* [libre-riscv-dev] daily kan-ban update 31may2020
From: Luke Kenneth Casson Leighton @ 2020-05-31 13:38 UTC (permalink / raw)
To: Libre-RISCV General Development
yesterday:
* went through inter-relationship between MultiCompUnit and ALU,
getting MCU to conform to the pipeline API. it's a mess, however it's
functional.
* started debugging ALU Function Unit through MultiCompUnit (closest
thing to actually connecting them to a regfile)
* added "read register mask" and "write register mask" capability to
MultiCompUnit
today:
* finding numerous errors where register-writes are being requested by
the ALU pipeline, where the data is *not* valid ("ok" signal set when
it should not be)
l.
---
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 353] formal proof of soc.regfile classes RegFile and RegFileArray needed
From: bugzilla-daemon @ 2020-05-30 22:38 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-353-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=353
--- Comment #27 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
(In reply to Cole Poirier from comment #26)
> This leads me to believe that either the proof is wrong and needs to be
> reorganized to conform to how Register is implemented in regfile/regfile.py,
the unit test for RegFileArray and RegFile leads me to believe that it is.
however it is worthwhile confirming this by writing a straight unit test,
exactly is done in regfile.py.
basically i have no idea what i am doing with Formal Proofs. i can read
them, i can *maybe* spot omissions once they're written, and i can just about
manage combinatorial ones. these sync/time-based ones: really no idea.
--
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 353] formal proof of soc.regfile classes RegFile and RegFileArray needed
From: bugzilla-daemon @ 2020-05-30 22:13 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-353-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=353
--- Comment #26 from Cole Poirier <colepoirier@gmail.com> ---
(In reply to Luke Kenneth Casson Leighton from comment #25)
> (In reply to Cole Poirier from comment #24)
>
> > Luke, is the use of Settle() warranted in the synchronous part of this proof?
>
> not at all.
>
> l.
Thanks, this helps clarify a little bit more for me the use and functionality
of Settle().
I think the proof as it stands may need a re-org... I tried filling in the
quadrants according the to 4-way truth table comment draft that I did, which I
saw you fixed. But nothing passes but the same Assert you added when you fixed
the truth table a few days ago (this is actually the else condition in the
code, but modified here to If for clarity):
```
with m.If(not Past(wp.wen)):
# if wen not set, reg should not change
comb += Assert(reg == Past(reg))
```
This leads me to believe that either the proof is wrong and needs to be
reorganized to conform to how Register is implemented in regfile/regfile.py, or
that Regfile itself doesn't properly implement what the proof says it should...
I'm thinking I should try re-organizing the proof first to see if that improves
things? What do you think?
--
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 30may2020
From: Cole Poirier @ 2020-05-30 22:06 UTC (permalink / raw)
To: Libre-RISCV General Development; +Cc: Libre-RISCV General Development
In-Reply-To: <CAPweEDz3P_sN0zov6Y4y8atNxjnJGPZqGggmZPUhtSTmwETgdg@mail.gmail.com>
On May 30 2020, at 3:02 pm, Luke Kenneth Casson Leighton <lkcl@lkcl.net> wrote:
> On Sat, May 30, 2020 at 10:40 PM Cole Poirier <colepoirier@gmail.com> wrote:
>>
>> Yesterday:
>>
>> Did not work on the project, except to read all of the
>> mailinglist/bug-report emails. Had intended to get several small family
>> errands done then do some work but as often happens errands took a lot
>> longer than expected.
>
> these guys are available for hire:
> https://www.youtube.com/watch?v=AEnvpvbfc8w
Hehe I reached out to them but they charge far too much :)
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
* Re: [libre-riscv-dev] daily kan-ban update 30may2020
From: Luke Kenneth Casson Leighton @ 2020-05-30 22:02 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <4890002B-EF8D-49EC-B1D9-EE74566ABE66@getmailspring.com>
On Sat, May 30, 2020 at 10:40 PM Cole Poirier <colepoirier@gmail.com> wrote:
>
> Yesterday:
>
> Did not work on the project, except to read all of the
> mailinglist/bug-report emails. Had intended to get several small family
> errands done then do some work but as often happens errands took a lot
> longer than expected.
these guys are available for hire:
https://www.youtube.com/watch?v=AEnvpvbfc8w
> Today:
>
> Do a very small amount of work on proof_regfile, basically try to
> further orient my self and understand the state machine (if that even is
> the correct terminology) of the proof re wen/ren. This in order to
> prepare to do more substantial work on the proof tomorrow.
cool.
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 353] formal proof of soc.regfile classes RegFile and RegFileArray needed
From: bugzilla-daemon @ 2020-05-30 22:03 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-353-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=353
--- Comment #25 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
(In reply to Cole Poirier from comment #24)
> Luke, is the use of Settle() warranted in the synchronous part of this proof?
not at all.
l.
--
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 353] formal proof of soc.regfile classes RegFile and RegFileArray needed
From: bugzilla-daemon @ 2020-05-30 21:41 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-353-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=353
--- Comment #24 from Cole Poirier <colepoirier@gmail.com> ---
(In reply to Cole Poirier from comment #23)
> (In reply to Luke Kenneth Casson Leighton from comment #22)
>
> > done. updated. basically, this is... complicated. there's time-dependent
> > interactions. i actually managed to get one case to work: when wen is
> > not set, the reg should not change. past value should equal the present
> > value.
>
> Ah it's time-dependent, that makes sense. Thanks, pulled and ran the test.
> Cool. How would I go about better understanding how ren and wen are supposed
> to interact? Studying the logic diagram? Or something else?
Luke, is the use of Settle() warranted in the synchronous part of this proof?
--
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 30may2020
From: Cole Poirier @ 2020-05-30 21:40 UTC (permalink / raw)
To: Libre-RISCV General Development; +Cc: Libre-RISCV General Development
In-Reply-To: <CAPweEDyie3Wt-iRDmAORDbezhDMJaav4e5yD9_mXu0_nGTxnVg@mail.gmail.com>
Yesterday:
Did not work on the project, except to read all of the
mailinglist/bug-report emails. Had intended to get several small family
errands done then do some work but as often happens errands took a lot
longer than expected.
Today:
Do a very small amount of work on proof_regfile, basically try to
further orient my self and understand the state machine (if that even is
the correct terminology) of the proof re wen/ren. This in order to
prepare to do more substantial work on the proof tomorrow.
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
* Re: [libre-riscv-dev] Request for Scoreboard and Functional Units Update
From: Cole Poirier @ 2020-05-30 21:34 UTC (permalink / raw)
To: Libre-RISCV General Development; +Cc: Libre-RISCV General Development
In-Reply-To: <CAPweEDxgDfgKJPrtf3RbL0QvpxgFPJOCxE=F+Dc0QQ92wZ-KOA@mail.gmail.com>
On May 30 2020, at 10:31 am, Luke Kenneth Casson Leighton
<lkcl@lkcl.net> wrote:
> i am really impressed by what michael did, very quickly, however it
> was the
> collaboration that really did it. cole as well, his enthusiasm is
> inspiring, and it is very funny that he knew flat-out zero about gate-level
> programming *and* python, let alone nmigen, even a few months ago.
Thanks Luke, the help from you, Michael, Jacob, Yehowshua, Jean-Paul,
and the others who I may be forgetting to mention, has been so
awe-inspiring. Your patience, friendliness, and sheer overall
helpfulness has been honestly amazing, and frankly inspiring, as is the
overall attitude and goals of the project. I am thrilled to be starting
to become a contributing member, and hopefully one-day, with lots of
effort and studying, I can I achieve somewhere near the competency and
brilliance of Michael, through learning from him and everyone else.
One small correction though, I did know python and rust prior to joining
the project. I'm not that brilliant ;) Gate-level programming as well as
nmigen still hurt my brain tremendously when thinking through them to
write code and proofs, however it's a very good kind of pain because
thanks again to your *painstakingly* attentive and patient help I'm learning.
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 358] new MCU-ALU test picked up RC / OE / CR handling issue
From: bugzilla-daemon @ 2020-05-30 21:22 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-358-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=358
--- Comment #3 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
(In reply to Luke Kenneth Casson Leighton from comment #2)
> however this highlights something else: the destination for CR output needs
> to be implicitly set to CR0 when RC is enabled, otherwise the output stage
> has no idea where to put the result.
... which is in decode2.cr_out bitfield.
so the unit tests need to be modified to check if cr out ok is set, rather than
use RC or the OP_CMP* test.
--
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 358] new MCU-ALU test picked up RC / OE / CR handling issue
From: bugzilla-daemon @ 2020-05-30 20:39 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-358-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=358
--- Comment #2 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
ah. just as in the unit tests which check if OP_CMP* is enabled, this was
missing in CommonOutputStage.
however this highlights something else: the destination for CR output needs to
be implicitly set to CR0 when RC is enabled, otherwise the output stage has ni
idea where to put the result.
--
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 358] new MCU-ALU test picked up RC / OE / CR handling issue
From: bugzilla-daemon @ 2020-05-30 19:48 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-358-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=358
Luke Kenneth Casson Leighton <lkcl@lkcl.net> changed:
What |Removed |Added
----------------------------------------------------------------------------
Assignee|lkcl@lkcl.net |mtnolan2640@gmail.com
--- Comment #1 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
michael, any clues?
--
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 358] New: new MCU-ALU test picked up RC / OE / CR handling issue
From: bugzilla-daemon @ 2020-05-30 19:47 UTC (permalink / raw)
To: libre-riscv-dev
https://bugs.libre-soc.org/show_bug.cgi?id=358
Bug ID: 358
Summary: new MCU-ALU test picked up RC / OE / CR handling issue
Product: Libre-SOC's first SoC
Version: unspecified
Hardware: PC
OS: Linux
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: ---
yippee! a new unit test (test_alu_compunit.py) just picked up that
we are using rc from Decode2ExecuteType in the wrong way. as RC and
OE are both of type "Data", the test needs to be on "rc_ok" enabled.
i think.
the symptoms: test_alu_compunit.py fails because CR0 is not being
outputted on OP_CMP. as in: cr0.ok is not being set.
it's not being set because in CommonOutputStage:
comb += self.o.cr0.data.eq(cr0)
comb += self.o.cr0.ok.eq(op.rc.rc & op.rc.rc_ok) # CR0 to be set
op.rc.rc & op.rc.rc_ok is *zero*, and yet the test in test_output_caller.py
(and test_alu_compunit.py) is this:
def check_extra_alu_outputs(self, alu, dec2, sim, code):
rc = yield dec2.e.rc.data
if rc:
....
--
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 216] LOAD STORE buffer needed
From: bugzilla-daemon @ 2020-05-30 19:40 UTC (permalink / raw)
To: libre-riscv-dev
In-Reply-To: <bug-216-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=216
--- Comment #53 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
commit 23b682daa011ace5cfbfbe2b60ece7369cbe403c
Author: Tobias Platen <tplaten@posteo.de>
Date: Sat May 30 21:11:02 2020 +0200
unit test for DataMerger
looks good, tobias. i added some use of "Settle()" which should be
used (as we just learned thanks to Cesar highlighting it) after any
combinatorial logic changes, rather than doing a full one-cycle "yield"
--
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] MultiCompUnit- ALU interaction. was: daily kan-ban update 30may2020
From: Luke Kenneth Casson Leighton @ 2020-05-30 19:05 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <CAPweEDxUtX=uFFTbYu7nSHOAMUSeLQ6yaDF1ZNrO5COkOL+cBQ@mail.gmail.com>
On Sat, May 30, 2020 at 7:06 PM Luke Kenneth Casson Leighton
<lkcl@lkcl.net> wrote:
> it will currently fail at the extsb unit test because the MCU expects *all* operands (non-optionally) to be requested from the regfile, and extsb does not have RB.
sorted. a "source operand read mask" is now passed in to the
MultiCompUnit, telling it *not* to request specific register file
ports that are not actually required.
should now complete without error:
$ python3 fu/compunits/test/test_alu_compunit.py
next phase: the write-side. again: just as read-ports should not be
requested which are not required, neither should write-ports.
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] MultiCompUnit- ALU interaction. was: daily kan-ban update 30may2020
From: Luke Kenneth Casson Leighton @ 2020-05-30 18:06 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <38EFD023-443F-419A-9306-19F7D6401DD0@gatech.edu>
On Saturday, May 30, 2020, Yehowshua <yimmanuel3@gatech.edu> wrote:
> When you say you got something working, do you mean that you got the
> decoder to decode, the issuer to issue, and the ALU FU to compute? All
> working together?
the interaction - the interface - between MultiCompUnit (a data "monitor"
aka Reservation Station) and a pipelined ALU.
MCU is a massively complex and compact FSM (the LDST CompUnit equally so).
it must:
* handle multiple ready/valid signalling to bring in multiple (optional)
operands from the regfile
* then use ready/valid signalling to kick off the ALU
* *WAIT* for ready/valid signalling from the ALU and capture the output
* finally use *yet more* ready/valid signalling to independently
acknowledge every single output being sent to its corresponding regfile for
write.
all of that *back-propagates* such that if the ALU *OUTPUT* is not ready,
the incoming data to the ALU must not be sent.
and every single one of those ready/valid events can occur independently at
any time.
and some of them are optional at the input phase.
and some of them are optional at the output phase.
it is quite ridiculously complex for such a relatively small amount of code.
> If this is the case, how can I make the codebase do this myself?
$ cd soc/src/soc
$ python3 fu/compunits/test/test_alu_compunit.py
it will currently fail at the extsb unit test because the MCU expects *all*
operands (non-optionally) to be requested from the regfile, and extsb does
not have RB.
l.
--
---
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
* Re: [libre-riscv-dev] MultiCompUnit- ALU interaction. was: daily kan-ban update 30may2020
From: Yehowshua @ 2020-05-30 17:50 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <CAPweEDzXH75dOEiRXGX0xnQeG5vgMqHTbuHDKZh+_CtZCU2=1g@mail.gmail.com>
When you say you got something working, do you mean that you got the decoder to decode, the issuer to issue, and the ALU FU to compute? All working together?
If this is the case, how can I make the codebase do this myself?
Yehowshua
_______________________________________________
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] MultiCompUnit- ALU interaction. was: daily kan-ban update 30may2020
From: Luke Kenneth Casson Leighton @ 2020-05-30 17:40 UTC (permalink / raw)
To: Libre-RISCV General Development
On Saturday, May 30, 2020, Luke Kenneth Casson Leighton <lkcl@lkcl.net>
wrote:
>
> > * more on ALU to MultiCompUnit.
> >
> > i *do not* know what i am doing, here. the time dependent signalling is
> critical and could take several days to weeks to get right.
>
> a simple bug where XER so and ca were swapped as inputs masked efforts
> to get the interaction working. no point trying to debug against a
> target with multiple unknowns, any one of which causes the entire test
> to fail.
>
> progress should be better, now.
we are reeeaally damn lucky.
i managed to get at least something running. it failed only because one
operation required one operand (exts). this leaves the CU waiting for RB
which never gets activated.
we are going to have to make a couple of modifications:
1. a "read mask". this will tell the CompUnit that some operands are not
required.
2. a "write mask" which actually already exists (Data.ok) for output
results to also be optional.
l.
--
---
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
* Re: [libre-riscv-dev] Request for Scoreboard and Functional Units Update
From: Luke Kenneth Casson Leighton @ 2020-05-30 17:31 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <F947F71E-FD73-44BA-8C1B-4C3E8052C573@gatech.edu>
On Saturday, May 30, 2020, Yehowshua <yimmanuel3@gatech.edu> wrote:
> Ok. Thanks for the well written update. Sounds like things are moving a
> long nicely.
slower without michael.
> Browsing through the codebase, I didn’t find anything alarming.
i am really impressed by what michael did, very quickly, however it was the
collaboration that really did it. cole as well, his enthusiasm is
inspiring, and it is very funny that he knew flat-out zero about gate-level
programming *and* python, let alone nmigen, even a few months ago.
the entire suite of FUs that we did is entirely combinatorial, which made
progress much faster.
the pipeline API makes life one hell of a lot easier.
the places that have been slow progress are the time-dependent FSMs.
l.
--
---
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
* Re: [libre-riscv-dev] Request for Scoreboard and Functional Units Update
From: Yehowshua @ 2020-05-30 17:08 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <CAPweEDxwQXzXpVzwY9fVAEeATVWfytpG5ccSE5vSorB7wekyGQ@mail.gmail.com>
Ok. Thanks for the well written update. Sounds like things are moving a long nicely.
Browsing through the codebase, I didn’t find anything alarming.
Yehowshua
_______________________________________________
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 Scoreboard and Functional Units Update
From: Luke Kenneth Casson Leighton @ 2020-05-30 16:26 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <17CF5C16-41BC-496D-95DD-4384E78C7EBD@gatech.edu>
On Sat, May 30, 2020 at 3:59 PM Yehowshua <yimmanuel3@gatech.edu> wrote:
>
> So browsing through the codebase, it seems we have about 10ish functional units,
soc.fu.*:
* ALU (done)
* Logical (done)
* ShiftRot (done)
* MUL (not done - Jacob)
* DIV (not done - Jacob)
* Branch (done)
* TRAP (specified)
* SYS (specified)
* LDST ("odd one out")
* SPR (specified)
* CR - Condition Register (done)
of these:
* SYS, TRAP and SPR need writing (they've been defined, no unit test exists yet)
* MUL and DIV we're waiting for Jacob
* LDST depends on a functional L0CacheBuffer, however does not "fit"
the FU mould and kinda-qualifies as "partly complete" because the
majority of functionality is in the *Computation Unit* rather than an
actual "Pipeline".
> about 29 Scoreboard components. How many more scoreboard components and
> functional units are needed for August?
scoreboard components to be written: none. the entirety of the
scoreboard functionality was done well over a year ago, including
shadowing which covers branches, exceptions, traps, interrupts (and
predication when we add it).
the only reason i had to make changes (2 months ago) was for the
mutli-signal capability.
tying the components *together* is where the complexity lies.
Function Units: see above.
one additional absolutely critical blocker (which i *may* have solved,
today): the Computation Unit "Manager" <-> ALU interaction. this
*critically* relies on properly implementing the pipeline API... in
both the CompUnit (as sender *and* receiver) and the ALU (as receiver
and sender).
yes, the CompUnit "sends" (operands) to the ALU, then "receives" the
results (from the ALU). that's its job - its sole purpose. it's
basically as complex a FSM as any **PAIR** of interacting Wishbone or
AXI4 Bus Master Router-Arbiters, back-to-back, in the same code.
> All the functional units have some formal verification tests, how confident are we
> that the scoreboard works correctly?
strictly speaking: not in the slightest, until there exists full
formal verification for it (and for each component). there's a
special budget of EUR 6,000 *specifically* for that one task, because
it's (a) extremely involved and (b) actually covers quite a lot of
interaction(s) and components.
on a "proof-of-concept" level: reasonably confident.
score6600_multi.py is functional for ALU operations (including
overlapping ones, including parallel execution), and when i was
testing speculative branch operations (including cancellation either
way - correct / incorrect branches), that worked too. however that
was for "single read/write".
the complexity lies in the "allocation" of the required components, to
meet the register and FU allocation. i've defined the "regspec" API
to help meet that.
https://libre-soc.org/3d_gpu/architecture/regfile/
so this is why i said, last week, that it would be a good idea to take
an incremental approach:
https://bugs.libre-soc.org/show_bug.cgi?id=346
this allows us to "have something working" - complete, prove and bug
fix both the regfile *and* Function Units, get the "hello world" demo
out the door much faster than would otherwise be achievable, and
*then* add in the Dependency Matrices.
it works by only issuing one instruction, using the regfile buses
*exclusively* for that *ONE* Function Unit, waiting for that *ONE*
instruction to complete, before moving on to the next one.
this basically means that we would have an IPC of somewhere under...
0.3. as in: 3-5 cycles per instruction.
adding in the Dependency Matrices then becomes a straightforward
task... *if* we know full well that the Function Units properly comply
to the Pipeline API, interact properly with their Computational Unit
"Manager", properly read and write registers according to the Go_Read
/ Write - Req_Read / Req_Write protocol.
once added, the DMs bring us up to near a 1.0 IPC (branch prediction
being the key, there).
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] Request for Scoreboard and Functional Units Update
From: Yehowshua @ 2020-05-30 14:58 UTC (permalink / raw)
To: Libre-RISCV General Development
So browsing through the codebase, it seems we have about 10ish functional units,
about 29 Scoreboard components. How many more scoreboard components and
functional units are needed for August?
All the functional units have some formal verification tests, how confident are we
that the scoreboard works correctly?
Yehowshua
_______________________________________________
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 30may2020
From: Luke Kenneth Casson Leighton @ 2020-05-30 13:28 UTC (permalink / raw)
To: Libre-RISCV General Development
In-Reply-To: <CAPweEDw4qDjKGT3XbnjqZ5fkafybiCg384F9KNN4qDKYm3kxuA@mail.gmail.com>
On Sat, May 30, 2020 at 12:34 PM Luke Kenneth Casson Leighton
<lkcl@lkcl.net> wrote:
>
> yesterday:
>
> * more on ALU to MultiCompUnit interaction. it is not pipeline API compliant (ready/valid signalling).
>
> today:
>
> * more on ALU to MultiCompUnit.
>
> i *do not* know what i am doing, here. the time dependent signalling is critical and could take several days to weeks to get right.
a simple bug where XER so and ca were swapped as inputs masked efforts
to get the interaction working. no point trying to debug against a
target with multiple unknowns, any one of which causes the entire test
to fail.
progress should be better, now.
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] daily kan-ban update 30may2020
From: Luke Kenneth Casson Leighton @ 2020-05-30 11:34 UTC (permalink / raw)
To: Libre-RISCV General Development
yesterday:
* more on ALU to MultiCompUnit interaction. it is not pipeline API
compliant (ready/valid signalling).
today:
* more on ALU to MultiCompUnit.
i *do not* know what i am doing, here. the time dependent signalling is
critical and could take several days to weeks to get right.
until it is right there is zero forward progress because this interaction
between CompUnit and ALU pipelines is absolutely critical.
all other tasks such as assembling pipelines, connecting them to register
files, connecting to the Dependency Matrices, is critically blocked and
held up until this inter-component interaction is correct.
assistance on this one task therefore appreciated.
l.
--
---
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] EU residency / businesses
From: Luke Kenneth Casson Leighton @ 2020-05-30 9:58 UTC (permalink / raw)
To: Libre-RISCV General Development
https://e-resident.gov.ee/start-a-company/
https://e-resident.gov.ee/become-an-e-resident/
https://yourcompanyinestonia.com/how-to-register-your-company-in-estonia-step-by-step/
we need to have an EU "business" presence, if we are to apply for EU
funding such as this:
https://essif-lab.eu/?page_id=134
a way to achieve that is to apply for Estonian E-residency, and
establish a business online, there. by making sure that Estonia
directly financially benefits, the country is happy to put a sovereign
stamp on 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
page: next prev 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