Iron. Also, the market sizes for IBM, HP, and Sun'
<"big iron" exist specifically to be those back-room servers that can do lot
<of disk I/Os per second (the web, eh?).
Even the web needs lots of IO, and more every day.
<BUT, I would like the Vax Lover Crowd to acknowledge that they integer
<performance of their machine is pathetic.
If that all you hang you hat on you win. Your still missing the point
and most everything with it.
<> Its not the speed
<>of the individual bus, but its the number of busses.
<
<That's of course bull.....
<
<>The more busses, the more parallelism and the less waiting.
<
<-IF- the speed of the busses is high enough!
They have to be very very fast and the system on the bus very very fast
and then you still have bus bandwidth conflicts. Therein lies the truth,
if someone delivers a PC that has multiple independent PCI buses that can
run in parallel will you start claiming that is better?
<>One
<>fast bus works well until you want to do multiple things, and
<>then it quickly becomes a bottleneck.
<
<Excuse me? Could you please back up this assertion with data? After all,
<at -some- point, all these busses have to get their data into/out of the CP
<right? And -that- is a "bottleneck" for sure... (Sure, you can have
<channel-to-channel I/O, but most aps are not just shuffling bits.)
How about channel to Memory where the cpu get and put most of it's stuff.
Or one bus that serives slow IO and another that is for memory acesses
for multiple cpus at full bandwidth.Anyone thats stuied computer design
and not software engineering would have studied system design and bus
throughput models.
<Sure, but AGP is better than -no- AGP, and it does show that there are othe
<busses available on a PC, yes? (Which was my original point.)
NO! those busses cannot operate in parellel and they operate and the
expense of each other. I'd add if you plug in a slow card the plug and
pray hardware may configure to that slower card at the expense of faster
ones around it.
All said and in the end, we have a troll.
Allison
Received on Sun Oct 24 1999 - 23:10:47 BST