🚀 go-pugleaf

RetroBBS NetNews Server

Inspired by RockSolid Light RIP Retro Guy

Article View: alt.folklore.computers
Article #623495

JSF/F-35

#623495
From: Anne Lynn Wheeler
Date: Mon, 14 May 2018 16:46
95 lines
5672 bytes
I've recently been involved in quite a few discussions about
implementation of F-35 ... recent part

more JSF
http://www.ausairpower.net/APA-JSF-Analysis.html

The F-22A system set a record for software complexity in a fighter, with
around 2.5 million lines of software source code cited. The system
departed from the historical use of low speed Mil-Std-1553B busses,
using the high speed Fibre Channel-Avionics Environment (FC-AE) serial
bus for high speed internal interconnects.

...

In comparing overall evolutionary growth potential, the F-22A wins
decisively over the JSF. A plethora of historical case studies of
multirole aircraft indicate that the two decisive drivers of evolution
into alternative roles are size and raw aerodynamic performance. The
F-22A with a larger airframe, wing, internal volume, radar bay, total
engine/electrical power and better stealth design has an unassailable
lead. This is true for a comparison of the basic F-22A vs the basic
JSF. A point of major concern expressed by most analysts is the paucity
of volumetric, power and cooling capacity for growth in the JSF over its
intended life cycle.

...

The recently redesigned CIP 2000 configuration uses up to 66 COTS based
Motorola/IBM PowerPC RISC (ie Apple Mac compatible) and Intel i960MX
processor chips and is aimed at cost reduction and supportability, with
a follow on upgrade planned to further increase computing power. Since
the 'G4' variant, PowerPC chips typically include an embedded 'Altivec'
short vector processor which is exceptionally well suited to signal
processing tasks, as found in radar, comms and EW processing.

... snip ...

https://en.wikipedia.org/wiki/Lockheed_Martin_F-35_Lightning_II#Overview

High speed data networking including IEEE 1394b[33] and Fibre
Channel.[34] (Fibre Channel is also used on Boeing's Super Hornet.[35])

... snip ...

trivia: other claims are 1.7 lines of code for F22 (and possibly 25M for
F35)

total trivia and off-topic: 1988 I was asked to help LLNL standardize
some serial stuff they were playing with that quickly becomes fibre
channel standard ... I had done various things on&off with LLNL going
back to 1979. At the time, I was also in the POWER group ... six chip
and I was working on using fibre channel to tie together large number of
systems ... for both commercial and scientific (planning on 16 system
mid-1992 and 128 system ye-1992 and increasing). The executive we
reported to then goes over to run SOMERSET, the AIM (Apple, IBM,
Motorola) effort to do single chip sub-set of POWER/PC. As chip
technology advances, they manage to put more and more in single chip and
eventually POWER & POWER/PC merge. Some of the problem for Apple is that
IBM wasn't keeping up with (electrical) power use optimization for
power/pc and has switched to Intel processors.

The problem for me was I was also doing commercial RDBMS scaleup for
large number of processors tied together as well as technical scaleup
with the national labs. I had meeting Jan1992 with CEO of Oracle for
"cluster scaleup" and within a few weeks of that meeting, IBM transfers
"cluster scaleup", tells us we can't work on anything with more than
four processors ... and "cluster scaleup" is announced as IBM
supercomputer (for technical and scientific *ONLY*). Within a few months
we leave IBM (problem was that IBM commercial mainframe groups
complained that if I was allowed to go ahead, it would be far superior
to what they were doing).

posts mentioning HA/CMP
http://www.garlic.com/~lynn/subtopic.html#hacmp
some "cluster scaleup" (and other HA/CMP) email from the period
http://www.garlic.com/~lynn/lhwemail.html#medusa

reference to AIM/Somerset
https://en.wikipedia.org/wiki/AIM_alliance
reference JAN1992 meeting with Ellison
http://www.garlic.com/~lynn/95.html#13
Apple moves to Intel
https://en.wikipedia.org/wiki/Apple%27s_transition_to_Intel_processors
Fibre Channel
https://en.wikipedia.org/wiki/Fibre_Channel
past posts mentioning IBM mainframe channel protocol layered on fibre
channel, drastically reducing native throughput
http://www.garlic.com/~lynn/submisc.html#ficon

original POWER chipset
http://www.garlic.com/~lynn/riospw.jpg

-- 
virtualization experience starting Jan1968, online at home since Mar1970
Technical Details
Message-ID: <87in7q423j.fsf@garlic.com>
Path: mbox-mo1.pugleaf.net!j75-v6ni26163wmj.0!nntp.google.com!proxad.net!feeder1-2.proxad.net!feeder.erje.net!1.eu.feeder.erje.net!eternal-september.org!feeder.eternal-september.org!reader02.eternal-september.org!.POSTED!not-for-mail

Show Full Headers
Complete Article Headers
X-Received: by 2002:a1c:8c0c:: with SMTP id o12-v6mr1250976wmd.10.1526316387908;        Mon, 14 May 2018 09:46:27 -0700 (PDT)
X-BeenThere: alt.folklore.computers@googlegroups.com
Received: by 2002:adf:9a85:: with SMTP id a5-v6ls4687651wrc.13.gmail; Mon, 14 May 2018 09:46:27 -0700 (PDT)
X-Received: by 2002:adf:c34d:: with SMTP id e13-v6mr873556wrg.14.1526316387046;        Mon, 14 May 2018 09:46:27 -0700 (PDT)
Path: mbox-mo1.pugleaf.net!j75-v6ni26163wmj.0!nntp.google.com!proxad.net!feeder1-2.proxad.net!feeder.erje.net!1.eu.feeder.erje.net!eternal-september.org!feeder.eternal-september.org!reader02.eternal-september.org!.POSTED!not-for-mail
From: Anne & Lynn Wheeler <ly...@garlic.com>
Newsgroups: alt.folklore.computers
Subject: JSF/F-35
Date: Mon, 14 May 2018 09:46:24 -0700
Organization: Wheeler&Wheeler
Lines: 95
Message-ID: <87in7q423j.fsf@garlic.com>
Mime-Version: 1.0
Injection-Info: reader02.eternal-september.org; posting-host="9878af0224987a0fe7bfc981ce48176c"; logging-data="1380"; mail-complaints-to="ab...@eternal-september.org"; posting-account="U2FsdGVkX18ugWtIWt07JdZ28Msq45vTsCZqmugLYgs="
User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/25.3 (gnu/linux)
Cancel-Lock: sha1:OoUmuWHRw0oA1sKGi010fOsPUx4= sha1:5aQHLP1TzaHzHAIfcJ8K0gkRt+o=
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit