× The internal search function is temporarily non-functional. The current search engine is no longer viable and we are researching alternatives.
As a stop gap measure, we are using Google's custom search engine service.
If you know of an easy to use, open source, search engine ... please contact support@midrange.com.



> 2) the tagged pointer protection is not hardware, but is done in
software, so
> need
> not contribute to make memory more expensive.

With all respect, the tagged pointer protection *is* hardware.
It could in theory be done by software, but it would incur unacceptable
overhead.

There are some other differences in AS/400/iSeries memory chips, compared
to standard PC - it has error-correction circuitry (which is not used on
PCs - they rarely have even parity protection).

    Alexei Pytel,
speaking only for myself.





                    thomas@inorbit.com
                    Sent by:                  To:     midrange-l@midrange.com
                    midrange-l-admin@mi       cc:
                    drange.com                Subject:     Tagged memory (was 
Re: Memory Upgrade)


                    09/26/2001 06:09 PM
                    Please respond to
                    midrange-l





Leif:

I agree it's technically feasible to handle this using conventional memory.
Various forms of 'tag RAM' are used elsewhere for various reasons, even for
Intel processors, I think most commonly for cache memories. There are
always alternatives.

And it might indeed be valid to state the reason as being pure profit for
IBM. That's simply presenting the reason from a non-technical viewpoint,
although I have to say that 'for profit' is the ultimate reason any
business does these things anyway and should be understood without saying.
To answer Dale's question that way would just leave him hanging.

However, I can't totally accept your second point for a couple reasons
which I'd gladly abandon if you can elaborate on what you wrote. First, the
'tagged' memory is a hardware fact; the tag bits physically exist. They
might be manipulated by software, I can't ultimately prove or disprove that
though I don't doubt it nor would I argue that you can't do it; but 'tags
active' is a PPC processor mode and that mode affects instruction execution
related to those bits.

Whether IBM's implementation is expensive due simply to profit motive or to
technical requirement is a separate question that can only be answered by
IBM. I'm sure some chip engineers would argue one way and others would
argue the other way. If nothing else, economies of scale argue that profit
is a determining factor here.

Tom Liotta

On Wed, 26 September 2001, "Leif Svalgaard" wrote:

>
> From: <thomas@inorbit.com>
> On Tue, 25 September 2001, "Draper, Dale" wrote:
> > Why exactly is it that IBM does not use PC standard memory chipsets?
>
> Maybe someone else can say it better but AS/400s need special memory.
Every
> 64 bits of AS/400 memory are accompanied by a special-purpose 65th bit,
the
> 'tag' bit. In short, this extra circuitry provides critical function such
as
> 'tagging' pointers in memory so that they cannot be modified except
through
> approved interfaces. This is a major part of hardware security
enforcement
> and the kind of thing that sets AS/400s apart. Such memory can be used on
> various other PowerPC systems that can run in 'tags inactive' mode, buth
> other memory cannot be used in AS/400s.
>
> ======> Tom, you are overstating the case a bit:
> 1) the tag bit could be stored in a byte, meaning that no special memory
> bandwidth
> is needed.
> 2) the tagged pointer protection is not hardware, but is done in
software, so
> need
> not contribute to make memory more expensive.
>
> As we all know, the reason AS/400 memory is so expensive is simply that
IBM
> charges for it what the market will bear (as per its monopoly position);
> this is called "milking the cow".
>
> _______________________________________________
> This is the Midrange Systems Technical Discussion (MIDRANGE-L) mailing
list
> To post a message email: MIDRANGE-L@midrange.com
> To subscribe, unsubscribe, or change list options,
> visit: http://lists.midrange.com/cgi-bin/listinfo/midrange-l
> or email: MIDRANGE-L-request@midrange.com
> Before posting, please take a moment to review the archives
> at http://archive.midrange.com/midrange-l.

--
Tom Liotta
The PowerTech Group, Inc.
19426 68th Avenue South
Kent, WA 98032
Phone  253-872-7788
Fax  253-872-7904
http://www.400Security.com


___________________________________________________
The ALL NEW CS2000 from CompuServe
 Better!  Faster! More Powerful!
 250 FREE hours! Sign-on Now!
 http://www.compuserve.com/trycsrv/cs2000/webmail/




_______________________________________________
This is the Midrange Systems Technical Discussion (MIDRANGE-L) mailing list
To post a message email: MIDRANGE-L@midrange.com
To subscribe, unsubscribe, or change list options,
visit: http://lists.midrange.com/cgi-bin/listinfo/midrange-l
or email: MIDRANGE-L-request@midrange.com
Before posting, please take a moment to review the archives
at http://archive.midrange.com/midrange-l.







As an Amazon Associate we earn from qualifying purchases.

This thread ...

Follow-Ups:

Follow On AppleNews
Return to Archive home page | Return to MIDRANGE.COM home page

This mailing list archive is Copyright 1997-2024 by midrange.com and David Gibbs as a compilation work. Use of the archive is restricted to research of a business or technical nature. Any other uses are prohibited. Full details are available on our policy page. If you have questions about this, please contact [javascript protected email address].

Operating expenses for this site are earned using the Amazon Associate program and Google Adsense.