Path: csiph.com!eternal-september.org!feeder3.eternal-september.org!news.eternal-september.org!.POSTED!not-for-mail From: Lynn Wheeler Newsgroups: alt.folklore.computers,comp.os.linux.misc Subject: Re: The joy of FORTRAN Date: Tue, 01 Oct 2024 13:30:58 -1000 Organization: Wheeler&Wheeler Lines: 40 Message-ID: <871q0zv1sd.fsf@localhost> References: <5mqdnZuGq4lgwm_7nZ2dnZfqnPSdnZ2d@earthlink.com> <36KdnVlGJu9VLW77nZ2dnZfqn_qdnZ2d@earthlink.com> <971448126.749088380.092448.peter_flass-yahoo.com@news.eternal-september.org> <59CJO.19674$MoU3.15170@fx36.iad> <3hOdnWpQ649QMGr7nZ2dnZfqnPidnZ2d@earthlink.com> <1smdnSjX3YoxgWf7nZ2dnZfqn_idnZ2d@earthlink.com> <1297730607.749420765.030433.peter_flass-yahoo.com@news.eternal-september.org> <871q0zmxjy.fsf@localhost> MIME-Version: 1.0 Content-Type: text/plain Injection-Date: Wed, 02 Oct 2024 01:31:07 +0200 (CEST) Injection-Info: dont-email.me; posting-host="825bc41c5e4d34394cd4d62590ef5c63"; logging-data="3077149"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX18CKXesCGBjLREc5oe7c67+J+d/SBlxgGs=" User-Agent: Gnus/5.13 (Gnus v5.13) Cancel-Lock: sha1:jrjx5adJd+WbZomt7v1t+2UxTUw= sha1:hzbfB9R2XTyGLGfGpWk+pbixHec= Xref: csiph.com alt.folklore.computers:227380 comp.os.linux.misc:58883 Lynn Wheeler writes: > somewhat like IBM's failed "Future System" effort (replacing all 370s) > http://www.jfsowa.com/computer/memo125.htm > https://people.computing.clemson.edu/~mark/fs.html > https://en.wikipedia.org/wiki/IBM_Future_Systems_project > > except FS was enormous amounts of microcode. i432 gave talk at early 80s > ACM SIGOPS at asilomar ... one of their issues was really complex stuff > in silicon and nearly every fix required new silicon. I continued to work on 360/370 all during FS, even periodically ridiculing what they were doing (which wasn't exactly career enhancing) ... during FS, 370 stuff was being killed off and claims lack of new 370 during FS gave the clone 370 system makers their market foothold. when FS finally imploded (one of the final nails was analysis that if 370/195 applications were redone for FS machine made out of the fastest hardware available, they would have throughput of 370/145 ... about 30times slowdown) there was mad rush to get stuff back into the 370 product pipelines, including kicking off the Q&D 3033&3081 efforts in parallel. I have periodically claimed that John did 801/RISC to go the extreme opposite of Future System (mid-70s there was internal adtech conference where we presented 370 16-cpu multiprocessor and the 801/RISC group presented RISC). I got dragged into helping with a 370 16-cpu multiprocessor and we con the 3033 processor engineers into working on it in their spare time (a lot more interesting than remapping 370/168 logic to 20% faster chips). Everybody thought it was great until somebody tells the head of POK that it could be decades before the POK favorite son operating system ("MVS") had effective 16-cpu support (at the time MVS docs had 2-cpu system support with only 1.2-1.5 times the throughput of a 1-cpu system (I had number of 2-cpu systems that had twice the throughput of single cpu system) and head of POK invites some of us to never visit POK again ... and the 3033 processor engineers to keep their heads down and no distractions. Note: POK doesn't ship a 16-cpu system until after the turn of the century (more than two decades later). -- virtualization experience starting Jan1968, online at home since Mar1970