Path: csiph.com!weretis.net!feeder9.news.weretis.net!news.quux.org!eternal-september.org!feeder2.eternal-september.org!news.eternal-september.org!.POSTED!not-for-mail From: Lynn Wheeler Newsgroups: alt.folklore.computers Subject: Re: Any interesting PDP/TECO photos out there? Date: Fri, 15 Nov 2024 17:45:58 -1000 Organization: Wheeler&Wheeler Lines: 89 Message-ID: <87r07bx2mh.fsf@localhost> References: <8327c51b-7eb9-08a4-3529-3a76bbd1b4a6@googlemail.com> <6thi0lxi9o.ln2@Telcontar.valinor> <3v4l0lxt7c.ln2@Telcontar.valinor> <878qtkx9ay.fsf@localhost> MIME-Version: 1.0 Content-Type: text/plain Injection-Date: Sat, 16 Nov 2024 04:46:02 +0100 (CET) Injection-Info: dont-email.me; posting-host="953000326951b79b1c2b7b6938103142"; logging-data="4044059"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX18+BDx/VemSGwzUq7rUMvCi1k88L2p4BO8=" User-Agent: Gnus/5.13 (Gnus v5.13) Cancel-Lock: sha1:QBuRIjiWd2AqW+H5HDMWCEFKQek= sha1:HAfoDGJSLWY40KlzwV37aUhqCD8= Xref: csiph.com alt.folklore.computers:228954 Lynn Wheeler writes: > the 360/67 came in within a year of taking intro class and univ. hires > me fulltime responsible of os/360 (tss/360 never came to fruition so ran > as 360/65 with os/360, I continue to get the machine room dedicated for > weekends). Student fortran ran under a second on 709 but initially over > a minute with os/360. I install HASP cutting the time in half. I then > start redoing stage2 sysgen to carefully place datasets and PDS members > to optimize arm seek and multi-track search, cutting another 2/3rds to > 12.9secs. Student fortran never got better than 709 until i install > Univ. of Waterloo WATFOR. whole still at univ, CSC came out to install CP67 (3rd after CSC itself and MIT Lincoln Labs) ... and I mostly played with it during my weekend dedicated time. Initially I spent most of the time rewritting CP67 pathlengths to improve OS/360 running in virtual machine, OS/360 test stream ran 322secs on real machine, but initially 856secs in virtual machine (534secs CP67 CPU). After a couple months I got CP67 CPU down to 113secs (from 534) ... and was asked to attend CP67 "official" announcement at spring '68 SHARE meeting in Houston ... where I gave presentations on both (earlier) OS/360 optimization and (more recent) CP67 optimization work (running OS/360 invirtual machine). I then rewrite I/O, ordered arm seek queuing (in place of FIFO) and multiple 4k page transfers I/O, optimized transfers/revolution for 2314 (disk) and 2301 (drum, from 70-80/sec to 270/sec peak), optimized page replacement, dynamic adaptive resource management and scheduling (for multi-user CMS interactive). CP67 initially had 1052&2741 terminal support with automagic terminal type identification. Univ. had some asciii (mostly tty33 ... but some tty35) ... so added tty/ascii support (including integrated with terminal type identification). I then wanted to have single dail-in phone number for all terminal types ("hunt group"). Didn't quiet work, since IBM telecommunication controller had taken short cut and hard-wired terminal line speed. This kicks off univ clone telecommunication project, building 360 channel interface board for Interdata/3 programmed to simulate IBM controller with the addition of being able to do dynamic line speed. Later it was upgraded with Interdata/4 for channel interface and cluster of Interdata/3s for line(/port) interfaces. was then sold as 360 clone controller by Interdata and later Perkin-Elmer, and four of us get written up for (some part of) IBM clone controller business. https://en.wikipedia.org/wiki/Interdata https://en.wikipedia.org/wiki/Perkin-Elmer#Computer_Systems_Division other ascii info ... originally 360 was suppose to be ascii machine, but ascii unit record was ready yet, so it was "temporary" going to be EBCDIC with old BCD machines. "Biggest Computer Goof Ever": https://web.archive.org/web/20180513184025/http://www.bobbemer.com/P-BIT.HTM other history https://en.wikipedia.org/wiki/Cambridge_Scientific_Center https://en.wikipedia.org/wiki/History_of_CP/CMS above (currently) has confusion about Future System and Gene Amdahl. Amdahl had won the battle to make ACS, 360 compatible ... and then leaves IBM when ACS/360 was killed https://people.computing.clemson.edu/~mark/acs_end.html ... before Future System started. https://en.wikipedia.org/wiki/IBM_Future_Systems_project https://en.wikipedia.org/wiki/History_of_CP/CMS#Historical_notes FS was completely different than 370 and was going to completely replace 370, during FS, 370 projects were being killed off, the lack of new 370 products during the FS period is credited with giving clone 370 makers (including Amdahl) their market foothold. When FS finally implodes there is mad rush to get stuff back into the 370 product pipelines, including quick and dirty 3033&3081 efforts in parallel ... more information http://www.jfsowa.com/computer/memo125.htm A decade ago, I was asked to track down the executive decision to add virtual memory to all 370s and found staff member reporting to the executive. Basically the (OS/360) MVT storage management was so bad that regions typically had to be specified four times later than used ... so that standard 1mbyte 370/165 only ran four regions concurrently, insufficient to keep the system busy and justified. Mapping MVT to 16mbyte virtual memory (VS2/SVS) allowed concurrent regions to be increased by factor of four times (with cap of 15 with 4bit storage protect keys, unique key for each concurrent running region) with little or no paging (sort of like running MVT in a CP67 16mbyte virtual machine). -- virtualization experience starting Jan1968, online at home since Mar1970