Re: Alpha remembrance day

Andrew wrote:

....

The reality was that the top of the Alphaserver range for most of the
90's was only really equivalent to a sun E4500/4000 (12 CPU's, 12GB RAM
redundant I/O).
The discussion (at least before you stuck your incompetent oar into it)
had nothing to do with Alpha vs. Sun or about the '90s: it was about
whether 64-bit support was of any significance before *now* (as you can
still ascertain - assuming that you are capable of extracting meaning
from simple text, though that fact is clearly not yet in evidence) by
returning to the start of this post and perusing the embedded quoted
material there).


Of course it was about Alpha vs the competition.

No, shithead. Just because that's what *you* want to talk about now doesn't make it the subject of the sub-thread which you are attempting to divert: that subject was (and still is) defined by its pre-existing content, as augmented by refutations of your more egregious drivel when that seemed appropriate.

....

You don't need 64bit support to
have a single OS instance that adresses more than 4GB of RAM.
Since I already pointed out Pentium's support for 64 GB of RAM since
1996 (a feature also supported by NT, of course), I'm afraid that one
can't consider the above as anything resembling a new contribution to
this conversation.

http://www.microsoft.com/whdc/system/platform/server/PAE/PAEmem.mspx

Sorry wrong again.

At the risk of being pedantic, to be wrong 'again' I would already have had to have been wrong in the current discussion at least once.

The Pentium may well have supported 64GB of RAM in
1996 but but Windows NT Server 4 never did.

By George, it appears that you may be right for once: I thought that I remembered some trans-4GB facilities (which Win2K later cleaned up as its AWE mechanisms) being introduced in some flavor(s) of NT V4, but I can't find any mention of them right now.

Neither did Windows 2000,

Wrong (again). While Microsoft *nominally* supports only up to 32 GB of RAM in Win2K Datacenter, had you even investigated the link that you yourself provided you would have seen that this was because of the lack of available hardware to test on 64 GB systems, and indeed "Inside Windows 2000" confirms that the Win2K code supports up to the full 64 GB system size.

....

Something
like Oracle consists of multiple processes but these processes need to
access the SGA which is where being able to support more than 4GB of
RAM for a single process becomes usefull.
Or, in the case of NT, instead uses a single process and maps around the
larger-than-4GB physical RAM that it's allowed to manage - an approach
often significantly more efficient than cobbling together multiple
separate processes in the Unix idiom (an idiom even more laughably
expressed in fumbling attempts to compensate for the lack of in-process
support for parallelism in the days before it had any support for
asynchrony or system-level process threading) but still not as efficient
as a 64-bit single-process approach.


This was impossible with NT because NT did not support more than 4GB of
physical memory. Of course 2003 is an NT derivative but it is also
64bit so your point lacks any relevance at all.

How about Win2K, moron? Even if the 32GB limitation that you believed existed were real, 32 GB would be more than enough to make the approach described above relevant.


You also seem to have entirely missed the whole user level and kernel
level threads support which has been inherant in many UNIX's since the
early 1990's.

Hardly, since I referred explicitly to the time before they appeared (a period of about 15 years after VMS had flexible asynchronous facilities for parallelizing operations within a single process). Since it was just a passing reference to a similarly-crippled Unix idiom the precise dates weren't the issue (though dates obviously aren't your strong suit anyway in this discussion, muddling their significance as you've consistently attempted to).

....

In reality Oracle TPC-C platforms hit a wall at about 40-50K TPM where
4GB SGA's became a necessity. The problem was that the 8400 only ever managed about 50% of this. Sequent through the use of OPS in a box demonstrated how with multiple Oracle instances each with its own SGA you could defeat this limit on a 32bit platform.
It is hard not to conclude from your posts that you don't reallly have
a good grasp of the subject
Since you have so far not managed to draw any competent conclusions
during this discussion, I'd hardly expect you to begin now.


So provide some examples of the incompetent conclusions that you claim
I have or havn't drawn.

I've provided them as they occurred, ***. Refresh what passes for your memory if you've managed to forget them already.

...

That 128 GB system, idiot, was a full 6 years ago (not that 64-bit
operation wasn't useful with as little as 8 or 16 GB of RAM, of course,
which takes us back a bit over 10 full years). Whereas the drivel to
which my earlier response was directed (as distinct from your own drivel
to which *this* response is directed) alleged that only *now* was 64-bit
support becoming interesting to customers.
You seem again to have compeletely missed the point.
No, you fucking idiot: the point (which once again you can see quoted
right up at the start of this post) was the ridiculous assertion that
64-bit support was only starting to become interesting *today*.


And your claim unless you had forgotten was that 64bit was interesting
a lot earlier than "today".

A claim which even your own incompetent posts have managed to support more than adequately - thereby raising the question of why the hell you chimed in at all, save that crapping all over other people's backyards seems to be your main purpose in life.

- bill
.