From: MidG971 <midgy971@gmail.com>
To: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Cc: linux-rockchip@lists.infradead.org,
Tomeu Vizoso <tomeu@tomeuvizoso.net>,
Simon Xue <xxm@rock-chips.com>, Heiko Stuebner <heiko@sntech.de>,
dri-devel@lists.freedesktop.org
Subject: Re: RK3568 NPU: what triggers the CNA weight-fetch DMA after the executer engages? (mainline rocket vs vendor rknpu)
Date: Fri, 20 Nov 2026 12:27:54 +0100 [thread overview]
Message-ID: <20261120112754.1400099-1-midgy971@gmail.com> (raw)
In-Reply-To: <20260721230746.175786-1-midgy971@gmail.com>
Hi Chaoyi, hi all,
A gentle follow-up on the thread above from July: no reply yet, and I
wanted to add the new evidence I gathered since, in case it sharpens
the question.
Since then I confirmed the engage/completion split explicitly:
- Loading the vendor rknpu and running ONE vendor job ("priming"),
then unloading it (no power cycle) and loading mainline rocket,
makes rocket's executers engage for the first time (S_POINTER
bit 16 = 0x1000e on all five units, matching the working vendor
signature). So the engage is one-time HW state established by a
*working vendor job*, not by probe/init writes.
- But completion still fails afterwards: even primed, rocket's job
times out with wt_rd = 0 / dt_wr = 0 (vendor: 0x1900 / 0x6400).
- An NIU reset pulse (CRU SOFTRST_CON2 bits 8..10) at resume CLEARS
the primed state (reads drop to 0); nothing we write re-arms it.
I also tested a kiln-style reset edge inside rockchip_pd_power()
at PD power-on (RK3576 kiln 0002 analog) on v7.4-rc3, including a
forced cold power cycle of the PMU island from userspace:
negative -- the pulse does not re-arm the sequencer, and the PD
never actually cold-cycles on this board.
- Cache coherency ruled out (forced dma_sync of all BOs at submit;
live DT has no dma-coherent). CBUF_DBG matches the vendor's engaged
values pre/post job. The board now runs mainline v7.4-rc3 and the
gate reproduces there unchanged.
So the refined question: after a vendor job has left the NPU in the
armed per-power-session state, which step of that job arms the CNA
weight-fetch sequencer - and is there any RK3568-visible precondition
(CBUF/DCOMP/weight-DMA enable, ordering vs. engage) I could replicate
in rocket so it computes without the vendor prime?
Happy to run any targeted capture on the board (RK3568, ROCK 3B).
Thanks again.
Kind regards,
Midgy
WARNING: multiple messages have this Message-ID (diff)
From: MidG971 <midgy971@gmail.com>
To: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Cc: linux-rockchip@lists.infradead.org,
Tomeu Vizoso <tomeu@tomeuvizoso.net>,
Simon Xue <xxm@rock-chips.com>, Heiko Stuebner <heiko@sntech.de>,
dri-devel@lists.freedesktop.org
Subject: Re: RK3568 NPU: what triggers the CNA weight-fetch DMA after the executer engages? (mainline rocket vs vendor rknpu)
Date: Fri, 20 Nov 2026 12:27:54 +0100 [thread overview]
Message-ID: <20261120112754.1400099-1-midgy971@gmail.com> (raw)
In-Reply-To: <20260721230746.175786-1-midgy971@gmail.com>
Hi Chaoyi, hi all,
A gentle follow-up on the thread above from July: no reply yet, and I
wanted to add the new evidence I gathered since, in case it sharpens
the question.
Since then I confirmed the engage/completion split explicitly:
- Loading the vendor rknpu and running ONE vendor job ("priming"),
then unloading it (no power cycle) and loading mainline rocket,
makes rocket's executers engage for the first time (S_POINTER
bit 16 = 0x1000e on all five units, matching the working vendor
signature). So the engage is one-time HW state established by a
*working vendor job*, not by probe/init writes.
- But completion still fails afterwards: even primed, rocket's job
times out with wt_rd = 0 / dt_wr = 0 (vendor: 0x1900 / 0x6400).
- An NIU reset pulse (CRU SOFTRST_CON2 bits 8..10) at resume CLEARS
the primed state (reads drop to 0); nothing we write re-arms it.
I also tested a kiln-style reset edge inside rockchip_pd_power()
at PD power-on (RK3576 kiln 0002 analog) on v7.4-rc3, including a
forced cold power cycle of the PMU island from userspace:
negative -- the pulse does not re-arm the sequencer, and the PD
never actually cold-cycles on this board.
- Cache coherency ruled out (forced dma_sync of all BOs at submit;
live DT has no dma-coherent). CBUF_DBG matches the vendor's engaged
values pre/post job. The board now runs mainline v7.4-rc3 and the
gate reproduces there unchanged.
So the refined question: after a vendor job has left the NPU in the
armed per-power-session state, which step of that job arms the CNA
weight-fetch sequencer - and is there any RK3568-visible precondition
(CBUF/DCOMP/weight-DMA enable, ordering vs. engage) I could replicate
in rocket so it computes without the vendor prime?
Happy to run any targeted capture on the board (RK3568, ROCK 3B).
Thanks again.
Kind regards,
Midgy
_______________________________________________
Linux-rockchip mailing list
Linux-rockchip@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-rockchip
next prev parent reply other threads:[~2026-11-20 11:28 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-21 23:07 RK3568 NPU: what triggers the CNA weight-fetch DMA after the executer engages? (mainline rocket vs vendor rknpu) Midgy BALON
2026-07-21 23:07 ` Midgy BALON
2026-11-20 11:27 ` MidG971 [this message]
2026-11-20 11:27 ` MidG971
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=20261120112754.1400099-1-midgy971@gmail.com \
--to=midgy971@gmail.com \
--cc=chaoyi.chen@rock-chips.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=heiko@sntech.de \
--cc=linux-rockchip@lists.infradead.org \
--cc=tomeu@tomeuvizoso.net \
--cc=xxm@rock-chips.com \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.