RE: LQ instruction question -- MI400

Thanks all. This is fascinating stuff.

> -----Original Message-----
> From: pytel@us.ibm.com [SMTP:pytel@us.ibm.com]
> Sent: Friday, December 10, 1999 12:00 PM
> To:   MI400@midrange.com
> Subject:      RE: LQ instruction question
> 
> Every pointer type needs to have all tag bits set to be a valid pointer.
> The last field in LQ instruction is a mask which is compared to pointer
> flag bits and is used to set a bit in a condition register to efficiently
> test for a pointer type.
> LQ instruction can be immediately followed by branch on condition register
> - no separate test instruction is needed.
> My guess (I may be wrong) - 15 is a test for null pointer.
> 
>     Alexei Pytel
> 
> 
> Leif Svalgaard <l.svalgaard@pentasafe.com> on 12/10/99 11:19:03 AM
> 
> Please respond to MI400@midrange.com
> 
> To:   MI400@midrange.com
> cc:
> Subject:  RE: LQ instruction question
> 
> 
> 
> 
> > I think the four bits in that nibble denote an ORed mask of pointer
> types.
> >
> > B'1000' = system pointer
> > B'0100' = instruction pointer
> > B'0010' = space pointer
> > B'0001' = data pointer
> >
> > I think LQ throws an exception if the source pointer is not one of the
> > types in the nibble.
> >
>      [Leif Svalgaard]  I have been thinking a bit (pun intended) more
> about this.
>      Frank Soltis's book says: A pointer in the original S/38 occupied
> four consecutive
>      4-byte words in memory, each with its own tag bit. We decided to
> have the
>      tag bit for every memory word set to 1 if that word contained any of
> the four parts
>      of a pointer. If there was no part of a pointer in the word, the tag
> bit was set
>      to 0. The pointer itself needed only one tag, so we said if all 4
> bits in the
>      consecutive four memory words were set to 1, then the pointer had a
> logical
>      tag of 1. If any of the 4 bits was 0, then the pointer had a logical
> tag of 0.
>      Later implementations of the AS/400 have a 64-bit (8-byte) memory
> word.
>      A 64-bit memory word requires 8 ECC (Error Correction Code) bits; so
> with
>      the tag bit, the AS/400 memories are packaged 73 bits wide. We still
> keep
>      pointers on 16-byte boundaries and each pointer has one logical tag
> bit.
>      For the AS/400 with the 64-bit memory word, the TWO tag bits in the
>      consecutive two words that hold the pointer must both be 1 for the
> pointer
>      to have a logical tag of 1. If either tag bit is 0, then the pointer
> has a logical
>      tag of 0.
> 
>      With all this in mind, how can the LQ instruction know what type of
> pointer
>      it is trying to load? there are only two physical tag bits available
> and they
>      must both be set to have a valid logical tag. Maybe Frank is not
> telling the
>      whole truth or maybe the 4-bit field is part of a design that was
> never actually
>      implemented?
> 
>      I've tried various combinations of the 4 bits, and it doesn't seem
> to matter.
>      ??????
> +---
> | This is the MI Programmers Mailing List!
> | To submit a new message, send your mail to MI400@midrange.com.
> | To subscribe to this list send email to MI400-SUB@midrange.com.
> | To unsubscribe from this list send email to MI400-UNSUB@midrange.com.
> | Questions should be directed to the list owner/operator:
> dr2@cssas400.com
> +---
> 
> 
> 
> +---
> | This is the MI Programmers Mailing List!
> | To submit a new message, send your mail to MI400@midrange.com.
> | To subscribe to this list send email to MI400-SUB@midrange.com.
> | To unsubscribe from this list send email to MI400-UNSUB@midrange.com.
> | Questions should be directed to the list owner/operator:
> dr2@cssas400.com
> +---
+---
| This is the MI Programmers Mailing List!
| To submit a new message, send your mail to MI400@midrange.com.
| To subscribe to this list send email to MI400-SUB@midrange.com.
| To unsubscribe from this list send email to MI400-UNSUB@midrange.com.
| Questions should be directed to the list owner/operator: dr2@cssas400.com
+---