flyingmonkeys1996 at gmail.com
Mon Apr 22 01:53:01 BST 2019
> Daniel this looks familiar, I can see parallels with what you begun. The
> FSM responds to bits instead of "COMMAND", I can see some things related to
> both L1 and L2.
> The code is heavily integrated with AXI4 Lite, which makes sense in that
> AXI4 divides into control and data channels.
> That it is software configureable (memory-addressable registers) makes it
> quite attractive.
> Basically on AXI4 you specify an area of memory that, if read or written is
> some config registers, and another area on the same channel will be the
> main data area.
> Whether that data area is actually memory, or a cache, or a peripheral, is
> entirely up to you. AXI4 doesn't care! It just responds to reads and
When I was in school I worked a bit with AXI4 for FPGA interconnects.
I will look at the git page this week as I am trying to finish the
assoc cache by the end of the day.
> The only thing with this code, the search algorithm for the L2 TLB is quite
> poor, it is linear, and a FSM.
> I start to see why you asked about the PLRU, it would be possible to use
> the same PLRU module from ariane ptw in the L2 Cache.
The PLRU change is almost there. It is implemented into the
AssocCache. The only issue is the PLRU module does not give an update
on the new PLRU tree after writing which I need for the cache (at
least from what I see). At least the assoc cache is almost there now!
> A software configureable MMU is really attractive, it allows protection of
> IO devices. Been looking for this for a year, this is the first one I have
> Hooray :)
More information about the libre-riscv-dev