1. 9
  1. 3

    “The main showstopper here might be that Mambo is likely to contain implementations for certain ISA extensions that IBM has never published, such as the tagged memory extensions used by the IBM i operating system. IBM is rather secretive about these extensions and has never published documentation for them. What I would say though, is that these extensions are actually quite minor — and aren’t nearly as secret as IBM thinks. Moreover, much of it is already exposed in patent filings, right down to the instruction encodings”

    There’s a little more data on what we talked about, calvin. So, details are in the patents. Trick is: I can’t look at the patents unless I never want to be involved in making a tagged processor to avoid triple damages.

    Oh well. Guess we’ll have to wait until we run into someone interested in both IBM i architecture and looking at patent filings. Alternatively, one of the CPU designers or IBM i’s lowest-level coders as before. We at least know there’s an easier route now.

    “As I understand it, most proprietary ISA vendors tend to have an internal “golden reference” C++ codebase which they use as a reference description of their ISA”

    Others and I have brought quite a few submissions to Lobsters with tools that automate or semi-automate creating such a spec by running on the real processor. That could help with some of that if they don’t open-source it. Funny enough, those tools usually find errors in both the specs and hardware. It might be more accurate than IBM’s “golden” reference. Maybe.