Path: csiph.com!eternal-september.org!feeder.eternal-september.org!nntp.eternal-september.org!.POSTED!not-for-mail From: Lynn Wheeler Newsgroups: comp.os.linux.misc,comp.unix.shell,alt.folklore.computers Subject: Re: [OT] Dead DEC Punch card times (was Re: Taking Speedy too seriously) Date: Sat, 07 Nov 2026 16:04:20 -1000 Organization: Wheeler&Wheeler Lines: 98 Message-ID: <875wy85ba3.fsf@localhost> References: <18dee4b6cab427fa$865$2574533$802601b3@news.usenetexpress.com> <11cdg33$47sq$1@dont-email.me> <11cdp6v$1qa8$3@gal.iecc.com> MIME-Version: 1.0 Content-Type: text/plain Injection-Date: Sun, 08 Nov 2026 02:04:28 +0000 (UTC) Injection-Info: dont-email.me; logging-data="4179762"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX18nQF/DSNgAjLYhkQ81rQEDRvCvbbcTP5k="; posting-host="98d7c4ad43b3a6b29b8871fe584fafd4" User-Agent: Gnus/5.13 (Gnus v5.13) Cancel-Lock: sha1:2GSwL4YQK3+pOSSMIeUCI3u/3kg= sha1:kI/HavjWbQ3rbRmf678+UJD5wpg= sha256:CzpI2io0aE1GCLsORfr0Am84IcRysVOGtv/CQZ/a3QM= sha1:njOrOH1FUlAgMMKKhkrxW17IznU= sha256:dxCMY0lFYgGOpXp4EQ+sVICHrNOoAo6LASrxXF9WDQA= Xref: csiph.com comp.os.linux.misc:95340 comp.unix.shell:27340 alt.folklore.computers:236662 c186282 writes: > The 'mainframe' era is nearly over - to be replaced > by cluster/distributed/AI. > > However IBM is already into all that, WILL make money. > > Many baskets ... How To Survive/Thrive. > > Hmmmm ... do remember when IBM was "typewriters" ... 1988, Nick Donofrio approves HA/6000, originally for NYTimes to move their newspaper system ("ATEX") off DEC VAXCluster to RS/6000 (running project out at Los Gatos lab). I rename it HA/CMP https://en.wikipedia.org/wiki/IBM_High_Availability_Cluster_Multiprocessing when I start doing technical/scientific cluster scale-up with national labs (LANL, LLNL, NCAR, etc) and commercial cluster scale-up with RDBMS vendors (Oracle, Sybase, Ingres, Informix) with VAXCluster support in same source base with UNIX (planning on using Hursley 9333 for mid-range and full FCS for both technical and commercial scaleup). DB2 was still all mainframe source, IBM non-mainframe "DB2" had yet to be developed. IBM S/88 (relogo'ed Stratus) Product Administrator started taking us around to their customers and also had me write a section for the corporate continuous availability strategy document (it gets pulled when both AS400/Rochester and mainframe/POK complain they couldn't meet requirements). Had coined "disaster survivability" and "geographic survivability" (as counter to disaster/recovery) when out marketing HA/CMP. One of the first HA/CMP customer installs was new Indian Reservation Casino in Connecticut, was suppose to have week of testing before opening ... but after 24hrs, they decided to open the doors (based on projected revenue; at the time was largest in the US, still one of the largest in the country) https://en.wikipedia.org/wiki/Foxwoods_Resort_Casino#Debt_default Early Jan92, there was HA/CMP meeting with Oracle CEO and IBM/AWD executive Hester tells Ellison that we would have 16-system clusters by mid92 and 128-system clusters by ye92. Mid-jan92, I update FSD on HA/CMP work with national labs and FSD decides to go with HA/CMP for federal supercomputers. By end of Jan, we are told that cluster scale-up is being transferred to Kingston for announce as IBM Supercomputer (SP, technical/scientific *ONLY*) and we aren't allowed to work with anything that has more than four systems (we leave IBM a few months later). A couple weeks later, 17feb1992, Computerworld news ... IBM establishes laboratory to develop parallel systems (pg8) https://archive.org/details/sim_computerworld_1992-02-17_26_7 Some speculation that HA/CMP would have eaten the mainframe in the commercial market. 1993 industry benchmarks (number of program iterations compared to the industry MIPS/BIPS reference platform): ES/9000-982 : 8CPU 408MIPS, (51MIPS/CPU) RS6000/990 (RIOS chipset) : 1-CPU: 126MIPS Executive we had reported to, goes over to head up Somerset/AIM (Apple, IBM, Motorola) to do single chip 801/RISC (Power/PC) and uses Motorola 88k bus/cache enabling SMP implementations. In the mid-90s, the i86 chip makers then do hardware layer that translates i86 instructions into RISC micro-ops for actual execution, largely negating the performance difference with RISC platforms. 1999 industry benchmarks: IBM PowerPC 440: 1,000MIPS Intel Pentium3 2,054MIPS Dec2000 (IBM mainframe) benchmark: IBM z900 16CPU: 2.5BIPS, 156MIPS/CPU Also 1988, IBM branch office asked if I could help LLNL (national lab) standardize some serial stuff they were working with ... which quickly becomes Fibre Channel Standard ("FCS", including some stuff I had done in 1980; initially planning on using 1gbit transfer, full-duplex, aggregate transfer 200mbytes/sec & 64-port non-blocking switches, with high-end HA/CMP installations). POK mainframe eventually announces its serial stuff (when it is already obsolete) as "ESCON" (initially 10mbytes/sec). Some POK engineers then become involved with FCS and define a heavy weight protocol that radically cuts the native throughput, eventually announced as FICON. Latest public benchmark I've found is 2010 z196 "Peak I/O" getting 2M IOPS using 104 FICON (20K IOPS/FICON). About the same time a native FCS is announced for E5-2600 server blades getting over million IOPS (two such FCS higher throughput than 104 FICON running over FCS). Note IBM docs has SAPs (system assist processors that do actual I/O) CPU be kept to 70% ... or 1.5M IOPS ... also no CKD DASD have been made for decades (just simulated with industry standard fixed-block devices). This "Evolution of the System z Channel" (SHARE 2011 presentation at wayback machine) https://web.archive.org/web/20170829213251/https://share.confex.com/share/117/webprogram/Handout/Session9931/9934pdhj%20v0.pdf talks about after 2010 z196 "Peak I/O" benchmark and "zHPF" that increased throughput from 20K IOPS/FICON to 52K IOPS/FICON then to 92K IOPS/FICON (aka from 1/50th to almost 1/10th the native FCS announced in 2010). -- virtualization experience starting Jan1968, online at home since Mar1970