ICM & STCM 
Author Message
 ICM & STCM

Quote:

>    o Changed the action taken by several decimal instructions when an invalid
>decimal sign was detected from instruction termination to instruction suppression

This is an interesting difference between S/360 and S/370.  Many instructions,
not just decimal instructions, were changed from termination to suppression.

This is required for virtual addressing to work, as a non-interruptable
instruction (all S/360 instructions) cannot page-fault when it is partly
executed.  If a page fault occurs, the instruction must be supressed, so
it can be restarted after the page-in is completed.

One important case is TR, where the possible memory reference addresses
cannot be known in advance.  The usual implementation is to do a trial
execution, where operands values are loaded but translated values are
not stored, and then, if successful, start over, but this time store the
results.  The instruction is defined not to reference any addresses in
the translation table that are not necessary for the data being translated.

-- glen



Mon, 22 Jan 2001 03:00:00 GMT  
 ICM & STCM

: 390 added the access register stuff (LAE STAM, LAM, etc.) The
: immediate and relative branch stuff is very recent and only works on
: CMOS machines.

Access Registers were available in ESA/370 architecture; before ESA/390.
--
| Edward E. Jaffe                | Voice:      (310) 338-0400 x318     |
| Mgr., Research & Development   | Facsimile:  (310) 338-0801          |

| 9841 Airport Blvd, Suite 700   | IBM Mail:   USS24J24 at IBMMAIL     |        
| Los Angeles, CA 90045          | Web page:   www.phoenixsoftware.com |



Mon, 22 Jan 2001 03:00:00 GMT  
 ICM & STCM

Quote:

> IIRC, CLCL arrived with MVCL, ICM & STCM in the S/370 instruction set.
> Is this when "compare logical and swap" and "compare double logical and
> swap" also appeared?

The compare and swap instructions came in with the 370 but only on the
model 145 and up.  IMS used compare and swap which meant it had a
minimum machine of a 370/145.  However, it would run with OS as a
virtual machine under VM on a 370/135 because VM simulated the
instructions (this was, of course, after virtual memory was announced on
the 370 for something other than emulators.)

Bob Eltgroth



Mon, 22 Jan 2001 03:00:00 GMT  
 ICM & STCM

Quote:

>It's interesting to note that the first S/370 models did not offer dynamic
>address translation. This feature made its appearance in GA22-7000-2(July
>1972) along with:

The S/370 135 and 145 had dynamic address translation, but it wasn't
enabled by the microcode. Some University of Maine hackers studied the
microcode, patched it to turn on virtual stuff, and then started porting
CP/67. That is cool for 1972-3, eh?

john alvord



Tue, 23 Jan 2001 03:00:00 GMT  
 ICM & STCM
+
+: EDMK and TRT were also 370 instructions not in the 360 instruction set.
+
+Braaaack!!  Wrong answer!!
+I hold in my hand a -5 version of the System/360 Reference Data
+(GX20-1703-5)  --  aka The Green Card.
+EDMK was a 'feature' instruction of the Decimal Feature Instructions.
+TRT was a normal ol' Sys/360 instruction.
+
+Jonesy
+Mainframe (Assembler) since 1966
+
I guess the cobwebs are thicker than I thought...it's been too many
years. Thanks for correcting my error.


Tue, 23 Jan 2001 03:00:00 GMT  
 ICM & STCM

Quote:


> >It's interesting to note that the first S/370 models did not offer dynamic
> >address translation. This feature made its appearance in GA22-7000-2(July
> >1972) along with:
> The S/370 135 and 145 had dynamic address translation, but it wasn't
> enabled by the microcode. Some University of Maine hackers studied the
> microcode, patched it to turn on virtual stuff, and then started porting
> CP/67. That is cool for 1972-3, eh?

Talk about bringing back memories! Yes, that was extremely nifty. It was
the 370/155 & 370/165 models which didn't have VS embedded in the
microcode (the customers who purchased these CPUs were more or less
shafted by the VS announcement - overnight their CPUs weren't worth
squat and IBM had a DAT box available for purchase at a mere $200,000).
I was working on a 370/145 and our FE (a very sharp guy) mentioned right
after IBM announced VS that there were undocumented areas of the
microcode and one time he was shooting some problem which he thought led
into one of these areas. He called the factory and was told that the
problem wasn't there and to look elsewhere, end of story.

Bill {*filter*}



Tue, 23 Jan 2001 03:00:00 GMT  
 ICM & STCM

Quote:



> +After I started this thread about the introduction of ICM & STCM, I came to
> +wondering about when other instructions came into being.  This morning, I was
> +reading a 1987 Principals of Operations manual trying to find the BSM command
> +when I discovered that it wasn't there.  I finally found it.  I had thought
> +that 31 bit addressing was older than 1987, or was I just reading a non-XA
> +manual?
> +
> +   So the question I have is: When (and what) were there major additions to
> the
> +instruction set.
> +   We've already determined that ICM & STCM were new to the 370 (1971) and I
> +assume that MVCL was added at that time.  What other major additions were 370
> +only.

> EDMK and TRT were also 370 instructions not in the 360 instruction set.

EDMK and TRT were in the 360/30 and 360/40 that I used. They are both
listed on my OS/360 green card.

The control registers were added with the 370. Also, the 370 made
standard instructions out of what were optional instructions on the 360.
I believe the 370 came standard with packed decimal and floating point
hardware.

--

Beyond Software, Inc.      http://www.beyond-software.com
"Transforming Legacy Applications"



Tue, 23 Jan 2001 03:00:00 GMT  
 ICM & STCM

Quote:

> : 390 added the access register stuff (LAE STAM, LAM, etc.) The
> : immediate and relative branch stuff is very recent and only works on
> : CMOS machines.

> Access Registers were available in ESA/370 architecture; before ESA/390.
> --
> | Edward E. Jaffe                | Voice:      (310) 338-0400 x318     |
> | Mgr., Research & Development   | Facsimile:  (310) 338-0801          |

> | 9841 Airport Blvd, Suite 700   | IBM Mail:   USS24J24 at IBMMAIL     |  
> | Los Angeles, CA 90045          | Web page:   www.phoenixsoftware.com |

Yes, you're right, they were! So what "significant" features were
added by IBM to change S370 to S390?

--
Robert Ngan
CSC Financial Services Group



Tue, 23 Jan 2001 03:00:00 GMT  
 
 [ 109 post ]  Go to page: [1] [2] [3] [4] [5] [6] [7] [8]

 Relevant Pages 
 

 
Powered by phpBB® Forum Software