Jonno Downes wrote:
Not exactly A2 related, but I suspect many of the denizens of this newsgroup will be familiar with the story of Mel, the original "Real Programmer" and his intimate familiarity of the internals of the RPC-4000 (a fascinating machine from a half century ago that used a rotating metal drum for random access memory).I have been poking around various archives and pieced together a few artifacts - not yet a copy of the specific code in question, but interesting (to me at least) anyway. I've summarized my findings so far at http://www.jamtronix.com/blog/2011/03/25/on-the-trail-of-a-real-programmer/Feedback and more links gratefully accepted here or on that blog post.
FWIW, essentially all drum-based computers had the same latency characteristic. Some of them used "one and a half-address instructions" in which each instruction had an extra address and performed an implicit branch to that address after each instruction. This allowed minimum-latency scheduling to be done by, at first, programmers like Mel, and later, by optimizing assemblers. The IBM 650 was perhaps the best known of these computers. SOAP (Symbolic Optimizing Assembly Programmer) was its corresponding assembler. -michael NadaNet 3.1 for Apple II parallel computing! Home page: http://home.comcast.net/~mjmahon/ "The wastebasket is our most important design tool--and it's seriously underused."