[Libre-soc-dev] efficient decoding algorithm for variable-length instructions

Cole Poirier colepoirier at gmail.com
Thu Nov 26 05:13:02 GMT 2020


On Wed, Nov 25, 2020 at 7:41 PM Luke Kenneth Casson Leighton <lkcl at lkcl.net>
wrote:

> On 11/26/20, Cole Poirier <colepoirier at gmail.com> wrote:
>
> no as it'd be in its own VLE-like page, and, with the encoding being
> specifically designed to embed the length *and* mode within the LSBs,
> drastically simplifies the 1st and 2nd phase decoding FSMs.  in fact
> 1st and 2nd stage FSM would reduce to a stateless one (combinatorial).
>

Ah that's key, very helpful. I wasn't sure if we were in the VLE page-like
proposal or not. Hard to keep track with the rapid pace of prototyping.



> however i realised, that, just i put in the intro on the wiki pages,
> the C encoding taking 2 bits is a whopping 48 chunk smashed out of the
> 64 entry (6 bit) space.
>
> [snip]
>
> conclusion: not viable.
>

To confirm. The radical idea of fully remapping all of v3.1B into a RVC
like 16/32/48/64 format dies here?

Cole


More information about the Libre-soc-dev mailing list