Article View: bit.listserv.asm370
Article #207Re: SV: Re: Shifting memory to the right
From: glen herrmannsfeldt
Date: Mon, 17 Oct 2005 20:11
Date: Mon, 17 Oct 2005 20:11
51 lines
3826 bytes
3826 bytes
Bill Fairchild <DASDBill2@aol.com> wrote: > In a message dated 10/10/2005 8:42:19 A.M. Central Daylight Time, > roland.johansson@seb.se writes: (someone wrote) >>Old channel connected tape stations could read tapes backwards and moved >> byte after byte to memory. The result was a block with bytes in reversed >> order. You used MVCIN to restore the block. > So can new channel connected tape stations. The read backwards CCW command > code has been supported since day one of S/360. It's in the PrincOps. Any > device which uses linear motion to move from one byte to the next on its > storage media is a candidate for read backwards. > If the device's control unit reference manual describes the command, > then it works for that device type. > Tapes, card readers, magnetic ink character readers, paper tape readers, etc. > The CCW data address points to the last byte of the buffer. > The bytes are read off the storage media by the control unit and > placed one at a time and in successively lower addresses in central > storage by the channel. Did the magnetic ink character readers support it? > This was used a lot in TOS/360 (Tape Operating System) when > reading backwards was often faster than reading forwards. > E.g., if you have to read a load module from a load library > and the tape is positioned somewhere in that library, then > you check the known position with the module name you need to read > in. If the needed module compares high, you use read forward. > If it compares low, you use read backwards. This is much > faster than backing the tape up to > the beginning of the load library and then reading forward. Not so long ago some people were running TOS/360 on the Hercules emulator. It took fixing some bugs in Read Backwards to get it to run. Note also that the P/370 AWSTAPE software doesn't support Read Backwards, even though the file format includes block length trailers. > The MVCIN instruction is also still supported. It is documented in the > z/Architecture PrincOps (SA22-7832-03). I believe it is an optional feature, the Move Inverse feature. I don't know which processor do or do not support it. -- glen
Technical Details
Message-ID:
<43540583.mailx95I16GVLW@seniti.ugcs.caltech.edu>Path:
arc1-ca.pugleaf.net!g2news1.google.com!news3.google.com!border1.nntp.dca.giganews.com!nntp.giganews.com!feed3.newsreader.com!newsreader.com!newsfeed.news2me.com!newsfeed2.easynews.com!newsfeed1.easynews.com!easynews.com!easynews!sn-xit-03!sn-xit-11!sn-xit-05!sn-xit-08!sn-xit-14!supernews.com!149.173.6.116.MISMATCH!foggy!vm.sas.com!ugcs.caltech.edu!gahReferences:
<54.4eb6281e.30855589@aol.com>Show Full Headers
Complete Article Headers
X-Google-Thread: fcdcb,f3744636c040b929
X-Google-Attributes: gidfcdcb,public
X-Google-Language: ENGLISH,ASCII-7-bit
Path: arc1-ca.pugleaf.net!g2news1.google.com!news3.google.com!border1.nntp.dca.giganews.com!nntp.giganews.com!feed3.newsreader.com!newsreader.com!newsfeed.news2me.com!newsfeed2.easynews.com!newsfeed1.easynews.com!easynews.com!easynews!sn-xit-03!sn-xit-11!sn-xit-05!sn-xit-08!sn-xit-14!supernews.com!149.173.6.116.MISMATCH!foggy!vm.sas.com!ugcs.caltech.edu!gah
From: glen herrmannsfeldt <gah@ugcs.caltech.edu>
Newsgroups: bit.listserv.asm370
Subject: Re: SV: Re: Shifting memory to the right
Date: Mon, 17 Oct 2005 13:11:47 -0700
Organization: SAS Inc.
Lines: 51
Sender: IBM Mainframe Assembler List <ASSEMBLER-LIST@LISTSERV.UGA.EDU>
Message-ID: <43540583.mailx95I16GVLW@seniti.ugcs.caltech.edu>
References: <54.4eb6281e.30855589@aol.com>
NNTP-Posting-Host: mozart.unx.sas.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Trace: foggy.unx.sas.com 1129580134 5320 10.19.150.41 (17 Oct 2005 20:15:34 GMT)
X-Complaints-To: usenet@unx.sas.com
NNTP-Posting-Date: Mon, 17 Oct 2005 20:15:34 +0000 (UTC)
Comments: Gated by NETNEWS@VM.SAS.COM
Return-Path: <owner-assembler-list@LISTSERV.UGA.EDU>
User-Agent: nail 9.30 2/20/02
Approved-By: glen herrmannsfeldt <gah@UGCS.CALTECH.EDU>
In-Reply-To: <54.4eb6281e.30855589@aol.com>
Return-Path: owner-assembler-list@LISTSERV.UGA.EDU
X-OriginalArrivalTime: 17 Oct 2005 20:15:32.0133 (UTC)
FILETIME=[86749550:01C5D357]
Originator: daemon@mozart.unx.sas.com