[libre-riscv-dev] pinmux in nmigen
rishucoding at gmail.com
Fri Apr 12 15:19:52 BST 2019
Hendrik, I think you are pointing to CISC vs RISC debate. I guess, one case
is RISC has simpler instructions which makes hw implementation of decoding
easier .. but for a complex x86 instruction: it will break to multiple
simple RISC instructions. So, that means processor pipeline executing one
complex instruction or 3-4 simple instructions to do the same task. Here, I
can't intuitively say which one is better in terms of energy! Please
correct me if I am missing something.
I believe Luke was pointing to carryout the timeline for subtasks which
needs to be completed in 4-5 months.
On Fri 12 Apr, 2019, 7:33 PM Hendrik Boom, <hendrik at topoi.pooq.com> wrote:
> On Fri, Apr 12, 2019 at 01:59:28PM +0100, Luke Kenneth Casson Leighton
> > On Fri, Apr 12, 2019 at 1:51 PM Rishabh Jain <rishucoding at gmail.com>
> > >
> > > one quick question: I checked this link:
> > > https://www.crowdsupply.com/libre-risc-v/m-class while I was reading
> > > post on riscv hw-dev group. It says " With RISC-V being 40% more power
> > > efficient than x86 or ARM...", an eye-opener
> > > for me.
> > it's down to the use of compressed instructions, resulting in a
> > reduction in cache size.
> That makes sense. But I thought RISC effificiency was originally
> attributed to simpler instruction decoding and simpler mapping of
> instructions to sets of actions.
> > > can we put implementation of pinmux in nmigen as a big task for NLnet
> > > foundation proposal?
> > yes, definitely. with small subtasks as well.
> > > we can discuss over breaking into milestons .. and have a rough
> > > for completion?
> > the last time it took... what... four to five months?
> Four to five months to make the timeline? Or to carry it out?
> -- hendrik
> libre-riscv-dev mailing list
> libre-riscv-dev at lists.libre-riscv.org
More information about the libre-riscv-dev