Between 360 and 370 there was ACS/360 ... that was killed w/o ever being announced (executives thought it might advance state-of-the-art too fast and company might loose control of the market). note discussion that some of the ACS/360 features show up more than 20yrs later with es/9000 https://people.cs.clemson.edu/~mark/acs_end.html
Old discussion about justification for all 370s moving to dynamic address translation. Problem was that MVT storage management was so bad, regions had to be four times larger than normally used (standard 370/165 1mbyte configurations only can practically run four regions). Moving to virtual memory, MVT could increase number regions by four times with little or no paging. http://www.garlic.com/~lynn/2011d.html#73 During Future System program (which was going to be completely different from 370 and going to replace 370) internal politics was killing off 370 efforts; the lack of 370 products during FS period is credited with giving clone processor makers a market foothold. With the death of FS, there was mad rush to get products back into the 370 pipeline. 3033 and 3081 were kicked off in parallel. some detailed references on FS, 3033, and 3081 http://www.jfsowa.com/computer/memo125.htm 303x external channels (channel director) was 158 engine with integrated channel microcode (and no 370 microcode). 3033 started out as 168-3 logic remapped to 20% faster chips. 3032 was 168-3 with new covers and using channel director. 3031 was 158 engine with just 370 microcode (and no integrated channel microcode) and 2nd 158 engine with integrated channel microcode (and no 370 microcode) ... a 3031MP was four 158 engines ... two dedicated for processors and two dedicated for channel directors. The head of POK also managed to convince corporate to kill off vm370 product, shutdown the vm370 development group and transfer all the people to POK (or otherwise they weren't going to be able to ship MVS/XA on time some 7-8yrs later). They weren't going to tell the vm370 until the very last minute to minimize the number of people that might escape. Somehow the information leaked early and number of the people managed to find other employment in the Boston area (joke that head of POK was one of the major contributors to the new DEC VAX/VMS project). Endicott did manage to save the vm370 product mission but had to reconstitute a development from scratch. During this period there was customer comments about VM370 code quality on VMSHARE http://vm.marist.edu/~vmshare There were some of the original VM370 that went to POK that did work on the tool virtual machine facility in support of MVS/XA development that was never intended to be made available to customers. Later when customers weren't migrating to MVS/XA as planned, there was decision to release the tool as the migration aid. As part of the tool, there was SIE (interpretive execution) microcode. SIE was never intended to be production performance, in part because there was insufficent room for the microcode, so it had to be swapped in and out. Old email discussion that for 3090 SIE was designed to be some real production operation (compared to 3081). http://www.garlic.com/~lynn/2006j.html#email810630 http://www.garlic.com/~lynn/2003j.html#email831118 old email about Amdahl's hypervisor, I had done a lot of work on Endicott's ECPS microcode assist and gave presentations on the implementation at monthly user group meetings. http://www.garlic.com/~lynn/94.html#21 Amdahl would talk to me about their hypervisor implementation http://www.garlic.com/~lynn/2006p.html#email801121 a number of yrs later IBM responds to hypervisor with PR/SM for 3090; 3090 announce 12Feb1985 https://www-03.ibm.com/ibm/history/exhibits/mainframe/mainframe_PP3090.html 3090 service processor (3092) was originally to be a 4331 running customized version of vm370 release 6 with all service screens done in CMS IOS3270. The service processor was then enhanced to a pair of redundant 4361s ... which also explains the requirement for pair of 3370 FBA devices (even for MVS customers, which has never supported FBA devices). CKD devices are still being required, even tho no real CKD devices have been made for decades ... simulated on industry standard fixed-block. Other trivia, original sql/relational (System/R) was done in bldg28 on vm370 370/145. The official followon new corporate DBMS was EAGLE. While company was preoccupied with EAGLE, was able to do technology transfer to Endicott for release as SQL/DS. When EAGLE finally implodes, a request is made about how long it would take to port to MVS which is eventually announced as DB2 ... originally for decision support only. Lots of history at the System/R reunion site http://www.mcjones.org/System_R/ initial release 1983 https://en.wikipedia.org/wiki/IBM_DB2 other trivia ... before ms/dos https://en.wikipedia.org/wiki/MS-DOS there was seattle computer https://en.wikipedia.org/wiki/Seattle_Computer_Products before seattle computer there was cp/m, https://en.wikipedia.org/wiki/CP/M before doing cp/m, kildall worked with cp/67 (precursor to vm370) at npg school https://en.wikipedia.org/wiki/Naval_Postgraduate_School -- virtualization experience starting Jan1968, online at home since Mar1970 ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO IBM-MAIN
