[Libre-soc-bugs] [Bug 238] POWER Compressed Formal Standard writeup

bugzilla-daemon at libre-soc.org bugzilla-daemon at libre-soc.org
Mon Nov 30 20:36:23 GMT 2020


--- Comment #135 from Luke Kenneth Casson Leighton <lkcl at lkcl.net> ---
alexandre, whilst it is beginning of day for you, cole and jacob, i have been
on this issue non-stop for 10 hours straight.

i need a rest so will answer briefly and tersely on key points only, in an
effort to allow you, with some thought (before more words), to understand.

(In reply to Alexandre Oliva from comment #133)

> not when you think of a single insn, but when you think of the multi-issue
> muxer, that's quite dramatic, and that's what my observations and
> suggestions from last night had to do with.

the multi-issue muxer is part of Phase 1 (actually, the connector/router
between 1 and 2) which Jacob, in comment #132 just before you replied here,
successfully implements in an O(log N) algorithm the "indices" that get passed
to the muxer.

without going into full detail right now, which i will probably best do in
video form, tomorrow, after resting, the issue that you highlight is a

the FSM is fine: can i ask you if you could kindly give some thought, after
reviewing jacob's multi-issue decoder in comment #132, "why did he say that?"
and after resting somewhat i will start again tomorrow with some diagrams.

You are receiving this mail because:
You are on the CC list for the bug.

More information about the libre-soc-bugs mailing list