From: bugzilla-daemon@libre-soc.org
To: libre-riscv-dev@lists.libre-riscv.org
Subject: [libre-riscv-dev] [Bug 325] create POWER9 TRAP pipeline
Date: Fri, 05 Jun 2020 15:43:30 +0000
Message-ID: <bug-325-13-529AkMPTMw@https.bugs.libre-soc.org/> (raw)
In-Reply-To: <bug-325-13@https.bugs.libre-soc.org/>
https://bugs.libre-soc.org/show_bug.cgi?id=325
--- Comment #50 from Luke Kenneth Casson Leighton <lkcl@lkcl.net> ---
(In reply to Cole Poirier from comment #46)
> Ok. I think now the nmigen should match the microwatt VHDL, however, there
> may be small errors as you made some modifications but left others for me to
> fix, and I got confused about some of your comments re a_i, b_i, but I did
> my best to interpret your comments while reading, line-by-line the vhdl from
> the comments.
microwatt decided to use a_in, b_in and c_in as the input lines for *SPRs*.
we are not going to do that.
therefore all places where SPRs are inputs, the names need to *be* SRR0,
*be* SRR1, *NOT* a_i, b_i, c_i.
however - some of the instructions *DO TAKE REGISTERS AS INPUT*.
see section 5.4.3, "mtmsr" for example: this takes a *REGISTER* (RS)
as the input, and moves it to the MSR (as output)
whereas OP_RFID, you can see clearly the pseudocode says:
nia <= SRR0
msr <= SRR1
however microwatt has this:
nia <- a_in
msr <- b_in
this is obviously a design decision that WE ARE NOT GOING TO COPY.
where they must have done this:
a_in <- SRR0
b_in <- SRR1
and then and only then could this microwatt code succeed:
nia <- a_in
msr <- b_in
we are **NOT** repeat **NOT** going to re-purpose register file lanes.
we have *SEPARATE* lanes for SPRs, *SEPARATE* lanes for integer registers.
if we were to copy what microwatt have done we would need full data-routing
crossbars in front of the register file ports to get data from the SPR
register files over to the integer inputs on the TRAP pipeline.
in an out-of-order system such "hacks" creates a severe architectural problem
for
Dependency Tracking and Management.
--
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
next prev parent reply index
Thread overview: 96+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-19 12:28 [libre-riscv-dev] [Bug 325] New: " bugzilla-daemon
2020-05-19 12:29 ` [libre-riscv-dev] [Bug 325] " bugzilla-daemon
2020-05-19 12:30 ` bugzilla-daemon
2020-05-19 14:11 ` bugzilla-daemon
2020-05-19 14:57 ` bugzilla-daemon
2020-05-19 15:49 ` bugzilla-daemon
2020-05-19 16:54 ` bugzilla-daemon
2020-05-19 18:09 ` bugzilla-daemon
2020-05-19 18:13 ` bugzilla-daemon
2020-05-19 20:43 ` bugzilla-daemon
2020-05-19 23:19 ` bugzilla-daemon
2020-05-19 23:31 ` bugzilla-daemon
2020-05-24 3:41 ` bugzilla-daemon
2020-05-24 3:43 ` bugzilla-daemon
2020-05-25 2:41 ` bugzilla-daemon
2020-05-27 14:43 ` bugzilla-daemon
2020-05-27 14:48 ` bugzilla-daemon
2020-05-27 14:49 ` bugzilla-daemon
2020-06-01 19:05 ` bugzilla-daemon
2020-06-02 11:21 ` bugzilla-daemon
2020-06-02 14:06 ` bugzilla-daemon
2020-06-02 17:54 ` bugzilla-daemon
2020-06-02 23:07 ` bugzilla-daemon
2020-06-02 23:07 ` bugzilla-daemon
2020-06-02 23:46 ` bugzilla-daemon
2020-06-02 23:54 ` bugzilla-daemon
2020-06-02 23:59 ` bugzilla-daemon
2020-06-03 0:11 ` bugzilla-daemon
2020-06-03 0:38 ` bugzilla-daemon
2020-06-03 0:47 ` bugzilla-daemon
2020-06-03 1:13 ` bugzilla-daemon
2020-06-03 1:28 ` bugzilla-daemon
2020-06-03 1:35 ` bugzilla-daemon
2020-06-03 1:41 ` bugzilla-daemon
2020-06-03 1:50 ` bugzilla-daemon
2020-06-03 2:31 ` bugzilla-daemon
2020-06-03 3:27 ` bugzilla-daemon
2020-06-04 0:29 ` bugzilla-daemon
2020-06-04 0:34 ` bugzilla-daemon
2020-06-04 22:41 ` bugzilla-daemon
2020-06-05 0:32 ` bugzilla-daemon
2020-06-05 0:35 ` bugzilla-daemon
2020-06-05 1:06 ` bugzilla-daemon
2020-06-05 1:09 ` bugzilla-daemon
2020-06-05 1:25 ` bugzilla-daemon
2020-06-05 2:13 ` bugzilla-daemon
2020-06-05 2:34 ` bugzilla-daemon
2020-06-05 3:37 ` bugzilla-daemon
2020-06-05 3:52 ` bugzilla-daemon
2020-06-05 4:19 ` bugzilla-daemon
2020-06-05 14:16 ` bugzilla-daemon
2020-06-05 15:12 ` bugzilla-daemon
2020-06-05 15:21 ` bugzilla-daemon
2020-06-05 15:33 ` bugzilla-daemon
2020-06-05 15:43 ` bugzilla-daemon [this message]
2020-06-05 15:46 ` bugzilla-daemon
2020-06-05 16:14 ` bugzilla-daemon
2020-06-05 18:14 ` bugzilla-daemon
2020-06-05 19:08 ` bugzilla-daemon
2020-06-05 19:15 ` bugzilla-daemon
2020-06-05 19:49 ` bugzilla-daemon
2020-06-05 20:12 ` bugzilla-daemon
2020-06-05 21:59 ` bugzilla-daemon
2020-06-05 22:02 ` bugzilla-daemon
2020-06-05 23:25 ` bugzilla-daemon
2020-06-05 23:46 ` bugzilla-daemon
2020-06-06 2:23 ` bugzilla-daemon
2020-06-07 0:31 ` bugzilla-daemon
2020-06-07 0:38 ` bugzilla-daemon
2020-06-07 0:39 ` bugzilla-daemon
2020-06-07 0:44 ` bugzilla-daemon
2020-06-07 0:51 ` bugzilla-daemon
2020-06-07 1:32 ` bugzilla-daemon
2020-06-07 1:42 ` bugzilla-daemon
2020-06-07 1:52 ` bugzilla-daemon
2020-06-07 2:09 ` bugzilla-daemon
2020-06-07 2:36 ` bugzilla-daemon
2020-06-07 3:09 ` bugzilla-daemon
2020-06-07 3:23 ` bugzilla-daemon
2020-06-07 6:11 ` bugzilla-daemon
2020-06-07 6:26 ` bugzilla-daemon
2020-06-07 20:42 ` bugzilla-daemon
2020-06-07 20:45 ` bugzilla-daemon
2020-06-07 20:51 ` bugzilla-daemon
2020-06-07 21:11 ` bugzilla-daemon
2020-06-07 21:18 ` bugzilla-daemon
2020-06-07 21:23 ` bugzilla-daemon
2020-06-07 21:31 ` bugzilla-daemon
2020-06-07 22:32 ` bugzilla-daemon
2020-06-07 22:34 ` bugzilla-daemon
2020-06-08 12:59 ` bugzilla-daemon
2020-06-08 13:42 ` bugzilla-daemon
2020-06-08 21:03 ` bugzilla-daemon
2020-06-08 22:51 ` bugzilla-daemon
2020-06-09 19:32 ` bugzilla-daemon
2020-06-09 20:59 ` bugzilla-daemon
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=bug-325-13-529AkMPTMw@https.bugs.libre-soc.org/ \
--to=bugzilla-daemon@libre-soc.org \
--cc=libre-riscv-dev@lists.libre-riscv.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
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