[Libre-soc-dev] Compressed instructions

[Alexandre Oliva]

On Nov 21, 2020, Luke Kenneth Casson Leighton <lkcl at lkcl.net> wrote:

> however the effect is a *square* law effect on power reduction that
> cascades through L1 to L2/L3, reduces TLB and MMU thrashing, and more.

... which filesystem compression doesn't help with at all.  gotcha.
thanks for enlightening me!  I'm fully sold on it now.

Shall we call this extension PowerSAVE? :-)

SAVE standing for Short, A??? Variable-length Encoding

> efforts to add transparent L1/L2 cache compression at the hardware
> level are complex enough to have been the subject of entire
> dissertations

*nod*, not going there.  I was talking about software-based compression,
along the lines of jffs, squashfs, and btrfs.


>> marketplace of CPUs.  Is the data that pointed us this way readily
>> available for my perusal, so that I can convince myself by studying it?

> RISC-V RVC and other studies.  if you happen to find them please do
> link them on the C wiki page.

I'm convinced now, so I'm not going to dig further, so the odds of my
going out looking for them are pretty thin.

As for editing the wiki...  It see it's ikiwiki.  Yay, I love it!

I particularly like that I can have a local copy to edit in a proper
editor, rather than in a browser.  But I'd need access (hint, hint ;-)
to the underlying repo for that to work.

-- 
Alexandre Oliva, happy hacker  https://FSFLA.org/blogs/lxo/
   Free Software Activist         GNU Toolchain Engineer
        Vim, Vi, Voltei pro Emacs -- GNUlius Caesar