Libre RISC-V Mailing list Archives (accessible via public-inbox)
 help / color / Atom feed
* Re: [libre-riscv-dev] Understanding the LibreSOC core
From: Michael Nolan @ 2020-06-08 21:19 UTC (permalink / raw)
  To: libre-riscv-dev
In-Reply-To: <CAPweEDzwpCAndDnTtgWCex-f7kRWJDquQN=kixjmawwVHxtFBQ@mail.gmail.com>

On 6/8/20 4:38 PM, Luke Kenneth Casson Leighton wrote:
> there's a BIOS??  oink :)
>
> if there's a BIOS, it means that at least some instructions can be
> loaded (into something - probably an on-board SRAM) and executed, and
> that at least means we can test _something_ before getting to that
> stage.
>
> (meaning: the instructions to initialise DDR3 have to execute _from_
> somewhere, they can't be executed from thin air)
>
> btw we were planning to put in a "Board Support Package" NLNet Grant Request.
>
We were going to need to do something like this anyway though, the 
actual SOC will need some low level boot code in rom right? For initial 
testing the 45f has 216kiB of bram, which is plenty for running test 
code and whatnot (granted, we will need some of that ram for other 
purposes).

--Michael


_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] [Bug 370] need a way to co-simulate hardware, qemu, microwatt, simulator, side-by-side
From: bugzilla-daemon @ 2020-06-08 22:03 UTC (permalink / raw)
  To: libre-riscv-dev
In-Reply-To: <bug-370-13@https.bugs.libre-soc.org/>

https://bugs.libre-soc.org/show_bug.cgi?id=370

--- Comment #2 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
(In reply to Michael Nolan from comment #1)
> Cycle accurate - as in checking that the results are the same after every
> step?

cycle-accurate means that yes, you _could_ check that the results are the
same after every step through each and every instruction (not that you
absolutely
have to: it's just that it's possible to do so).

a JIT compiler (pearpc's JIT, qemu JIT) that is very specifically *not*
guaranteed to be the case, because several emulated instructions can end up
being
replaced by one (optimised) sequence of host-native instructions.

JIT-translated code would clearly be absolutely useless for us to attempt to
run and compare against, for that reason.

spike (the RISC-V simulator) went to a lot of trouble to even maintain
cycle-accurate emulation of the PTW, the MMU - pretty much everything,
*specifically* so that the software (BBL, linux kernel etc.) could be worked on
in parallel with development of some hardware, and the specification formalised
even before that.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* Re: [libre-riscv-dev] daily kan-ban update 08jun2020
From: Luke Kenneth Casson Leighton @ 2020-06-08 22:13 UTC (permalink / raw)
  To: Libre-RISCV General Development
In-Reply-To: <E0FB3D82-BADB-4C2D-B179-FA45B5FD90D0@getmailspring.com>

On Mon, Jun 8, 2020 at 10:17 PM Cole Poirier <colepoirier@gmail.com> wrote:

> I'll try to put just a few very specific questions (such as the
> advantages/high level summary of Simple-V) for you and other technical
> project members to answer. I would try answer this myself given your
> present state, but unfortunately I don't think I can understand and
> explain something like Simple-V on my own in a day.

yyeah.  last time i explained it to someone (in detail) it was to
Alain.  it took six hours.

the summary: rather than have dozens of instructions ADD x1, x10 ADD
x2, x11 ADD x3, x12, instead you deploy SimpleV - with *one*
instruction - telling it (by setting VL) exactly how many registers,
in sequence, you would like that *ONE* instruction to push into the
instruction queue.

that's basically all there is to it.  it should be pretty obvious
therefore that it is effectively a very simple version of an
instruction "compression algorithm".

in effect, Simple-V is a hardware-level for-loop.  if you have heard
of Zero-Overhead Loops, it is a bit like that.  except, whilst ZOHLs
loop around a *group* of instructions, Simple-V gives the option to
apply the for-loop to *ANY* instruction, and does so *on* that
instruction *before* moving on to the next one.

it's like a Sub- Program Counter, in effect.


> Can I ask you to see if you're able to answer some of these questions
> today, if your illness permits?

it's fine, now: i took... i won't go into the medical details, there's
a procedure i follow which clears out toxins and it was effective.
also, a drink made from large quantities of ginger root, cardamons,
black pepper and chilis, caused me to cough and splutter and generally
hawk and spit profusely (as might be expected), and surpriise! i'm
feeling much better.

l.

_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* Re: [libre-riscv-dev] Understanding the LibreSOC core
From: Luke Kenneth Casson Leighton @ 2020-06-08 22:17 UTC (permalink / raw)
  To: Libre-RISCV General Development
In-Reply-To: <2731f72d-5638-b594-9de4-1f0db635da44@gmail.com>

On Mon, Jun 8, 2020 at 10:19 PM Michael Nolan <mtnolan2640@gmail.com> wrote:
>
> On 6/8/20 4:38 PM, Luke Kenneth Casson Leighton wrote:
> > there's a BIOS??  oink :)
> >
> > if there's a BIOS, it means that at least some instructions can be
> > loaded (into something - probably an on-board SRAM) and executed, and
> > that at least means we can test _something_ before getting to that
> > stage.
> >
> > (meaning: the instructions to initialise DDR3 have to execute _from_
> > somewhere, they can't be executed from thin air)
> >
> > btw we were planning to put in a "Board Support Package" NLNet Grant Request.
> >
> We were going to need to do something like this anyway though, the
> actual SOC will need some low level boot code in rom right?

the original bugreport is basically for the hardware only
https://bugs.libre-soc.org/show_bug.cgi?id=22

as that milestone has been set and approved, if anyone does write any
low-level boot code, it can't come from that budget.  this is just how
it works.

> For initial
> testing the 45f has 216kiB of bram, which is plenty for running test
> code and whatnot

oh good.

> (granted, we will need some of that ram for other
> purposes).

L1 caches.  regfiles.

_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* Re: [libre-riscv-dev] Understanding the LibreSOC core
From: Luke Kenneth Casson Leighton @ 2020-06-08 22:18 UTC (permalink / raw)
  To: Libre-RISCV General Development
In-Reply-To: <CAPweEDwLmSCi4LQ5ksaa9CyaMaXUQ7r7D6bu=3WYwzpT8CqCCQ@mail.gmail.com>

On Mon, Jun 8, 2020 at 11:17 PM Luke Kenneth Casson Leighton
<lkcl@lkcl.net> wrote:

> as that milestone has been set and approved, if anyone does write any
> low-level boot code, it can't come from that budget.  this is just how
> it works.

i could say "annoyingly", however i'm extremely grateful that NLNet
has provided some funding *at all*.

l.

_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* Re: [libre-riscv-dev] daily kan-ban update 08jun2020
From: Cole Poirier @ 2020-06-08 22:29 UTC (permalink / raw)
  To: Libre-RISCV General Development
In-Reply-To: <CAPweEDw1B0+9E7+Z8haPKQ7ejk1eV-m8dRdxG8dFi3p_GLKCpw@mail.gmail.com>


> On Jun 8, 2020, at 3:13 PM, Luke Kenneth Casson Leighton <lkcl@lkcl.net> wrote:

> yyeah.  last time i explained it to someone (in detail) it was to
> Alain.  it took six hours.
> 
> the summary: rather than have dozens of instructions ADD x1, x10 ADD
> x2, x11 ADD x3, x12, instead you deploy SimpleV - with *one*
> instruction - telling it (by setting VL) exactly how many registers,
> in sequence, you would like that *ONE* instruction to push into the
> instruction queue.
> 
> that's basically all there is to it.  it should be pretty obvious
> therefore that it is effectively a very simple version of an
> instruction "compression algorithm".
> 
> in effect, Simple-V is a hardware-level for-loop.  if you have heard
> of Zero-Overhead Loops, it is a bit like that.  except, whilst ZOHLs
> loop around a *group* of instructions, Simple-V gives the option to
> apply the for-loop to *ANY* instruction, and does so *on* that
> instruction *before* moving on to the next one.
> 
> it's like a Sub- Program Counter, in effect

Aha that makes sense! I’ll integrate this into the rest of the insights from the list earlier today.

> 
>> Can I ask you to see if you're able to answer some of these questions
>> today, if your illness permits?
> 
> it's fine, now: i took... i won't go into the medical details, there's
> a procedure i follow which clears out toxins and it was effective.
> also, a drink made from large quantities of ginger root, cardamons,
> black pepper and chilis, caused me to cough and splutter and generally
> hawk and spit profusely (as might be expected), and surpriise! i'm
> feeling much better.
> 
> l.

I’m glad to hear you’re feeling better! However you’ve figured out how to make it happen. Thanks Luke, I’ll hopefully have something for you in about an hour.

Cole
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] [Bug 325] create POWER9 TRAP pipeline
From: bugzilla-daemon @ 2020-06-08 22:51 UTC (permalink / raw)
  To: libre-riscv-dev
In-Reply-To: <bug-325-13@https.bugs.libre-soc.org/>

https://bugs.libre-soc.org/show_bug.cgi?id=325

--- Comment #89 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
ok so i added two new signals to Decode2Execute1Type, called
traptype and trapaddr.  the idea is that rather than get main_stage.py
to *hard-code* what type of trap it is, and *hard-code* the address to
jump to, the *decoder* says what the trap type is, and where to jump to.

in this way we can detect interrupts, privileged instructions, and so on,
in the *decoder*.

unfortunately... this means that the decoder needs access to MSR.  whoops.
this is slightly unfortunate, because up until now, PowerDecoder2 needed
absolutely nothing - no information *at all* - about the "state".  didn't
need the PC, didn't need anything.


+        with m.If(op.internal_op == InternalOp.OP_TRAP):
+            comb += e.traptype.eq(TT_TRAP) # request trap interrupt
+            comb += e.trapaddr.eq(0x70)    # addr=0x700 (strip first nibble)
+
+        return m

+        # privileged instruction
+        with m.If(instr_is_privileged(m, op.internal_op, e.insn) &
+                  msr[MSR_PR]):
+            # privileged instruction trap
+            comb += op.internal_op.eq(InternalOp.OP_TRAP)
+            comb += e.traptype.eq(TT_PRIV) # request privileged instruction
+            comb += e.trapaddr.eq(0x70)    # addr=0x700 (strip first nibble)

-- 
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* Re: [libre-riscv-dev]  Request for input and technical expertise for Systèmes Libres Amazon Alexa IOT Pitch 10-JUN-2020
From: Cole Poirier @ 2020-06-09  1:17 UTC (permalink / raw)
  To: Libre-RISCV General Development
In-Reply-To: <CAPweEDw5_fU-y3rewKuL+A0C5seEFXy4MVVy2bryrZfBh24vqQ@mail.gmail.com>

Thank you Staf, Lauri, Hendrick, Jacob, and Luke, your provided
insights, criticisms, and questions have allowed me to make a much
more informative script for Wednesday's pitch. I'm still working on
the revised script, however I now have a work-in-progress polished
version of the presentation to show. There's a 1 min recorded video of
the presentation available on youtube (unlisted) here
(https://www.youtube.com/watch?v=0alD47XlsbM) if you'd like to take a
look. Unfortunately youtube has lowered the quality. Also the
script/text on the slides in the video is out of date and will be
updated tomorrow.

Thank you all, again, your help has been incredibly valuable,

Cole


On Mon, Jun 8, 2020 at 8:28 AM Luke Kenneth Casson Leighton
<lkcl@lkcl.net> wrote:
>
> (btw thank you staf for the insights)
>
> On Mon, Jun 8, 2020 at 2:56 PM Hendrik Boom <hendrik@topoi.pooq.com> wrote:
> >
> > On Mon, Jun 08, 2020 at 12:13:48PM +0100, Luke Kenneth Casson Leighton wrote:
> > >
> > > all of these things are at the architectural level.  we are not doing
> > > anything fancy at the gate level.  it is a matter of making
> > > *architectural* decisions that reduce power consumption, operating
> > > within the exact same gate-level power consumption constraints as
> > > every other ASIC out there.
> >
> > You point out that the CPU and GPU share cache, being the same processor.
>
> yes.  or: the CPU instructions and GPU instructions, by being in the
> same ISA, the GPU *workload* will push CPU workload(s) out of the
> (same) L1 Cache.
>
> >
> > But we are designing a four-core chip?
>
> yes.  therefore there will be 1x L1 Data and 1x L1 Instruction Cache
> per each of those four cores.
>
> >  To what extent to the four cores share cache?
>
> L1?  not at all - ever.
>
> > And on avoiding data copying between CPU ad GPU:
> >
> > I believe the OpenGL API involves copying data from CPU buffers to GPU
> > buffers, with the understanding that the CPU copies can be discarded
> > while the GPU goes on with its copy.
>
> ... because the assumption is that the GPU is a completely and utterly
> separate processor, the "command" to perform that copy is expected to
> involve the excruciatingly-painful process previously mentioned, from
> which i excluded the userspace-kernelspace context-switching so as not
> to have people run away screaming in terror.
>
> in our case: it would simply be... a memcpy.
>
> > Having the same storage for both sets of buffers could obviously obviate
> > these copies, except that software that uses this API will likely rely
> > on being able to overwrite the CPU-side buffers with impunity.  So the
> > copy will still have to be done.
>
> sounds reasonable to me.  actually now that i think about it, if the
> buffer is placed into a shmem segment with copy-on-write semantics,
> the memcpy will not be needed, and the "overwriting", because of the
> CoW semantics, would only be done on-demand.
>
> this however would be an optimisation.
>
> the *only reason* that we can even remotely consider such an
> optimisation is precisely because of the hybrid architecture.
>
> > Do I misunderstand OpenGL?  Is Vulcan different?
>
> don't know.
>
> > Will users want to bypass these libraries and use the graphics instructios directly?
>
> only if they want to become an assembly-level expert, with all the
> inherent implications and performance-complexity tradeoffs that always
> come with doing assembly programming.
>
> > Or is there some other sublety I'm missing?
>
> no idea :)
>
> l.
>
> _______________________________________________
> libre-riscv-dev mailing list
> libre-riscv-dev@lists.libre-riscv.org
> http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* Re: [libre-riscv-dev]  Request for input and technical expertise for Systèmes Libres Amazon Alexa IOT Pitch 10-JUN-2020
From: Luke Kenneth Casson Leighton @ 2020-06-09 10:34 UTC (permalink / raw)
  To: Libre-RISCV General Development
In-Reply-To: <CAEg7hun9a8OZz3YOE+VxLr=mmzHeasO1mypntVd6zYm4x1sH9A@mail.gmail.com>

On Tue, Jun 9, 2020 at 2:17 AM Cole Poirier <colepoirier@gmail.com> wrote:

> version of the presentation to show. There's a 1 min recorded video of
> the presentation available on youtube (unlisted) here
> (https://www.youtube.com/watch?v=0alD47XlsbM) if you'd like to take a
> look.

0:49 - billions of cryptocurrency is lost if the hardware wallet
cryptochip cannot be trusted.

that's the "fear" version.  do we want to present a "fear" strategy?
(you know what i mean)

rework:

0:49 - cryptocurrency hardware wallets and banking identification
terminals containing cryptochips can be trusted if the hardware is
formally verified and the entire HDL available for a full independent
audit.

_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] [Bug 336] ALU CompUnit needs to recognise that RA (src1) can be zero
From: bugzilla-daemon @ 2020-06-09 12:36 UTC (permalink / raw)
  To: libre-riscv-dev
In-Reply-To: <bug-336-13@https.bugs.libre-soc.org/>

https://bugs.libre-soc.org/show_bug.cgi?id=336

--- Comment #57 from Cesar Strauss <cestrauss@gmail.com> ---
(In reply to Luke Kenneth Casson Leighton from comment #56)
> (In reply to Cesar Strauss from comment #55)
> > (In reply to Luke Kenneth Casson Leighton from comment #54)
> > > hmmm i tried putting OP_NOP in there, and both compunit1 and parallel
> > > locked up.  this tends to indicate a combinatorial loop.  any clues?
> > 
> > I see. I'm looking into it.
> 
> it may be because "now" is set at the default action.  i have yet to work
> out how to detect combinatorial loops.  there may be something that can be
> done using yosys synth, michael showed me something a couple weeks ago.  ltp
> command?

Found it manually, staring from valid_o, and changing comb to sync along the
way. Interesting debug experience.

I don't really recall being much afflicted by this sort of issue. But then, I
normally try to avoid using latches as much as possible, this may be the
reason.

commit c8c13adf3da9a6ca8b7765edc597ec7fdf19e8d8
Author: Cesar Strauss <cestrauss@gmail.com>
Date:   Tue Jun 9 08:57:31 2020 -0300

    Avoid a combinatorial loop on valid_o

    The path was:

    all_rd (1) -> all_rd_pulse (1) -> alui_l.s (1) ->
    -> alu.p.valid_i (1) -> ALU (zero-delay) -> alu.n.valid_o (1) ->
    -> rok_l.r (1) -> all_rd (0)

    Decided to break the loop on the reset of the read-done, write proceed
    latch (rok_l.r), with no ill effects on performance.

    Added a test case for this, using the zero-delay ALU (OP_NOP).

-- 
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] [Bug 336] ALU CompUnit needs to recognise that RA (src1) can be zero
From: bugzilla-daemon @ 2020-06-09 12:43 UTC (permalink / raw)
  To: libre-riscv-dev
In-Reply-To: <bug-336-13@https.bugs.libre-soc.org/>

https://bugs.libre-soc.org/show_bug.cgi?id=336

--- Comment #58 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
(In reply to Cesar Strauss from comment #57)
> (In reply to Luke Kenneth Casson Leighton from comment #56)
> > it may be because "now" is set at the default action.  i have yet to work
> > out how to detect combinatorial loops.  there may be something that can be
> > done using yosys synth, michael showed me something a couple weeks ago.  ltp
> > command?
> 
> Found it manually, staring from valid_o, and changing comb to sync along the
> way. Interesting debug experience.

i've done that before :)

> I don't really recall being much afflicted by this sort of issue. But then,
> I normally try to avoid using latches as much as possible, this may be the
> reason.

yyeah they're not a "normal" way to do FSMs.  however with some aspects being
combinatorial and some being sync, we can't use "standard" techniques.

nicely done.  test_core.py still works, which is important.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] [Bug 371] New: code removed by commit 12297566322355ce5fed2e2a5460bea54f69e79e
From: bugzilla-daemon @ 2020-06-09 12:48 UTC (permalink / raw)
  To: libre-riscv-dev

https://bugs.libre-soc.org/show_bug.cgi?id=371

            Bug ID: 371
           Summary: code removed by commit
                    12297566322355ce5fed2e2a5460bea54f69e79e
           Product: Libre-SOC's first SoC
           Version: unspecified
          Hardware: PC
                OS: Mac OS
            Status: CONFIRMED
          Severity: enhancement
          Priority: ---
         Component: Source Code
          Assignee: lkcl@lkcl.net
          Reporter: lkcl@lkcl.net
                CC: libre-riscv-dev@lists.libre-riscv.org
   NLnet milestone: ---

tobias, hi, you removed some code by not doing a git merge, properly,
overwriting work that i'm doing.  can you please put it back?
thanks.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] [Bug 371] code removed by commit 12297566322355ce5fed2e2a5460bea54f69e79e
From: bugzilla-daemon @ 2020-06-09 12:49 UTC (permalink / raw)
  To: libre-riscv-dev
In-Reply-To: <bug-371-13@https.bugs.libre-soc.org/>

https://bugs.libre-soc.org/show_bug.cgi?id=371

Luke Kenneth Casson Leighton <lkcl@lkcl.net> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Assignee|lkcl@lkcl.net               |libre-soc@platen-software.d
                   |                            |e

--- Comment #1 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
commit 12297566322355ce5fed2e2a5460bea54f69e79e
Author: Tobias Platen <tplaten@posteo.de>
Date:   Tue Jun 9 14:00:50 2020 +0200

    fixes for DualPortSplitter

@@ -307,19 +308,11 @@ class L0CacheBuffer(Elaboratable):
     def __init__(self, n_units, mem, regwid=64, addrwid=48):
         self.n_units = n_units
         self.mem = mem
-        self.regwid = regwid
-        self.addrwid = addrwid
         ul = []
         for i in range(n_units):
             ul.append(LDSTPort(i, regwid, addrwid))
         self.dports = Array(ul)

-    def truncaddr(self, addr):
-        """truncates the address to the top bits of the memory granularity
-        """
-        nbits = log2_int(self.mem.regwid)
-        return addr[nbits:]
-
     def elaborate(self, plat

-- 
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] [Bug 371] code removed by commit 12297566322355ce5fed2e2a5460bea54f69e79e
From: bugzilla-daemon @ 2020-06-09 13:06 UTC (permalink / raw)
  To: libre-riscv-dev
In-Reply-To: <bug-371-13@https.bugs.libre-soc.org/>

https://bugs.libre-soc.org/show_bug.cgi?id=371

--- Comment #2 from Tobias Platen <libre-soc@platen-software.de> ---
done

-- 
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] [Bug 371] code removed by commit 12297566322355ce5fed2e2a5460bea54f69e79e
From: bugzilla-daemon @ 2020-06-09 13:07 UTC (permalink / raw)
  To: libre-riscv-dev
In-Reply-To: <bug-371-13@https.bugs.libre-soc.org/>

https://bugs.libre-soc.org/show_bug.cgi?id=371

--- Comment #3 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
the procedure that should be used is:

* edit and save
* git diff (to check and review the current status of work in progress)
* git commit
* git pull
* git push
* *RELOAD* all editor windows (or use an editor that auto-detects)

the process that you used, we may deduce that it was:

* edit and save
* git pull
* re-save local file WITHOUT CHECKING
* git commit
* git push

can you please:

1) adjust working practices to the first process
2) restore the erased code
3) close this bugreport when done

thanks.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] [Bug 371] code removed by commit 12297566322355ce5fed2e2a5460bea54f69e79e
From: bugzilla-daemon @ 2020-06-09 13:08 UTC (permalink / raw)
  To: libre-riscv-dev
In-Reply-To: <bug-371-13@https.bugs.libre-soc.org/>

https://bugs.libre-soc.org/show_bug.cgi?id=371

Luke Kenneth Casson Leighton <lkcl@lkcl.net> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|CONFIRMED                   |RESOLVED
         Resolution|---                         |FIXED

--- Comment #4 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
(In reply to Tobias Platen from comment #2)
> done

excellent, thank you.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] daily kan-ban update 09jun2020
From: Luke Kenneth Casson Leighton @ 2020-06-09 13:11 UTC (permalink / raw)
  To: Libre-RISCV General Development

yesterday:

* reviewed slide deck
* did some minor "no-brain" code-morphs
* a bit on TRAP including adding a privilege testing function

today:

* a bit more on OP_TRAP
* augmented LenExpand to be byte-capable (for shift/mask in LD/ST)

rest of today:

* looking to do proper byte shift/mask in L0CacheBuffer.

---
crowd-funded eco-conscious hardware: https://www.crowdsupply.com/eoma68

_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] [Bug 371] code removed by commit 12297566322355ce5fed2e2a5460bea54f69e79e
From: bugzilla-daemon @ 2020-06-09 13:17 UTC (permalink / raw)
  To: libre-riscv-dev
In-Reply-To: <bug-371-13@https.bugs.libre-soc.org/>

https://bugs.libre-soc.org/show_bug.cgi?id=371

--- Comment #5 from Tobias Platen <libre-soc@platen-software.de> ---
I changed my editor settings to that it that auto-detects when a file was
changed by an external program.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* Re: [libre-riscv-dev] daily kan-ban update 09jun2020
From: Tobias Platen @ 2020-06-09 13:23 UTC (permalink / raw)
  To: libre-riscv-dev
In-Reply-To: <CAPweEDyugeW9YALUA3gXEvLdMVDStt62ODw4wcJfuK5icMZ+3A@mail.gmail.com>

yesterday:

not much, reading some of the code only

today:

ld/st splitter and port interface
 

_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* Re: [libre-riscv-dev] daily kan-ban update 09jun2020
From: Luke Kenneth Casson Leighton @ 2020-06-09 16:20 UTC (permalink / raw)
  To: Libre-RISCV General Development
In-Reply-To: <20200609152307.f83c703da2bc996013891b8d@platen-software.de>

On Tue, Jun 9, 2020 at 2:23 PM Tobias Platen
<libre-soc@platen-software.de> wrote:
>
> yesterday:
>
> not much, reading some of the code only
>
> today:
>
> ld/st splitter and port interface

we're going to need this, it's coming up on the critical path, because
it's the way that mis-alignment will be taken care of.

i've just added that extra argument to LenSplitter which allows it to
create a *byte* mask, where LDSTSplitter rather hilariously deals only
with bits.

l.

_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] [Bug 365] ROCM/Libre-SOC GPU Opcode interoperability
From: bugzilla-daemon @ 2020-06-09 17:04 UTC (permalink / raw)
  To: libre-riscv-dev
In-Reply-To: <bug-365-13@https.bugs.libre-soc.org/>

https://bugs.libre-soc.org/show_bug.cgi?id=365

--- Comment #13 from Jacob Lifshay <programmerjake@gmail.com> ---
(In reply to Luke Kenneth Casson Leighton from comment #12)
> (In reply to Yehowshua from comment #11)
> > (In reply to Jacob Lifshay from comment #7)
> > > From what I understand, ROCm is only for OpenCL/CUDA-style compute, it
> > > doesn't implement the Vulkan or OpenGL APIs:
> > > https://github.com/RadeonOpenCompute/ROCm/issues/706
> > > https://github.com/RadeonOpenCompute/ROCm/issues/131
> > 
> > Hi Jacob, you are correct - however - Mesa has a Vulkan implementation that
> > can sit on top of ROCM.

If your talking about RADV, it does not require ROCM, it doesn't even require
LLVM (though may require some refactoring to build without LLVM), since it
works with two different compiler backends: ACO and LLVM.

AMDVLK also doesn't require ROCM, though does require LLVM.

> 
> from 706:
> 
> "ROCm is AMD's compute stack. If you want Vulkan support, you have two
> options. 1) the Mesa community RADV driver or 2) AMD's AMDVLK driver (which
> should be also part of their AMDGPU-PRO driver)."
> 
> my interpretation of that is that he hasn't explicitly said "no" (which is
> where the confusion comes about), he's said, "if you want vulkan, you need
> RADV or AMDVLK" from which we *deduce* that there is no connection between
> the two.
> 
> now, given that AMDGPU llvm support is now upstream, it *might* be the case
> that two out of three of these projects *happen* to use the exact same
> AMDGPU llvm compiler support.

All of RADV, AMDVLK, RadeonSI (Mesa Gallium driver), and ROCM can use LLVM as
their compiler backend.

> 
> my understanding of AMDVLK - jacob will be able to clarify - is that it's
> a radically different approach, basically a sort-of effort to port and
> libre-license what was formerly a proprietary Win32 driver to linux, where
> the team working on it were isolated from what went into the upstream
> AMDGPU llvm.

From what I understand, AMDVLK was/is the shared codebase between AMD's
proprietary Windows Vulkan driver and their open-source Linux Vulkan driver. On
Windows and previously on Linux, it uses their proprietary shader compiler
stack, which they have not open-sourced. AMDVLK was refactored to be able to
use LLVM before their initial Linux open-source release.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* [libre-riscv-dev] wishbone does not have byte-enable (but it does have user-tags)
From: Luke Kenneth Casson Leighton @ 2020-06-09 17:10 UTC (permalink / raw)
  To: Libre-RISCV General Development

http://cdn.opencores.org/downloads/wbspec_b4.pdf

one of the things that i have assumed is possible to do in wishbone is
to have a bank of byte-enable lines for the memory read/write
requests.  am i correct in thinking that this is what "sel" (as an
array) is for?

https://git.libre-soc.org/?p=soc.git;a=blob;f=src/soc/minerva/wishbone.py;hb=HEAD#l16

also i've noticed that there is the concept of user and cycle "tags"
which can be optionally added.  this would give us a way to do
cache-line tagging and many other things.

l.

_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* Re: [libre-riscv-dev] daily kan-ban update 09jun2020
From: Jacob Lifshay @ 2020-06-09 17:21 UTC (permalink / raw)
  To: Libre-RISCV General Development
In-Reply-To: <CAPweEDyugeW9YALUA3gXEvLdMVDStt62ODw4wcJfuK5icMZ+3A@mail.gmail.com>

yesterday:
not much

today:
working on mul and div units -- they will most likely increase the core's
gate count by a large amount, particularly the div pipeline, since it's
designed for high performance, not as much for low area.

Also, I saw the new *inter-core* speculative execution vulnerability in
Intel processors, the previous ones were mostly intra-core.

Jacob
_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* Re: [libre-riscv-dev] daily kan-ban update 09jun2020
From: Luke Kenneth Casson Leighton @ 2020-06-09 17:44 UTC (permalink / raw)
  To: Libre-RISCV General Development
In-Reply-To: <CAC2bXD6Ct+RW_=p-J-M_0PdNtFA9XFS-OTFGim4WPCNr5WosAQ@mail.gmail.com>

On Tue, Jun 9, 2020 at 6:21 PM Jacob Lifshay <programmerjake@gmail.com> wrote:

> yesterday:
> not much

:) rest is good

> today:
> working on mul and div units -- they will most likely increase the core's
> gate count by a large amount, particularly the div pipeline, since it's
> designed for high performance, not as much for low area.

hm hm well as long as it is below 45k LUTs we should be good.  last
resort there is always the microwatt div algorithm, which i noticed in
its FSM has the option to skip large batches of zeros (8 at a time).
personally i hope it fits, hmm it should be easy to check, with
synth_ecp5
this is for test_div_pipe_core_bit_width_8_fract_width_4_radix_2.il

=== top ===

   Number of cells:               3411
     CCU2C                         461
     L6MUX21                       116
     LUT4                         1777
     PFUMX                         539
     TRELLIS_FF                    518

that's a very small one, though, isn't it?  bit-width of 8?

> Also, I saw the new *inter-core* speculative execution vulnerability in
> Intel processors, the previous ones were mostly intra-core.

oh no!  i don't know whether to laugh, start to feel sorry for them,
or look it up and make sure we don't make the same mistake.  probably
all of those :)

l.

_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

* Re: [libre-riscv-dev] Request for input and technical expertise for Systèmes Libres Amazon Alexa IOT Pitch 10-JUN-2020
From: Cole Poirier @ 2020-06-09 19:01 UTC (permalink / raw)
  To: Libre-RISCV General Development; +Cc: Libre-RISCV General Development
In-Reply-To: <CAPweEDyws116d9oKzSPhx6MpH-8C-ncfd+uPH6D6hgVG7+63Cg@mail.gmail.com>

On Jun 9 2020, at 3:34 am, Luke Kenneth Casson Leighton <lkcl@lkcl.net> wrote:
> 0:49 - billions of cryptocurrency is lost if the hardware wallet
> cryptochip cannot be trusted.
> 
> that's the "fear" version.  do we want to present a "fear" strategy?
> (you know what i mean)
> 
> rework:
> 
> 0:49 - cryptocurrency hardware wallets and banking identification
> terminals containing cryptochips can be trusted if the hardware is
> formally verified and the entire HDL available for a full independent
> audit.

Thanks, I like that formulation much better. I'll make these edits on
the wiki page, and send a link with the updated video later today. Or
Yehowshua may be able to embed the presentation. We will see.

Cole

_______________________________________________
libre-riscv-dev mailing list
libre-riscv-dev@lists.libre-riscv.org
http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev

^ permalink raw reply

page:   latest

Libre RISC-V Mailing list Archives (accessible via public-inbox)

Archives are clonable: git clone --mirror https://inbox.libre-soc.org/libre-riscv-dev

Example config snippet for mirrors


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git