Re: Tagged memory (was Re: Memory Upgrade)

[Douglas Handy <dhandy1@xxxxxxxxxxxxx>]

Randy,

>I think Frank Soltis probably has the last and authoritative word on the 
>subject.

(snip)

>Pointers CANNOT be counterfeited. .... Anyone else who creates a pointer, 
>copies a pointer, or
>modifies a pointer has NO WAY [emphasis added] to turn the tag bits on and
>will end up with a useless 16-byte entity."

I know that is what Dr. Frank claims.  I've read the book too.  But I've also
read Leif's book.  And before you decide that a pointer CANNOT be counterfeited,
and that there is NO WAY to turn the tag bits on, you may want to read chapters
6 & 7 of Leif's book.  And follow his instructions to create a program which
DOES counterfeit a pointer and DOES turn on the tag bit.

Try it on your own system and you'll see.  It *is* possible.  Leif's book isn't
theory.  He provides the code and instructions to back up his assertions.

Leif's book is at http://iseries400.org/ and comes highly recommended.  You can
learn *alot* about the system by reading his book...

Doug